Next Article in Journal
Parametric Study on Ducted Micro Wind Energy Harvester
Next Article in Special Issue
A Novel Feature Identification Method of Pipeline In-Line Inspected Bending Strain Based on Optimized Deep Belief Network Model
Previous Article in Journal
Evaluation of Urban Mobility Problems and Freight Solutions from Residents’ Perspectives: A Comparison of Belo Horizonte (Brazil) and Szczecin (Poland)
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Review

Residual Strength Assessment and Residual Life Prediction of Corroded Pipelines: A Decade Review

1
School of Petroleum and Natural Gas Engineering, Southwest Petroleum University, Chengdu 610500, China
2
PetroChina Southwest Oil and Gas Field Gas Branch, Chengdu 610500, China
3
Sinopec Petroleum Engineering Zhongyuan Corporation, Puyang 457000, China
*
Author to whom correspondence should be addressed.
Energies 2022, 15(3), 726; https://doi.org/10.3390/en15030726
Submission received: 14 December 2021 / Revised: 12 January 2022 / Accepted: 15 January 2022 / Published: 19 January 2022

Abstract

:
Prediction of residual strength and residual life of corrosion pipelines is the key to ensuring pipeline safety. Accurate assessment and prediction make it possible to prevent unnecessary accidents and casualties, and avoid the waste of resources caused by the large-scale replacement of pipelines. However, due to many factors affecting pipeline corrosion, it is difficult to achieve accurate predictions. This paper reviews the research on residual strength and residual life of pipelines in the past decade. Through careful reading, this paper compared several traditional evaluation methods horizontally, extracted 71 intelligent models, discussed the publishing time, the evaluation accuracy of traditional models, and the prediction accuracy of intelligent models, input variables, and output value. This paper’s main contributions and findings are as follows: (1) Comparing several traditional evaluation methods, PCORRC and DNV-RP-F101 perform well in evaluating low-strength pipelines, and DNV-RP-F101 has a better performance in evaluating medium–high strength pipelines. (2) In intelligent models, the most frequently used error indicators are mean square error, goodness of fit, mean absolute percentage error, root mean square error, and mean absolute error. Among them, mean absolute percentage error was in the range of 0.0123–0.1499. Goodness of fit was in the range of 0.619–0.999. (3) The size of the data set of different models and the data division ratio was counted. The proportion of the test data set was between 0.015 and 0.4. (4) The input variables and output value of predictions were summarized.

1. Introduction

The pipeline is the primary transportation mode of oil and gas, which also accounts for a considerable proportion of the national economy, and the safe operation of pipelines is also closely related to people’s lives. Due to the vast area, complex geology, different soil properties, and significant differences in a corrosive environment, pipelines are very vulnerable to external corrosion, which reduces their safety and service life. Pipeline leakage is one of the most critical potential safety hazards of long-distance oil and gas pipeline transportation.
According to the 11th EGIG report [1], incidents caused by corrosion accounted for 26% during the period 2009–2013 and 24% during the period 2004–2013, and the incidents caused by corrosion accounted for 26.63% during the period 2010–2019.The incidents with leak size pinhole/crack caused by corrosion accounted for 38% (Figure 1).
With the frequent accidents caused by corroded pipelines, it is still necessary to do more research on pipeline residual strength evaluation and residual life prediction. The significance of residual strength evaluation and residual life prediction has two aspects: (a) accurate assessment and prediction makes it possible to prevent unnecessary accidents and casualties; (b) accurate assessment and prediction can avoid the waste of resources caused by the large-scale replacement of pipelines through repairing it in advance. Therefore, residual strength assessment and residual life prediction have attracted a large number of scholars, and due to the popularity of artificial intelligence and machine learning in recent years; a large number of scholars use intelligent models as their research methods. For example, we search the literature in the ScienceDirect database with the following requirements: (1) Search target: ”residual strength assessment” or “residual life prediction”; (2) Period: 2009–2021; (3) Article type: “Review articles” and “Research articles”. A total 168 papers were retrieved.
These papers can be roughly divided into the evaluation of traditional methods and the prediction of intelligent models. Most of the research based on traditional methods has been performed well, but in the research using intelligent models, researchers can only compare the basic models with the improved models, due to their limited energy, and there is no more comprehensive review to compare a large number of intelligent models. The purposes of this paper are to:
  • Provide selection reference for researchers;
  • Compare the advantages and disadvantages of the methods to help researchers understand each method;
  • Provide a reference for future research.
The rest of this paper is organized as follows: Section 2 introduces the literature review methodology. Section 3 reviews the prediction models and methods, and classifies them according to traditional methods and intelligence methods. Section 4 discusses the applicable conditions of traditional methods, compares the prediction accuracy under different pipe steel grades, and reviews the model, data size, input variable, output value, publishing time, performance of intelligent methods, and the future research directions. Section 5 summarizes the primary conclusions of this paper.

2. Methodology

The methodology of this review is summarized as follows, mainly including four steps:
  • Step 1: Multiple database searches.
According to our preliminary search results, there is not enough quantity in a single database. In order to summarize more comprehensively and have more reference value, we have combined the search results of multiple databases. The critical information of the search is as follows:
Object: residual life/strength prediction of corroded pipeline.
Database: Google Scholar, Web of Science, ASCE, SPE, ScienceDirect, CNKI.
Keywords: residual strength, residual life, evaluation method, intelligent model.
Language: English.
Period: 2009–2021
  • Step 2: Review and screening.
In the collected literature, many are related to the residual strength evaluation and residual life prediction, but the experimental object is not the corroded pipeline. In order to achieve better results and determine that the content is directly related to the residual life prediction and residual strength evaluation of the corroded pipeline, we read each paper carefully.
  • Step 3: Extracting information from papers.
Read the paper in-depth and extract meaningful information, such as the utilized model, prediction accuracy, data size, proportion of test data set, input variables, and output value.
  • Step 4: Discussion and conclusion.
Discuss the information extracted in step 3, make a comprehensive review, summarize the existing research, and put forward possible research directions in the future.

3. Literature Review

3.1. Traditional Evaluation Methods

3.1.1. ASME B31G-1984

In the late 1960s, Texas Eastern transportation company and American Natural Gas Association (AGA) conducted relevant research on corroded pipelines and proposed NG-18 formula [2]. All subsequent formulas of this series evolved from it, and the expression is shown in Equation (1).
P f = σ f l o w ( 1 A A 0 1 A A 0 1 M )
In 1984, ASME B31G-1984, as the earliest residual strength evaluation criterion of corroded pipelines [3], was proposed by American Society of Mechanical Engineers based on NG-18. The specific parameters in NG-18 formula were given. l 2 D t 20 is defined as a short defect and l 2 D t 20   is defined as a long defect. According to different defect length, there are two formulas for calculating failure pressure of pipeline (Equation (2)).
P f = σ f l o w ( 1 A A 0 1 A A 0 1 M )

3.1.2. ASME B31G-1991

In 1991, American Society of Mechanical Engineers had made some modifications to B31G-1984, and proposed ASME B31G-1991 [4]. The new criterion retained the original flow stress, and modified the Folias bulging coefficient and the calculation formula of long defect failure pressure, the expression is shown in Equation (3).
P f = σ f l o w 2 t D ( 1 d t )
Compare to B31G-1984, the results of B31G-1991 evaluation criterion is less conservative.

3.1.3. Modified B31G

Kiefner and others of the American Natural Gas Association (AGA) [5] found that improper definition of flow stress, inaccurate expression of the Folias bulging coefficient, and inaccurate calculation of metal loss area caused B31G-1984 to be too conservative. In view of the above problems, Kiefner and his colleagues proposed the modified B31G criterion. The modified evaluation criterion does not distinguish the size of defects when simplifying the projected area of defect profile, but takes A = 0.85 dL. Therefore, this evaluation method is also called “RSTRENG 0.85 dL evaluation method”. The expression of failure pressure is shown in Equation (4).
P f = σ f l o w 2 t D ( 1 0.85 d t 1 0.85 d t 1 M )

3.1.4. ASME B31G-2009

Based on the previous two editions of ASME B31G, the criterion was revised again in 2009 and ASME B31G-2009 was obtained [6]. This version adopts the concept of hierarchical evaluation for the first time (Figure 2). The higher the evaluation level, the more accurate the evaluation result. However, the difficulty of evaluation also increases [7]. Therefore, different levels of the evaluation methods should be selected according to the actual situation in the application.
  • Zero-level evaluation
According to the collected corrosion defect parameters and pipeline parameters, query the table to obtain the maximum allowable length of this defect. If the actual corrosion length is less than the maximum longitudinal length, it is safe; otherwise, it fails to pass the evaluation. At this time, maintenance measures shall be taken, or a higher-level evaluation method shall be selected. The zero-level evaluation is simple to use, but the results are conservative.
2.
First-level evaluation
First, calculate the failure pressure of the corroded pipeline by the Modified B31G method, and then compare it with the product of the pipeline safety factor and the operating pressure for evaluation. The first-level evaluation needs to be completed by professionals such as corrosion technicians or coating inspectors.
3.
Second-level evaluation
The criterion recommends that the second-level evaluation use the RSTRENG effective area method to evaluate the residual strength of corroded pipelines. The effective area method has a wide range of applications, and it is also applicable to independent defects and interacting defect groups. However, it also has certain limitations. The effective area calculation requires a detailed measurement of the defect size, and software is also required, so it is rarely used in actual working conditions.
4.
Third-level evaluation
It is recommended to use the finite element analysis method for stress analysis of the corroded pipeline. The finite element analysis method is a mathematical simulation method, which calculates the bearing capacity of the pipeline by considering many factors such as the real stress–strain curve of material, actual load, boundary conditions, and so on. The evaluation process is more cumbersome, but the results are more accurate.

3.1.5. DNV-RP-F101

In 1999, British Gas Company (BG) and DET NORSKE VERITAS (DNV) jointly developed the specification for the evaluation of pipelines with corrosion defects, namely, DNV-RP-F101 [8]. The DNV-RP-F101 criterion provides two evaluation criteria: partial safety factor and allowable stress [9]. The main difference between the two evaluation methods lies in the different safety criteria.
  • Partial safety factor method
The partial safety factor method is a set of safety guidelines based on the DNV offshore criterion OS-F101 and the submarine pipeline system, which fully considers uncertain factors such as the depth of corrosion defects and material properties. The calculation formula of failure pressure is shown in Equation (5).
P f = γ m 2 t σ u D t 1 γ d ( d t ) * 1 γ d ( d t ) * M
2.
Allowable stress method
The allowable stress method is a safety criterion design based on allowable stress. It does not consider many complicated factors. The calculation is simple but not as objective and accurate as the partial safety factor method. The calculation formula of failure pressure is shown in Equation (6).
P f = σ u 2 t D t ( 1 d t 1 d t 1 M )

3.1.6. PCORRC

PCORRC (Pipeline Corrosion Criterion) [10] is a recent evaluation method mainly used to evaluate the residual strength of the medium and high strength steel pipes with blunt corrosion defects due to plastic instability. This method is obtained by Stephens using shell elements to simulate corrosion defects. In this method, the failure pressure of pipelines is determined by tensile strength, not yield strength or flow stress. The calculation formula of failure pressure is shown in Equation (7).
P f = σ u 2 t D t { 1 d t [ 1 exp ( 0.157 l D t D d 2 ) ] }
The failure pressure calculation formula is obtained by fitting the finite element calculation results, mainly considering defects’ length and depth.

3.1.7. RSTRENG

On the basis of ASME B31G-1991, Kiefner and Vieth developed the RSTRENG calculation program, called RSTRENG [11] method, by redefining the Folias factor and material flow stress, and describing the shape of corrosion defects in more detail. RSTRENG is mainly used to evaluate the residual strength of externally corroded pipelines, including RSTRENG 0.85-area method and RSTRENG effective area method [12].
  • RSTRENG 0.85-area method
RSTRENG only requires two parameters: defect depth and length, but adds the flow stress value defined in ASME B31G. In contrast, ASME B31G is more conservative than RSTRENG 0.85-area method, and is the same as the modified B31G in the definitions of flow stress, Folias factor, and defect projection area. The calculation formula is shown in Equation (8).
P f = σ f l o w 2 t D ( 1 0.85 d t 1 0.85 d t 1 M )
2.
RSTRENG effective area method
The RSTRENG effective area evaluation method requires defect depth, defect length, data along the axial and circumferential directions of defects, and detailed corrosion profile. The calculation of the effective area is closer to the actual results. The effective area method has higher accuracy, but the calculation is more complex. The calculation formula is shown in Equation (9).
P f = σ f l o w 2 t D ( 1 A A 0 1 A A 0 1 M )

3.1.8. Others

In addition to the above evaluation methods, there are still some other evaluation methods, such as SY/T 6151-2009 [13] and BS 7910-2005 [14]. SY/T 6151-2009 “evaluation method for corrosion damage of steel pipeline” is the latest oil and gas industry criterion of China issued in December 2009.Compared with ASME B31G criterion, SY/T 6151 criterion considers the influence of circumferential corrosion length, applies fracture mechanics theory to determine the maximum safe working pressure, and classifies and evaluates according to the degree of pipeline corrosion damage. The BS7910-2005 method divides corrosion defects into single defects and combined defects, and uses tensile strength instead of flow stress in the calculation formula.

3.1.9. Comparison

Several existing main residual strength evaluation criteria for corroded pipelines are introduced above, including ASME B31G, modified B31G, DNV-RP-F101, RSTRENG, etc. The above methods have different formula definitions, bulging coefficient and defect area, and their application scope, applicable defect type, and load type are different. The comparison of main criteria and methods is shown in Table 1 and Table 2.

3.2. Intelligent Methods

In the actual pipeline transportation system, many influencing factors do not have a clear functional relationship, and the practical application effect of traditional methods is often not ideal. Therefore, some intelligent methods are gradually used in the field of pipeline corrosion prediction, such as fuzzy mathematics theory method, artificial neural network method, chaos theory method, support vector machine, and so on.

3.2.1. ANN

Deep learning is a branch of machine learning, and ANN is a neural network in deep learning. ANN builds mathematical models by abstracting, simplifying, and simulating biological neural networks’ structure and operating mechanism to process information [15]. A large number of biological neurons connects biological neural networks. Similarly, ANN is also composed of multiple neurons connected according to certain rules. Figure 3 below shows an artificial neural network [16].
In Figure 3, the neural network includes input layer, hidden layer, and output layer. Suppose a training sample is x = (x1, x2, x3, …, xm) ∈ Rm, the corresponding output vector is y= (y1, …, yn), and n is the number of categories. Each neuron has a weight. The input weight of the nth node of the hidden layer is ω 1 h , ω 2 h , , ω m h , and the corresponding offset is γ h . The input weight of the jth output layer node is ω 1 j , ω 2 j , , ω k j , and the corresponding offset is θ j . k is the number of hidden layer nodes. In addition, the hidden layer can be multiple layers.
According to Figure 3, the input of the jth output neuron is shown in Equation (10).
β j = h = 1 k ω h j b h
The output of the jth output neuron is shown in Equation (11).
y j = f ( β j + θ j )
The input of the hth hidden layer neuron is shown in Equation (12).
α h = i = 1 m ω i h x i
The output of the hth hidden layer neuron is shown in Equation (13).
b h = f ( α h + γ h )
In recent years, a growing number of researchers has been using ANN in the oil and gas industry [17], including predicting the remaining strength and remaining life of corroded pipelines. The basic idea of its application is to collect and sort out the pipeline data and then use the built model to train the data set. ANN can better perceive the nonlinear relationship between corrosion factors and corrosion rate to accurately predict the corrosion trend (Figure 4).
Artificial neural networks have many advantages. For example, they can learn any nonlinear function, and artificial neural networks can learn the weights that map any input to output. It also faces some challenges, such as slow training when there is a lot of data, many parameters, and weak interpretability.

3.2.2. Fuzzy Mathematics

Aiming at the randomness and fuzziness of the system, it judges and extracts the uncertainty of the system according to the theory and method of fuzzy mathematics to achieve the purpose of analyzing the system. In short, it is an evaluation method that uses the membership theory of fuzzy mathematics to transform the qualitative evaluation of objects affected by many factors into quantitative evaluation to clarify the fuzzy phenomenon.
  • Triangular fuzzy mathematics theory.
In Figure 5, m is the kernel of A*; u + l is the blindness of A*; u is the membership function of the triangular fuzzy number; A* is the triangular fuzzy number, denoted as A * = ( l i j , m i j , u i j ) .
μ A * ( x ) = { ( x m + l ) / l , l x m ( m + u x ) / u , m x u 0 , others
The triangular fuzzy number A * = ( l i j , m i j , u i j ) is used to represent the judgment result of the importance of evaluation factor μ i to evaluation factor μ j . Among them, m i j is the possible value of measuring the result, which is generally determined by the 1–9 scale method shown in Table 3. l and u represent fuzzy degree. The larger the u-l, the stronger the fuzzy degree. The importance of μ j to μ i is shown in Equation (15).
A * j i = A * i j = ( 1 / l i j , 1 / m i j , 1 / u i j )
Assuming that the fuzzy numbers q1 and q2 are represented by parameters (l1, m1, u1) and (l2, m2, u2), respectively, the algebraic operation law of triangular fuzzy numbers q1 and q2 can be expressed as Equation (16).
{ q 1 q 2 = ( l 1 , m 1 , u 1 ) ( l 2 , m 2 , u 2 ) = ( l 1 + l 2 , m 1 + m 2 , u 1 + u 2 ) q 1 q 2 = ( l 1 , m 1 , u 1 ) ( l 2 , m 2 , u 2 ) = ( l 1 l 2 , m 1 m 2 , u 1 u 2 ) q 1 q 2 = ( l 1 , m 1 , u 1 ) ( l 2 , m 2 , u 2 ) = ( l 1 l 2 , m 1 m 2 , u 1 u 2 ) C q 1 = ( C l 1 , C m 1 , C u 1 )
  • Establish unit fuzzy judgment matrix.
Suppose there are t objects, and the kth (k = 1, 2, …, t) object is compared in pairs for n factors in turn (as long as n(n − 1)/2 times), the unit fuzzy judgment matrix is obtained (Equation (17)).
A ( k ) = ( A * ) n × n
where ( A * ) = ( l i j ( k ) , m i j ( k ) , u i j ( k ) ) .
  • Aggregate unit fuzzy judgment matrix.
According to the specific conditions of the t factors, the weight r k is given respectively, and then their respective unit fuzzy judgment matrix seasons can be changed to the fuzzy judgment matrix A* by the operation rules of triangular fuzzy numbers, and its elements (Equation (18))
A * = ( l i j , m i j , u i j ) = 1 K = 1 t r k [ k = 1 t ( l i j ( k ) , m i j ( k ) , u i j ( k ) ) r k ]
2.
General steps of fuzzy comprehensive evaluation method [20].
  • Establish factor set X = ( X 1 , X 2 , , X i ) , which is composed of evaluation indexes; Construct weight vector A = ( a 1 , a 2 , , a i ) . Define the comment set as W = ( w 1 , w 2 , , w i ) , and obtain the corresponding weight set Y of the factor set Y = ( Y 1 , Y 2 , , Y i ) .
  • Construct weight vector A = ( a 1 , a 2 , , a i ) .
  • Construct evaluation matrix (Equation (19)).
    R = [ r 11 r 12 r 1 j r 21 r 22 r 2 j r i 1 r i 2 r i j ]
    where r x y ( x = 1 , 2 , , i ; y = 1 , 2 , , j ) represents the degree of membership of the factor level index X x to the yth comment set w y .
  • Calculate fuzzy matrix.
Obtain the membership vector B of the factor layer index to the comment set (Equation (20)):
B = Y R = ( Y 1 , Y 2 , , Y i ) [ r 11 r 12 r 1 j r 21 r 22 r 2 j r i 1 r i 2 r i j ] = ( b 1 , b 2 , , b j )
when x = 1 j b x 1 , let b * x = b x / x = 1 j b x to obtain (Equation (21)):
B * = ( b 1 * , b 2 * , , b j * )
where B* is the membership vector of target layer index x to comment set W. According to the specific content of B*, the corresponding evaluation can be obtained.

3.2.3. Chaos Theory and Method

In 1905, H. Poincare discovered chaos for the first time in his research and put forward the H. Poincare conjecture: a small error in the initial conditions produces a great error in the final phenomenon, so the prediction becomes impossible. In 1963, the American meteorologist Lorenz discovered in numerical experiments that deterministic systems sometimes exhibit random behavior phenomena, and then he called it “deterministic nonperiodic flow” in the literature [21]. In 1975, Li TY and Yorke gave a specific definition of chaos for the first time [22]: chaos is a kind of random and random phenomenon that occurs in a deterministic system and is sensitive to initial conditions. It is a phenomenon that exists widely in nature.
The mathematics model of Chaos:
  • Collect a digital sequence (x0, x1, x2, …, xi, …, xs) of a certain characteristic quantity of the observed system.
  • Using difference can generate new first-order difference sequence, second-order difference sequence… (Equations (22) and (23)).
Δ x n = x n + 1 x n
Δ ( Δ x ) = Δ 2 x
  • Take the number of observations as the horizontal axis and the characteristic quantity as the vertical axis to make a graph, which can intuitively and qualitatively grasp the time structure and trend of the phenomenon change.
  • Based on the prediction sequence, calculate any item with one or more items in front of the sequence by assuming the changing structure (Equation (24)):
x n + 1 = f ( x n ) = f ( f ( x n 1 ) ) = f 2 ( x n 1 ) = f n ( x 0 )
Chaos theory is the analysis of irregular and unpredictable phenomena and processes. In essence, a chaotic process is a deterministic process, but it is disorderly, fuzzy, and random on the surface. This is similar to the corrosion development process of pipeline system, but the required sample size must be sufficient.

3.2.4. SVM

Support vector machine, which Cortes and Vapnik first proposed in 1995 [23], is a practical algorithm for nonlinear classification and regression problems in the case of small samples. When dealing with the regression problem, the basic idea is to map the low-dimensional nonlinear regression problem to the high-dimensional feature space, and establish a model in the high-dimensional feature space to learn the data set for regression fitting [24].
Using the basic idea of support vector machine, the data set (x1, x2, …, xn) is mapped to a high-dimensional feature space, and then the data set X is used to establish a model in this space for linear regression. The regression form is as Equation (25).
f ( x i ) = ω φ ( x i ) + b
where ω , b is regression factor, ϕ is the coefficient to be determined in the model.
In order to obtain the regression function, the above problem is transformed into the following planning problem (Equation (25)).
m i n 1 2 ω T ω + C i = 1 n ξ i + C i = 1 n ξ i *
Constraints are:
s . t . { y i ω φ ( x i ) b ε + ξ i * ω φ ( x i ) + b y i ε + ξ i ξ i , ξ i * 0
where C is the penalty term constant, ε is the insensitive loss function, and ζ i , ζ i * are the slack variables.
By introducing Lagrange function, the above optimization problem can be transformed into Lagrange dual problem, and the solution is as follows:
f ( x ) = i = 1 l ( α i α i * ) K ( X d , X ) + b
where a i , a i * is the Lagrange multiplier, when ( a i a i * ) is not 0, the corresponding sample is support vector; K ( X d , X ) is the kernel function, the selection of kernel function should make it a point product of high-dimensional feature space.
SVM as a typical machine learning method, is widely used in classification and regression. It can avoid the neural network falling into local optimization, and it is usually used in the case of small amount of data such as pipeline corrosion failure.

3.2.5. Comparison

Choosing appropriate methods can effectively improve the evaluation effect and prediction accuracy. The advantages and disadvantages of each method are listed in Table 4 to facilitate researchers choosing and using a suitable method.

3.2.6. Intelligent Prediction Models Review

By reading a large number of literature, and extracting and sorting out the information in the literature, 71 intelligent prediction models in Table 5 were finally obtained. Some of these models are basic models, but more of them are hybrid models improving their algorithms, data cleaning methods, and optimizers. The hybrid model often achieves higher accuracy and better performance. These models are sorted as follows according to data size, input variables, output variables, performance, publishing time, etc.

4. Discussions

4.1. Publishing Time

Figure 6 shows the number of publications from 2011 to November 2021, for 71 models. Although this is not all the literature, the search results are sorted by relevance, and the data in the figure are still representative and reliable. The figure shows that from 2011 to 2015, the research progress of using intelligent models to predict remaining strength and remaining life was relatively stable. Although there was a sharp decline in 2016–2018, the overall trend was stable. After 2019, related research showed a spurt of growth. It can be inferred that the prediction of remaining strength and remaining life is still a research hot spot.

4.2. Result Analysis of Traditional Evaluation Methods

Due to the differences in various evaluation methods in many aspects [54], the calculation results also be affected. In all, 64 groups of data were collected from the literature [12], including 40 groups of low-strength steel grade corrosion pipes (X42, X46-1, X46-2, X46-3, X46-4, X52-1, X52-2, and X56) and 24 groups of medium and high-strength steel grade corrosion pipes (X60, X65, and X80), including defect size parameters, pipe size parameters, material parameters, and burst test pressure. The result analysis of various evaluation methods is shown in Figure 7, Figure 8, Figure 9 and Figure 10. As the figures show, ASME B31G has large errors in evaluating whether it is a medium-to-high strength pipeline or a low-strength pipeline. The Modified B31G has improved significantly. When evaluating low-strength steel pipes, the DNV-RP-F101 allowable stress method and PCORRC have similar errors. However, when evaluating high-strength steel-grade pipelines, the accuracy of the DNV-RP-F101 allowable stress method is much higher than that of PCORRC.

4.3. Prediction Accuracy

Error indicator can be used to evaluate the performance of prediction model [55,56,57,58,59]. By counting the indicators used in the discussed models, this paper summarizes 18 indicators used to evaluate the prediction accuracy. Their expressions are shown in Equations (28)–(43), Figure 11 indicates that the most frequently used error indicators are MSE, R2, MAPE, RMSE, and MAE. Among these indicators, MSE, RMSE, and MAE have no benchmark because the data dimension because the data sets dimensions are different. MAPE and R2 can be compared in different usage scenarios because they reflect relative errors. The closer R2 is to one, the higher the prediction accuracy. The smaller the MAPE, the higher the prediction accuracy. MAPE and R2 in residual strength and residual life prediction models are counted in the Table 6. Among the 71 models, the range of MAPE is between 0.0123 and 0.1499, the range of R2 is between 0.619 and 0.999. Lewis once gave a reference, when the MAPE is less than 0.1, the model performance is excellent; when the MAPE is greater than 0.1 and less than 0.2, the model performance is good; when the MAPE is greater than 0.2 and less than 0.5, the model performance is reasonable; and when the MAPE is greater than 0.5, the model is not suitable.
M S E = 1 n i = 1 n ( R i P i ) 2
M R E = 1 n i = 1 n | R i P i R i |
R E = R i P i R i
R 2 = 1 i = 1 n ( R i P i ) 2 i = 1 n ( R i ¯ P i ) 2  
R M S E = 1 n i = 1 n ( R i P i ) 2
R M S P E = 1 n i = 1 n ( R i P i R i ) 2
U 95 = 1.96 i = 1 n ( R i R ¯ ) n 1 i = 1 n ( R i P i ) 2 n
N S E = 1 i = 1 n ( R i P i ) 2 i = 1 n ( R i R i ¯ ) 2
M A E = 1 n i = 1 n | R i P i |  
S S E = i = 1 n ( R i P i ) 2
A I P = 100 % n i = 1 n | 1 P i R i |
A V P = 1 A I P
S T D E = s t d ( R i P i )
A E = | R i P i |
a 20 index = er 20 n
μ = 1 n i = 1 n P i R i

4.4. Data Size and Data Division

Data size is one of the main factors affecting forecasting performance. Too much data will lead to too much calculation, while too little data may lead to the insufficient model accuracy. Table 7 provides statistical information on the data size of 71 smart models, which can provide a basis for selecting data sizes in subsequent studies. The original data are usually divided into three data sets in machine learning, including training set, validation set, and test set. The training set is used to train the model; the validation set data are used to adjust the parameters of the training model; and the test set data are used to measure the performance of the training model. However, only 2 of the 71 models divide the original data into three data sets, and the remaining 69 models only divide it into the training and test sets (Figure 12). The proportion of test set is in the range of 0.015–0.4.

4.5. Input Variable and Output Value

In the intelligent model, how to determine the input variables is a very critical issue [60,61]. Therefore, in the remaining strength and remaining life prediction model, it is necessary to consider which factors are used as input variables fully. According to the input variables, it can be divided into two categories. One is to simply use certain historical data as input variables to predict the future trend of the variable, such as using the historical wall thickness of the pipeline to predict the remaining wall thickness or using the historical corrosion rate to predict the future corrosion rate. The other is the prediction that considers multiple factors, such as predicting the burst pressure of the pipeline through pipeline size parameters, defect parameters, environmental parameters, and material parameters (Table 8). The former is simple to calculate, and convenient to obtain data, but the prediction accuracy is not necessarily high, because this type of prediction assumes that external factors are stable. The latter is difficult to obtain data, and needs to consider the nonlinear relationship of multiple variables, but the prediction results are often more comprehensive and accurate. According to the statics of the models compiled in this paper, 10 of the 71 models are simple time-series predictions, and the rest are forecasting considering multiple factors.
The prediction targets of these models can be roughly divided into the following four categories: burst pressure, remaining thickness, corrosion rate, and others. Among them, burst pressure accounts for 36%, remaining thickness accounts for 18.7%, corrosion rate accounts for 21.3%, corrosion defect depth accounts for 6.7%, and the others accounts for 17.3%. The proportion of each item is shown in Figure 13. It can be seen from Figure 13 that the model with burst pressure as the output value is still the most, the rest are similar.

4.6. Future Research Directions

Based on the literature review, the future development direction of the residual strength and residual life prediction models is summarized as follows:
  • Most models ignore setting the validation set. In fact, in machine learning, adjusting parameters can effectively improve the prediction performance of the model.
  • Many of the existing models have achieved good accuracy, but few papers mention the stability of these models. If these models are needed to be used in actual working conditions, stability is also important.
  • Existing models usually have small amounts of data collected, leading to limitations in their predictions. More efforts can be made in data collection to improve their generality.
  • At present, most studies are mainly based on uniform corrosion under normal conditions, but do not consider the degradation of pipeline materials, in fact, the change in mechanical characteristics can be very large, while the kinetics of degradation of mechanical properties differs in different climatic zones [62,63]. More specific conditions can be considered for further research in the future.

5. Conclusions

This paper reviews the assessment of pipeline residual strength and residual life prediction works from 2009 to November 2021. After screening, a total of 71 models are carefully reviewed. The parameters, application scope, defect type, load type, and accuracy of the traditional evaluation methods are compared, but publishing time, prediction accuracy, data size, data division, input variable, and output value are further discussed. Based on the analysis and discussion results, the following primary conclusions can be drawn:
  • In the past ten years, from 2011 to 2018, the research progress of remaining strength and remaining life has been relatively stable and the number increased significantly after 2018. The improved hybrid model based on the basic model is a research hotspot. Furthermore, predicting with improved intelligent models will be the trend in the future.
  • The accuracy of Modified B31G is higher than ASME B31G, but it is not suitable to evaluate medium–high strength steel grades pipelines. PCORRC and DNV-RP-F101 are similar in evaluating low strength pipelines, and DNV-RP-F101 has a better performance in evaluating medium–high strength pipelines.
  • The most frequently used error indicators are MSE, R2, MAPE, RMSE, and MAE. Among them, MAPE is in the range of 0.0123–0.1499; R2 is in the range of 0.619–0.999.
  • The proportion of test data set is between 0.015 and 0.4, and only 2 of 71 models are using the validation set. In fact, correctly setting the proportion of data can further improve the prediction accuracy and achieve better results. Researchers also need to pay more attention to this aspect.
  • Models are divided into considering a single variable in the time series, and considering multiple factors based on input variables. There are 61 of 71 models in this paper considering multiple factors. These models can be divided into four main categories based on output value. Among them, burst pressure accounts for 36%, remaining thickness accounts for 18.7%, corrosion rate accounts for 21.3%, corrosion defect depth accounts for 6.7%, and the others accounts for 17.3%.

Author Contributions

Conceptualization, H.L.; formal analysis, H.L.; investigation, H.L.; resources, Q.Z.; writing—original draft preparation, H.L.; writing—review and editing, K.H.; visualization, C.S.; supervision, K.H. All authors have read and agreed to the published version of the manuscript.

Funding

This research received no external funding.

Institutional Review Board Statement

Not applicable.

Informed Consent Statement

Not applicable.

Data Availability Statement

Not applicable.

Acknowledgments

Thanks to Lu Hongfang for his careful guidance during the writing of the thesis.

Conflicts of Interest

The authors declare no conflict of interest.

Nomenclature

AProjected area of defect on axial through wall plane
A*The triangular fuzzy number
A0Cross sectional area of original pipe wall at defect
a20-indexer20/n
er20Number of samples whose absolute error is less than 20%
MFolias Bulging Coefficient
nSample size
fuTensile strength (considering temperature reduction effect)
PfThe residual strength of the pipe
PiPrediction value at time k
R2 Goodness of Fit
RiReal value at time i
stdPopulation standard deviation
U95The confidence level of the expanded uncertainty is 95%
σ flow The flow stress
σ u The tensile strength of the pipe
ε d Quantile coefficient of defect depth
γ m Partial safety factor
γ d Defect depth safety factor
(d/t) *(d/t) meas + εd·std (d/t)
(d/t) measMeasured value of defect depth ratio
Abbreviations
AEAverage Error
AGAAmerican National Gas Association
AIPAverage Invalidity Percent
ANNArtificial Neural Network
ANPAnalytic Network Process
ASMEAmerican Society of Mechanical Engineers
AVPAverage Validity Percent
AWAnode Wastage
BCBicarbonate
BDBulk Density
BGBritish Gas Company
BPBurst Pressure
BPNNBack Propagation Neural Network
BSWBasic Sediments and Water
BWNNB-spline Wavelet Neural Network
CCCoating Condition
CDDCorrosion Defect Depth
CGCrossings
CMCCalcium/Magnesium ion Content
CPCathodic Protection
CRCorrosion Rate
CSCuckoo Search
CVCross Validation
dThe depth of corrosion defect
DPipe Diameter
DCDissolved Chloride
DNNDeep Neural Networks
DNVDET NORSKE VERITAS
EGIGEuropean Gas Pipeline Incident Data Group
ELMExtreme Learning Machines
EMElastic Modulus
FSFree Spans
FSMField Signature Method
FSNNFuzzy Surfacelet Neural Network
GAGenetic Algorithm
GBDT Gradient Boosting Decision Tree
GBMGradient Boosting Machine
GM(1,1)First Order Univariate Gray System Model
GPRGas Production Rate
GRNNGeneral Regression Neural Network
GSGGas Specific Gravity
HOLLiquid Holdup
HTKHeat Transfer Coefficient of Inner wall
IDAImproved Dragonfly Algorithm
IPSAImproved Particle Swarm Algorithm
JCJoint Condition
KRKriging
lthe length of corrosion defect
LWPLocally Weighted Polynomials
MAEMean Absolute Error
MAPEMean Absolute Percentage Error
MARSMultivariate Adaptive Regression Splines
MLMetal Loss
MOGWOMultiobjective Grey Wolf Optimization
MREMean Relative Error
MSEMean Square Error
NSENash-Sutcliffe Efficiency
NSGANondominated Sorting Genetic Algorithm
OCOxygen Content
OPOperating Pressure
OPROil Production Rate
ORPOxidation-reduction potential
PPressure
PCAPrincipal Component Analysis
PCO2Partial Pressure of CO2
PCORRCPipeline Corrosion Criterion
PPPipe-to-soil Potential
PSIDDeposition Rate
PSOParticle Swarm Optimization
PSOParticle Swarm Optimizer
RBFRadial Basis Function
RERelative Error
RFRandom Forest
RMSERoot Mean Square Error
RMSRERoot Mean Squared Relative Error
RPRedox Potential
RSRough Set
SCSulfate ion Concentrations
SECStray Electric Current
SGDStochastic Gradient Descent
SRSoil resistivity
SSCNSubspace Clustered Neural Network
SSEError Sum of Squares
SMTSThe material tensile limit
SMYSThe minimum yield stress
STCSalt Content
STDEPopulation standard deviation of error
SUPSupport Condition
SVMSupport Vector Machine
SVRSupport Vector Regression
TTime(years)
TAUWGWall shear stress (gas phase)
TAUWHLLiquid-maximum wall shear stress
TAUWWTWall shear stress (liquid phase)
TDATraditional Dragonfly Algorithm
TMTemperature
ULLiquid flow rate
USGSuperficial Velocity Gas
UTSUltimate Tensile Strength
wThe width of corrosion defect
WCWater Content
WNNWeighted nearest neighbor
WPRWater Production Rate
WTWall Thickness
YSYield Strength

References

  1. EGIG. Available online: https://www.egig.eu/reports (accessed on 19 October 2021).
  2. Lyons, C.J.; Race, J.M.; Chang, E.; Cosham, A.; Barnett, J. Validation of the ng-18 equations for thick walled pipelines. EFA 2020, 112, 104494. [Google Scholar] [CrossRef]
  3. The American Society of Mechanical Engineers. Manual for Determining the Remaining Strength of Corroded Pipelines; ASME: New York, NY, USA, 1984; pp. 1–38. [Google Scholar]
  4. The American Society of Mechanical Engineers. Manual for Determining the Remaining Strength of Corroded Pipelines; ASME: New York, NY, USA, 1991; pp. 1–47. [Google Scholar]
  5. Kiefner, J.F.; Vieth, P.H. A Modified Criterion for Evaluating the Remaining Strength of Corroded Pipe; Pipeline Research Committee, American Gas Association: Washington, DC, USA, 1989. [Google Scholar]
  6. Ma, B.; Jian, S.; Wang, J.; Han, K. Analysis on the latest assessment criteria of ASME b31g-2009 for the remaining strength of corroded pipelines. JFAP 2011, 11, 666–671. [Google Scholar] [CrossRef]
  7. Ma, B.; Shuai, J.; Li, X.; Wang, J.; Feng, Q. Advances in the newest version of ASME b31g-2009. NGI 2011, 31, 112–115. [Google Scholar]
  8. Veritas, D.N. Corroded Pipelines; RP, 2004; p. 11. Available online: http://opimsoft.com/download/reference/rp-f101_2006-10.pdf (accessed on 19 October 2021).
  9. Xiao, K.; Liu, Y.; Wang, L.; Qian, Y. A Study on Assessment Methods for the Remaining Strength of Corroded Pipelines; GCI: Anchorage, AK, USA, 2013. [Google Scholar]
  10. Stephens, D.R.; Leis, B.N.; Kurre, M.D.; Rudland, D.L. Development of an alternative criterion for residual strength of corrosion defects in moderate-to high-toughness pipe. In Proceedings of the 2000 International Pipeline Conference, Calgary, AB, Canada, 1–5 October 2000. [Google Scholar]
  11. Tomar, M.S.; Fingerhut, M. Reliable application of rstreng criteria for in-the-ditch assessment of corrosion defects in transmission pipelines. NACE Int. Corros. Conf. Ser. 2006, 176, 1–8. [Google Scholar]
  12. Wang, L.B. Development of Software for Residual Strength Evaluation and Residual Life Prediction of Corroded Pipelines. Master’s Thesis, Xi’an Shiyou University, Xi’an, China, 2014. [Google Scholar]
  13. Hua, C. Contrastive Study on New and Old Evaluation Standards of SY/T 6151 for Corrosion Pipeline. CCI 2016, 45, 1476–1479. [Google Scholar]
  14. Chen, Z.; Wu, M.; Xie, F.; Wang, D.; Guo, Q.; Ma, F. Evaluation method and remaining life prediction of corroded pipeline residual strength. MEM 2015, 5, 97–101. [Google Scholar]
  15. Rosenblatt, F. The perceptron: A probabilistic model for information storage and organization in the brain. Psychol. Rev. 1958, 65, 386–408. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  16. Katz, W.T.; Snell, J.W.; Merickel, M.B. Artificial neural networks. Methods Enzymol. 1992, 210, 610–636. [Google Scholar]
  17. Rahmanifard, H.; Plaksina, T. Application of artificial intelligence techniques in the petroleum industry: A review. Artif. Intell. Rev. 2019, 52, 2295–2318. [Google Scholar] [CrossRef]
  18. Zhao, Y.; Zhao, B. Research on pressure pipeline explosion based on triangular fuzzy mathematics and fault tree analysis. JLUPCT 2018, 6, 65–69. [Google Scholar]
  19. Wind, Y.; Saaty, T. Marketing Applications of the Analytic Hierarchy Process. Manag. Sci. 1980, 26, 641–658. [Google Scholar] [CrossRef]
  20. Liang, Q. Pressure pipeline leakage risk research based on trapezoidal membership degree fuzzy mathematics. GST 2019, 24, 48–53. [Google Scholar]
  21. Lorenz, E.N. Deterministic nonperiodic flow. SNY 1963, 20, 130–141. [Google Scholar] [CrossRef] [Green Version]
  22. Hunt, B.R.; Li, T.Y.; Kennedy, J.A.; Nusse, H.E. Period three implies chaos. SNY 2004, 6, 77–84. [Google Scholar]
  23. Cortes, C.; Vapnik, V.; Llorens, C. Support-vector networks. Mach. Learn. 1995, 20, 273–297. [Google Scholar] [CrossRef]
  24. Liu, H.; Liu, D.; Zheng, G.; Liang, Y. Research on natural gas short term load forecasting based on support vector expression. Chin. J. Chem. Eng. 2004, 12, 5. [Google Scholar]
  25. Qu, C. Study on Residual Life Prediction METHOD of Corrosive Defective Pipeline. Master’s Thesis, Northeast University, Shenyang, China, 2014. [Google Scholar]
  26. Yan, J. Study on Prediction and Evaluation Method of Inner WALL corrosion of SUBMARINE pipeline. Master’s Thesis, Dalian University of Technology, Dalian, China, 2020. [Google Scholar]
  27. Qin, X.; Liu, W.; Chen, L. Pipeline corrosion prediction based on improved bee colony algorithm and grey model. J. Beijing Univ. Chem. Technol. 2021, 48, 74–80. [Google Scholar]
  28. Wang, W.H. Corrosion Rate Prediction and Residual Life Research of Buried Oil and Gas Pipelines. Master’s Thesis, Xi’an University of Architecture and Technology, Xi’an, China, 2019. [Google Scholar]
  29. Cheng, X. Study on Corrosion Residual Life Prediction of Buried Gas PIPELINE Based on Comprehensive Detection. Master’s Thesis, South China University of Technology, Guangzhou, China, 2016. [Google Scholar]
  30. Peng, S.; Zhang, Z.; Liu, E.; Liu, W.; Qiao, W. A new hybrid algorithm model for prediction of internal corrosion rate of multiphase pipeline. J. Nat. Gas. Sci. Eng. 2021, 85, 103716. [Google Scholar] [CrossRef]
  31. Ben Seghier, M.E.A.; Keshtegar, B.; Taleb-Berrouane, M.; Abbassi, R.; Trung, N. Advanced intelligence frameworks for predicting maximum pitting corrosion depth in oil and gas pipelines. Process Saf. Environ. 2021, 147, 818–833. [Google Scholar] [CrossRef]
  32. Ossai, C.I. Corrosion defect modelling of aged pipelines with a feed-forward multi-layer neural network for leak and burst failure estimation. Eng. Fail. Anal. 2020, 110, 104397. [Google Scholar] [CrossRef]
  33. Sun, J.; Zhao, B.; Gao, D.; Xu, L. Fuzzy surfacelet neural network evaluation model optimized by adaptive dragonfly algorithm for pipeline network integrity management. Appl. Soft. Comput. 2021, 113, 107862. [Google Scholar] [CrossRef]
  34. Zhang, T.; Zhou, L. Combining Forecasting Model of Pipeline’s Corrosion Rate Based on Artificial Immune Algorithm. In Proceedings of the International Conference on Pipelines and Trenchless, Wuhan, China, 19–22 October 2012. [Google Scholar]
  35. El-Abbasy, M.S.; Senouci, A.; Zayed, T.; Mirahadi, F.; Parvizsedghy, L. Condition Prediction Models for Oil and Gas Pipelines Using Regression Analysis. J. Constr. Eng. Manag. 2014, 140. [Google Scholar] [CrossRef]
  36. Luo, Z.; Hu, X.; Gao, Y. Corrosion research of wet natural gathering and transportation pipeline based on SVM. In Proceedings of the International Conference on Pipelines and Trenchless, Xi’an, China, 16–18 October 2013. [Google Scholar]
  37. Lu, H.; Xu, Z.D.; Iseley, T.; Matthews, J.C. Novel Data-Driven Framework for Predicting Residual Strength of Corroded Pipelines. J. Pipeline Syst. Eng. 2021, 12, 04021045. [Google Scholar] [CrossRef]
  38. Zheng, Y.; Shu, J.; Ren, C.; Zhang, F. Prediction of Gathering Pipeline Internal Corrosion Rate Based on Improved Wavelet Neural Network Model. In Proceedings of the International Conference on Pipelines and Trenchless Technology, Beijing, China, 26–29 October 2011. [Google Scholar]
  39. Sun, B.C.; Li, S.X.; Yu, S.R.; Zeng, H.L. Improved BP algorithm to predict the residual strength of corroded pipelines. CJCP 2011, 5, 404–408. [Google Scholar]
  40. Sharifi, M.; Yao, K.T.; Raghavendra, S.; Ershaghi, I.; House, R.; Blouin, J. Prediction of Remaining Life in Pipes using Machine Learning from Thickness Measurements. In Proceedings of the SPE Western Regional Meeting, Garden Grove, CA, USA, 27–30 April 2015. [Google Scholar]
  41. Hou, P.P. Research on the Influence of Corrosion Defects on the Residual Strength of Oil and Gas Pipelines. Master’s Thesis, Xinjiang University, Xinjiang, China, 2017. [Google Scholar]
  42. Sun, B.C.; Wu, J.W.; Li, L.; She, Z.G. Improved GA-BP algorithm for oil and gas pipeline corrosion residual strength prediction. JSPU Nat. Sci. Ed. 2013, 3, 160–167. [Google Scholar]
  43. Ma, S.; Li, J.F.; Bai, R.; Dai, Z. Prediction of residual strength of oil and gas pipelines based on PCA-SVR model. OGST 2019, 10, 1119–1124. [Google Scholar]
  44. Wang, W.H.; Luo, Z.S.; Zhang, X.S. Prediction of buried pipeline corrosion remaining life based on PSO-GRNN model. Surf. Technol. 2019, 10, 267–275. [Google Scholar]
  45. Yang, X.D.; Zhou, Y.L.; Liu, Z.J.; Lu, L.; Yu, T.Q.; Liu, Y. Research on residual strength prediction technology of corroded pipeline based on RS-PSO-SVM algorithm. PEC 2020, 3, 8–12. [Google Scholar]
  46. Xie, P.; Liu, H.; Gong, Y.H.; Ni, P.P.; Heman, A. Evaluation of residual strength of external corrosion of submarine pipelines based on deep learning. OGST 2021, 6, 651–657. [Google Scholar]
  47. Luo, Z.S.; Yuan, H.W. GM-RBF submarine pipeline corrosion prediction model based on error compensation. CJSS 2018, 3, 96–101. [Google Scholar]
  48. Ma, G. Residual Strength Prediction of Single-Defect Pipeline Based on Correlation Analysis and SVM Algorithm. Master’s Thesis, Xi’an Petroleum University, Xi’an, China, 2020. [Google Scholar]
  49. Li, J.G.; Lin, S.J.; Long, W.; Xu, L. Prediction of remaining life of metal pipes in uniform corrosion based on FSM non-destructive testing. Surf. Technol. 2016, 3, 7–11. [Google Scholar]
  50. Li, Q.; Sun, C.M.; Huang, Z.Q.; Xiao, X.; Tang, H.P. Combined forecasting method of GA-BP neural network for failure pressure of Lan-Cheng-Yu corroded pipelines. OJSST 2015, 11, 83–89. [Google Scholar]
  51. Zhang, Y. Research on Residual Strength of Multipoint Corrosion Defective Pipeline Based on Finite Element and PSO-BP. Master’s Thesis, Xi’an University of Architecture and Technology, Xi’an, China, 2020. [Google Scholar]
  52. Bi, A.R.; Luo, Z.S.; Song, Y.Y.; Zhang, X.S. Residual strength analysis of internally corroded submarine pipeline based on FOA-GRNN model. CSSJ 2020, 6, 78–83. [Google Scholar]
  53. Jia, S.Q.; Qie, Y.H.; Li, Y.T.; Li, N.N. Research on burst pressure prediction of oil and gas pipelines with uniform corrosion defects based on GA-BPNNs algorithm. JSST 2020, 12, 105–110. [Google Scholar]
  54. Syrotyuk, A.; Vytyaz, O.; Ziaja, J. Damage to flexible pipes of coiled tubing equipment due to corrosion and fatigue: Methods and approaches for evaluation. Min. Mineral. Depos. 2017, 11, 96–103. [Google Scholar] [CrossRef] [Green Version]
  55. Lu, H.; Iseley, T.; Matthews, J.; Liao, W.; Azimi, M. An ensemble model based on relevance vector machine and multi-objective salp swarm algorithm for predicting burst pressure of corroded pipelines. J. Petrol. Sci. Eng. 2021, 203, 108585. [Google Scholar] [CrossRef]
  56. Xu, Z.D.; Zhu, C.; Shao, L.W. Damage identification of pipeline based on ultrasonic guided wave and wavelet denoising. J. Pipeline Syst. Eng. 2021, 12, 04021051. [Google Scholar] [CrossRef]
  57. Lu, H.; Iseley, T.; Matthews, J.; Liao, W. Hybrid machine learning for pullback force forecasting during horizontal directional drilling. Automat. Constr. 2021, 129, 103810. [Google Scholar] [CrossRef]
  58. Xu, Z.D.; Yang, Y.; Miao, A.N. Dynamic Analysis and Parameter Optimization of Pipelines with Multidimensional Vibration Isolation and Mitigation Device. J. Pipeline Syst. Eng. 2021, 12, 04020058. [Google Scholar] [CrossRef]
  59. Lu, H.; Matthews, J.C.; Azimi, M.; Iseley, T. Near Real-Time HDD Pullback Force Prediction Model Based on Improved Radial Basis Function Neural Networks. J. Pipeline Syst. Eng. 2020, 11, 04020042. [Google Scholar] [CrossRef]
  60. Peng, S.; Chen, R.; Yu, B.; Xiang, M.; Lin, X.; Liu, E.E. Daily natural gas load forecasting based on the combination of long short term memory, local mean decomposition, and wavelet threshold denoising algorithm. J. Nat. Gas. Sci. Eng. 2021, 95, 104175. [Google Scholar] [CrossRef]
  61. Lu, H.; Behbahani, S.; Ma, X.; Iseley, T. A multi-objective optimizer-based model for predicting composite material properties. Constr. Build. Mater. 2021, 284, 122746. [Google Scholar] [CrossRef]
  62. Maruschak, P.; Prentkovskis, O.; Bishchak, R. Defectiveness of external and internal surfaces of the main oil and gas pipelines after long-term operation. J. Civil. Eng. Manag. 2016, 22, 279–286. [Google Scholar] [CrossRef]
  63. Panin, S.; Maruschak, P.; Vlasov, I.; Syromyatnikova, A.; Bolshakov, A.; Berto, F.; Prentkovskis, O.; Ovechkin, B. Effect of Operating Degradation in Arctic Conditions on Physical and Mechanical Properties of 09Mn2Si Pipeline Steel. Procedia Eng. 2017, 178, 597–603. [Google Scholar] [CrossRef]
Figure 1. Distribution of incidents: (a) 2004–2013; (b) 2009–2013; (c) 2010–2019; (d) with leak size pinhole/crack (2010–2019).
Figure 1. Distribution of incidents: (a) 2004–2013; (b) 2009–2013; (c) 2010–2019; (d) with leak size pinhole/crack (2010–2019).
Energies 15 00726 g001
Figure 2. The evaluation process of ASME B31G-2009.
Figure 2. The evaluation process of ASME B31G-2009.
Energies 15 00726 g002
Figure 3. Neural network structure.
Figure 3. Neural network structure.
Energies 15 00726 g003
Figure 4. Nine ANN-based models for residual strength or residual life prediction.
Figure 4. Nine ANN-based models for residual strength or residual life prediction.
Energies 15 00726 g004
Figure 5. Membership function curve of triangular fuzzy number [18].
Figure 5. Membership function curve of triangular fuzzy number [18].
Energies 15 00726 g005
Figure 6. The number of related intelligent models from 2011 to November 2021.
Figure 6. The number of related intelligent models from 2011 to November 2021.
Energies 15 00726 g006
Figure 7. Comparison of burst pressure and predicted failure pressure of low-strength pipelines calculated by different methods: (a) ASME B31G; (b) Modified B31G; (c) Allowable stress; (d) PCORRC.
Figure 7. Comparison of burst pressure and predicted failure pressure of low-strength pipelines calculated by different methods: (a) ASME B31G; (b) Modified B31G; (c) Allowable stress; (d) PCORRC.
Energies 15 00726 g007
Figure 8. Comparison of burst pressure and predicted failure pressure of medium and high strength pipelines calculated by different methods: (a) ASME B31G; (b) Modified B31G; (c) Allowable stress; (d) PCORRC.
Figure 8. Comparison of burst pressure and predicted failure pressure of medium and high strength pipelines calculated by different methods: (a) ASME B31G; (b) Modified B31G; (c) Allowable stress; (d) PCORRC.
Energies 15 00726 g008
Figure 9. Errors in calculating failure pressure of corroded pipelines of low, medium, and high strength steel grades by different methods: (a) RMSE; (b) MAE; (c) MSE.
Figure 9. Errors in calculating failure pressure of corroded pipelines of low, medium, and high strength steel grades by different methods: (a) RMSE; (b) MAE; (c) MSE.
Energies 15 00726 g009
Figure 10. Different methods to calculate relative error of failure pressure of: (a) low-strength steel grade corroded pipeline; (b) high-strength steel grade corroded pipelines.
Figure 10. Different methods to calculate relative error of failure pressure of: (a) low-strength steel grade corroded pipeline; (b) high-strength steel grade corroded pipelines.
Energies 15 00726 g010
Figure 11. The frequency of using various error indicators in 71 models.
Figure 11. The frequency of using various error indicators in 71 models.
Energies 15 00726 g011
Figure 12. Division proportion of raw data.
Figure 12. Division proportion of raw data.
Energies 15 00726 g012
Figure 13. Output value of 71 models.
Figure 13. Output value of 71 models.
Energies 15 00726 g013
Table 1. Comparison of parameters in residual strength evaluation methods.
Table 1. Comparison of parameters in residual strength evaluation methods.
Evaluation MethodFlow StressFolias Bulging CoefficientCorrosion Projection Area
ASME B31G1.1SMYS M = 1 + 0.8 L 2 D t 2 3 d l (parabolic);
d l (rectangle).
Modified B31GSMYS + 68.95 M = { 1 + 0.6275 ( l D t ) 2 0.003375 ( l D t ) 4 ( l 2 D t 50 ) 0.032 l 2 D t + 3.3 ( l 2 D t 50 ) 0.85 d l (between parabolic and rectangle)
SY/T 6151-2009SMTS + 68.95 M = { 1 + 0.6275 ( l D t ) 2 0.003375 ( l D t ) 4 ( l 2 D t 50 ) 0.032 l 2 D t + 3.3 ( l 2 D t 50 ) 0.85 d l (between parabolic and rectangle)
DNV-RP-F101SMTS M = 1 + 0.31 [ L D t ] 2 d l
PCORRCSMTS
RSTRENG 0.85-area methodSMTS + 68.95 M = { 1 + 0.6275 ( l D t ) 2 0.003375 ( l D t ) 4 ( l 2 D t 50 ) 0.032 l 2 D t + 3.3 ( l 2 D t 50 ) 0.85 d l (between parabolic and rectangle)
RSTRENG Effect area methodSMTS + 68.95 M = { 1 + 0.6275 ( l D t ) 2 0.003375 ( l D t ) 4 ( l 2 D t 50 ) 0.032 l 2 D t + 3.3 ( l 2 D t 50 )
Table 2. Comparison of residual strength evaluation methods for pipes with different corrosion defect.
Table 2. Comparison of residual strength evaluation methods for pipes with different corrosion defect.
Evaluation MethodBest Scope of ApplicationDefect TypeLoad Type
ASME B31GMedium and low strength steelIsolated defectInternal pressure
Modified B31GMedium and low strength steelIsolated defect or treat the interaction defect as an isolated defectInternal pressure
SY/T 6151-2009Carbon steel and low alloy steel pipes with blunt and low stress concentration corrosion damageIsolated defect or treat the interaction defect as an isolated defectInternal pressure
DNV-RP-F101Medium and high strength steelSingle defect/interaction defect, complex shape defectInternal pressure/axial compressive stress
PCORRCMedium and high strength steelIsolated defect or treat the interaction defect as an isolated defectInternal pressure
RSTRENG Effect area Medium and low strength steelComplex shape defectInternal pressure
Table 3. Scale method [19].
Table 3. Scale method [19].
ScaleRelative Comparison
1Two factors are equally important
3One factor is slightly more important than the other
5One factor is obviously more important than another
7One factor is obviously much more important than another
9One factor is absolutely more important than another
2,4,6,8The importance is between 1.3.5.7.9
Table 4. Merits and limitations of various methods.
Table 4. Merits and limitations of various methods.
MethodsMeritLimitation
ANNIt has strong robustness and fault tolerance to noise neural network, can fully approach complex nonlinear relations, and has the function of associative memory.Neural network needs a large number of parameters and its interpretability is not strong.
Fuzzy mathematicsIt is able to make a more scientific, reasonable, and realistic quantitative evaluation of the data with the hidden information presenting fuzziness. The evaluation result is a vector, not a point value. It contains rich information that can describe the evaluated object more accurately and be further processed to obtain reference information.The calculation is complicated, and the determination of the index weight vector is subjective. When the index set is large, it is difficult to compare the membership degrees, and even causes the evaluation to fail.
Chaos theoryIt can effectively explain or solve nonlinear complex problems, and has obvious effect in short-term prediction.Chaos behavior is very sensitive to initial conditions, so sufficient and accurate data are required. The effect of long-term prediction is poor.
SVMIt can achieve good performance under less data, and has good generalization performance, which is not easy to over fit.The speed of large-scale training samples is slow. The traditional SVM is not suitable for multi classification and is sensitive to missing data, parameters, and kernel function.
Table 5. 71 intelligent prediction models.
Table 5. 71 intelligent prediction models.
ReferenceModel(s)Data Size (s)Proportion of Training Set, Validation Set, and Test SetInput Variable(s)OutputPerformanceYear
[25]GA-BP302:0:1OC, pH, TM, P, UL, SC, WC, l, w, dBurst pressureMSE = 0.00024659;
R2 = 0.99988;
2014
[26]GBDT254:0:1SC, pH, TM, UL, PCorrosion rateMSE = 0.0000326;
MAPE = 0.0225;
R2 = 0.9834;
2020
[27]IABC-EGM (1,1)182:0:1Elbow wall thickness valueRemaining thicknessMRE = 0.0228;2021
[28]RS-PSO-GRNN203:1:1SR, ORP, pH, SEC, SCCorrosion rateRSE = 0.0058;
MAPE = 0.0561
2019
[29]ANN154:0:1D, WT, UTS, YS, l, dRemaining thicknessRE;2016
[30]PCA-CPSO-SVR600.85:0:0.15TM, HOL, P, PCO2, UL, TAUWWT, TAUWG, pHCorrosion rateMAE = 0.083;
RMSE: 0.027;
MAPE = 0.166;
2021
[30]SVR600.85:0:0.15TM, HOL, P, PCO2, UL, TAUWWT, TAUWG, pHCorrosion rateMAE = 0.102;
RMSE: 5.9%;
MAPE = 0.079;
2021
[30]PCA-SVR600.85:0:0.15TM, HOL, P, PCO2, UL, TAUWWT, TAUWG, pHCorrosion rateMAE = 0.194;
RMSE: 8.1%;
MAPE = 0.067;
2021
[30]PCA-GA-SVR600.85:0:0.15TM, HOL, P, PCO2, UL, TAUWWT, TAUWG, pHCorrosion rateMAE = 0.098;
RMSE: 3.1%;
MAPE = 0.061;
2021
[30]PCA-PSO-SVR600.85:0:0.15TM, HOL, P, PCO2, UL, TAUWWT, TAUWG, pHCorrosion rateMAE = 0.083;
RMSE: 2.7%;
MAPE = 0.053;
2021
[31]ANN259194:0:65T, DC, PP, WC, pH, BC, RP, SC, BD, SR, CCRemaining thicknessRMSE = 1.44117;
MAE = 1.05954;
RMSRE = 1.59692;
U95 = 3.67005;
NSE = 0.64576;
2021
[31]MARS259194:0:65T, DC, PP, WC, pH, BC, RP, SC, BD, SR, CCRemaining thicknessRMSE = 1.31190;
MAE = 0.94897;
RMSRE = 1.43685;
U95 = 3.34730;
NSE = 0.70646;
2021
[31]M5Tree259194:0:65T, DC, PP, WC, pH, BC, RP, SC, BD, SR, CCRemaining thicknessRMSE = 1.39073;
MAE = 0.92780;
RMSRE = 1.00858
U95 = 3.52255;
NSE = 0.67012;
2021
[31]LWP259194:0:65T, DC, PP, WC, pH, BC, RP, SC, BD, SR, CCRemaining thicknessRMSE = 1.60183;
MAE = 1.15470;
RMSRE = 1.88149;
U95 = 3.90985;
NSE = 0.56237;
2021
[31]KR259194:0:65T, DC, PP, WC, pH, BC, RP, SC, BD, SR, CCRemaining thicknessRMSE = 1.15683;
MAE = 0.90728;
RMSRE = 0.98986;
U95 = 3.09315;
NSE = 0.77175;
2021
[31]ELM259194:0:65T, DC, PP, WC, pH, BC, RP, SC, BD, SR, CCRemaining thicknessRMSE = 1.50760;
MAE = 1.12518;
RMSRE = 1.51676;
U95 = 3.82753;
NSE = 0.61235;
2021
[32]SSCN32509:0:1CR, TM, OP, GPR, OPR, WPR, BSW, PCO2, GSGCorrosion defect depthMSE = 0.0238;
2020
[32]DNN32509:0:1CR, TM, OP, GPR, OPR, WPR, BSW, PCO2, GSGCorrosion defect depthMSE = 0.04592020
[32]GBM32509:0:1CR, TM, OP, GPR, OPR, WPR, BSW, PCO2, GSGCorrosion defect depthMSE = 0.05572020
[32]RF32509:0:1CR, TM, OP, GPR, OPR, WPR, BSW, PCO2, GSGCorrosion defect depthMSE = 0.06782020
[33]BWNN-IPSA3022:0:8The six first evaluation indexes I1~I6The pipeline integrity management levelMSE = 3.162021
[33]FSNN-TDA3022:0:8The six first evaluation indexes I1~I6The pipeline integrity management levelMSE = 1.382021
[33]FSNN-IDA3022:0:8The six first evaluation indexes I1~I6The pipeline integrity management levelMSE = 0.792021
[34]ANN--CRCorrosion rateSSE = 0.000010
MSE = 0.000257
MAE = 0.000754
MAPE = 0.12921
MSPE = 6.064%
2012
[34]Grey forecasting model--CRCorrosion rateSSE = 0.000073
MSE = 0.000710
MAE = 0.001569
MAPE = 0.08772
MSPE = 2.935%
2012
[34]Stepwise regression forecasting model--CRCorrosion rateSSE = 0.000010
MSE = 0.000261
MAE = 0.000674
MAPE = 0.09612
MSPE = 4.432%
2012
[34]Combining forecasting model--CRCorrosion rateSSE = 0.000002
MSE = 0.000122
MAE = 0.000191
MAPE = 0.01585
MSPE = 0.637%
2012
[35]12-inch gas pipelines15408:0:2T, AW, CC, CP, CG, D, FS, JC, ML, OP, SUPpipeline conditionR2 = 0.9880
AVP = 0.979
AIP = 0.021
RMSE = 0.008
MAE = 0.098
2014
[35]20-inch oil pipelines9008:0:2T, AW, CC, CP, CG, D, FS, JC, ML, OP, SUPpipeline conditionR2 = 0.9940
AVP = 0.962
AIP = 0.038
RMSE = 0.015
MAE = 0.152
2014
[35]24-inch gas pipelines25508:0:2T, AW, CC, CP, CG, D, FS, JC, ML, OP, SUPpipeline conditionR2 = 0.9920
AVP = 0.983
AIP = 0.017
RMSE = 0.005
MAE = 0.079
2014
[35]Gas pipelines49908:0:2T, AW, CC, CP, CG, D, FS, JC, ML, OP, SUPpipeline conditionR2 = 0.9910
AVP = 0.978
AIP = 0.022
RMSE = 0.005
MAE = 0.099
2014
[35]Oil pipelines49908:0:2T, AW, CC, CP, CG, D, FS, JC, ML, OP, SUPpipeline conditionR2 = 0.9900
AVP = 0.979
AIP = 0.021
RMSE = 0.004
MAE = 0.094
2014
[36]SVM5-HOL, HTK, PSID, USG, TAUWHL, ANGLE, TAUWGCorrosion rate11.16% < RE < 25%2013
[36]BPNN5-HOL, HTK, PSID, USG, TAUWHL, ANGLE, TAUWGCorrosion rate19.54% < RE < 33.33%2013
[36]Multiple regression5-HOL, HTK, PSID, USG, TAUWHL, ANGLE, TAUWGCorrosion rate25.32% < RE < 44.44%2013
[37]MOGWO-SVM4539:0:1D, WT, UTS, YS, EM, BP, l, w, dBurst pressureMAE = 0.237;
MAPE = 0.01353;
RMSE = 0.315;
R2 = 0.999;
a20-index = 1.000;
STDE = 0.276;
μ = 0.999
2021
[37]NSGA-II-SVM4539:0:1D, WT, UTS, YS, EM, BP, l, w, dBurst pressureMAE = 0.437;
MAPE = 0.03220;
RMSE = 0.760;
R2 = 0.997;
a20-index = 0.978;
STDE = 0.731;
μ = 1.009
2021
[37]SVM4539:0:1D, WT, UTS, YS, EM, BP, l, w, dBurst pressureMAE = 1.726;
MAPE = 0.14987;
RMSE = 4.231;
R2 = 0.735;
a20-index = 0.867;
STDE = 4.229;
μ = 1.109
2021
[37]PSO-SVM4539:0:1D, WT, UTS, YS, EM, BP, l, w, dBurst pressureMAE = 1.437;
MAPE = 0.09772;
RMSE = 1.984;
R2 = 0.986;
a20-index = 0.956;
STDE = 1.843;
μ = 1.018
2021
[38]WNN-GA3022:0:8TM, pH, PCO2, CC, BC, SC, CMCCorrosion rateRE < 0.0325852011
[39]Momentum and adaptive learning rate2944:0:1Pipe size parameters,
Material parameters,
Defect parameters
Burst pressureMSE = 9.8437 × 10−42011
[39]Elasticity BP2944:0:1Pipe size parameters,
Material parameters,
Defect parameters
Burst pressureMSE = 7.5571 × 10−62011
[39]Levenberg-Marquardt2944:0:1Pipe size parameters,
Material parameters,
Defect parameters
Burst pressureMSE = 1.7521 × 10−102011
[40]SGD RegressorThousands3:0:1WT, TRemaining thicknessR2 = 0.801814
R2-5fold cross validation = 0.79844
2015
[40]SVM Linear KernelThousands3:0:1WT, TRemaining thicknessR2 = 0.785331
R2-5fold cross validation = 0.782201
2015
[40]SVM Linear Poly KernelThousands3:0:1WT, TRemaining thicknessR2 = 0.61937
R2-5fold cross validation = 0.60278
2015
[40]SVM Linear RBF KernelThousands3:0:1WT, TRemaining thicknessR2 = 0.80267
R2-5fold cross validation = 0.79202
2015
[40]Random ForestThousands3:0:1WT, TRemaining thicknessR2 = 0.99872
R2-5fold cross validation = 0.96418
2015
[41]Linear model153:0:2l, w, dBurst pressureR2 = 0.8626,
F value = 3.55
DOF = 9
AE = 1.762
2017
[41]2FI model153:0:2l, w, dBurst pressureR2 = 0.9212,
F value = 3.12
DOF = 6
AE = 1.402
2017
[41]Quadratic model153:0:2l, w, dBurst pressureR2 = 0.9577,
F value = 1.53
DOF = 3
AE = 0.095
2017
[42]GA-BP(L-M)-4:0:1D, WT, YS, CR, d, lBurst pressureMSE = 3.40 × 10−102013
[43]PCA-SVR148128:0:20D, WT, YS, CR, d, lBurst pressureRMSE = 0.34
MAE = 0.0191
2019
[43]PCA-GRNN148128:0:20D, WT, YS, CR, d, lBurst pressureRMSE = 1.50
MAE = 0.0869
2019
[43]PCA-WNN148128:0:20D, WT, YS, CR, d, lBurst pressureRMSE = 1.25
MAE = 0.0553
2019
[43]PCA-SVM148128:0:20D, WT, YS, CR, d, lBurst pressureRMSE = 1.07
MAE = 0.0671
2019
[44]PSO-GRNN603:0:1WC, STC, SR, ORP, SEC, pH, SC, DC;Corrosion defect depthRE < 0.1377;
MRE = 0.0663;
2019
[45]RS-PSO-SVM7969:0:10Pipe steel grade, D, WT, d, lBurst pressureMAPE = 0.0123;
RMSE = 0.17 MPa;
2020
[45]BPNN7969:0:10Pipe steel grade, D, WT, d, lBurst pressureMAPE = 0.0797;
RMSE = 1.58 MPa;
2020
[45]PSO-WNN7969:0:10Pipe steel grade, D, WT, d, lBurst pressureMAPE = 0.0596;
RMSE = 0.84 MPa;
2020
[46]DNN163114:0:49l, w, d, Pipeline internal pressureMaximum equivalent stressRE = 0.0039;
MSE = 0.00054;
R2 = 0.99607
2021
[47]GM-RBF154:0:1CRCorrosion rateMRE = 0.0637;
R2 = 0.9
2018
[48]PSO-SVM129109:0:20Pipe steel grade, D, WT, d, l, YS, UTSBurst pressureMRE = 0.013362020
[48]CS-SVM129109:0:20Pipe steel grade, D, WT, d, l, YS, UTSBurst pressureMRE = 0.029712020
[48]GA-SVM129109:0:20Pipe steel grade, D, WT, d, l, YS, UTSBurst pressureMRE = 0.033442020
[48]CV-SVM129109:0:20Pipe steel grade, D, WT, d, l, YS, UTSBurst pressureMRE = 0.039422020
[49]Rlife10515:0:6Transport medium, impurities, oxygen content and othersRemaining thickness-2016
[50]GA-BP464:0:1d, l, D, WT, YS, CR;Burst pressureMSE = 0.006122015
[51]PSO-BP120105:0:15l, w, d, axial and circumferential spacing of corrosion defectBurst pressureAE = 3.9%
RE < 6.4%
2020
[52]FOA-GRNN3530:0:5D, WT, UTS, w, d, lBurst pressureMRE = 7.81%2020
[53]GA-BPNNs3927:6:6D, WT, Pipe steel grade, UTS, YS, w, d, lBurst pressure−7.78% < RE < 6.06%2020
Table 6. MAPE and R2 statistics of residual strength and residual life forecasting results.
Table 6. MAPE and R2 statistics of residual strength and residual life forecasting results.
Error IndicatorMin.Max.Average
MAPE0.01230.14990.0708
R20.6190.9990.833
Table 7. The data size of prediction models.
Table 7. The data size of prediction models.
Burst PressureRemaining ThicknessCorrosion RateCorrosion Defect DepthOthers
Max.Min.MeanMax.Min.MeanMax.Min.MeanMax.Min.MeanMax.Min.Mean
453151672591518860154332506026124990302171
Table 8. The input variables of prediction models.
Table 8. The input variables of prediction models.
Input Variables TypeParameters
Environmental factorP, UL, TM, SR, ORP, PCO2, TAUWWT, TAUWG, PP, RP, BD, CC, OP, BSW, GSG, GPR, OPR, WPR, AW, CP, CG, JC, FS, ML, SUP, HTK, USG, BP, EM, STC, OC, pH, SC, WC, SEC, HOL, DC, BC, CMC, SEC
Corrosion Defect datal, w, d
Pipe dataD, WT
MaterialUTS, YS, TS, EM, BP, Pipe steel grade
OthersT, CR
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Share and Cite

MDPI and ACS Style

Li, H.; Huang, K.; Zeng, Q.; Sun, C. Residual Strength Assessment and Residual Life Prediction of Corroded Pipelines: A Decade Review. Energies 2022, 15, 726. https://doi.org/10.3390/en15030726

AMA Style

Li H, Huang K, Zeng Q, Sun C. Residual Strength Assessment and Residual Life Prediction of Corroded Pipelines: A Decade Review. Energies. 2022; 15(3):726. https://doi.org/10.3390/en15030726

Chicago/Turabian Style

Li, Haotian, Kun Huang, Qin Zeng, and Chong Sun. 2022. "Residual Strength Assessment and Residual Life Prediction of Corroded Pipelines: A Decade Review" Energies 15, no. 3: 726. https://doi.org/10.3390/en15030726

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop