Automatic CAD model retrieval based on design documents using semantic processing and rule processing
Introduction
The product design process is roughly divided into two stages: early design and detail design. In the early design stage, engineers create initial design information described in sketches, rough 3D models, or design documents. Design documents at the early design stage generally include important information which can help engineers to create detailed design information. Design documents contain product specifications and design directions for a specific design using textual descriptions [1]. In the detail design stage, product design information is generally represented by CAD models, and it contains geometry, tolerance, and material information for a specific product design.
Reuse of CAD model is very important for manufacturing companies where similar products are produced. Engineers can efficiently make decisions for design details of new product from existing detailed design information of similar products. If existing CAD models have design information related to the design of a new product, their reuse saves costs and reduces time of product design. According to the statistics in industries [2], only about 20% of OEM's investment is on new design while about 80% is on the reuse of existing designs, with or without modification. Aberdeen Group [3] shows that design reuse helped top performing organizations to achieve 76% of their engineering targets and a 30% reduction in design time.
Since design documents generated in the early design stage contain product specifications and design directions for new product design, they can be used as input queries to retrieve existing CAD models. Most existing CAD model retrieval methods [4], [5], [6], [7] were limited to use design documents because they supported searching by 2D sketches or by 3D geometries. Searching by 2D sketches or by 3D geometry models requires 2D sketches or a detailed 3D model as an input query, respectively.
Product lifecycle management (PLM) systems provide engineers a function to manually create links between design documents and CAD models, but they do not have a function to automatically generate links based on the design information in design documents and CAD models. Engineers have to identify design information in design documents and CAD models to create links between them manually. It is a complex and time-consuming task if there were too many design documents and CAD models to be linked. It becomes worse if some design documents and CAD models were generated by different engineers. Engineers use the check-in/check-out function to manage their design outputs, but this function does not assist engineers to make meaningful links between the design outputs. CAD model retrieval approach based on design documents can help engineers to manage links between design documents and CAD models by using semantic processing and rule processing.
CAD models can contain sufficient text in the following circumstances: Commercial CAD systems provide predefined CAD objects (i.e., point, circle, surface) and those CAD objects have several attributes (i.e., name, type). Many manufacturing companies develop CAD templates or domain-specific user-defined features (UDF) and utilize them in the product design stage to reduce design cost and lead-time [8]. When engineers create CAD templates and UDFs, they use domain specific terms in order to share design intentions of the CAD templates and UDFs with other engineers. In addition, engineers give special names to specific CAD objects in a CAD model so that they can find the specific CAD objects quickly during the CAD modeling process. CAD models, therefore, include enough text to be searched by matching text in design documents.
There exists a semantic gap between text in CAD models and text in design documents. This semantic gap can occur for the following two reasons. First, domain-specific terms may have semantic ambiguity due to abbreviations, acronyms, synonyms, and polysemy. For example, the term “SW” in the tire design domain is used for different concepts (Sidewall or SectionWidth). The semantic ambiguity of domain-specific terms should be removed to improve retrieval performance. Second, text in design documents in the early design stage includes abstract design descriptions while text in CAD models has detailed design descriptions. For instance, it is difficult to directly match “3 channel patterns”, written in a tire design document and “circumferential groove”, referring to CAD objects in a tire CAD model. In order to match these two terms, it is necessary to know that “3 channel patterns” means a tread pattern that has 3 circumferential grooves. Thus, design information hidden behind text in CAD models and text in design documents should be recognized.
The semantic ambiguity of terms in engineering text can be resolved by using a domain ontology. Several studies [1], [9], [10], [11] have used a domain ontology and a concept distance measurement method to handle the semantic ambiguity issues. They extracted concepts from terms in engineering texts using domain ontology. If a word in a text matched multiple concepts, they removed the semantic ambiguity using concept distance between different concepts in the domain ontology. Min et al. [12] used WordNet to disambiguate meaning of extracted text that was associated with a particular 3D model. Yu and Hsu [13] used a domain corpus to moderate the semantic ambiguity of terms in CAD drawings.
Hidden design information in CAD models and design documents can be explicitly represented by using a domain ontology and rules together. Some studies have used a domain ontology and rules to represent design knowledge and to infer new knowledge. Wang et al. [14] used a 3D model ontology and relationship rules to search 3D models. Kim et al. [15] used an assembly ontology and rules to infer new assembly information.
In this paper, we propose an automatic CAD model retrieval approach based on design documents that contain initial design information. The proposed approach reduces the semantic gap between CAD models and design documents by using semantic processing and rule processing. Semantic processing is used to generate semantic representations from the text in CAD models and text in design documents using a domain ontology and shallow natural language processing (NLP). Since a semantic representation consists of concepts and their relationships, design information in CAD models and design documents can be converted to semantically structured information. The semantic ambiguity of terms is resolved by heuristic rules and a concept distance measurement method. Hidden design information in CAD models and design documents are extracted by a given rule base. Then, similarity calculation is conducted between semantic representations to search CAD models relevant to a design document. Tire design examples are used in the paper to demonstrate the feasibility of the proposed approach.
The remainder of this paper is organized as follows. Section 2 presents related works. Section 3 describes the overall architecture of the proposed approach. Section 4 provides an analysis of CAD models and design documents. Section 4 also shows technical details of how to generate semantic representations, how to reduce semantic gaps, and how to search CAD models with similarity calculation. Section 5 describes the implementation of the proposed approach. Section 6 provides an evaluation of our approach with real industry data. Section 7 discusses limitations of the proposed approach. Section 8 provides the conclusion and suggestions for future work.
Section snippets
Related works
General approaches for CAD model retrieval are briefly reviewed in advance. Then, studies of semantic-based CAD model retrieval are described and compared with the proposed approach. Studies related to extracting semantic information from engineering documents are also introduced.
Overview of the approach
The overall procedures of our approach are as follows. First, text in CAD models and text in design documents are analyzed; characteristics of texts and semantic gaps of texts are recognized (discussed in Section 4.1). Second, based on the analysis of the texts, a semantic reference model (i.e., a domain ontology and a rule base) is constructed (discussed in Section 4.2). Third, semantic representations are generated from existing CAD models and input design documents using the semantic
Analyzing CAD models and design documents for tire design
Technical terms are first analyzed because they are most frequently used during product design. Then, text in CAD models and text in design documents are also analyzed to recognize their characteristics and semantic gaps.
Implementations
Fig. 19 shows multiple views of the tire design ontology developed in this research. The left side of Fig. 19 shows a user interface of Protégé 4.3 in which classes, individuals, properties, and rules for a tire design are constructed. The middle and right sides of Fig. 19 show a taxonomy view and a graph view of the tire design ontology, respectively. For the ontology visualization, SOVA (simple ontology visualization API) [47] plugin for a Protégé is adopted. Fig. 20 shows examples generated
Experiments
Experiments were conducted using tire layout CAD models and tire design documents, which were generated during PCR (Passenger Car Radial) tire design processes. 485 tire layout CAD models and 58 tire design documents were collected from a tire company. Tire layout CAD models contained an average of 558 domain-specific terms. Tire design documents were consisted of one page per tire design case. Each tire basic document has averagely 231 domain-specific terms.
In order to evaluate the performance
Discussions
In the previous sections, the design document based CAD model retrieval approach has been proposed, and it has been verified that resolving the semantic gap between CAD models and design documents can improve the retrieval performance. Nevertheless, there are still several limitations that need to be discussed here.
First, the proposed approach requires domain-specific textual contents for CAD models. As described in Section 4.3, the proposed approach requires the textual information in CAD
Conclusion and future work
This paper proposed an automatic approach for CAD model retrieval using design documents that contain initial design information. Design documents generated in the early design stage contain abstract design descriptions, while CAD models contain detailed design descriptions. Therefore, the semantic gap between the two design descriptions should be reduced to facilitate design document based CAD model retrieval. In this paper, semantic processing and rule processing were exploited to resolve
Acknowledgements
This research was financially supported by Hankook Tire Co. Ltd. and by a grant (Project ID: 14IFIP-B091004-01) from Plant Research Project funded by Ministry of Land, Infrastructure and Transport of the Korean government. The authors gratefully acknowledge their support.
Sang Min Jeon is a Ph.D. candidate in industrial and systems engineering at the Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea. He has been a research engineer since 2004 at Hankook Tire Co. Ltd., Daejeon, South Korea. He received the B.S. degree in mechanical engineering from the Sejong University, Seoul, South Korea in 2002. He received the M.S. degree in mechanical engineering from the Yonsei University, Seoul, South Korea in 2004. His research interests
References (49)
Knowledge-based product development using XML and KCs
Comput. Des.
(2000)- et al.
Developing an engineering shape benchmark for CAD models
Comput. Des.
(2006) - et al.
A roadmap for parametric CAD efficiency in the automotive industry
Comput. Des.
(2013) - et al.
Content-based text mining technique for retrieval of CAD documents
Autom. Constr.
(2013) - et al.
Ontology-based assembly design and information sharing for collaborative product development
Comput. Des.
(2006) - et al.
Toward an efficient triangle-based spherical harmonics representation of 3D objects
Comput. Aided Geom. Des.
(2008) - et al.
3D shape retrieval by Poisson histogram
Pattern Recognit. Lett.
(2011) - et al.
Automatic discovery of common design structures in CAD models
Comput. Graph.
(2010) - et al.
A geometric reasoning approach to hierarchical representation for B-rep model retrieval
Comput. Des.
(2015) - et al.
Multiresolutional similarity assessment and retrieval of solid models based on DBMS
Comput. Des.
(2006)
Retrieving 3D CAD model by freehand sketches for design reuse
Adv. Eng. Inform.
Design reuse oriented partial retrieval of CAD models
Comput. Des.
Knowledge-based part similarity measurement utilizing ontology and multi-criteria decision making technique
Adv. Eng. Inform.
SWRL: a semantic web rule language combining OWL and RuleML
W3C Memb. Submiss.
Protus 2.0: ontology-based semantic recommendation in programming tutoring system
Expert Syst. Appl.
Explicit reference modeling methodology in parametric CAD system
Comput. Ind.
Ontology-based design information extraction and retrieval
AI EDAM
The Design Reuse Benchmark Report: Seizing the Opportunity to Shorten Product Development
Content-based search techniques for searching CAD databases
Comput. Aided Des. Appl.
A survey of content based 3D shape retrieval methods
Multimed. Tools Appl.
A survey on partial retrieval of 3D shapes
J. Comput. Sci. Technol.
Retrieval effectiveness of an ontology-based model for information selection
VLDB J. Int. J. Very Large Data Bases
Developing engineering ontology for information retrieval
J. Comput. Inf. Sci. Eng.
A personalized query expansion approach for engineering document retrieval
Adv. Eng. Inform.
Cited by (32)
Multi-dimensional modeling and abnormality handling of digital twin shop floor
2023, Journal of Industrial Information IntegrationDesigner-Centric Spatial Design Support
2022, Automation in ConstructionExtraction of Formal Manufacturing Rules from Unstructured English Text
2021, CAD Computer Aided DesignCitation Excerpt :In the industry, the most prevalent form of encoding manufacturing knowledge has been unstructured text (approximately 80% of information [2,3]). Therefore, for the efficient retrieval and reuse of such textual knowledge, previous efforts on the formal knowledge acquisition from manufacturing text have focused on concept or hierarchy extraction for text classification [4–7], structured knowledge construction [8–14], and ontology creation [15–18]. However, the acquisition of complex formal manufacturing rules has received less attention in the industry.
Feature-based ontological framework for semantic interoperability in product development
2021, Advanced Engineering InformaticsComputer aided design (CAD) model search and retrieval using frequency domain file conversion
2020, Additive ManufacturingCitation Excerpt :Multiple groups have developed retrieval methods with design documents [33,34]. Jeon et al. [34] designed a semantic reference model that generates the semantic representations from the design documents (search query) as well as the models in the database. Then, they calculate a similarity measure and find how many components are matched between the representations [34].
Clustering and retrieval of mechanical CAD assembly models based on multi-source attributes information
2019, Robotics and Computer-Integrated Manufacturing
Sang Min Jeon is a Ph.D. candidate in industrial and systems engineering at the Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea. He has been a research engineer since 2004 at Hankook Tire Co. Ltd., Daejeon, South Korea. He received the B.S. degree in mechanical engineering from the Sejong University, Seoul, South Korea in 2002. He received the M.S. degree in mechanical engineering from the Yonsei University, Seoul, South Korea in 2004. His research interests include semantic-based design information retrieval, design knowledge extraction from text data, traceability of design information, and design automation based on CAD/CAE.
Jae Hyun Lee received the M.S. and Ph.D. degrees in industrial engineering from the Korea Advanced Institute of Science and Technology (KAIST), Daejeon, in 2001 and 2008, respectively. He was an Associate Researcher from 2008 to 2013 at the Systems Integration Division, Engineering Laboratory, National Institute of Standards and Technology (NIST), Gaithersburg, MD, USA. He has been an assistant professor since 2013 at Daegu University, Daegu, South Korea. His research interests are developing information models for sustainable product design, product lifecycle management, and standards to represent product design and manufacturing information.
Gyeong June Hahm received Ph.D. degree in industrial engineering from the Korea Advanced Institute of Science and Technology (KAIST), Daejeon, in 2014. He has been a researcher since 2015 at the Broadcasting & Telecommunications Media Research Laboratory, ETRI. His research interests include semantic-based information retrieval system, product design and manufacturing information recommendation system, and product lifecycle management.
Hyo Won Suh received the B.S. degree in mechanical engineering from the Yonsei University, Seoul, South Korea. He received the M.S. degree in mechanical engineering, from the KAIST, South Korea, and Ph.D. degree in Industrial Engineering from WVU, in 1991. His past work experiences include researcher in Daewoo Heavy Industries, Co. Ltd., South Korea, Research Assistant in concurrent Eng. Res. Cent. CERC, USA and Chief researcher in KITECH, South Korea. He is currently an Professor in the Department of Industrial and Systems Engineering, KAIST, South Korea. His research interests include product lifecycle management, Ontology and Engineering Applications, Workflow and Businees Process Mangement and New product development. Prof. Suh is a member of ASME.