Abstract
Purpose: The purpose of this study is to achieve accurate matching of new process cases to historical process cases and then complete the reuse of process knowledge and assembly experience. Design/methodology/approach: By integrating case-based reasoning (CBR) and ontology technology, a multilevel assembly ontology is proposed. Under the general framework, the knowledge of the assembly domain is described hierarchically and associatively. On this basis, an assembly process case matching method is developed. Findings: By fully considering the influence of ontology individual, case structure, assembly scenario and introducing the correction factor, the similarity between non-correlated parts is significantly reduced. Compared with the Triple Matching-Distance Model, the degree of distinction and accuracy of parts matching are effectively improved. Finally, the usefulness of the proposed method is also proved by the matching of four practical assembly cases of precision components. Originality/value: The process knowledge in historical assembly cases is expressed in a specific ontology framework, which makes up for the defects of the traditional CBR model. The proposed matching method takes into account all aspects of ontology construction and can be used well in cross-ontology similarity calculations.
Original language | English |
---|---|
Pages (from-to) | 80-98 |
Number of pages | 19 |
Journal | Assembly Automation |
Volume | 42 |
Issue number | 1 |
DOIs | |
Publication status | Published - 11 Jan 2022 |
Keywords
- Assembly case matching
- Case-based reasoning
- Complex product
- Ontology
- Semantic similarity