Fault Identification of Assembly Processes Using Fuzzy Set Theory 2020-01-0487
Effective identification of sources of faults in modern manufacturing systems play a critical role in their performance and productivity. Tracking faults in a typical manufacturing system is inherently an inverse problem which makes it more challenging and difficult to solve. Presented in this article is the development of a new methodology for fault identification and root-cause analysis of complex assembly systems. A combination of a knowledge-based system and fuzzy set theory is used to develop this new technique, which is an intelligent system that mimics the behavior of an expert in the field, and can trace back the source or sources of the fault to the relevant station.
Presented are the concepts of faults, their detection in an assembly line, and their generic characteristics. Study of the fault's fundamental properties reveals that there are certain levels of uncertainty involved in describing them. This has led us to the adoption of fuzzy set theory as a basic tool for development of this new technique. This article reports on recent progress made in this area and outlines some of the preliminary results obtained so far. It is shown that based on the characteristics of the faults and the type of operations, it is possible to relate the faults to the relevant station. Examples from real assembly operations are provided to show the effectiveness of this approach.