Article ID: | iaor1993871 |
Country: | United Kingdom |
Volume: | 30 |
Issue: | 12 |
Start Page Number: | 2857 |
End Page Number: | 2872 |
Publication Date: | Dec 1992 |
Journal: | International Journal of Production Research |
Authors: | Pham D.T., Oztemel E. |
Keywords: | artificial intelligence: expert systems |
The majority of available microcomputer packages for statistical process control (SPC) are off-line programs which present information regarding quality in the form of control charts. The user has to interpret the charts to infer process and product quality. This paper describes XPC, an on-line expert system for SPC. The system produces mean and range charts and interprets them automatically. XPC consists of five main modules. The first module ascertains process parameters and constructs the charts. The second module performs capability analysis to ensure that these control charts are compatible with the process specifications. The third module interprets on-line data, detects possible out-of-control situations and suggests corrective actions. The fourth module updates the charts to improve process capability. The last module produces periodical reports. XPC is based on Leonardo, an expert system shell with a hybrid knowledge representation facility enabling the use of rules, rulesets, frames, procedures and classes.