An enhanced case-based diagnosis mechanism for abnormal production administration

Abstract

Abnormal production (AP) is an unavoidable evil in which manufacturers must hold all production resources until the AP issue is resolved. This study proposes a new case-based diagnosis mechanism (named eDM) that allows manufacturers to accelerate AP resolution. eDM consists of two intelligent agents implemented by an enhanced case-based reasoning algorithm. Also, eDM provides the AP factor analysis result from four dimensions: human operator, equipment, raw material, and production method. The feature-aggregation function diagnoses AP by inferring the potential symptoms to improve the accuracy of the AP factor analysis. To validate the feasibility and efficiency of eDM, this study investigates a manufacturer in Taiwan as the experimental target and conducts two field experiments. Experimental results show that for all the cases the diagnosis can be accomplished after two to three iterations of eDM. Compared with a general diagnosis process in terms of 188 cases, eDM evaluates, on average, seven to eight cases for each iteration that exhibits a relative increase in reasoning efficiency. eDM is also shown to be an intelligent expert system that provides inexperienced production engineers (PEs) with suggestions based on historical cases to accelerate the AP resolution process.