Improving the performance of production lines with an expert system using a stochastic approach

Abstract

In our increasingly competitive world, nowadays companies implement improvement strategies in every department and, in particular, in their manufacturing systems. This paper discusses the use of a global method, based on a knowledge-based approach, aiming at the development of a software tool for modeling and analysis of production flows. The main goal is the improvement of the performance of the production line. This method is based on data-processing and data-mining techniques and will help the acquisition of the meta-knowledge that is needed for finding correlations among different events in the line. Different techniques will be used: a graphical representation of the production, identification of specific behavior and research of correlations among events in the production line. Most of these techniques are based on statistical and probabilistic analyses. Events are expressed in the form of phenomena. To carry out high-level analyses, a stochastic approach will be used to identify breakdown models, which are the expression of specific correlations between phenomena. Breakdowns models will be the basis for, finally, defining action plans to improve the performance of the manufacturing lines.