Interpretative identification of the faulty conditions in a cyclic manufacturing process

The intensive development of information and communication technologies in recent years has led to an increase in data size and complexity. Conventional approaches, with associated methods of analysis based on descriptive and inductive statistics, may no longer be suitable for extracting the valuable information that is hidden in the available data. Computer-controlled manufacturing systems are becoming rich sources of data. Plastic injection moulding and die casting systems are typical examples of such manufacturing systems where the parts are produced by repeating the same sequence of steps that make up a manufacturing cycle. For each cycle, similarly structured data is generated. In this work a method for systematic data analysis for cyclic manufacturing processes is presented. The proposed data-analysis method integrates well-known heuristic algorithms, i.e., decision trees and clustering, with the purpose of identifying types of faulty operating conditions. The result of the analysis is an interpretable model for decision support that can be used for fault identification, to search for root causes, and to develop prognostic systems. A holistic approach of applying the proposed data-analysis method, along with suggestions and guidelines for implementation, is presented. A case study is presented in which the proposed method is applied to real industrial data from a plastic injection-moulding process