A fault diagnosis mechanism for heterogeneous manufacturing environments is developed. Using the correlation coefficient among quality characteristic values (QCVs) of products enables the functional correlation between processes to be uniformly treated according to causal relations among processes, despite their functional heterogeneity. Complex causal relations between QCVs are graphically represented by the influence graph, which is developed to model the diagnostic knowledge of our method. This mechanism realizes more accurate diagnostic capabilities than black-box methods, and still, does not require exhaustive modelling of the entire process, unlike model-based reasoning methods. The viability of this diagnostic approach was verified via simulation.
Read full abstract