Framework of Cascade Quality Prediction Method Using Latent Variables for Multi-Stage Manufacturing

Abstract

Prediction model in data mining context is the formulation that explains the relationship between predictor and response variables. In similar, quality prediction model in manufacturing context is the formulation that explains the relationship between manufacturing operation and quality variables. Quality prediction model, as the key to realize the real-time quality manufacturing process, has been developed using various data mining techniques. Unfortunately, most of quality prediction models are developed in single-stage manufacturing system (SMS) where the relationship between manufacturing operation and quality variables is straightforward. Previous studies show that single-stage quality system cannot solve quality problem in multi-stage manufacturing system due to the complex variable relationships. This conceptual study is intended to propose a framework to develop quality prediction model which is able to deal with the complex variable relationships in multi-stage manufacturing system (MMS). This framework, named Cascade Quality Prediction Method (CQPM), is developed based on the characteristics of multi-stage manufacturing system that have been explained in several studies. CQPM is expected to produce more accurate quality prediction model since it is able to explain all type of existed variable relationship in MMS. However further investigation regarding the performance of CQPM and the selection of the data mining technique to be employed is required