A Combined Support Vector Machine and Support Vector Representation Machine Method for Production Control

Abstract

Machine learning techniques have been widely applied to production processes with the aim of improving product quality, supporting decision-making, or implementing process diagnostics. These techniques proved particularly useful in manufacturing industry where huge variety of heterogeneous data, related to different production processes, can be gathered and recorded but where traditional models fail due to the complexity of the production process. In this study, we describe a novel Machine Learning methodology to associate some product attributes (either defects or desirable qualities) to process parameters. Namely we combine Support Vector Machine (SVM) and the Support Vector Representation Machine (SVRM) to perform instance ranking. The combination of SVM and SVRM guarantees a high flexibility in modeling the decision surfaces (thanks to the kernels) while limiting overfitting (thanks to the principle of margin maximization). Thus, this method is well suited for modeling unknown, possibly complex relationships, that may not be captured by simple handcrafted models. We apply our method to production data of an investment casting industry placed in South Italy. We obtain an instance ranking that may be used to infer proper values of process parameter set-points.