Quality Prediction in Complex Industrial Process with Support Vector Machine and Genetic Algorithm Optimization: A Case Study

Abstract

The yarn production is a complex industrial process, and the relation between the spinning variables and the yarn properties has not been established conclusively so far. The SVM regression algorithms are briefly introduced in this study, and then SVM models for predicting yarn properties have been presented. Model selection which amounts to search in hyper-parameter space is performed for study of suitable parameters with Genetic Algorithms. The yarn experimental results indicate that GA- SVM models are capable of remaining the stability of predictive accuracy, and more suitable for noisy and dynamic industrial process.