Quality Diagnosis in Dynamic Process Based on Multi-Feature

Recognition of quality abnormal patterns for a dynamic process has seen increasing demands nowadays in the real-time process fault detection and diagnosis. Based on the analysis of the quality abnormal patterns in a dynamic process, a novel method based on multi-feature of quality abnormal patterns by using a multi-SVM (MSVM) was proposed. The simulation results indicate that the recognition accuracies of the MSVM classifiers with the different features are quite different. It is shown that this MSVM model with suitable features can increase the recognition accuracy.