Título: Quality Abnormal Pattern Recognition of Dynamic Process Based on MSVM
Autores: Liu, Yumin; Zhengzhou University
Zhou, Haofei; Zhengzhou University
Zhang, Shuai; Zhengzhou University
Fecha: 2014-05-01
Publicador: TELKOMNIKA: Indonesian journal of electrical engineering
Fuente:
Tipo: info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
Tema: Pattern Recognition; Dynamic Process; MSVM; Kernel Function
Descripción: The improvement of the effective recognition of quality abnormal patterns in dynamic process has seen increasing demands nowadays in the real-time monitor and diagnose of automatic manufacturing. Based on the analysis of the dynamic process of quality abnormal pattern, this paper presents a recognition model of quality abnormal pattern recognition using a Multi-SVM. Contrasting with performance of recognition model based on different kernel functions, suitable kernel functions were selected for the recognition model. Furthermore, we have contrasted the model proposed in this paper with the model adopted by Vahid. Simulation results show that the recognition model proposed in this paper has very high recognition accuracy for all patterns, and the overall average recognition accuracy is 97.78%.
Idioma: No aplica