Fault Diagnosis of the Three-Tank System Based on Extended Probabilistic Neural Network

摘要：

A fault diagnosis approach based on extended probabilistic neural network (EPNN) for isolating the faults of the three-tank system is presented in this paper. Firstly the data are preprocessed to remove noise by wavelet packet transform, then PNN is used to diagnose faults. To validate the performance and effectiveness of the proposed scheme, EPNN is applied to diagnose the faults in three-tank system. Simulation studies showed that the proposed algorithm is more accurate, reliable and computationally efficient than that based on PNN.

关键词： fault diagnosis PNN wavelet packet three-tank system

作者: Jifeng Zou Qing Yang Yingjun Song

作者单位: Shenyang Ligong University, Shenyang, China Shenyang Ligong University, Shenyang, China Changchun University of Science and Technology, Changchu

会议类型: 国际会议

会议名称: 2010 International Conference on Measurement and Control Engineering(2010年IEEE测量与控制工程国际会议 ICMCE2010)

会议地点: 成都

会议语种:英文

页码: 758-761

在线出版日期: 2010-11-16（万方平台首次上网日期，不代表论文的发表时间）