Process Monitoring and Fault Diagnosis based on a Hybrid Modeling Technique

摘要：

A hybrid model based process monitoring and fault diagnosis approach is developed, in order to make full use of the advantages of various modeling methods. An ANN-based hybrid modeling technique with serial configuration is adopted to develop an accurate process model. Based on the hybrid model, principal component analysis (PCA) is used to deal with the correlations among high-dimensional process variables for process monitoring; and a model-based fault estimation and diagnosis method is used to determine the cause to fault. The main advantage of the proposed approach over existing works lies in that, it has good performance both in process monitoring and fault diagnosis. The application results on a three-tank system show the effectiveness of the proposed approach.

关键词： Hybrid modeling process monitoring fault diagnosis neural network PCA

作者: Dong SUN Ning-yun LU Yan GUO Bin JIANG

作者单位: College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 21001 Baoshan Iron & Steel Co. LTD Engineering Equipment Division, Shanghai 200122

会议类型: 国际会议

会议名称: The 31st Chinese Control Conference(第三十一届中国控制会议)

会议地点: 合肥

会议语种:英文

页码: 5357-5362

在线出版日期: 2012-07-01（万方平台首次上网日期，不代表论文的发表时间）