Small fault detection method of instruments based on independent component subspace algorithm and ensemble strategy
HU Jichen1,HUANG Guoyong1,SHAO Zongkai1,2,WANG Xiaodong1,2,ZOU Jinhui1,2
1. Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming Yunnan 650500, China
2. Yunnan Engineering Research Center for Mineral Pipeline Transportation, Kunming Yunnan 650500, China
Abstract:To solve the problem of small fault detection of instruments in process industry, independent components were extracted by Independent Component Analysis (ICA) from instruments recorded data. And independent component subspaces were established according to the contribution matrix. Fault detection model was constructed in each independent component subspace with statistical variables. A proper ensemble strategy was chosen by combining all the fault detection results. Finally, the instrument with fault was located by contribution algorithm. The simulation results with TE (Tennessee Eastman) process show that this method has higher precision on small fault detection and more flexibility with proper ensemble strategy.
胡吉晨 黄国勇 邵宗凯 王晓东 邹金慧. 基于独立子空间算法与集成策略的仪表微小故障诊断方法[J]. 计算机应用, 2013, 33(07): 2063-2066.
HU Jichen HUANG Guoyong SHAO Zongkai WANG Xiaodong ZOU Jinhui. Small fault detection method of instruments based on independent component subspace algorithm and ensemble strategy. Journal of Computer Applications, 2013, 33(07): 2063-2066.