System fault detection method based on block slow feature analysis

• Main Authors: QIAO XINYU, WANG WEIJUN, CHENG CHAO, SHAO JUNJIE, LI HUALIANG, FU CAIXIN
• Format: Patent
• Language: Chinese; English
• Published: 09.07.2021
• Subjects: ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVEREDIN A SINGLE OTHER SUBCLASS; CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; MEASURING; MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES; MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR; PHYSICS; TARIFF METERING APPARATUS; TESTING; TESTING STATIC OR DYNAMIC BALANCE OF MACHINES ORSTRUCTURES; TESTING STRUCTURES OR APPARATUS NOT OTHERWISE PROVIDED FOR

The invention discloses a system fault detection method based on block slow feature analysis and belongs to the field of fault diagnosis. According to the method, a problem that the strong noise interference and the fault state in the traction system cannot be effectively identified by the existing method is solved. According to the structural characteristics of the traction system, high-order statistical characteristics among variables are analyzed through mutual information, calculation complexity is reduced, the performance of each sub-block is effectively monitored by utilizing a dynamic slow characteristic analysis method, and the two designed test statistics respectively have a time sequence characteristic and a first-order difference characteristic, the strong noise condition in the traction system can be monitored, and then the strong noise interference and the fault state in the traction system can be effectively separated according to the designed logic decision. The method can be applied to the fie