Method and system for detecting abnormity of multi-working-condition operation state of rotary mechanical equipment

• Main Authors: LI XUEFEI, JIN YANG, ZHANG XIANGYIN, LI CAO, BI YE, ZHANG QINGZHEN, WANG JINSHEN, SHAO LINGXING, ZHANG HUIPING, QI HAITAO, CHOI, YONG-BOK, XIANG GANG, CHENG LIN
• Format: Patent
• Language: Chinese; English
• Published: 08.11.2022
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; MEASURING; PHYSICS; TESTING; TESTING STATIC OR DYNAMIC BALANCE OF MACHINES ORSTRUCTURES; TESTING STRUCTURES OR APPARATUS NOT OTHERWISE PROVIDED FOR

The invention discloses a multi-working-condition operation state anomaly detection method for rotary mechanical equipment. The method comprises the following steps: collecting and selecting vibration signals of the rotary mechanical equipment in a multi-working-condition normal operation state, learning a description model, collecting vibration signals of the rotary mechanical equipment under real-time monitoring, and describing the model for anomaly detection; learning an improved support vector data description model from vibration signals of the rotary mechanical equipment in a multi-working-condition normal operation state as a training process, and performing anomaly detection on real-time monitoring signals of the rotary mechanical equipment as a testing process; in the training process, time domain features and frequency domain features of the subsequences are extracted and standardized, and an improved support vector data description model is learned; in the testing process, time domain features and