Hydroelectric generating set fault diagnosis method based on GASF and parallel CNN-GRU-MSA

• Main Authors: ZHANG JIANBO, ZHAO XIANGKUAN, TANG KUAJI, DU ZHAORUI, LI XIANG, ZENG YUN
• Format: Patent
• Language: Chinese; English
• Published: 26.07.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; MEASURING; MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES; PHYSICS; TESTING

The invention relates to the technical field of hydroelectric generating set fault diagnosis, and discloses a hydroelectric generating set fault diagnosis method based on GASF and parallel CNN-GRU-MSA, and the method comprises the steps: collecting the original fault waveform data of a hydroelectric generating set, mapping the information of an original time sequence of the original fault waveform data of the hydroelectric generating set into features on a two-dimensional image through a GASF method, and carrying out the fault diagnosis of the hydroelectric generating set. And then spatial feature extraction is carried out on the two-dimensional image features through a CNN network, original fault waveform data of the hydroelectric generating set are input into a GRU network, one-dimensional time sequence feature extraction is carried out, processed results are fused through a multi-head attention mechanism, and the results are analyzed. According to the hydroelectric generating set fault diagnosis method bas