Wind turbine generator health assessment method based on improved stack type self-coding

• Main Authors: GAO DELAN, SHI RUXIN, CAO QINGCAI, WANG JUAN, TADAO, ZHANG JIANXIN, LIU XIANRONG, CAO SHANQIAO, ZHANG SHUXIANG, WU LIDONG, XUN JIAMENG, ZHANG SHUXIAO, XU ZHIXUAN, GUO XUFENG, ZHANG LIXING
• Format: Patent
• Language: Chinese; English
• Published: 29.04.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention discloses a wind turbine generator health assessment method based on improved stack type self-coding, and relates to the technical field of wind power generation, and the method comprises the following steps: S1, obtaining a training data set: carrying out the cleaning of the operation data of a wind turbine generator, and then carrying out the linear normalization processing, and obtaining effective training data and test data, s2, constructing a plurality of stack-type self-encoding models; S3, training each stack-type self-encoding model; S2, constructing a plurality of stack-type self-encoding models; S3, training each stack-type self-encoding model; s4, integrating and extracting depth features of the training data set; and S5, taking the trained reference model as a generator on-line state detector, inputting the volume data into the reference model, and obtaining and outputting the health degree of the generator of the wind turbine generator in each time period. The accuracy is improved o