Transformer model measurement and analysis method

• Main Authors: XU WEIBIN, YI YONGHAI, ZUO SHUMING, TAN WEIJUN, LU TINGHUI, KUANG ZIFENG, DAI WENXIA, LIANG YINGJIE, GAN TUANJIE, HUANG YICHENG
• Format: Patent
• Language: Chinese; English
• Published: 11.02.2022
• Subjects: ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVEREDIN A SINGLE OTHER SUBCLASS; CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; MEASURING; MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR; PHYSICS; TARIFF METERING APPARATUS; TESTING

The invention discloses a transformer model measurement and analysis method, which comprises the following steps: respectively acquiring a vibration signal and temperature of transformer equipment through an acceleration sensing module and a temperature sensing module, and carrying out feature extraction on the vibration signal; acquiring a load value on the transformer equipment by using a power meter; and training a neural network according to the extracted vibration signal features, temperature and load values, generating a measurement network model in combination with a genetic algorithm, and obtaining a visual analysis report through the measurement network model. According to the method, the corresponding measurement network model is obtained by combining the vibration signal, the temperature and the load and performing matching based on the neural network, so that a transformer model is suitable for the adaptive matching process of different acquired data, and a corresponding measurement basis is provi