Transformer fault type judgment method and device, computer equipment and storage medium

• Main Authors: CHEN HAOMIN, XI YU, XIN WENCHENG, YAO SENJING, TAN SHIQIANG, AO BANG, ZHANG FAN
• Format: Patent
• Language: Chinese; English
• Published: 05.03.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; MEASURING; MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; TESTING

The invention relates to a transformer fault type judgment method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring a real-time value of contentdata of dissolved gas in oil in a transformer; inputting the real-time value as an input feature vector into a preset wavelet neural network function to obtain an output value, and presetting an optimization weight parameter in the wavelet neural network function, wherein the optimization weight parameter is obtained based on a differential evolution algorithm; and judging the fault type of the transformer according to the transformer fault code corresponding to the output value. By adopting the method, the training speed of the neural network can be increased, the generalization ability of awavelet neural network function is improved, the accuracy of fault judgment is effectively improved, the fault types of the transformer are judged according to the fault codes, the fault types are accurately divided in advance