Method and system for predicting compatibility of capacitor silicone rubber sealing ring and impregnant

• Main Authors: LEE DONG-WOO, SONG HO-YOUNG, WU PEIWEI, LI ZIYONG, WANG HONGBIN, ZHAO CHONGZHI, LI ZHUYA, HUANG QINGDAN, HUANG HUIHONG, WANG TINGYAN, WEI KAIQING, LIU JING, WEI XIAODONG
• Format: Patent
• Language: Chinese; English
• Published: 23.06.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS; PHYSICS

The invention discloses a method and a system for predicting compatibility of a capacitor silicone rubber sealing ring and an impregnant. The method comprises the following steps: measuring characteristic variables of a capacitor silicone rubber sealing ring and impregnant compatible solution as a construction training sample; constructing a BP neural network model; optimizing an initial weight and a threshold value of the BP neural network model by using a genetic algorithm; performing iterative training on the optimized BP neural network model in a training sample to obtain a trained compatibility prediction model; and performing compatibility prediction on the compatible solution of the target capacitor silicon rubber sealing ring and the impregnant by using the trained compatibility prediction model to obtain a compatibility prediction value. According to the method, the BP neural network model is constructed and optimized by using the genetic algorithm to obtain the prediction model with high adaptive an