Cable and accessory aging detection method and system based on BP neural network

• Main Authors: MENG ZHENGZHENG, LI LONGJI, GAO KAI, CHEN LONGXIAO, TANG QINGHUA, SONG PENGXIAN, ZENG HAO
• Format: Patent
• Language: Chinese; English
• Published: 27.08.2024
• 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 ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES; MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR; PHYSICS; TARIFF METERING APPARATUS; TESTING

The invention discloses a BP neural network-based cable and accessory aging detection method and system, and the method comprises the steps: taking the interface leakage current of cable body insulation and accessory insulation as the life characterization parameters of a cable and accessories thereof, taking the temperature, interface pressure and aging time as the input of a BP neural network, and taking the interface leakage current as the output; performing an accelerated thermal aging test on the cable and the accessory sample thereof under different temperatures and interface pressures to obtain a data set; according to the pre-trained neural network, life characterization parameters of the normally running cable and the accessories thereof are predicted; and predicting the service lives of the cable and the accessories thereof according to the service life characterization parameter prediction value and the cable failure threshold value. According to the normal operation conditions of the cable and the