Online fault classification method and equipment for high-voltage electronic switch equipment and storage medium

• Main Authors: FAN NAIYUAN, LIU ZHIGANG, XIAO XI, JIANG SHUYAO, WANG XIAO, LI WEI, ZENG PING, JIANG ZHANGYUE, XIAO GUANGYI, DONG XIANGYUN, CHENG KAILONG
• Format: Patent
• Language: Chinese; English
• Published: 03.11.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; PHYSICS

The invention discloses an online fault classification method and device for a high-voltage electronic switch device and a storage medium, and the method comprises the steps: randomly selecting and segmenting monitoring parameters of the high-voltage electronic switch device, and reconstructing a one-dimensional data set; processing the one-dimensional data set by using a sliding window to obtain a plurality of one-dimensional subsequences; if the distance between the two adjacent one-dimensional subsequences is smaller than a set distance threshold value and the categories corresponding to the two adjacent one-dimensional subsequences are the same, deleting one of the two adjacent one-dimensional subsequences, and selecting K one-dimensional subsequences with the maximum weight; and constructing a training set by using the one-dimensional subsequences, and training a convolutional neural network to obtain a classification model. According to the method, the sliding window is used for identifying the subseque