Power transmission line slope displacement nonlinear prediction method and system induced by rainfall

• Main Authors: ZHAO CHAO, LIU ZHUOYA, WANG MIAN, XIAO SHUZHOU, WEI YANXUN, WU JIANRONG, LIU XIN, ZHANG QILI, LUO XIN, YAN KANG, HUANG JUNKAI, ZHAO QIANGFEI, ZHANG XUN, DING JIANGQIAO, FAN QIANG, DAI JIYULEI
• Format: Patent
• Language: Chinese; English
• Published: 27.10.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a rainfall-induced power transmission line slope displacement nonlinear prediction method and system, and relates to the technical field of slope online monitoring, and the method comprises the steps: collecting the monitoring data of the rainfall and slope displacement of a power transmission line channel; preprocessing the data, and extracting related features from the monitoring data; constructing an LSTM model by using a machine learning algorithm, and training and optimizing the model; and evaluating and verifying the model by using the reserved test data. According to the rainfall-induced power transmission line slope displacement nonlinear prediction method and system provided by the invention, the prediction model is constructed by using a machine learning algorithm, and compared with a traditional empirical threshold method and a physical model method, the rainfall-induced slope displacement can be predicted more accurately, the prediction accuracy and stability are improved,