A Method for Substation Equipment Temperatue Prediction

Abstract

The temperature change of the power transmission line and substation equipment can reflect their potential safety hazard caused by their aging and overload. Based on the nonlinear analysis of forecasting substation equipment temperature data can realize effectively early warning of equipment failure and avoid huge losses caused by the accident. This paper puts forward a method for temperature forecasting, based on the chaotic time series and BP neural network. It collects data from wireless temperature sensors to establish a time series of substation equipments’ temperature. Software simulation results showed that the prediction method has higher prediction accuracy than that of the traditional method.

Research on dynamic prediction method of temperature environment of unmanned aerial vehicle platform based on physical information and neural network

“…This kind of The method model is stable, but there are problems such as lag in the prediction results; the second method is to rely on the laws of the data itself for prediction, such as neural networks and statistical induction. Related research can refer to [7][8][9]. The model accuracy of this type of method is acceptable, but There is a lack of basic theoretical support for heat transfer, and the model has poor generalization ability.…”