Short-term prediction method and prediction system for top oil temperature of distribution transformer

Abstract

The invention discloses a short-term prediction method for the top oil temperature of a distribution transformer, and the method comprises the steps: S1, obtaining the historical data of the top oil temperature of the distribution transformer, and processing the historical data into time series data; S2, initializing various parameters in an ISSA algorithm; S3, inputting the number m of the sparrow populations and the dimension n of the position of the sparrow into a one-dimensional composite chaotic mapping model (SPM) to generate an initial sparrow population of an ISSA algorithm; S4, substituting the hyper-parameter value represented by the position of each sparrow into the double-layer LSTM model, and training the double-layer LSTM model after normalization processing in combination with the training data divided in the step S1; S5, determining a discoverer, a follower and a reconnaissitor; S6, updating the position of the optimal sparrow; S7, judging whether an iteration ending requirement is met or not; and S8, inputting the top oil temperature time sequence data into the model to obtain a prediction result of the top oil temperature. The method has the advantages of high prediction precision and the like.

Description

technical field [0001] The invention mainly relates to the technical field of substations, in particular to a short-term prediction method and a prediction system for the top layer oil temperature of a distribution transformer. Background technique [0002] With the development of power technology, the safe and stable operation of power transformers is a necessary condition to ensure the reliability and economy of modern power systems. The insulation damage and service life reduction caused by the temperature limit of the transformer is one of the important factors affecting the load capacity of the power transformer. Therefore, monitoring the internal temperature of the power transformer is an effective method to judge the real-time operation status of the transformer. The hot spot temperature of the transformer winding and the top layer oil temperature are important indicators to measure the internal thermal state of the transformer. Due to the immature development of meas...

AI Technical Summary

Problems solved by technology

However, in the existing distribution transformer top layer oil temperature prediction model, the prediction model based on the finite volume method and the finite element method needs the data of various static and physical indicators of the transformer as support and the calculation is time-consuming; the differential temperature based on the improved thermal circuit model The equation prediction model is too idealized to guarantee the prediction accuracy; the hyperparameter adjustment in the data-driven machine learning prediction model is time-consuming and labor-intensive, and the prediction effect cannot be guaranteed to be optimal

Images