SF6 equipment gas pressure prediction method based on Prophet-LSTM model

Abstract

The invention relates to an SF6 equipment gas pressure prediction method based on a Prophet-LSTM model, and the method comprises the following steps: collecting and preprocessing data during the operation of SF6 electrical equipment, carrying out the normalization of the data, and dividing the data into a training set and a test set; training the data of the training set through a Prophet model and a Bayesian optimized LSTM (Long Short-Term Memory Network) model respectively; inputting training set prediction results of the Prophet model and the LSTM model and training set real data to an optimal weight coefficient acquisition module, and obtaining a combined weight of the two models; inputting test set data to the combination model, and checking the prediction performance of the combination model according to the test set prediction result and the test set real data; and finally, using the perfect combined prediction model for SF6 pressure prediction. According to the invention, the Prophet-LSTM model is applied to the prediction of the pressure value in the SF6 electrical equipment, thereby facilitating the judgment of overheating faults and leakage faults possibly existing in the equipment through the gas pressure value, and achieving an early warning effect.

Description

technical field [0001] The invention relates to a method for predicting the gas pressure of SF6 equipment based on the Prophet-LSTM model used in the field of electric equipment detection. Background technique [0002] SF6 (sulfur hexafluoride) gas has good insulation and arc extinguishing properties, and has been widely used in power transformation equipment. However, SF6, as an insulation medium for power transformation equipment, also has some hidden dangers. For example, the gas leakage problem commonly exists in closed GIS (gas insulated substation) equipment. Once leakage occurs, due to the action of high-voltage arc, SF6 will decompose and produce some toxic substances, which will cause the air in the GIS room to be hypoxic and poisonous, threatening On the other hand, the leakage of SF6 gas will also reduce the insulation and arc extinguishing performance of the equipment. Therefore, it is necessary to take measures to realize the rapid and effective monitoring of SF...

AI Technical Summary

Problems solved by technology

[0003] At present, for the prediction of time series data such as SF6 gas pressure, a single time series model or a prediction method based on neural network is mostly used. However, time series usually contain linear components and nonli

Images