Transformer state prediction method and device and storage medium

Abstract

The invention discloses a transformer state prediction method, and the method comprises the steps: building a neural network classifier, taking the state quantity of a normalized transformer as a neural network input element, taking an early warning level as an output element, and carrying out the learning training of a neural network through historical monitoring data; calculating a prediction state quantity of historical detection data by adopting a binary linear regression analysis method; and finally, taking the prediction state quantity of each state quantity as the input of the trained neural network classifier, wherein the early warning level output by the neural network is the early warning level of the transformer at a certain time point in the future. According to the change trend of the early warning level in the future time period, corresponding measures are taken according to the operation and maintenance rules of the power system, and targeted and preventable maintenanceof the transformer is achieved. The invention further discloses a device based on the method and a computer readable storage medium. The method has practical significance in improving the operation safety of the transformer equipment, reducing the operation risk of the equipment and saving the operation and maintenance cost.

Description

technical field [0001] The invention relates to the field of state monitoring and maintenance of power system equipment, in particular to a transformer state prediction method, device and storage medium. Background technique [0002] Transformers are the core equipment in power transmission and transformation of power grids. With the rapid development of power grids, the market demand for power transmission and distribution equipment is generally on the rise, and the number of transformers is increasing rapidly. Once the transformer fails, it will not only affect the power supply of the city, but also cause explosion accidents, and the consequences will be disastrous. The overheating defect is the most important fault of the transformer. [0003] In recent years, the online monitoring technology of power equipment has developed maturely. By installing a variety of sensors in the transformer, various parameters of the transformer can be accurately and comprehensively monitor...

AI Technical Summary

Problems solved by technology

This early warning method is only based on historical monitoring data, and does not combine the status trend of the transformer for prediction

Images