Equipment defect time prediction method based on capacitive equipment defect data

Abstract

The invention discloses an equipment defect time prediction method based on capacitive equipment defect data, and relates to the technical field of electrical equipment and information. Feature engineering processing and defect time modeling are carried out by adopting a whole set of method; for data with more abnormal values, missing values and redundant values of a power grid company, firstly missing value filling and data cleaning are performed, new features are constructed through feature decomposition, and feature dimensionality reduction and denoising are performed by using an auto-encoder; and for the processed feature data, feature model construction is performed by using various machine learning methods such as a gradient boosting tree and a deep learning method. The method has the advantages of being easy to implement, high in calculation speed, high in prediction precision, good in prediction robustness and systematized in prediction process.

Description

technical field [0001] The invention relates to the field of electrical equipment and information technology, in particular to a method for predicting equipment defect time based on capacitive equipment defect data Background technique [0002] Capacitive equipment is a device that uses a capacitive shielding insulation structure. It mainly includes current transformers, voltage transformers, capacitive sleeves and coupling toilet containers, etc., accounting for about 40% to 50% of the total power transmission and transformation equipment, and is the largest number of equipment in substations. The healthy operation of capacitive equipment and the safety of electrical equipment are very important to substations. Any unexpected failure may lead to major accidents and huge economic losses. Therefore, it is of great significance to realize the online detection and prediction of capacitive devices. At present, the research on online monitoring of capacitive equipment mainly fo...

AI Technical Summary

Problems solved by technology

However, this method requires an independent laboratory, and since the performance of equipment parameters of various manufacturers is not very consistent, it is obviously unrealistic to perform climate chamber experiments on all types of equipment.

At the same time, the actual working environment of capacitive equipment is more complex than the experimental environment. Simply considering the experimental data and abandoning the work and maintenance data of the capacitive equipment collected by the power grid company over the years to conduct research and prediction may lead to relatively one-sided conclusions

Images