Monitoring and diagnosis method, device and equipment of power transformer and medium

By employing techniques such as adaptive multi-scale filtering, long short-term memory networks, trend quantification models, and improved weighted evidence theory, the problem of early identification and accurate diagnosis of oil sludge faults in power transformers has been solved, thereby improving the safety and stability of the power system.

CN121723263APending Publication Date: 2026-03-24CHINA THREE GORGES UNIV
0 Cites 2 Cited by

Patent Information

Application Number
CN202511968025.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-24
Publication Date
2026-03-24

AI Technical Summary

Technical Problem

Existing monitoring and diagnostic technologies are insufficient for the early identification, accurate diagnosis, and timely intervention of faults related to oil sludge buildup in power transformers, which affects the safety and stability of the power grid.

Method used

Adaptive multi-scale filtering is used to process multi-dimensional monitoring data. Long short-term memory network and trend quantification model are combined to extract the time-series dynamic features of oil sludge. An improved weighted evidence theory fusion algorithm is used to integrate key influencing factors from multiple sources. Convolutional neural network is used to locate potential fault types and generate diagnostic reports and real-time intervention instructions.

Benefits of technology

It enables early identification and accurate diagnosis of transformer oil sludge-related faults, improves the operational safety and stability of the power system, and supports the health management of equipment throughout its entire life cycle.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to a monitoring and diagnosing method, device and equipment of a power transformer and a medium. The method comprises the following steps: acquiring multi-dimensional monitoring data acquired by a sensor array in a full state of a transformer, and denoising to obtain a clean data sequence; inputting the cleaning data into a long short-term memory network to extract oil deposition time sequence dynamic characteristics, and combining a trend quantification model to study and judge a deposition accumulation trend and generate a trend curve; if the accumulation amount or the rate in the curve exceeds a preset threshold value calibrated based on historical fault data and industry standards, multi-source deposition risk key influence factors are collected, and after preprocessing, an improved weighted evidence theory is adopted for fusion to obtain deposition risk dominant factors; and inputting the factor into a convolutional neural network to locate a potential fault type, generating an adaptive diagnosis report, and if a high-risk fault exists, triggering and outputting a real-time intervention instruction. According to the method, early recognition, accurate diagnosis and timely intervention of oil deposition associated faults are realized, and the operation safety and stability of a power system are improved.
Need to check novelty before this filing date? Find Prior Art