A New Method for Diagnosing Transformer Winding Faults Based on mRMR-RF Feature Selection and an Inverse Distance Weighted KNN Model
Open Access
- 23 March 2026
- journal article
- research article
- Published by MDPI AG in Algorithms
- Vol. 19 (3) , 241
Abstract
Accurately extracting deviation features in frequency response curves, which reflect winding deformation states, and selecting appropriate machine learning algorithms are critical for achieving a precise quantitative diagnosis of winding deformation based on frequency response analysis (FRA). To address the existing challenges in transformer winding fault diagnosis, including the absence of a systematic feature evaluation framework for frequency response data and the limited recognition accuracy of machine learning models, a novel hybrid feature selection and diagnostic framework was developed. First, a high-dimensional feature pool comprising 25 numerical indices was extracted from experimental FRA curves. To eliminate feature redundancy and arbitrary selection, a hybrid mechanism integrating maximum-relevance, minimum-redundancy (mRMR) with random forest (RF) was developed to dynamically construct task-specific optimal feature subsets. Furthermore, an inverse-distance-weighted K-nearest neighbors (IKNN) model was introduced to enhance diagnostic sensitivity by accounting for feature-space distance variations. Experimental results obtained from a laboratory winding model demonstrate that the proposed mRMR-RF-IKNN model significantly outperforms traditional and optimized benchmarks across multiple macro-evaluation metrics. This study provides a systematic, intelligent screening mechanism that ensures high-precision identification of both the types and severity of faults in power transformers.Keywords
This publication has 29 references indexed in Scilit:
- A New Data Augmentation Model for Fault Diagnosis of Transformer Windings Under Scarce Fault DataIET Electric Power Applications, 2026
- On the utility of ordered incremental attribute learning-based variance and mRMR techniquesKnowledge and Information Systems, 2025
- Enhanced detection of power transformer winding faults through 3D FRA signatures and image processing techniquesElectric Power Systems Research, 2025
- Application of generative AI-based data augmentation technique in transformer winding deformation fault diagnosisEngineering Failure Analysis, 2024
- Diagnosis method of transformer winding mechanical deformation fault based on sliding correlation of FRA and series transfer learningElectric Power Systems Research, 2024
- The actual measurement and analysis of transformer winding deformation fault degrees by FRA using mathematical indicatorsElectric Power Systems Research, 2020
- State diagnosis method of transformer winding deformation based on fusing vibration and reactance parametersIET Electric Power Applications, 2020
- Evaluation of Numerical Indices for Objective Interpretation of Frequency Response to Detect Mechanical Faults in Power Transformers2019
- Detecting the location and severity of transformer winding deformation by a novel adaptive particle swarm optimization algorithmInternational Transactions on Electrical Energy Systems, 2018
- FRA interpretation using numerical indices: State-of-the-artInternational Journal of Electrical Power & Energy Systems, 2017