A Fault Diagnosis and Localization Method for Distribution Networks Based on APC-SVM and PC-AZOA

SVM–KNN Hybrid Learning Framework for Transmission Line Fault Identification and Localization

A paradigm shift in energy grid operations has arisen from swift improvements in measurement and computer technology, allowing contemporary systems to integrate self-healing functionalities. An essential prerequisite for these systems is the fast identification and localisation of transmission line faults to guarantee grid reliability and expedite service restoration. This research introduces an innovative SVKN method for precise detection and localisation of transmission line problems. Voltage and current signals undergo initial preprocessing before being decomposed with the Wild Horse Optimisation (WHO) method to isolate high-frequency features and low-frequency approximations. The amalgamation of Support Vector Machine (SVM) and K-Nearest Neighbours (KNN) facilitates efficient classification and localisation. The findings indicate that the suggested SVKN method surpasses current models such as SVKN, SVM, KNN, Two Stage KNN and Two Stage SVM, in both fault type classification and the identification of the impacted transmission line. The SVKN model attained an accuracy of 94.13% in predicting fault positions, hence validating its precision. The suggested SVKN framework markedly enhances Transmission Line Fault Identification and Localisation, providing a dependable and effective solution for real-time fault management in advanced smart grids.

A Leakage Fault Diagnosis Method for Low-Voltage Distribution Areas Based on Multidimensional Feature Extraction and LightGBM

Complex Fault Diagnosis Strategy for Distribution Networks Based on Dynamic Variation Characteristics of Zero-Sequence Current

Large-scale integration of high-proportion new energy sources and continuous expansion of network scale complicate the transient characteristics of distribution networks. Conventional fault diagnosis methods suffer from insufficient feature extraction and weak capture of topological correlation, which degrade diagnosis accuracy. To tackle this issue, this paper proposes a complex fault diagnosis strategy for distribution networks based on analysis of the dynamic variation law of zero-sequence current. First, multivariate variational mode decomposition (MVMD) is adopted to process zero-sequence current signals, which effectively fuses multi-dimensional zero-sequence current data and fully excavates fault features. Moreover, the zebra optimization algorithm is utilized to optimize the parameters of MVMD for further improving feature extraction performance. Subsequently, a graph convolutional neural network is employed to extract temporal features from the processed waveforms, enhancing the model’s recognition capability under high-resistance faults and typical disturbance conditions. Finally, multiple IEEE test systems are used for verification, which demonstrates the effectiveness and feasibility of the proposed method.

A Rolling Bearing Fault Diagnosis Method Using Adaptive Decomposition and Impact Feature Enhancement Fusion

To address the issues of parameter dependency on empirical settings, insufficient fault feature extraction capability, and limited classification accuracy in rolling bearing fault diagnosis using Variational Mode Decomposition (VMD), a novel fault diagnosis method based on adaptive signal decomposition and intelligent classification integration is proposed. The VMD parameters are adaptively optimized using the Subtraction-Average-Based Optimizer (SABO), and a kurtosis–correlation criterion is introduced to select a single fault-sensitive intrinsic mode function, from which time-domain features are extracted to construct fault feature vectors. The Moth-Flame Optimization Algorithm (MFOA) is employed to optimize the parameters of the Kernel Extreme Learning Machine (KELM) for fault state identification. From the perspective of methodological symmetry, the averaged population update of SABO is invariant to the ordering of search agents, VMD exhibits equivalence under permutation of mode labels, and KELM constructs the sample similarity matrix using a symmetric kernel function. These symmetry-related structures are integrated into the parameter optimization, modal decomposition, and fault classification stages of the proposed method. Experimental validation using the CWRU rolling bearing dataset demonstrates that the proposed method reaches a fault recognition accuracy of 96.73%, outperforming other comparative models and exhibiting superior diagnostic precision and robustness.

Adaptive Traveling Wave Protection Strategy for Distribution Network Based on SVMD and Temporal Homological Class Flux Mapping

To address the issues of maloperation and misjudgment in existing protection methods under highimpedance grounding, complex topologies, and non-fault transient disturbances, an adaptive traveling wave protection strategy for distribution networks based on Successive Variational Mode Decomposition (SVMD) and temporal homological class flux mapping is proposed. First, the signals acquired by broadband current sensors are processed with a 50 Hz notch filter, a high-pass filter, and an SVMD-wavelet threshold denoising procedure to eliminate interference, thereby ensuring the stability and reliability of the extracted topological features. Subsequently, the criterion of temporal homological class flux mapping is investigated to determine the adaptive traveling wave protection operation logic. Finally, a typical 10 kV radial distribution network model is built, and a comprehensive analysis of the proposed protection performance is conducted. The results demonstrate that the proposed method operates reliably and stably under various system configurations, fault locations, and fault resistances, meeting the requirements for practical engineering applications.

A protection strategy for distribution networks using IoT technology and support vector machine

This paper presents an intelligent protection framework for fault detection, classification, and location in power distribution networks by combining Discrete Wavelet Transform (DWT)-based feature extraction, Support Vector Machine (SVM)-based decision making, and Internet of Things (IoT)-enabled cloud monitoring. An IEEE 16-bus distribution system is modeled in MATLAB/Simulink, where transient current signals are processed using DWT to extract discriminative time–frequency features. A comparative evaluation of different mother wavelets and decomposition levels is performed to identify the most effective feature extraction configuration in terms of accuracy and computational efficiency. The extracted features are processed locally by SVM-based models for fault detection, classification, and location, while selected fault-related features are simultaneously transmitted to the ThingSpeak cloud platform for cloud-assisted monitoring and remote accessibility. The proposed framework is evaluated under a wide range of operating conditions, including different fault types, overload events, load switching, capacitor switching, and scenarios with integrated photovoltaic and wind generation. The results demonstrate 100% fault classification accuracy and fault-location accuracies ranging from 97.95% to 99.88% within the investigated simulation scenarios. Furthermore, the proposed approach effectively distinguishes faults from non-fault disturbances, thereby reducing the likelihood of false fault indications. The findings demonstrate that the proposed intelligent protection framework provides accurate and reliable fault detection, classification, and location through optimized DWT-based feature extraction and SVM-based decision making under the investigated simulation scenarios. Nevertheless, additional validation using noisy measurements and hardware-based experimental platforms is required to further assess the robustness and practical applicability of the proposed protection methodology under real operating conditions.