Jul 2026· 2026 5th International Conference on Energy and Electrical Power Systems (ICEEPS)· pp. 205-209· 0 citations· 15 references
Abstract
Accurate fault diagnosis in distribution networks is often limited by empirical parameter selection in Variational Mode Decomposition (VMD) and insufficient fault feature representation under complex operating conditions. To overcome these limitations, an Improved Artificial Hummingbird Algorithm-Variational Mode Decomposition-Two-Dimensional Convolutional Neural Network (IAHA-VMD-2DCNN) framework is proposed for adaptive feature extraction and fault classification. Using minimum envelope entropy as the objective function, IAHA is employed to optimize key VMD parameters adaptively. The decomposed components are reconstructed into two-dimensional time–frequency feature maps and subsequently fed into a Two-Dimensional Convolutional Neural Network (2DCNN) for automatic feature learning and fault classification. Based on simulation data from the IEEE 33-bus distribution network, the diagnostic performance of the proposed method is evaluated under 11 operating conditions and different transition resistances. The results show that the proposed framework effectively suppresses mode mixing and achieves an overall fault classification accuracy of 95.92%. In addition, it demonstrates strong robustness and excellent feature learning capability under complex operating conditions.
To address the issues of insufficient feature extraction and low localization accuracy in distribution network fault diagnosis, this study proposes a fault classification and localization method based on APC-SVM and PC-AZOA. The model performs a simultaneous decomposition of three-phase signals using multivariate variational modal decomposition and employs the energy entropy of each model component as the feature vector; During the classification stage, the method integrates electrical and physical constraints, introducing three-phase energy imbalance and variance into the support vector machine ’ s parameter optimization process for the first time to dynamically adjust the penalty factor and kernel parameters; finally, a traveling wave propagation time error model is constructed, and an adaptive zebra optimization algorithm constrained by physical information is proposed. By innovatively embedding prior physical knowledge into the search space constraints, the method effectively suppresses invalid searches and improves convergence efficiency. Experimental results show that the model achieves a classification accuracy of up to 98.4% with a positioning error below 1%, demonstrating both high precision and high efficiency.
Dahua Li, Xinrui Yang, Yu Song et al.· 2026 IEEE International Conf...· 0 citations
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.
Ruihao Zhou, Penghui Liu, Wenxiang Li et al.· Processes· 0 citations
This paper proposes a method of fault detection in analog circuits which involves various steps, including selection of benchmark circuits, dataset preparation, signal decomposition, model training, and performance analysis. The main aim of this work is to provide solid performance even in noisy environments. Monte Carlo analysis is used to generate a synthetic dataset with 200 runs per fault class by introducing component tolerances and realistic faults. A multi-stage pipeline is proposed; it begins with resampling the signals and normalizing them, and then noise is added at different levels: 5 dB, 10 dB and 20 dB. Feature fusion is performed by combining time-, frequency-, and statistical-domain features. Statistical-domain features are extracted by applying Variational Mode Decomposition (VMD) to split them into four IMF levels, followed by the application of Continuous Wavelet Transform (CWT) for time–frequency-domain analysis. Support Vector Machine (SVM), Random Forest, and Gradient Boosting are used as base-level classification models. A stacking ensemble model is developed which uses Random Forest, Gradient Boosting, and Extra Trees as base learners and Logistic Regression as the meta-learner.
Archana Dhamotharan, Balakumar Muniandi, Vennila Anandaraj Umapathy et al.· Journal of Sensor and Actuat...· 0 citations
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.
The diagnosis of faults in power transformers (PT) plays a crucial role in ensuring the reliability and stability of power systems. However, traditional fault detection techniques are prone to low detection accuracy and are not stable enough under complex operating conditions. To address these challenges, this paper proposes a novel hybrid Variational Mode Decomposition (VMD), Graph Attention Network (GAN) with Adaptive Extreme Learning Machine (AELM) method for a transformer fault diagnosis framework. VMD can efficiently extract discriminative frequency bands of the transformer signals, GAN can dynamically learn the importance and relationship of the extracted feature, and AELM can classify rapidly and accurately with low complexity. The dataset was obtained from simulations of various fault conditions in the Matlab/Simulink. The experimental results demonstrate that the proposed method has an accuracy of 99.5%, a precision of 99.66%, a recall of 99.33%, and an F1-score of 99.5% compared to existing methods. The proposed hybrid framework enables efficient classification capability, feature learning with attention, and adaptive feature extraction, which contributes to improved performance.
Aiming at the problems of wind turbine gearbox vibration signals with multi-frequency characteristics, difficulties in fault feature extraction and insufficient generalisation ability of traditional diagnostic models. In this study, a gearbox fault diagnosis method is proposed, which integrates variational mode decomposition (VMD) optimised by the subtraction-average-based optimiser (SABO) with a classification framework combining convolutional neural network (CNN) and support vector machine (SVM). First, the SABO algorithm is introduced to optimise the key parameters of VMD (modal number
k
and penalty factor
α
), which overcomes the limitations of traditional empirical selection and simple optimisation algorithms. Second, CNN and SVM are fused to construct an end-to-end integrated diagnostic model, using CNN to automatically extract fault features in the intrinsic modal functions (IMFs) obtained from VMD decomposition, avoiding the tediousness and subjectivity of feature selection by manual and traditional methods, and then inputting these features into SVM for classification. Finally, using the gearbox data set of Southeast University, five fault types are diagnosed and classified by MATLAB simulation experiment platform. The results demonstrate that the model constructed in this paper achieves a diagnostic accuracy of 96.43%, significantly outperforming multiple mainstream comparative models. It exhibits excellent robustness and adaptability under both noisy interference and variable operating conditions, while maintaining high computational efficiency. This provides a reliable technical solution for intelligent fault diagnosis and predictive maintenance of wind turbine gearboxes.
Minan Tang, Zhihao Fan, Jinping Li et al.· Transactions of the Institut...· 0 citations
