Hybrid Learning Framework for Motor Fault Diagnosis via Optimized Wavelet-Based Time–Frequency Analysis and Deep Feature Classification

The significant advantages of permanent magnet synchronous motors, such as very good dynamic properties, high efficiency and power density, have led to their frequent use in many drive systems today. However, like other types of electric motors, they are exposed to various types of faults, including stator winding faults. Stator winding faults are mainly inter-turn short circuits and are among the most common faults in electric motors. In this paper, the possibility of using the spectral analysis of symmetrical current components to extract fault symptoms and the machine-learning-based K-Nearest Neighbors (KNN) algorithm for the detection and classification of the PMSM stator winding fault is presented. The impact of the key parameters of this classifier on the effectiveness of stator winding fault detection and classification is presented and discussed in detail, which has not been researched in the literature so far. The proposed solution was verified experimentally using a 2.5 kW PMSM, the construction of which was specially prepared for carrying out controlled inter-turn short circuits.

Thermographic image-based diagnosis of failures in electrical motors using deep transfer learning

Fast and reliable fault detection is critical in photovoltaic (PV) systems to improve reliability and energy yield and reduce maintenance costs, ensuring safe and efficient operation under varying operating conditions. Although recent data-driven PV fault detection techniques (FDTs) in literature have demonstrated high diagnostic accuracies, they often suffer from practical limitations, offline operation, lack of fault localization and/or inability to concurrently identify faults. To address these challenges, a unified framework is proposed that simultaneously integrates real-time operation, fault classification and localization, and concurrent-fault identification in a single compact diagnostic approach. This is realized by developing a parallel feedforward neural network (FFNN) architecture whose performance is enhanced by a residual model-based structure, resulting in a more interpretable, scalable, reliable and accurate scheme. In addition, Grey Wolf Optimizer–Support Vector Machine (GWO–SVM) feature selection is incorporated to select the most influential diagnostic features, thus reducing data redundancy, enhancing diagnostic accuracy, and shortening training time. The proposed approach was tested to diagnose five types of PV faults (open circuit, short circuit, partial shading, degradation, and simultaneous faults), as well as classify their intensity and location. Simulation results show that the proposed FFNNs consistently outperform conventional Support Vector Machines (SVMs) in classification accuracy, with accuracies exceeding 98% and 99% for fault classification and localization, respectively, and above 95% for noisy data. Moreover, GWO-SVM proved to offer more stable feature subsets compared to Particle Swarm Optimization–SVM (PSO–SVM) in the considered feature selection structure. Simulation results validated the effectiveness of the proposed unified multiclassification fault diagnosis approach, even under system uncertainties, making it suited for real-world PV systems.

Electric vehicles are one of the most important means in the industrial sector due to their frequent use and depend primarily on electric motors. Electric motors of all types, synchronous and asynchronous, face many faults in the rotor and stator, affecting the performance's reliability. Researchers are seeking to find ways that enable us to detect and diagnose faults in electric motors based on smart and fast methods. Early detection of problems in electric motors is vital, especially in areas such as electric vehicles. This study focuses on magnetic rotor breakage (MRB) in permanent magnet synchronous motors (PMSM). We use a simulation tool such as COMSOL Multiphysics as a simulation tool. This platform is a widely used software for modeling and analyzing complex electromagnetic systems. The study also addresses fault detection using machine learning. This involves using data analysis and pattern recognition techniques to distinguish between normal and defective states of the motor. This is an important step to improve the reliability of motors and identify potential failures in advance. Five different machine learning algorithms such as Extreme Gradient Boosting (XGBoost), AdaBoost, Gradient Boosting (GB), Naive Bayes (NB), and Random Forest (RF) are used in the study. Data from four different cases obtained from the PMSM design were used to train and test the machine-learning models. The results obtained show how accurate the proposed models are in diagnosing PMSM problems, especially MRB.

During the last two decades, there has been remarkable growth in the processing capacity of computers and the evolution of digital cameras. As a result, the thermographic technique and thermal analysis became more applied in electromechanical maintenance due to the low measuring device cost. Simultaneously, new methods based on Deep Learning focused on image and video processing have emerged. In this sense, this contribution aims to verify the applicability of using the deep learning technique of convolutional neural networks to classify patterns of thermographic images of a bench grinder. The methodology used was the collection of thermographic pictures of a bench grinder after starting, without, and after applying loads to the discs. This procedure induced a temperature increase in the grinding machine housing since some types of faults in electric motors can be diagnosed due to over-temperature by thermographic inspection. Furthermore, a Python computational code was developed using a convolutional neural network to classify different grinder operation profiles based on thermal images. In conclusion, the technique proved promising for diagnosing motor failures by thermography and can be implemented in automatic predictive maintenance routines.

This study aims to develop a real-time model for detecting and classifying various fault types in power distribution networks to enhance reliability and operational efficiency. A hybrid DWT–SVM approach is essential for accurately detecting and classifying faults in modern power distribution systems, especially under non-stationary and dynamic conditions. The proposed method addresses a range of fault scenarios, including single-phase-to-ground, line-to-line, double-line-to-ground, and three-phase faults, within a 33 kV distribution network. A hybrid approach combining Discrete Wavelet Transform (DWT) and Support Vector Machine (SVM) is introduced. Using the Debauchies-4 (Db4) wavelet, DWT effectively decomposes transient fault currents at the source terminal, capturing critical time-frequency domain features. Fault classification is performed using an SVM optimized with a Radial Basis Function (RBF) kernel and Particle Swarm Optimization (PSO), enabling precise mapping of data into higher-dimensional spaces for optimal separation. Validation conducted with MATLAB R2023b demonstrates a detection accuracy of 100% and a classification accuracy of 99%. Comparative analyses against models such as PSO-based Support Vector Machine (PSO-SVM), DWT-DNN and wavelet transform with artificial neural networks (WT-ANN) on the IEEE 13-bus system highlight the proposed method's superior performance. This innovative approach proves to be robust, adaptable, and highly effective across diverse fault scenarios, offering significant improvements in accuracy and reliability for fault detection and classification in power distribution networks. The method supports real-time operation by using high-speed simulation platforms MATLAB/Simulink to process signals and classify faults within milliseconds using a pre-trained SVM model.

This study presents a comprehensive deep learning framework for diagnosing acoustic faults in electric motors. The framework uses Mel spectrograms and a lightweight convolutional neural network (CNN). The method classifies three motor states, engine_good, engine_broken, and engine_heavyload, based on audio recordings from the IDMT-ISA-ELECTRIC-ENGINE dataset. To prevent data leakage and ensure a robust evaluation, the study employed file-level splitting, session separation, 5-fold cross-validation, and repeated trials. The raw audio signals were transformed into Mel spectrograms and processed through a CNN architecture that integrates convolutional, pooling, normalization, and dropout layers. Quantitative metrics, including THD, spectral entropy, and SNR, further characterize the acoustic distinctions between motor states. The proposed model achieved a test accuracy of 99.7%, outperforming or matching state-of-the-art approaches, such as ResNet-18, CRNN, and Transformer classifiers, as well as traditional MFCC-based baselines. Noise robustness and sensitivity analyses demonstrated stable performance under varying SNR conditions and preprocessing settings. Feature-importance maps revealed that low-frequency regions (0–40 Mel bins) were key discriminative components linked to physical fault mechanisms. Computational evaluation confirmed the model’s real-time feasibility on embedded hardware with low latency and a modest parameter count. Though primarily validated on one motor type, external-domain testing revealed strong adaptability. Future work may incorporate transfer learning or multimodal fusion. Overall, the proposed framework provides a highly accurate, interpretable, and efficient solution for real-time motor fault diagnosis and predictive maintenance in industrial environments.

The Complexity-entropy causality plane (CECP) is a parsimonious representation space for time series. It has only two dimensions: normalized permutation entropy () and Jensen-Shannon complexity () of a time series. This two-dimensional representation allows for detection of slow or rapid drifts in the condition of mechanical components monitored through sensor measurements. The CECP representation can be used for both predictive analytics and visual monitoring of changes in component condition. This method requires minimal pre-processing of raw signals. Furthermore, it is insensitive to noise, stationarity, and trends. These desirable properties make CECP a good candidate for machine condition monitoring and fault diagnostics. In this work we study the effectiveness of CECP on three rotary component condition assessment applications. We use CECP representation of vibration signals to differentiate various machine component health conditions for rotary machine components, namely roller bearing and gears. The results confirm that the CECP representation is able to detect, with high accuracy, changes in underlying dynamics of machine component degradation states. From class separability perspective, the CECP representation is able to generate linearly separable classes for the classification of different fault states. This classification performance improves with increasing signal length. For signal length of 16,384 data points, the fault classification accuracy varies from 90% to 100% for bearing applications, and from 85% to 100% for gear applications. We observed that the optimum parameter for CECP representatino depends on the application. For bearing applications we found that embedding dimension D = 4, 5, 6, and embedding delay τ = 1, 2, 3 are suitable for good fault classification. For gear applications we find that embedding dimension D = 4, 5, and embedding delay τ = 1, 5 are suitable for fault classification.

This paper presents the early faults detection in electric vehicle motor based on flux performance examination in defective electrical machine using finite element methods (FEM). Depend on time step, the proposed technique has been designed and examine to produce efficient method under high accuracy and short time to detect the faults in Electric Vehicle motors. To decrease the probability and time of electric motor faults, the early detection of these faults will give enough time to prevent many problems during the motion. The different waveforms timing of motor torque in every situation associated with the waveforms of stator current provide spreading in the proposed method. The results show fast fault detections and a Novel technology was established to extort the fault of induction motor.

Faults in three-phase electric motors often occur in power plants. Unfortunately, the disturbances are unpredictable and reduce unit performance. This paper presents an Internet of Things (IoT) based intrusion handling system for secure and economic data communication in industrial fields. The build system can monitor and control with FLM (First Line Maintenance). FLM is a minor corrective maintenance activity carried out while the unit is operating with the provision of simple equipment. Device design and testing using the ESP8266 microcontroller module to obtain motor vibration, current, and temperature information for motor conditions supported by the application as a user interface. The result prevents further damage to the electric motor by adding an external fan and a grease pump that serves for additional engine cooling. This research contributes to improving the performance of the generator at PT. Indonesia Power UJP West Java II Palabuhanratu is one of the steam power plants in West Java, Indonesia

Rolling bearing is a pivotal component for rotating equipment, which has high failure rates. Bearing failure can cause the equipment to lose control or even casualties, resulting in significant economic losses. This article diagnoses the bearings in variable operational conditions. A novel fault diagnosis framework is proposed to improve the efficiency of fault classification. The variational modal decomposition (VMD) is first utilized to expand the features of the fault signal. Then, principal component analysis (PCA) selects the most representative fault features from the VMD results. After that, the multi-information fusion data is applied to improve the classification accuracy of the support vector machine (SVM). The comparison with respect to some traditional classification methods is illustrated in detail. The diagnostic results show that the proposed framework is a validated tool for diagnosing the bearings.

Data-driven fault classification methods are receiving great attention as they can be applied to many real-world applications. However, they work under the assumption that training data and testing data are drawn from the same distribution. Practical scenarios have varying operating conditions, which results in a domain-shift problem that significantly deteriorates the diagnosis performance. Recently, domain adaptation (DA) has been explored to address the domain-shift problem by transferring the knowledge from labeled source domain (e.g., source working condition) to unlabeled target domain (e.g., target working condition). Yet, all the existing methods are working under single-source single-target (1S1T) settings. Hence, a new model needs to be trained for each new target domain. This shows limited scalability in handling multiple working conditions since different models should be trained for different target working conditions, which is clearly not a viable solution in practice. To address this problem, we propose a novel adversarial multiple-target DA (AMDA) method for single-source multiple-target (1SmT) scenario, where the model can generalize to multiple-target domains concurrently. Adversarial adaptation is applied to transform the multiple-target domain features to be invariant from the single-source-domain features. This leads to a scalable model with a novel capability of generalizing to multiple-target domains. Extensive experiments on two public datasets and one self-collected dataset have demonstrated that the proposed method outperforms state-of-the-art methods consistently. Our source codes and data are available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/mohamedr002/AMDA</uri> .

Detection and classification are two significant tasks for industrial fault diagnosis. However, conventional methods typically treat these tasks as separate and independent problems, and necessitate a retraining process when new fault samples or classes are collected. Therefore, an incremental support vector data description scheme using Gaussian kernel function is pro-posed for industrial process fault diagnosis in a unified frame-work. In this framework, the decision boundary is updated incrementally only based on the specific original support vectors and newly collected samples. An adaptive threshold and a restructured radius are proposed to promote accuracy in the fault detection. In the classification procedure, the hyperspheres for all known classes are constructed by decision tree. The new sample that does not belong to any known class is identified as an unknown class. Without a time-consuming retraining process, the proposed diagnosis method with the incremental learning capability can synchronously achieve the fault detection and classification task. Experimental results demonstrate the effectiveness and superiority in terms of diagnosis performance. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —In practical industrial processes, new fault samples are collected and new fault classes emerge continually. Under such scenarios, fault diagnosis with incremental learning capability is becoming increasingly important. This work proposes a unified incremental framework for fault diagnosis based on support vector data description, which is able to achieve fault detection and classification synchronously. For fault detection, an adaptive threshold and a restructured radius are developed. For fault classification, hypersphere-shaped boundaries of all fault classes are given via the decision tree-based strategy. The proposed method is updated to include new fault samples and fault classes without dimensionality reduction or any distributional assumptions.

This work proposes a support vector machine (SVM) based fault detection and classification method for a transmission system. The novelty of this work is that the time and frequency series parameters at both the ends of a line, amounting to 144, computed over the most recent eight samples, are considered the input data for the developed SVM model. With this higher number of features for the SVM model, the power system faults are detected and classified with a quarter cycle data of power frequency. The developed SVM, trained with operating scenarios involving 25,168 faults and no faults conditions with different fault resistances and angles of fault inception, can classify all symmetrical non-symmetrical faults. The algorithm is tested on an IEEE 9-bus system with 32 samples per cycle sampling rate and is evaluated with ten-fold cross-validation and four evaluation metrics. This methodology provides an average accuracy of 99.89 per cent for all fault scenarios despite measurement noise having a signal-to-noise ratio of 30 dB, 35 dB, and 40 dB. The comparative analysis presented in this work reveals that the developed SVM model performs better than five other reported classification algorithms in terms of the accuracy of the classification of faults.

Magnetic flux leakage testing is widely used in the defect inspection of ferromagnetic materials. Pulsed magnetic flux leakage (PMFL) testing technique is a new type of electromagnetic nondestructive testing technology. A new approach for defect classification by using magnetic flux leakage testing technology and principal component analysis based signal interpretation is presented. For defect classification, different features have been extracted from magnetic flux leakage signals using time-frequency analysis. The results from study show that the proposed technique can be used to classify the two types of defects: surface and sub surface discontinuities and the introduced technique are effective in the classification of defects.