Non-intrusive electrical and mechanical fault diagnosis of induction motors via Fourier-transform-aided learning

Non-intrusive electrical and mechanical fault diagnosis of induction motors via Fourier-transform-aided learning (cid:73)

Robust Open-Circuit Fault Diagnosis of PMSMs Using Feature Fusion of Current Signatures With Deep Neural Networks

Permanent magnet synchronous motors (PMSMs) are broadly used in diverse applications due to their inherent advantages. Open-circuit faults (OCFs) are among the major fault classifications in PMSMs, posing significant concerns due to their contribution to torque ripples, vibrations, and efficiency degradation. Therefore, accurate and real-time OCF diagnosis is essential for reliable operation and predictive maintenance practices. This underscores the importance of a robust diagnostic framework that enables early fault detection and localization, supports embedded integration, and requires no additional dedicated sensors. However, existing studies rarely address these requirements together. To overcome these limitations, this article proposes a novel OCF diagnostic framework that fuses features derived from multiple strategies, including wavelet energy-based features, frequency-domain features extracted from current waveforms, and speed measurement data. The extracted feature vector is used as input to a lightweight deep neural network. The proposed approach enhances interpretability and enables seamless embedded integration compared to conventional raw-data-driven machine learning models. In addition, an extended refinement layer is incorporated to enable integrated fault detection and classification for OCF while enhancing diagnostic transparency. The effectiveness of the proposed method is demonstrated through MATLAB/Simulink simulations using the PLECS Blockset and further validated in real-time with an RTBox-based hardware-in-the-loop setup using a C2000 launchpad. Furthermore, experimental validation is conducted using a domain-adaptation strategy based on transfer learning. Performance evaluation confirms diagnostic accuracy exceeding 99% across varying operating conditions. The validation process achieves fault detection within 22% of a fundamental electrical cycle, with fault localization occurring within 40% of an average, demonstrating the robustness and adaptability of the proposed method. A sensitivity analysis of the proposed algorithm’s feature vector validates the effectiveness of high-frequency features. Furthermore, the risk distribution matrix provides insights supporting informed maintenance decisions.

A comparative study of machine and deep learning models for time-series-based bearing fault diagnosis of induction motors.

Accurate fault detection in induction motors (IMs) under varying load conditions remains a critical challenge in industrial condition monitoring (CM). Inspired by the foundational work, which highlighted the impact of mechanical load on fault signature detectability. This study proposes a multi-modal signal analysis approach to bearing fault diagnosis using stator current, rotor speed, and flux-induced voltage signals. A custom fifteen-class dataset was collected, comprising healthy and faulty motor states at 0%, 50%, and 100% load levels. Unlike conventional approaches that rely on extensive preprocessing and handcrafted feature extraction, the proposed framework operates directly on raw signals, enabling a lightweight, computationally efficient, and easily deployable solution. This design significantly reduces implementation complexity while maintaining high diagnostic performance, making it suitable for real-time and industrial applications. Two types of models were evaluated in this study: traditional machine learning models and deep learning models. Experimental results demonstrate significant performance gains compared to single-sensor models, highlighting the benefits of cross-domain signal fusion. Models specifically designed to process time-series data, such as the Temporal Convolutional Network (TCN) and particularly the Long Short-Term Memory (LSTM), exhibit outstanding performance. During the training and validation phases, the LSTM model achieved perfect classification accuracy (100%), outperforming all other evaluated models. However, during the deployment-oriented evaluation on unseen test data, the SVM and TCN models demonstrated the most consistent generalization performance, achieving perfect prediction results across all tested samples. Recent architectures, such as the Transformer, also demonstrate strong potential; with careful hyperparameter tuning, their performance especially in terms of generalization can be further enhanced.

Research on Fault Feature Extraction and Intelligent Diagnosis Technology of Motor Drive in Embedded Systems

Motor drive systems operating in embedded environments are frequently affected by noise, dynamic loading conditions, and electromagnetic interference, making timely fault diagnosis difficult. To improve diagnostic accuracy and real-time performance, this study proposes an intelligent fault diagnosis framework based on embedded multi-source data acquisition and feature fusion. High-precision sensors are employed to synchronously collect vibration and current signals, while improved wavelet packet decomposition and principal component analysis are combined to extract discriminative multi-dimensional fault features and eliminate redundant information. A lightweight convolutional neural network optimized for embedded deployment is then developed to perform low-latency fault classification and edge inference. Experimental results show that the proposed method achieves an average F1-score exceeding 97% under complex mixed-fault conditions, while maintaining an average detection latency of approximately 45 ms. The proposed framework demonstrates strong robustness and computational efficiency, providing practical support for intelligent industrial maintenance and offering reference solutions for embedded sensing, signal processing, and electromagnetic compatibility environments.

Hybrid Measurement and Deep Learning Framework for Harmonic Estimation in Induction Motors

Induction motors (IMs) are widely used in industrial applications due to their robustness, low cost, and simple construction. However, the increasing integration of power electronic devices such as inverters, soft starters, and variable frequency drives (VFDs) has made modern energy systems more complex, introducing significant harmonic distortions. These harmonics alter the sinusoidal nature of supply voltages, causing additional losses, torque pulsations, overheating, and reduced efficiency. In particular, odd-order harmonics such as the 5th, 7th, 11th, and 13th adversely affect motor performance by generating reverse torques, increasing mechanical vibrations, and accelerating insulation and bearing degradation. To address this challenge, this study investigates harmonic estimation in IMs using a combination of real measurements and artificial intelligence. Voltage signals were acquired from motors under star-delta, soft starter, and VFD-fed conditions at an industrial facility. To augment the dataset and model real noise environments, conditional Generative Adversarial Networks (cGANs) were employed to generate synthetic signals at varying signal-to-noise ratios. A feedforward neural network was then trained with these real and synthetic signals to estimate the amplitudes of key harmonics. The proposed model, optimized using the Adam optimization algorithm significantly improved estimation accuracy, reducing the Mean Absolute Error (MAE) from 0.9008 to 0.2993 and the Root Mean Squared Error (RMSE) from 1.0195 to 0.4123. The proposed framework also achieved very accurate estimation of the 5th, 7th, 11th, and 13th harmonics compared to ground-truth measurements. These results demonstrate the potential of combining real-world measurements, synthetic data generation, and machine learning regression for accurate harmonic characterization in IMs, contributing to improved diagnostics, monitoring, and efficiency in industrial energy systems.

Multi-Sensor Fusion and Frequency-Domain Analysis for Predictive Maintenance of Industrial Induction Motors

Unplanned failures of induction motors impose serious operational and financial penalties on industrial facilities, yet the fault signatures that precede such failures are detectable well in advance through careful sensor instrumentation and data-driven analysis. This paper presents an end-to-end Internet-of-Things (IoT) predictive maintenance scheme based on two off-the-shelf sensors: a DS18B20 one-wire digital thermometer and 2 piezo vibration sensor modules, with an ESP32 edge device for running the full machine learning pipeline offline, independent from any cloud services. Four operating scenarios are considered: healthy condition, BPFO (bearing outer race fault), misaligned shaft, and rotor imbalance. Based on 1-second sampling intervals, 17 descriptors are derived, including statistics in the time domain, Fourier harmonic peaks, energy ratios between different frequency bands, and temperature gradients measured across all sensors. A dual-stage feature selection method using mutual information (MI) score and Random Forest mean decrease impurity (MDI) ranking reduces the number of features to the 10 most relevant descriptors, reducing the computational complexity by 41% at the expense of 5.6% F1-macro. On a balanced 600-sample synthetic dataset, the resulting Random Forest classifier attains 87.3% hold-out accuracy, 91.0±1.9% five-fold cross-validation accuracy, and a macro area-under-the-ROC-curve of 0.980. End-to-end inference takes just 39 ms on the ESP32, easily meeting the 200 ms requirement for real-time alerting.