This paper proposes a knowledge-based input configuration to inform deep learning models for both electrical and mechanical fault diagnosis, rather than increasing model complexity, and confirms that, while conventional feature processing techniques perform well for electrical fault diagnosis, only the proposed FFT-informed input effectively captures both electrical and mechanical fault patterns.
The necessity for stable and efficient Brushless DC (BLDC) motors has increased due to the quick uptake of electric vehicles (EVs). Due to their compact size, high efficiency, and low maintenance requirements, BLDC motors are ideal for propulsion applications. To support safe, efficient operation and enable predictive maintenance in EVs, BLDC motors must operate reliably. Traditional fault detection techniques frequently depend on intrusive, sensor-based temperature, vibration, and current monitoring. Despite their effectiveness, these methods raise integration difficulties, system complexity, and cost, particularly in sealed or small motor designs. This paper presents an acoustic-based non-intrusive fault detection approach that utilizes artificial intelligence (AI) and acoustic signal processing. Motor noises under several states of normal operation, bearing fault, and propeller fault are captured and analyzed to extract essential acoustic properties, including Zero Crossing Rate (ZCR), Root Mean Square (RMS), Spectral Centroid, and Mel-Frequency Cepstral Coefficients (MFCCs). A dataset comprising the retrieved features is assessed using a number of supervised machine learning (ML) models. Comparative results show that the Voting Classifier (VC) achieves the best performance among the evaluated models, with approximately 98% classification accuracy on the test dataset. The results demonstrate the feasibility of using acoustic signals for non-intrusive BLDC motor condition monitoring under controlled laboratory conditions.
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.
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.
The article describes how a robust classification system can be set up and evaluated using the example of typical partial discharges in gas-insulated DC systems.
AC motors, particularly induction motors, remain the most widely used machines in industrial applications due to their simplicity, robustness, and efficiency. Given their critical role, continuous monitoring and regulation of induction motor parameters are essential to ensure reliability and prevent unexpected failures. This research presents an internet of things (IoT-based) system for real-time monitoring and control of a three-phase induction motor. Various sensors are employed to measure key parameters such as motor temperature, current, and voltage, with the collected data transmitted to a processing unit and displayed on a server for remote access. To enhance fault resilience, the system integrates both automatic and manual control mechanisms for starting or stopping motors under abnormal conditions. The proposed approach enables continuous monitoring, early fault detection, and predictive maintenance, thereby improving overall operational efficiency and reducing downtime. Induction motors, first introduced by Nikola Tesla, account for over 50% of global electricity consumption and are deployed in nearly 90% of industrial operations. Their dominance stems from inherent advantages, including being self-starting, cost-effective, reliable, and maintenance-friendly, as well as offering a strong power factor, compact design, and high efficiency. By leveraging IoT technology, this work bridges the gap between traditional motor operation and modern Industry 4.0 practices, providing a scalable solution for smart industrial environments.