Induction Motor Fault Diagnosis Research Articles

Performance of vibration and current signals in the fault diagnosis of induction motors using deep learning and machine learning techniques

Induction motors (IMs) play a pivotal role in various industrial applications, powering critical systems such as pumps, compressors, fans, blowers, and refrigeration and air conditioning systems. Monitoring the health of these IMs is essential for ensuring reliable operation. Numerous sensors, including vibration, current, temperature, acoustic, and power sensors, can be employed for their health monitoring. This article conducts a comprehensive comparative analysis of two widely used sensors—vibration and current, for classifying different health states of IMs, such as a healthy condition, bearing fault, and misalignment. The study employed deep learning techniques, specifically 1D and 2D convolutional neural networks, trained on raw data. Additionally, machine learning techniques, including random forest and XGBoost, were utilized and trained on features derived from preprocessed signals using fast Fourier transform and discrete wavelet decomposition. Comparative results indicated that vibration signals achieved remarkably high accuracy, nearly 100%, in detecting the investigated mechanical faults, while current signals, after signal processing and manual feature extraction, achieved an accuracy of 87.41%. These results demonstrate that, though current sensors are a viable alternative to vibration sensors, their performance can be affected by the type and degree of the considered faults. This study also highlights the attributes of vibration and current signals in the health monitoring of rotating machinery such as IMs.

Fault Diagnosis of Induction Motors under Limited Data for Across Loading by Residual VGG-Based Siamese Network

This study proposes an improved few-shot learning model of the Siamese network residual Visual Geometry Group (VGG). This model combined with time–frequency domain transformation techniques effectively enhances the performance of across-load fault diagnosis for induction motors with limited data conditions. The proposed residual VGG-based Siamese network consists of two primary components: the feature extraction network, which is the residual VGG, and the merged similarity layer. First, the residual VGG architecture utilizes residual learning to boost learning efficiency and mitigate the degradation problem typically associated with deep neural networks. The employment of smaller convolutional kernels substantially reduces the number of model parameters, expedites model convergence, and curtails overfitting. Second, the merged similarity layer incorporates multiple distance metrics for similarity measurement to enhance classification performance. For cross-domain fault diagnosis in induction motors, we developed experimental models representing four common types of faults. We measured the vibration signals from both healthy and faulty models under varying loads. We then applied the proposed model to evaluate and compare its effectiveness in cross-domain fault diagnosis against conventional AI models. Experimental results indicate that when the imbalance ratio reached 20:1, the average accuracy of the proposed residual VGG-based Siamese network for fault diagnosis across different loads was 98%, closely matching the accuracy of balanced and sufficient datasets, and significantly surpassing the diagnostic performance of other models.

Introducing Model-Based Residual Spectrum Analysis for a Practical Improvement in Induction Motors Fault Diagnosis

Introducing Model-Based Residual Spectrum Analysis for a Practical Improvement in Induction Motors Fault Diagnosis

Efficiency-Centered Fault Diagnosis of In-Service Induction Motors for Digital Twin Applications: A Case Study on Broken Rotor Bars

The uninterrupted operation of induction motors is crucial for industries, ensuring reliability and continuous functionality. To achieve this, we propose an innovative approach that utilizes an efficiency model-based digital shadow system for in situ failure detection and diagnosis (FDD) in induction motors (IMs). The shadow model accurately estimates IM losses and efficiency across various operational conditions. Our proposed method utilizes efficiency as the primary indicator for fault detection, while losses serve as condition indicators for fault diagnosis based on real-time motor parameters and loss sources. We introduce a bond graph as a fault diagnosis network, linking loss sources, motor parameters, and faults. This interconnected approach is the key aspect of our proposed diagnostic method and aims to be used in fault diagnosis as a general method. A case study of a broken rotor bar is used to validate the proposed method using a dataset of five motors. Among these, one motor operates without failure, while the remaining four exhibit broken rotor faults categorized as 1, 2, 3, and 4. The proposed method achieves 99.99% precision in identifying one to four defective rotor bars in IMs. Comparative analysis demonstrates good performance compared to vibration-based FDD approaches. Moreover, our methodology is computationally efficient and aligned with Industry 4.0 requirements.

CNN-ELMNet: fault diagnosis of induction motor bearing based on cross-modal vector fusion

Abstract As the primary driving equipment in industrial, accurate fault diagnosis and condition monitoring of induction motor is crucial for ensuring operational safety. This paper focuses on the bearing faults of induction motors, which have a substantial impact on both the mechanical and electromagnetic systems of the motors. However, in diagnostic tasks, we are faced with the challenges of multi-source, multi-modal data, significant influence from environmental noise, and minimal differentiation between fault data. This paper proposed a novel cross-modal vector fusion fault diagnosis and classification model (CNN-ELMNet), which includes a cross-modal vector fusion network (VF) based on D-S evidence theory, feature extraction layer (FE) and classification layer (CL). Specifically, the VF prioritizes the integration of diagnostic results from individual vibration signals or stator current signals within convolutional neural networks with the features of the input implicit vectors as decision-making evidence, followed by weighted vector fusion through D-S evidence theory at the decision level. The FE focuses on retaining the convolutional, pooling, and fully connected layers of the convolutional network and freezing the final fully connected layer, thus preserving training parameters and fully utilizing the network’s powerful FE capabilities. The CL includes an Extreme Learning Machine optimized for random hyperparameters using the snow ablation optimizer (SAO) algorithm, which offers rapid convergence and high classification recognition rates. The CNN-ELMNet model combines a convolutional network with an extreme learning machine optimized by the SAO algorithm, which not only preserves the model’s FE capability but also enhances the convergence speed and classification recognition rate of the model. Experimental results on real datasets demonstrate that the proposed model exhibits strong stability, generalization, and high accuracy in fault diagnosis, achieving accuracy rate of 99.29% and 98.75%. This provides a more feasible solution for the bearing fault diagnosis of induction motors and holds promising prospects for practical applications.

Wing technique as a comprehensive method for stator and rotor inter‐turn fault diagnosis in wound rotor induction motors

Wing technique as a comprehensive method for stator and rotor inter‐turn fault diagnosis in wound rotor induction motors

Fault Diagnosis in Induction Motors through Infrared Thermal Images Using Convolutional Neural Network Feature Extraction

The development of diagnostic systems for rotating machines such as induction motors (IMs) is a task of utmost importance for the industrial sector. Reliable diagnostic systems allow for the accurate detection of different faults. Different methods based on the acquisition of thermal images (TIs) have emerged as diagnosis systems for the detection of IM faults to prevent the further generation of faults. However, these methods are based on artisanal feature selection, so obtaining high accuracy rates is usually challenging. For this reason, in this work, a new system for fault detection in IMs based on convolutional neural networks (CNNs) and thermal images (TIs) is presented. The system is based on the training of a CNN using TIs to select and extract the most salient features of each fault present in the IM. Subsequently, a classifier based on a decision tree (DT) algorithm is trained using the features learned by the CNN to infer the motor conditions. The results of this methodology show an improvement in the accuracy, precision, recall, and F1-score metrics for 11 different conditions.

Fault diagnosis of induction motor in the cooling water supply system using a multi-channel data fusion transformer with limited sample conditions*

Abstract Induction motors play a vital role in the cooling water supply system of hydropower facilities. However, it is not feasible to collect sufficient fault samples in a hydropower station. The scarcity of labeled samples poses a challenge in developing powerful diagnostic models with high classification accuracy. To address this challenge, this paper proposes a multi-channel data fusion strategy based on a transformer for feature enhancement. Initially, the original signals are transferred into non-overlapping single-channel data patches to preserve correlation features across different channels. Next, temporal and spatial attention modules are applied to process the data patches, which can learn and fuse temporal and spatial information, respectively. Subsequently, the data patches are embedded to retain position information and represent fault-related features through class embedding, which are further processed by a transformer encoder with self-attention mechanisms. Finally, the classification task is achieved by using a multilayer perceptron layer connected to the class embedding. While dealing with limited training samples, the proposed method can learn robust features that are beneficial to improve the fault diagnosis ability of induction motors. The comparison of the proposed method with three basic models and two improved methods demonstrates the superiority of the proposed method in accuracy and feature clustering performance under limited sample conditions. In addition, ablation experiments demonstrate the necessity of each module in the proposed method.

Infrared image fault diagnosis based on dual-stream attention convolution network

The development of infrared image detection technology has improved the real-time performance and safety of fault diagnosis. To address the problem of insufficient features caused by the low resolution of infrared images, a fault diagnosis model for induction motor infrared images based on Dual-Stream Attention Convolutional (DSAC) is proposed. Firstly, this model employs a dual-stream convolutional neural network to extract spatial features in the X and Y directions of the infrared images separately. This dual-stream structure allows the network to simultaneously learn and utilize information from both X and Y directions, enabling a more comprehensive capture of temperature distribution and variation trends in the infrared images. Then, a convolutional attention mechanism is introduced to assign weights to the obtained features. The attention maps generated by the convolutional attention layer enhance key features while suppressing unimportant information, thereby enhancing the focusing performance of the DSAC model on critical features. Finally, the weighted dual-stream features are fused to achieve the goal of fault diagnosis for induction motor infrared images. The DSAC model is validated using the induction motor infrared image dataset from Babol Noshirvani University of Technology, demonstrating excellent diagnostic accuracy and speed on small sample datasets, providing a feasible solution for fault diagnosis of induction motor infrared images.

Open-switch fault diagnosis and fault-tolerant control for three-phase VSI-fed induction motor drive

Open-switch fault diagnosis and fault-tolerant control for three-phase VSI-fed induction motor drive

Bearing fault diagnosis in induction motor using continuous wavelet transform and convolutional neural networks

Induction motors are widely used in various industries due to their high efficiency, reliability and low cost. However, faults in these motors can lead to serious problems, such as unexpected shutdowns, decreased efficiency, and even damage to other parts of the system. Monitoring and diagnosing these faults are necessary. In this study, we propose a new approach for diagnosing bearing faults using convolutional neural network (CNN) and continuous wavelet transform (CWT). The suggested approach uses Scalograms with various CWT types as the network's input and utilizes many epochs and various batch sizes (Multi Ep-Batch) throughout the bearing fault classification training and testing phases. To assess our method, we implemented an extension of the Squeeze Net pre-trained model (transfer learning). The results show that the proposed method outperforms traditional methods in terms of accuracy and computational efficiency in detecting bearing faults. These results are based on publicly available MFPT data, and the proposed approach is compared to traditional methods. This work opens new research avenues in the field of bearing fault diagnosis and provides a promising solution for real-world applications.

Fault Diagnosis of Three-Phase Induction Motor (IM) Using a Hybrid ELSE-RNN Technique

This manuscript proposes a hybrid technique for fault detection and classification in a three-phase induction motor (IM). The proposed hybrid technique combines enhanced ladder spherical evaluation (ELSE) and recurrent neural networks (RNN); hence, it is called the ELSE–RNN method. The main goal of the manuscript is to detect and categorize the faults that occur in the IM. The key objective of the proposed method is to enhance the performance of supercapacitor (SC) storage technology and fuzzy-tuned proportional–integral (PI) supervision over conventional control. The main contribution of this paper is developing an effective fault diagnosis method for three-phase IMs. The presence of stator, rotor, winding, and bearing faults is employed using signal processing techniques, such as the Hilbert transform and SIFT. The proposed ELSE–RNN technique is utilized with the end goal of detecting and classifying faults. Here, the proposed ELSE–RNN technique recognizes motors’ healthy or unhealthy conditions in many situations to distinguish faults for protection. The proposed ELSE–RNN technique reduces the complexity of detecting and classifying faults with a validated system and increases the system's accuracy. The ELSE–RNN technique is implemented in MATLAB, and its performance is compared to existing techniques.

The Potentiality of Integrating Model-Based Residuals and Machine-Learning Classifiers: An Induction Motor Fault Diagnosis Case

The Potentiality of Integrating Model-Based Residuals and Machine-Learning Classifiers: An Induction Motor Fault Diagnosis Case

Comparative analysis of harmonic sensitivity for stator fault diagnosis in induction motors

Induction motors play a vital role in various industrial applications due to their commendable efficiency and reliability. However, their susceptibility to faults, especially in challenging industrial environments, highlights the need for vigilant fault detection to prevent unforeseen downtimes and reduce subsequent repair costs. Early fault diagnosis is crucial in this context. A systematic approach to diagnosing faults in asynchronous motors involves the application of signal processing techniques, particularly utilizing the Fast Fourier Transform (FFT). The FFT, as a mathematical tool, enables a comprehensive analysis of signals, facilitating the identification and isolation of their frequency components. Monitoring the frequency components within a motor's signal provides a means to determine the existence and severity of faults. FFT analysis allows for the monitoring of four distinct categories of harmonics: time harmonics (TH), rotor slot harmonics (RSH), rotor bar fault harmonics (RBFH), and eccentricity fault harmonics (EFH). Each type of harmonic offers valuable insights into specific fault categories. Empirical evidence, drawn from experimental results, emphasizes the heightened sensitivity of rotor slot harmonics (RSH) in detecting stator faults. Continuous monitoring of the RSH frequency component enables the prompt detection and localization of stator faults, along with an assessment of their severity. Additionally, this diagnostic methodology proves effective in identifying micro short-circuits between stator coils, allowing for a proactive strategy in predictive maintenance. This proactive approach enables anticipatory part replacement before degradation progresses to the point of causing comprehensive failure in the production chain. The combination of FFT-based signal processing and harmonic analysis establishes a robust framework for the early detection and localization of faults in asynchronous motors within industrial settings. This contributes to enhanced operational reliability and efficiency, ultimately ensuring smoother industrial processes.

A Novel Customised Load Adaptive Framework for Induction Motor Fault Classification Utilising MFPT Bearing Dataset

This research presents a novel Customised Load Adaptive Framework (CLAF) for fault classification in Induction Motors (IMs), utilising the Machinery Fault Prevention Technology (MFPT) bearing dataset. CLAF represents a pioneering approach that extends traditional fault classification methodologies by accounting for load variations and dataset customisation. Through a meticulous two-phase process, it unveils load-dependent fault subclasses that have not been readily identified in traditional approaches. Additionally, new classes are created to accommodate the dataset’s unique characteristics. Phase 1 involves exploring load-dependent patterns in time and frequency domain features using one-way Analysis of Variance (ANOVA) ranking and validation via bagged tree classifiers. In Phase 2, CLAF is applied to identify mild, moderate, and severe load-dependent fault subclasses through optimal Continuous Wavelet Transform (CWT) selection through Wavelet Singular Entropy (WSE) and CWT energy analysis. The results are compelling, with a 96.3% classification accuracy achieved when employing a Wide Neural Network to classify proposed load-dependent fault subclasses. This underscores the practical value of CLAF in enhancing fault diagnosis in IMs and its future potential in advancing IM condition monitoring.

Open-circuit fault diagnosis in three-phase induction motor using model-based technique

Open-circuit fault diagnosis in three-phase induction motor using model-based technique

Unsupervised GAN With Fine-Tuning: A Novel Framework for Induction Motor Fault Diagnosis in Scarcely Labeled Sample Scenarios

Unsupervised GAN With Fine-Tuning: A Novel Framework for Induction Motor Fault Diagnosis in Scarcely Labeled Sample Scenarios

Few-Shot Lightweight SqueezeNet Architecture for Induction Motor Fault Diagnosis Using Limited Thermal Image Dataset

Few-Shot Lightweight SqueezeNet Architecture for Induction Motor Fault Diagnosis Using Limited Thermal Image Dataset

Harnessing attention mechanisms in a comprehensive deep learning approach for induction motor fault diagnosis using raw electrical signals

Induction motors are widely used in various industrial applications due to their simplicity, robustness, and high efficiency. In recent years, deep learning approaches have shown great potential for detecting and diagnosing faults in induction motors. However, it was observed that the convolutional neural network (CNN) might miss the crucial long-range temporal dependencies of the significant features. At the same time, the recursive neural network (RNN) may face issues such as vanishing gradient and less computational efficiency if the data is too long with complex patterns. This paper proposes a novel deep-learning model that combines a one-dimensional CNN and an RNN into two independent pipelines. The spatial, temporal, long-term, and short-term features can be extracted from the raw input signal. A multi-head mechanism, a state-of-the-art deep learning technique in natural language processing (NLP), enables the model to focus more on relevant features and prevent overfitting. Specifically, our method simplifies the conventional fault diagnosis workflow while maintaining competitive accuracy compared to several state-of-the-art methods. By leveraging the ability to detect faults directly from raw, unprocessed electrical signals, our approach offers a practical, cost-effective solution for real-time fault detection in industrial applications. This innovation has the potential to significantly reduce downtime and the associated operational costs, thereby providing immediate practical value in various industrial settings.

Machine learning-based fault diagnosis for three-phase induction motors in ventilation systems

ABSTRACTInduction motors are crucial in industrial drive systems and nuclear and radiological facilities due to their durability and ease of maintenance. Even though the systems are reliable, they have several faults. One of these faults is the instability of the facility’s electrical network. This may lead to catastrophic consequences such as instability in HVAC and ventilation systems, which affects operational safety. Air instability in the HVAC system is a critical concern in the radio pharmaceutical industry. Controlled environments are vital for safety and regulatory compliance. Maintaining air quality and stability is crucial to protect radioactive materials and ensure personnel safety. A healthy and faulty motor condition dataset proposed and used in the study was generated based on a simulated actual supply of electric data. A fault diagnosis is necessary to increase reliability and minimise risks. This paper proposes a simple, reliable, and economical machine-learning-based fault classifier for induction motors. The method analyzes stator currents, motor speed, torque, and three-phase voltage supply to classify some faults resulting from high amplitude and zeros of voltage. A case study of an air handling unit with a 2 hp, 4-pole, 50 Hz three-phase induction motor was modelled and tested with the proposed dataset using various classifiers, including decision trees, logistic regression, discriminant analysis, Naive Bayes, Ensemble, and K-Nearest Neighbor (KNN).