Induction Motor Fault Diagnosis Research Articles

Robust Interpretable Deep Learning for Intelligent Fault Diagnosis of Induction Motors

In modern manufacturing processes, motivations for automatic fault diagnosis (FD) are increasingly growing as a result of the great trends toward achieving zero breakdowns. Induction motors (IMs) represent a critical part in most of the applications. Due to its high potential of automatic feature extraction, the deep learning (DL)-based FD of IM has recently been introduced and has essentially emphasized on the diagnosis using the vibration analysis. However, this approach has not received considerable attention when using the current analysis, although it represents a cost-effective alternative. Moreover, the already implemented DL architectures are still suffering from lack of physical interpretability. In this article, a new DL architecture called deep-SincNet is implemented for a multi-FD task. The proposed end-to-end scheme automatically learns the fault features from the raw motor current and accordingly finalizes the FD process. A high accuracy for several separated and combined faults, a more physical interpretability, a high robustness against noisy environments, and a significant gain in implementation cost prove the competitive performance of the proposed approach.

On-Line Parameter Identification of a Squirrel Cage Induction Motor

Based on the principle of coordinate transformation, a mathematical model of induction motors in the three-phase stationary coordinate system was transformed to that in the synchronous rotating coordinate system. For motors with low-speed rotors, the multi-variable, high-order, strong-coupling and nonlinear equation of motors was further transformed to a linear equation. However, it was found difficult to solve the deduced linear equation through the method of least squares due to its high singularity. The steady-state stator resistance could be predetermined by temperature revision on the stator resistant in the motor nameplate. Identification of four motor parameters (Ls,M, Rr, Lr) was followed by the recursive least-squares method. Simulations of motor parameter estimation were carried out in Simulink of Matlab. The recursive least-squares method was used to deal with the measured data. The results demonstrate that the real-time electrical parameters (Ls, σ, Tr) can be accurately predicted. Given the assumption of Ls = Lr in the classical motor theory, the other three electrical parameters (M, Rr, Lr) can also be identified. The identification of these parameters is of great importance for the analysis, control and fault diagnosis of induction motors.

Induction Motor Fault Classification using Pattern Recognition Neural Network

The industrial growth has escalated the use of induction motors as prime movers in modern industry. This is due to its low cost, simple construction and ruggedness. Although rugged, these may fail earlier than expected life due to, excessive mechanical, electrical and environmental stresses. Automatic Artificial Intelligence (AI)-based systems are nowadays widely employed in the domain of induction motor fault identification with high success rate. Artificial neural network are utilized extensively for the detection and diagnosis of various induction motor faults. These systems generally use supervised learning, where the models are pre-trained such that these are skilled enough to classify the absence or presence of faults in motor under investigation. In this paper, a highly effective approach for detection of different motor fault conditions, based on pattern recognition technique is presented. In the proposed method the statistical time domain features are computed from three phase motor current and used as inputs of ANN. Seven different classes of motor conditions: healthy, broken rotor bar, broken rotor bar with stator winding short circuit and inner and outer race bearing defects were considered. The results indicates that the proposed methodology is highly effective for diagnosis of various induction motor faults with high success rate.

Fault Diagnosis of Induction Motor Using Convolutional Neural Network

Induction motors are among the most important components of modern machinery and industrial equipment. Therefore, it is necessary to develop a fault diagnosis system that detects the operating conditions of and faults in induction motors early. This paper presents an induction motor fault diagnosis system based on a CNN (convolutional neural network) model. In the proposed method, vibration signal data are obtained from the induction motor experimental environment, and these values are input into the CNN. Then, the CNN performs fault diagnosis. In this study, fault diagnosis of an induction motor is performed in three states, namely, normal, rotor fault, and bearing fault. In addition, a GUI (graphical user interface) for the proposed fault diagnosis system is presented. The experimental results confirm that the proposed method is suitable for diagnosing rotor and bearing faults of induction motors.

DCNN-Based Multi-Signal Induction Motor Fault Diagnosis

Deep learning (DL) architecture, which exploits multiple hidden layers to learn hierarchical representations automatically from massive input data, presents a promising tool for characterizing fault conditions. This paper proposes a DL-based multi-signal fault diagnosis method that leverages the powerful feature learning ability of a convolutional neural network (CNN) in images. The proposed deep model is able to learn from multiple types of sensor signals simultaneously so that it can achieve robust performance and finally realize accurate induction motor fault recognition. First, the acquired sensor signals are converted to time–frequency distribution (TFD) by wavelet transform. Then, a deep CNN is applied to learning discriminative representations from the TFD images. Since then, a fully connected layer in deep architecture gives the prediction of induction motor condition based on learned features. In order to verify the effectiveness of the designed deep model, experiments are carried out on a machine fault simulator where both vibration and current signals are analyzed. Experimental results indicate that the proposed method outperforms traditional fault diagnosis methods, hence, demonstrating effectiveness in induction motor application. Compared with conventional methods that rely on delicate features extracted by experienced experts, the proposed deep model is able to automatically learn and select suitable features that contribute to accurate fault diagnosis. Compared with single-signal input, the multi-signal model has more accurate and stable performance and overcomes the overfitting problem to some degree.

A Comparative Study between Machine Learning Algorithm and Artificial Intelligence Neural Network in Detecting Minor Bearing Fault of Induction Motors

Most of the mechanical systems in industries are made to run through induction motors (IM). To maintain the performance of the IM, earlier detection of minor fault and continuous monitoring (CM) are required. Among IM faults, bearing faults are considered as indispensable because of its high probability incidence nature. CM mainly depends upon signal processing and fault detection techniques. In recent decades, various methods have been involved in detecting the bearing fault using machine learning (ML) algorithms. Additionally, the role of artificial intelligence (AI), a growing technology, has also been used in fault diagnosis of IM. Taking the necessity of minor fault detection and the detailed study about the role of ML and AI to detect the bearing fault, the present study is performed. A comprehensive study is conducted by considering various diagnosis methods from ML and AI for detecting a minor bearing fault (hole and scratch). This study helps in understanding the difference between the diagnosis approach and their effectiveness in detecting an IM bearing fault. It is accomplished through FFT (fast Fourier transform) analysis of the load current and the extracted features are used to train the algorithm. The application is extended by comparing the result of ML and AI, and then explaining the specific purpose of use.

Rational-Dilation Wavelet Transform Based Torque Estimation from Acoustic Signals for Fault Diagnosis in a Three-Phase Induction Motor

Condition monitoring of electric drives play a significant role for a safe working environment. Induction motors are widely used in industries and any fault in it leads to interruption in the process or complete shutdown of the equipment. In this paper, acoustic-based fault detection in a three-phase induction motor is done by estimating the torque from the acoustic signals released by the machine. The fault detection is possible as acoustic emission is different for faults such as single phasing, bearing cage damage, and broken rotor bars. The acoustic signals are processed using rational-dilation wavelet transform (RADWT) technique to extract the fault features and thereby diagnose the fault type. The torque estimation is done using multiple regression method by extracting the energy possessed in the processed acoustic signal and the faults are diagnosed precisely. An experimental setup comprising of a three-phase induction motor with brake drum loading is used to validate this approach. The RADWT has adjustable frequency resolution in comparison with other wavelet methods. When high Q-factor filters are employed in the RADWT, better representation of different faults are obtained in the decomposed sub-bands. In addition, characteristic frequencies of different faults are calculated analytically and validated by observing the frequencies in the FFT spectrum of acoustic fault signals.

Data-Driven Robust Fault Detection and Isolation of Three-Phase Induction Motor

This paper deals with data-driven fault diagnosis of three-phase induction motor. The tools from subspace identification based data-driven scheme are utilized to design a framework of fault detection and isolation. The fault detection scheme is so designed that it caters for even small magnitude faults. In order to discriminate different faults, a fault isolation algorithm is proposed. Isolation thresholds are designed. The results show the effectiveness of the proposed schemes.

Machine Learning-Based Fault Diagnosis for Single- and Multi-Faults in Induction Motors Using Measured Stator Currents and Vibration Signals

In this paper, a practical machine learning-based fault diagnosis method is proposed for induction motors using experimental data. Various single- and multi-electrical and/or mechanical faults are applied to two identical induction motors in lab experiments. Stator currents and vibration signals of the motors are measured simultaneously during experiments and are used in developing the fault diagnosis method. Two signal processing techniques, matching pursuit, and discrete wavelet transform, are chosen for feature extraction. Three classification algorithms, support vector machine (SVM), K-nearest neighbors (KNN), and ensemble, with 17 different classifiers offered in MATLAB Classification Learner toolbox are used in the study to evaluate the performance and suitability of different classifiers for induction motor fault diagnosis. It is found that five classifiers (fine Gaussian SVM, fine KNN, weighted KNN, bagged trees, and subspace KNN) can provide near 100% classification accuracy for all faults applied to each motor, but the remaining 12 classifiers do not perform well. A novel curve fitting technique is developed to calculate features for the motors that stator currents or vibration signals under certain loadings are not tested for a particular fault. The proposed fault diagnosis method can accurately detect single- or multi-electrical and mechanical faults in induction motors.

An Approach on MCSA-Based Fault Detection Using Independent Component Analysis and Neural Networks

This paper presents a novel approach on motor current signature analysis (MCSA) for broken bar fault detection of induction motors (IMs), using as input the current signal measured from one of the three motor phases. Independent component analysis (ICA) is used over the Fourier-domain spectral signals obtained from the input and its autocorrelation function. The standard deviation of spectral components within a region of interest (ROI) of an ICA signal output was found to exhibit substantial differences between damaged and healthy motors. Separation of the ROI in one, two, and three sectors leads to an improved extraction of feature vectors, which are further fed into a neural network for classification purposes. The assessment of the proposed method is carried out through several experiments using two damage levels (broken bar and half broken bar) and two load motor conditions (50% and 75%), with a classification accuracy ranging from 90% to 99%. The contribution of this paper lies in a new technique of signal processing for ICA-based feature extraction in a 3-D feature space for IM fault diagnosis.

Broken Rotor Bar Fault Detection of Induction Motors Using a Joint Algorithm of Trust Region and Modified Bare-bones Particle Swarm Optimization

A precise detection of the fault feature parameter of motor current is a new research hotspot in the broken rotor bar (BRB) fault diagnosis of induction motors. Discrete Fourier transform (DFT) is the most popular technique in this field, owing to low computation and easy realization. However, its accuracy is often limited by the data window length, spectral leakage, fence effect, etc. Therefore, a new detection method based on a global optimization algorithm is proposed. First, a BRB fault current model and a residual error function are designed to transform the fault parameter detection problem into a nonlinear least-square problem. Because this optimization problem has a great number of local optima and needs to be resolved rapidly and accurately, a joint algorithm (called TR-MBPSO) based on a modified bare-bones particle swarm optimization (BPSO) and trust region (TR) is subsequently proposed. In the TR-MBPSO, a reinitialization strategy of inactive particle is introduced to the BPSO to enhance the swarm diversity and global search ability. Meanwhile, the TR is combined with the modified BPSO to improve convergence speed and accuracy. It also includes a global convergence analysis, whose result proves that the TR-MBPSO can converge to the global optimum with the probability of 1. Both simulations and experiments are conducted, and the results indicate that the proposed detection method not only has high accuracy of parameter estimation with short-time data window, e.g., the magnitude and frequency precision of the fault-related components reaches 10−4, but also overcomes the impacts of spectral leakage and non-integer-period sampling. The proposed research provides a new BRB detection method, which has enough precision to extract the parameters of the fault feature components.

Efficiency Assessment of Induction Motors Operating Under Different Faulty Conditions

Fault diagnosis in induction motors has been a topic that has drawn an increasing attention among the electrical engineering community, including both industry and academia. Diverse techniques have been developed in order to detect the presence of possible faults in their early stages so that forced outages of the motor and consequent economic consequences can be avoided. However, little attention has been paid to the implications of the presence of these faults in terms of motor efficiency reduction. The efficiency drops caused by the existence of faults or anomalies in the motor, which can be present during long time intervals, can lead to economic losses that can be even greater than those caused by eventual motor outages. In spite of this fact, many industrial users are not aware of the efficiency repercussions of the operation under unhealthy conditions. As a consequence, it becomes necessary to accurately study and quantify the efficiency decrements caused by the presence of possible failures, so that the users can have this information available to adopt proper maintenance decisions. This paper analyses how different noncatastrophic failures influence the value of motor efficiency; different types of rotor faults as well as bearing failures are considered. In this paper, it is shown that the presence of these failures indeed strongly affects the motor efficiency and may have serious implications on the motor performance and operational cost.

Induction Motor Faults Diagnosis when Considering Bars Skew and Saturation Effects

The objective of the work presented in this paper is the diagnosis of the three-phase induction machine with secondary effects such as the rotor bars skewing and the saturation phenomenon. To enable reliable diagnosis of an induction machine, a mathematical model is required to simulate the machine behavior. Among the existing mathematical models, the approach of the winding function is the most promising because it takes into account the actual distribution of the windings in the stator slots. Nevertheless, the major drawback of this model is the non-consideration of the skewing effect of the bars and the non-linear evolution of the FMM between the ends of the slots. The aim of this paper is to use the modified winding function approach (MWFA) with 2D extension to take into account the rotor bars skewing and saturation effects in the presence of faults such as the rotor broken bars, the short-circuit between stator turns and the eccentricity. A series of simulations is conducted to study the spectral contents of the stator current of the induction squirrel cage motor in the various operating cases.

Reference Signal Injection in Induction Motors Drives to Electrical Failures Detection

This paper shows an alternative method to electrical fault diagnosis in three-phase induction motors using reference signal injection. The proposal is based on the insertion of search reference harmonic signals in the supply voltage by the frequency inverter module of the induction machine and the observation of the signals of the electric current of the motor, preprocessed through the FFT and machine signature component analysis. In order to obtain a greater precision of fault classification and state of degradation through intelligent systems, results are validated by different algorithms whose performance are compared in the following methods: k nearest neighbors, naive Bayes, support vector machine, multilayer perceptron and decision tree. The practical results for the tests with controlled simulation of the electrical faults of broken rotor bars and short circuit in stator windings show the capacity that this insertion technique has when it is used as a tool to diagnose three-phase induction motors. The five proposals of intelligent systems result in a classification with success rates of $$93\%$$ to $$100\%$$ in different classes, separated into types of faults and according to the degradation intensity.

Diagnostics of mechanical and electrical faults in induction motors using wavelet-based features of vibration and current through support vector machine algorithms for various operating conditions

Fault diagnosis of induction motors (IMs) is always a challenging task in the practical industrial field, and it is even more challenging in the case of inadequate information of IM working conditions. In this paper, a new methodology for fault detection has been proposed for IMs to detect various electrical and mechanical faults as well as their severities, where the data are unavailable at required operating conditions (i.e., speed and load) based on wavelet and support vector machine (SVM). For this, the radial, axial and tangential vibrations, and three-phase current signals are acquired from IMs having different faults. The acquired time domain signal is then transformed to time–frequency signals using continuous wavelet transform (CWT). Ten different base wavelets are used to investigate the impact of different wavelet function on the fault diagnosis of IMs. Statistical features are extracted based on the CWT, and then appropriate feature(s) are selected using the wrapper model. These features are fed to the SVM to detect whether a defect has occurred. The fault detection is performed for identical speed and load case using a number of mother wavelets. To analyze the robustness of the present system, diagnosis is attempted for various operational conditions of IMs. The result showed that the feature(s) selected using the Shannon wavelet diagnose, the fault categories of IM more accurately as compared to other wavelets, and remarkably found to be robust at all working conditions of IMs. The work is finally extended to perform the fault diagnosis when limited information is available for the training. From the results, it is observed that the proposed methodology does not only take care of the practical problem of unavailability of data at different operating conditions, but also shows good performance and takes low computation time, which are vital requirements of a condition monitoring and diagnostic system.

Convolution Neural Network Based Fault Diagnosis of Induction Motor

Convolution Neural Network Based Fault Diagnosis of Induction Motor

Fault Diagnosis of Induction Motors Using Recurrence Quantification Analysis and LSTM with Weighted BN

Motor fault diagnosis has gained much attention from academic research and industry to guarantee motor reliability. Generally, there exist two major approaches in the feature engineering for motor fault diagnosis: (1) traditional feature learning, which heavily depends on manual feature extraction, is often unable to discover the important underlying representations of faulty motors; (2) state‐of‐the‐art deep learning techniques, which have somewhat improved diagnostic performance, while the intrinsic characteristics of black box and the lack of domain expertise have limited the further improvement. To cover those shortcomings, in this paper, two manual feature learning approaches are embedded into a deep learning algorithm, and thus, a novel fault diagnosis framework is proposed for three‐phase induction motors with a hybrid feature learning method, which combines empirical statistical parameters, recurrence quantification analysis (RQA) and long short‐term memory (LSTM) neural network. In addition, weighted batch normalization (BN), a modification of BN, is designed to evaluate the contributions of the three feature learning approaches. The proposed method was experimentally demonstrated by carrying out the tests of 8 induction motors with 8 different faulty types. Results show that compared with other popular intelligent diagnosis methods, the proposed method achieves the highest diagnostic accuracy in both the original dataset and the noised dataset. It also verifies that RQA can play a bigger role in real‐world applications for its excellent performance in dealing with the noised signals.

Induction Motor Condition Monitoring for Sustainable Manufacturing

Abstract As the power source for virtually all manufacturing systems, induction motor represents an integral part in modern manufacturing. Reliable functioning of induction motors is critical to minimizing machine downtime and maintaining high performance, which contributes to scrap-free production and overall sustainability in manufacturing. Due to the complex physical mechanisms, reliable and low-cost motor condition monitoring has remained a challenge, especially for small and medium-sized manufacturers (SMMs). This paper describes a data-driven method for real-time induction motor condition monitoring and fault diagnosis, based on Dictionary Learning and Nystrom method. The integrated method is highlighted by improved data discriminability and effectiveness in handling data high dimensionality. Experimental evaluation using vibration signal as fault indicator confirmed high accuracy of the proposed method in induction motor multi-fault classification and an 80% reduction in execution time.

A Motor Fault Diagnosis System Based on Cerebellar Model Articulation Controller

The purpose of this paper is to construct a smart induction motor fault diagnosis system with cerebellar model articulation controller (CMAC). First, we divide induction motor faults in three kinds, rotor mandrel fault, bearing fault and electrical fault. Then, we subdivide them into ten types, in each of which the vibration signal spectra of induction motors were measured and sorted for establishing the individual fault types. From the information on motor faults, we identify representative characteristic frequency spectra for the faults to further establish the correlations between each of the fault types and its corresponding characteristic frequency spectrum as the basis for the development of a motor fault diagnosis system. In this paper, the theoretic basis is CMAC, and the data of vibration signal spectrum measured against the motor faults are used to train the fault diagnosis system. We then conducted fault diagnoses with the data of actual motor run. The test results demonstrated that the proposed induction motor fault diagnosis system is capable of fast algorithm, requires less data to train with, as well as has excellent power of identification.

Fault Diagnosis and Fault Tolerant Control of a Three-Phase VSI Supplying Sensorless Speed Controlled Induction Motor Drive

Fault diagnosis in variable speed drives under inverter faults has been widely addressed in the literature. However, research activities in this field have been always focused only on sensored motor drives. This paper deals with a mixed model-based and signal-based approach for both insulated-gate bipolar transistor (IGBT) open-circuit fault diagnosis and fault tolerant control in sensorless speed-controlled induction motor (IM) drive. Sliding mode observer (SMO) is used for speed and stator currents estimation and simultaneously open-switch fault diagnosis. Unlike the classical sensored drive systems, this structure presents particular dynamics under faulty operation-mode which can be taken into account for fault detection and identification (FDI) process designing. The proposed diagnostic algorithm is based on similarity test between measured and estimated currents to define the FDI index in the inverter. The proposed method allows detection and localization of single and multiple IGBT open-switch faults. To improve the reliability of the motor drive, the ability of the SMO to reconstitute the motor state estimation after the disturbance stage of the FTC application is verified. The proposed FDI and FTC schemes are implemented on a dSPACE DS1104 controller board for a 3-kW IM drive system. Several experiments are displayed to show the effectiveness and feasibility of the proposed method.