Fault Detection In Induction Motors Research Articles

FAULT DETECTION OF INDUCTION MOTORS

In this work described method of fault detection of induction motors. Induction motors are broadly utilized in numerous mechanical applications. Subsequently, it is exceptionally imperative to monitor and detect any faults during their operation in arrange to alarm the administrators so that potential issues can be avoided before they happen. In common, a fault within the acceptance motor causes it to induce hot amid its operation. This paper presents a developed protection method algorithm that uses unbalanced power components and simulates the overall design based on the Matlab Simulink. Three-phase voltage and current data are observed first, followed by signs of unbalanced power, according to the digital relay safety algorithm. The relay then uses a negative sequence reactive power sign to decide if the fault is internal or external. A negative sign for negative sequence reactive power indicates a fault inside the motor, while a positive sign indicates a fault outside the motor.

Detection of Broken Rotor Bars in Nonlinear Startups of Inverter-Fed Induction Motors

Fault detection in induction motors powered by inverters operating in nonstationary regimes remains a challenge. The trajectory in the time-frequency plane of harmonics related to broken rotor bar develops very in proximity to the path described by the fundamental component. In addition, their energy is much lower than the amplitude of the first harmonic. These two characteristics make it challenging to observe them. The Dragon Transform (DT), here presented, is developed to overcome the described problem. In this article, the DT is assessed with nonlinear inverter-fed startups, where its high time and frequency resolutions facilitate the monitoring of fault harmonics even with highly adjacent trajectories to the first harmonic path.

Comparative Analysis of Signal Processing Techniques for Fault Detection in Three Phase Induction Motor

Signal processing is considered as an efficient technique to detect the faults in three-phase induction motors. Detection of different varieties of faults in the rotor of the motor are widely studied at the industrial level. To extend further, this research article presents the analysis on various signal processing techniques for fault detection in three-phase induction motor due to the damages in rotor bar. Usually, Fast Fourier Transform (FFT) and STFT are used to analyze the healthy and faulty motor conditions based on the signal characteristics. The proposed study covers the advantages and limitations of the proposed wavelet transform (WT) and each technique for detecting the broken bar of induction motors. The good frequency information can be collected from FFT techniques for handling multiple faults identification in three-phase induction motor. Despite the hype, the detection accuracy gets reduced during the dynamic condition of the machine because the frequency information on sudden time changes cannot be employed by FFT. The WT method signal analysis is compared with FFT to propose fault detection method for induction motor. The WT method is proving better accuracy when compared to all existing methods for signal information analysis. The proposed research work has simulated the proposed method with MATLAB / SIMULINK and it helps to effectively detect the healthy and faulty conditions of the motor.

Fault Indexing Parameter Based Fault Detection in Induction Motor via MCSA with Wiener Filtering

Fault detection in an induction motor, particularly at premature stage has become necessary to avoid unexpected damage in industrial process. In this paper, an approach to detect the early stage faults in induction machine using motor current signature analysis (MCSA) is presented. It is proposed to estimate the fault severity from stator current using noise cancelation by an adaptive filter (Wiener filter). Wavelet De-noising technique is implemented to reduce the effect of noise floor in noise canceled stator current. Different categories of bearing faults, broken rotor fault and stator inter turn faults in induction motor are estimated with and without de-nosing using pre-fault component cancelation (Noise cancelation). In addition, fault index based on standard deviation (SD) and simple square integral (SSI) value of noise canceled stator current are proposed. The proposed fault detection topology is examined using simulations and experiments on a 3HP, 1HP and 0.5HP induction motors for bearing, broken rotor and stator inter turn faults respectively.

Rotor Fault Detection in Squirrel Cage Induction Motors using MCSA and DWT Techniques

This article presents the fault detection of broken rotor bar (BRB) faults in squirrel cage induction motors (SCIMs). This work applied two diagnostic methods on stator current signal. It is necessary to verify the machine health to avoid any catastrophic damage. The first method uses the fast Fourier transform (FFT) which is generally called motor current signature analysis (MCSA). We carefully verified the spectral content of the stator current to detect BRB fault. The new harmonics allows us to take a good decision about BRB fault. The second method is based on the discrete wavelet transform (DWT). This technique is widely used in the diagnosis field of rotating machinery. According to DWT method, we used the mean square error (MSE) as a good indicator. An experimental test with different conditions of the induction motor has been performed. The experimental results have been exploited using MCSA and DWT methods to achieve a good decision.

Bearing/Incipient/Open Phase Fault Detection and Diagnosis of Multi-Phase Induction Motor Drives Equipped By GBDTI2HO Technique

In this paper, a hybrid system is performed with fault detection and diagnosis on multi-phase induction motor (IM). The proposed method is hybrid of integrated Harris Hawk optimization (IHHO) and gradient boosting decision trees (GBDT) thus called the GBDTI2HO method. Here, additional operators are included in this paper to improve HHO’s search behaviour namely crossover and mutation. Distorted waveforms are generated by different frequency patterns to indicate the time domain frequency as an assessment of failure. For this signal representation, the discrete wavelet transformation (DWT) is suggested. It extracts the characteristics and forwards them to IHHO technique to form the possible data sets. After the generation of the data set, GBDT classifies the ways of failure reached as winding of stator in multi-phase IM. The implementation of the proposed system is compared with existing systems, such as ANN, S-Transform and GBDT. The proposed method is executed on MATLAB/Simulink work platform to demonstrate the successfulness of proposed system, statistical measures are determined, as precision, sensitivity and specificity, mean median and standard deviation. For demonstrating the successfulness of proposed system, statistical measures are determined as precision, sensitivity, specificity, mean median as well as standard deviation. In 50 trails the proposed method, 0.98 for accuracy, 0.96 for specificity, 1.60 for recall as well as 0.97 for precision. In 100 trail the proposed method, 0.96 for accuracy, 0.93 for specificity, 0.87 for recall as well as 0.99 for precision.

Induction Motor Multiclass Fault Diagnosis Based on Mean Impact Value and PSO-BPNN

This paper presents a feature selection model based on mean impact value (MIV) to solve induction motor (IM) fault diagnosis on the current signal. In this paper, particle swarm optimization (PSO) is combined with back propagation neural network (BPNN) to classify the current signal of IM. First, the purpose of this study is to establish IM fault diagnosis system. Additionally, this study proposes a feature selection process that is composed of MIV, whose objective is to reduce the number of classifier input features. Secondly, the features are extracted as a feature database after analyzing the current signal of IM, and the fault diagnosis is established through the model of PSO-BPNN. Finally, redundant features are deleted through this feature selection process and a classifier is built. The result shows that the feature selection model based on MIV can filter the features effectively at a signal to noise ratio of 30 dB and 20 dB for the IM fault detection problem. In addition, the computing time of BPNN is also reduced which is helpful for online detection.

A Smart Sensor-Based cEMD Technique for Rotor Bar Fault Detection in Induction Motors

Induction motors (IMs) are commonly used in industrial and domestic applications. Reliable IM fault detection can improve machinery production quality and operation safety and prevent unexpected failures. However, reliable motor fault diagnosis is still a challenging research and development task, especially in real machinery monitoring applications, due to the limitations in data acquisition (DAQ) systems and fault detection techniques. The first objective of this work is to develop a wireless smart sensor DAQ system for the current signal measurement. The second objective is to propose a new correlation empirical mode decomposition (cEMD) technique to detect broken rotor bar faults. The proposed cEMD technique can differentiate the line current and its sideband components from other frequencies and accentuate fault features over intrinsic mode function sidebands so as to improve fault detection accuracy. The effectiveness of the developed smart sensor DAQ system and the cEMD technique is verified experimentally under different motor conditions.

Stator Winding Fault Detection and Classification in Three-Phase Induction Motor

Induction motors (IMs) are the workhorse of the industry and are subjected to a harsh environment. Due to their operating conditions, they are exposed to different kinds of unavoidable faults that lead to unscheduled downtimes and losses. These faults may be detected early through predictive maintenance (i.e., deployment of condition monitoring systems). Motor current signature analysis (MCSA) is the most widely used technique to detect various faults in industrial motors. The stator winding faults (SWF) are one of the major faults. In this paper, we present an induction motor fault detection and identification system using signal processing techniques such as fast Fourier transform (FFT), short-time Fourier transform (STFT), and continuous wavelet transform (CWT). A three-phase motor model is developed in MATLAB Simulink and simulated under various fault conditions. The current signature is observed using FFT, spectrogram, and scalogram to detect the faults. It is observed that under some fault conditions, the current signature analysis remains indistinguishable from the non-fault case. Therefore, deep learning (DL) methods are adopted here to identify these faults. The time-series data of healthy and unhealthy conditions are obtained from the simulation results. The comparative investigation among DL models confirmed the superiority of the long short-term memory (LSTM) model, which achieved 97.87% accuracy in identifying the individual faults.

Minimum Distance-Based Detection of Incipient Induction Motor Faults Using Rayleigh Quotient Spectrum of Conditioned Vibration Signal

In this article, we propose a single-vibration sensor-based method for detecting incipient faults in squirrel cage induction motors (SCIMs). We consider defects in different parts of the bearing (inner raceway, outer raceway, cage train, and rolling element) and in a single bar of the rotor. The vibration signal is dominated by the fundamental rotational frequency and its harmonics. The dominant components result in numerical errors while estimating the relatively indistinct fault-specific spectral components. In this article, we precondition the vibration signal by suppressing multiple dominant components using an extended Kalman filter-based method. The suppression of the dominant components reduces the spectral leakage, exposes minute fault components, and improves the overall amplitude estimation. Subsequently, we estimate the fault frequency and amplitude using an accurate and low-complexity Rayleigh-quotient-based spectral estimator. The thresholds for fault detection are determined from a small number of healthy data, and an adaptive minimum distance-based detector is used for hypothesis testing. The proposed test improves detection and reduces false alarms under noisy conditions. We test the complete algorithm using data from a 22-kW SCIM laboratory setup. The proposed method has achieved 100% accuracy with the publicly available 12-kHz drive-end bearing data from Case Western Reserve University, Cleveland, OH, USA.

Convolutional neural network with batch normalisation for fault detection in squirrel cage induction motor

Convolutional neural network with batch normalisation for fault detection in squirrel cage induction motor

유도전동기에 발생되는 고장 신호 검출 해석 모델에 관한 연구

본 논문은 유도전동기의 기하학적 문제 및 축계의 진동공학적 안정성에 영향을 미치는 인한 불평형 자기 흡인력의 계산 방법론을 제시하였다. 이를 통해 검출 가능한 전기적 고장 신호를 해석적으로 산출하였다. 일반적으로 과도한 소음과 진동이 기하학적 문제를 통해 유도전동기에 발생한다. 회전자의 비정상적인 조립이 존재하면 축 방향과 원주 좌표의 함수인 공극에 의한 퍼미언스가 나타난다. 본 논문에서 불평형 자기 흡인력은 퍼미언스와 기자력파를 이용하여 계산되며, 평행 편심뿐만 아니라 정적 및 동적 오정렬의 경우다. 오정렬과 편심률의 비율을 기준으로 하면 오정렬과 편심도가 증가함에 따라 불평형 자기 흡인력과 자기 압력이 증가한다는 것을 알 수 있다. 이때 불평형 자기 흡인력은 전원 주파수의 동기 성분뿐만 아니라 다른 성분에서도 발생함을 알 수 있다.

Deep convolutional neural network based on adaptive gradient optimizer for fault detection in SCIM

Early fault detection in squirrel cage induction motor (SCIM) can minimize the downtime and maximize production. This paper presents an adaptive gradient optimizer based deep convolutional neural network (ADG-dCNN) technique for bearing and rotor faults detection in squirrel cage induction motor. Multiple MEMS accelerometers have been used for vibration data collection, and sensor data fusion is employed in the model training and testing. ADG-dCNN allows the automatic feature extraction from the vibration data and minimizes the need for human expertise and reduces human intervention. It eliminates the error caused by manual feature extraction and selection, which is dependent on prior knowledge of fault types. This paper presents an end-to-end learning fault detection system based on deep CNN. The dataset for training and testing of the proposed method is generated from the test set-up. The proposed classifier attained an average accuracy of 99.70%. This paper also presents the recently developed SHapley Additive exPlanations (SHAP) methodology for evaluation of fault classification from the proposed model. The proposed technique can also be extended to other machinery with multiple sensors owing to its end-to-end learning abilities.

Electrical fault detection in three-phase induction motor using deep network-based features of thermograms

In this paper, an automatic method is proposed for detecting the operating faults in three-phase induction motors based on thermal images. If these faults are not detected or fixed on time, they can lead to permanent motor failure. This is why non-invasive and non-destructive experiments are significantly considered. In this paper, first, the region of interest is detected in the thermograms using SIFT-based key-points matching. Then, these images are transformed into representative feature vectors based on a pre-trained convolutional neural network. Then, the training vector samples are clustered into cold and hot clusters by K-means. For each cluster, an SVM-based classifier is trained. The test feature vector samples are clustered and mapped into classes using the corresponding trained SVM-based classifiers. Evaluating the proposed method on the datasets including real thermal images, shows that this algorithm can detect 100% of the faults of the induction motor.

Advanced Detection of Rotor Electrical Faults in Induction Motors at Start-Up

It has been lately shown that, traditional diagnostic approaches for rotor electrical faults detection in induction motors can be dangerously misleading. That is due to many different fault cases that mask the fault signatures thus leading to false negative alarms, or a plethora of harmless conditions that generate signatures similar to the faulty ones leading to false positive alarms. Aiming for reliable fault detection, a new trend has appeared, that of the analysis of the stator current at start-up of the motor. This method proves to be reliable in many cases, however there are still cases where it can lead to false positive alarms especially when applied on motors by diagnostic engineers for the first time. Aiming for a more reliable approach, a new method is proposed in this paper. The proposed novel method consists of the analysis of the zero-sequence current under transient motor operation and specifically the start-up. The paper's findings demonstrate the method's reliability and superiority over the analysis of a single current.

Autocorrelation Aided Random Forest Classifier-Based Bearing Fault Detection Framework

Rolling bearing defects in induction motors are usually diagnosed using vibration signal analysis. For accurate detection of rolling bearing defects, appropriate feature extraction from vibration signals is necessary, failure of which may lead to incorrect interpretation. Considering the above fact, this article presents an autocorrelation aided feature extraction method for diagnosis of rolling bearing defects. To this end, the vibration signals of healthy as well as different faulty bearings were recorded using accelerometers and autocorrelation of the respective vibration signals were done to examine their self-similarity in time scale. Following this, several statistical, hjorth as well as non-linear features were extracted from the respective vibration correlograms and were subjected to feature reduction using recursive feature elimination technique. The dimensionally reduced top ranked feature vectors were subsequently fed to a random forest classifier for classification of vibration signals. A large number of experiments were carried out for (i) three different fault diameters at (ii) four different shaft speeds and also at (iii) two different sampling frequencies. Besides, for each condition, six binary class and one multiclass classification problem is also addressed in this paper, resulting in a total 112 different classification tasks. It was observed that the proposed method has yielded very high accuracy in identifying different bearing defects which can be practically implemented for automated bearing fault detection of induction motors.

Phase to phase fault detection of 3-phase induction motor using FRA technique

The purpose for preparing this paper is to innovate a new method to detection and diagnosis the three-phase induction motor electrical failures, especially the failures that occur in Stator winding. Stator winding breakdown largely contributes to induction motor failures. To understand internal fault in induction motors winding, four cases studies of different three-phase induction motors (TPIM) were analysed according to two conditions: normal winding condition and windings shorted between two phases. In this paper, the measurement of frequency response analysis (FRA) on the stator winding with inter-phase short is presented. Additionally, Frequency Response Analysis (FRA) interpretation technique classify and quantify the fault is also proposed. For interpretation of the FRA, a statistical indicator, which is NCEPRI algorithm is used for comparison the measured responses.

Establish Induction Motor Fault Diagnosis System Based on Feature Selection Approaches with MRA

This paper proposes a feature selection (FS) approach, namely, correlation and fitness value-based feature selection (CFFS). CFFS is an improvement feature selection approach of correlation-based feature selection (CFS) for the common failure cases of the induction motor. CFFS establishes the induction motor fault detection (FD) system with artificial neural network (ANN). This study analyzes the current signal of the induction motor with multiresolution analysis (MRA), extracts the features, and uses feature selection approaches (ReliefF, CFS, and CFFS) to reduce the number of features and maintain the accuracy of the induction motor fault detection system. Finally, the induction motor fault detection system is trained by the feature selection approaches selected features. The best induction motor fault detection system will be established through the comparison of the efficiency of these FS approaches.

Induction motor fault detection based on multi‐sensory control and wavelet analysis

Detection and fault-tolerant control (FTC) of faults in the early stage is desirable in improving efficiency. An implementation strategy is proposed for the individual controllers that work collectively in induction motor (IM) drive by interswitching from one form of a control strategy to another. The interswitching occurs between voltage by frequency (V/f) open-loop control, closed-loop (V/f) control, sensorless vector control and sensor vector control. Optimal performance capabilities are attained with vector control, whereas V/f is a setup that is affordable but with increased speed. In this study, the faults are open and short circuits winding faults, speed sensor failures and stator winding faults. When the severity of the fault is high, an embedded protection entity interrupts the motor. Daubechies 10 wavelet is used due to its significant vanishing moments compared to the other types of Daubechies as fault index with the stator current of 1 kW IM. A novel enhanced model reference adaptive system is employed for sensorless vector control to assess the motor speed. Both the simulation and experiment (using the F28335 DSP controller) indicate that the framework is effective in detecting the fault, ensuring the robustness of the FTC scheme and proving the effectiveness of the proposed algorithm.

Time-Frequency Analysis Based on Minimum-Norm Spectral Estimation to Detect Induction Motor Faults

In this work, a new time-frequency tool based on minimum-norm spectral estimation is introduced for multiple fault detection in induction motors. Several diagnostic techniques are available to identify certain faults in induction machines; however, they generally give acceptable results only for machines operating under stationary conditions. Induction motors rarely operate under stationary conditions as they are constantly affected by load oscillations, speed waves, unbalanced voltages, and other external conditions. To overcome this issue, different time-frequency analysis techniques have been proposed for fault detection in induction motors under non-stationary regimes. However, most of them have low-resolution, low-accuracy or both. The proposed method employs the minimum-norm spectral estimation to provide high frequency resolution and accuracy in the time-frequency domain. This technique exploits the advantages of non-stationary conditions, where mechanical and electrical stresses in the machine are higher than in stationary conditions, improving the detectability of fault components. Numerical simulation and experimental results are provided to validate the effectiveness of the method in starting current analysis of induction motors.