Broken Rotor Bars In Induction Motors Research Articles

Improved Diagnostic Approach for BRB Detection and Classification in Inverter-Driven Induction Motors Employing Sparse Stacked Autoencoder (SSAE) and LightGBM

This study introduces an innovative approach to diagnostics, employing a unique combination of techniques including a stratified group K-fold cross-validation method and a sparse stacked autoencoder (SSAE) alongside LightGBM. By examining signatures derived from motor current, voltage, speed, and torque, the framework aims to effectively detect and classify broken rotor bars (BRBs) within inverter-fed induction machines. In this kind of cross-validation method, class labels and grouping factors are spread out across folds by distributing motor operational data attributes equally over target label stratification and extra grouping information. By integrating SSAE and LightGBM, a gradient-boosting framework, we elevate the precision and efficacy of defect diagnosis. The SSAE feature extraction algorithm proves to be particularly effective in identifying small BRB signatures within motor operational data. Our approach relies on comprehensive datasets collected from motor systems operating under diverse loading conditions, ranging from 0% to 100%. Using a sparse stacked autoencoder, the model lowers the dimensionality and noise of the motor fault data. It then sends the cleaned data to the LightGBM network for fault diagnosis. LightGBM leverages the attributes of the sparse stacked autoencoder to showcase the distinctive qualities associated with BRBs. This integration offers the potential to improve defect identification by furnishing input representations that are both more precise and more concise. The proposed model (SSAE with LightGBM) was trained using 80% of the data, while the remaining 20% was used for testing. To validate the proposed architecture, we evaluate the accuracy, precision, recall, and F1-scores of the results using motor global signals, with the help of confusion matrices with receiver operating characteristic (ROC) curves. Following the training of a new LightGBM model with refined hyperparameters through Bayesian optimization, we proceed to conduct the final classification utilizing the optimal feature subset. Evaluation of the test dataset indicates that the BRBs diagnostic framework facilitates the detection and classification of issues with induction motor BRBs, achieving accuracy rates of up to 99% across all loading conditions.

Detection of Broken Rotor Bars in Cage Induction Motors Using Machine Learning Methods.

In this paper, the performance of machine learning methods for squirrel cage induction motor broken rotor bar (BRB) fault detection is evaluated. Decision tree classification (DTC), artificial neural network (ANN), and deep learning (DL) methods are developed, applied, and studied to compare their performance in detecting broken rotor bar faults in squirrel cage induction motors. The training data were collected through experimental measurements. The BRB fault features were extracted from measured line-current signatures through a transformation from the time domain to the frequency domain using discrete Fourier Transform (DFT) of the frequency spectrum of the current signal. Eighty percent of the data were used for training the models, and twenty percent were used for testing. A confusion matrix was used to validate the models' performance using accuracy, precision, recall, and f1-scores. The results evidence that the DTC is less load-dependent, and it has better accuracy and precision for both unloaded and loaded squirrel cage induction motors when compared with the DL and ANN methods. The DTC method achieved higher accuracy in the detection of the magnitudes of the twice-frequency sideband components induced in stator currents by BRB faults when compared with the DL and ANN methods. Although the detection accuracy and precision are higher for the loaded motor than the unloaded motor, the DTC method managed to also exhibit a high accuracy for the unloaded current when compared with the DL and ANN methods. The DTC is, therefore, a suitable candidate to detect broken rotor bar faults on trained data for lightly or thoroughly loaded squirrel cage induction motors using the characteristics of the measured line-current signature.

DBF-CNN: A Double-Branch Fusion Residual CNN for Diagnosis of Induction Motor Broken Rotor Bar

DBF-CNN: A Double-Branch Fusion Residual CNN for Diagnosis of Induction Motor Broken Rotor Bar

A novel dataset and lightweight detection system for broken bars induction motors using optimizable neural networks

Broken rotor bars (BRBs) in induction motors (IMs) are a common kind of failure and one of the most difficult to detect since the induction motor continues to run properly in the absence of any evidence of a malfunction. There have been several approaches presented for identifying BRBs in IMs. However, in order to parameterize the current signal, they need tools with a high computational cost, making an online implementation of the appropriate monitoring system difficult. As a result, this paper proposes a novel AI-based approach to detect and classify BRBs faults in IMs using novel multi-class datasets from two three-phase, 400V induction motors; 2.2kW, two poles, 50 Hz, 24 stator slots and with 20,29 and 32 rotor bars numbers (M24Ns,(20,29,32)Nb), and 2.2kW, four poles, 60 Hz, 36 stator slots with 28 and 44 rotor bars numbers (M36Ns, (28,44)Nb) to help in the analysis of healthy and faulty IMs, as well as classification performance evaluation and benchmarking. The developed lightweight, intelligent, and autodetection system employs a self-configurable neural network model for BRBs in IM models. It provides four classification outputs: healthy, one-BRB, two-BRBs, and three-BRBs. The simulation results characterize the performance of the (M24Ns, (20,29,32) Nb) and (M36Ns, (28,44) Nb) IMs and the combined mode for both motors, demonstrating that the proposed approach is very effective in detecting and classifying BRBs, with a 99.8 % and a prediction time of 1.64 microseconds.

Induction Motor Broken Rotor Bar Fault Diagnosis Based on Third-Order Energy Operator Demodulated Current Signal

Motor current signature analysis (MCSA) has been widely used for fault diagnosis of induction motors (IMs) because of its non-invasiveness and comparatively low cost. However, the spectral leakage of the fundamental supply frequency can obscure the fault characteristic component when IMs operating at no-load or low-load conditions. In this paper, a broken rotor bar (BRB) fault diagnosis approach based on the third-order energy operator (TOEO) demodulated current signals is presented. The TOEO approach performs effectively in reducing the negative impact of the fundamental supply frequency spectral leakage and enhancing the BRB fault features. Theoretical and experimental results show that the TOEO approach can excellently reveal the fault characteristic frequency, instead of the sideband frequencies. Besides, the results are compared with the Teager-Kaiser energy operator (TKEO). The capability of the presented approach has several advantages over the TKEO, especially when the IMs are fed by an inverter.

Current and Stray Flux Combined Analysis for the Automatic Detection of Rotor Faults in Soft-Started Induction Motors

Induction motors (IMs) have been extensively used for driving a wide variety of processes in several industries. Their excellent performance, capabilities and robustness explain their extensive use in several industrial applications. However, despite their robustness, IMs are susceptible to failure, with broken rotor bars (BRB) being one of the potential faults. These types of faults usually occur due to the high current amplitude flowing in the bars during the starting transient. Currently, soft-starters have been used in order to reduce the negative effects and stresses developed during the starting. However, the addition of these devices makes the fault diagnosis a complex and sometimes erratic task, since the typical fault-related patterns evolutions are usually irregular, depending on particular aspects that may change according to the technology implemented by the soft-starter. This paper proposes a novel methodology for the automatic detection of BRB in IMs under the influence of soft-starters. The proposal relies on the combined analysis of current and stray flux signals by means of suitable indicators proposed here, and their fusion through a linear discriminant analysis (LDA). Finally, the LDA output is used to train a feed-forward neural network (FFNN) to automatically detect the severity of the failure, namely: a healthy motor, one broken rotor bar, and two broken rotor bars. The proposal is validated under a testbench consisting of a kinematic chain driven by a 1.1 kW IM and using four different models of soft-starters. The obtained results demonstrate the capabilities of the proposal, obtaining a correct classification rate (94.4% for the worst case).

Walsh–Hadamard Domain-Based Intelligent Online Fault Diagnosis of Broken Rotor Bars in Induction Motors

Mechanical failures are the most common defects in induction motors (IMs). They derive from the continuous starts and stops with high-load torque. They can cause interruptions in production lines with great economic losses. Therefore, online monitoring systems, allowing a continuous monitoring for fault diagnosis in early stages, have been intended for many researches in last years. Broken rotor bars (BRBs) are common failures, which are among the most difficult to detect since the induction motor works with apparent normality without giving any signal about the defect. Several methodologies have been proposed to detect BRBs in IMs. However, they require high-computational-complexity algorithms for parameterizing the current signal, making it difficult to achieve an online implementation of the corresponding monitoring system. Hence, aiming to overcome the limitations provoked by complex parameterizations of the current signal and to improve the fault classification accuracy, in this work, a novel methodology, based on a hardware processing system implemented on a field-programmable gate array (FPGA), for electric current signal analysis in the Walsh–Hadamard domain is proposed to achieve online intelligent BRB diagnosis. The <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula> -nearest neighbors ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$k$ </tex-math></inline-formula> -NN) algorithm is used for classifying different operational conditions from the Walsh–Hadamard transform (WHT) of the electric-current signal. Experimentally obtained results from applying the proposed method on acquired real data demonstrate that the introduced approach reaches a remarkable high efficiency on detecting and classifying BRBs.

Deep machine learning with grey wolf algorithm and central deference Kalman filter based broken rotor bars detection in induction motor

The present study tries to propose a new method which is using Central deference Kalman Filter (CDKF) as input index of deep machine learning (DML), for simulating state estimation and broken rotor bars (BRBs) diagnosis in induction motors (IMs). In addition, an advanced selective ensemble (DML) method applying the grey wolf optimization (GWO) algorithm to diagnose the BRBs in IMs is proposed in the following study. Here, in the initial step, in order to take sufficient datum within the usual efficiency, it is needed to train the DML network. The outcomes indicate that the offered scheme can more accurately and powerfully detect diverse forms of BRBs with an accuracy of more than 98%. And also, Filter precision is enhanced via changing the sigma points of the filter, however, the stability of the filter enhances more because of its utilization, and the CDKF is further stable and precise in comparison to the Unscented Kalman filter (UKF). The CDKF performance is assessed to estimate the speed and is used as input index of DML to diagnose the broken rotor bar in IMs. The obtained outcomes prove the performance of this combined scheme.

ANN-Based Pattern Recognition for Induction Motor Broken Rotor Bar Monitoring under Supply Frequency Regulation

The requisite of direct-on-line (DOL) starting for various applications in underground mines subjects the rotor bars of heavy-duty squirrel cage induction motors (SCIMs) to severe stresses, resulting in sustained fault in the rotor bars, unlike the applications where mostly reduced voltage starting is preferred. Furthermore, SCIMs working in underground mines are also affected by unforeseen frequency fluctuations. Hence, the paper proposes a discrete wavelet transform (DWT)-based broken rotor bar detection scheme using the stator current analysis of SCIM when subjected to a frequency regulation (±4% of 50 Hz supply) in steady-state, as prevalent in underground mines. In this regard, the level-seven detailed coefficient obtained by the DWT-based multi-resolution analysis of stator current corresponding to the healthy rotor is compared with that of the faulty rotor to extract the necessary features to identify the fault. Further implementation of the proposed scheme is done using artificial neural network (ANN)-based pattern recognition techniques, wherein both feed-forward backdrops and cascaded forward backdrop type ANNs have been used for fault pinpointing based on the feature extraction results obtained from DWT. The scheme is developed and analysed in MATLAB/Simulink using 5.5 kW, 415 V, 50 Hz SCIM, which is further validated using the LabVIEW-based real-time implementation.

A new transform discrete wavelet technique based on artificial neural network for induction motor broken rotor bar faults diagnosis

The main objective of this article is to contribute the automatic fault diagnosis of broken rotor bars in three-phase squirrel-cage induction motor using vibration analysis. In fact, two approaches are combined to do so, based on signal processing technique and artificial intelligence technique. The first technique is based on discrete wavelet transform (DWT) to detect the harmonics that characterize this fault, using the Daubechies wavelet vibration analysis according to three axes (X, Y, Z). This application permits having the approximation mode function and the details (recd). To exact choice of reconstruction details which contains the information of the broken rotor bars faults, two statistical studies based on the root mean square values (RMS) and Kurtosis shock factor calculation are carried out for each (recd). The choice of (recd) is conditioned by (RMS) and Kurtosis values as: RMSrecd1 < RMSrecd2 and Kurtosisrecd1 > Kurtosisrecd2. Experimental results showed that (recd1 and recd2) satisfied the condition set for (RMS) and Kurtosis values. At the end of first technique, a spectral envelop of recd1 is adopted to detect the broken rotor bars fault and the second technique based on artificial neural network (ANN) is used to identify the number of broken rotor bars. The characteristics of features used as input variables of ANN are the RMS of recd1 and recd2, and the Kurtosis shock factor of recd1 and recd2. The experimental results demonstrated the high efficiency of the proposed method with rotor broken bars fault classification rate of 98.66%.

Detection of induction motor broken rotor bar faults under no load condition by using support vector machines

An important fault in induction motor is the broken rotor bar. Many techniques have been proposed for the detection of the rotor fault. However, the traditional techniques like motor current signature analysis have difficulty in detecting the rotor faults at 'no load' condition due to low slip. In this study, an algorithm which uses fast Fourier transform, principal component analysis and intelligent classifiers is proposed. The proposed algorithm was able to accurately detect the rotor faults of different severity levels at low slip. Experiments were carried out with three submersible induction motors. Four different rotor faults and healthy motor conditions were investigated for each motor. The motors were loaded different load levels to test the proposed algorithm. The best results were achieved with medium Gaussian support vector machine. The condition of having any faulted bar in the motor was obtained with 100% accuracy. Faults classification carried out by 92.2% accuracy.

Detection of induction motor broken rotor bar faults under no load condition by using support vector machines

Detection of induction motor broken rotor bar faults under no load condition by using support vector machines

Induction motors broken rotor bars detection using RPVM and neural network

PurposeThe purpose of this study aims to focus on the detection and identification of the broken rotor bars (BRBs) of a squirrel cage induction motor (SCIM). The presented diagnosis technique is based on artificial neural networks (NNs) that use as inputs the results of the spectral analysis using the fast Fourier transform (FFT) of the reduced Park’s vector modulus (RPVM), along with the load values in which the motor operates.Design/methodology/approachFirst, this paper presents a comparative study between FFT applied on Hilbert modulus, Park’s vector modulus and RPVM to extract feature frequencies of BRB faults. Moreover, the extracted features of FFT applied to RPVM and the load values were selected as NNs’ inputs for the detection of the number of BRBs.FindingsThe obtained simulation results using MATLAB (Matrix Laboratory) environment show the effectiveness and accuracy of the proposed NNs based approach.Originality/valueThe current paper presents a novel diagnostic method for BRBs’ fault detection in SCIM, based on the combination between the signal processing analysis (FFT of RPVM) and artificial intelligence (NNs).

Induction motor broken rotor bar fault detection techniques based on fault signature analysis – a review

The induction motor is the most popular motor in energy conversion and industrial drive systems. This popularity is due to its robustness, low cost, and easy maintenance. Electrical, mechanical, thermal, magnetic and environmental stresses cause faults in the induction motor during the operation process. One of the challenging topics for many researchers is the development of a reliable efficient induction motor fault diagnostic techniques. The broken rotor bar fault is one of the critical faults that need to be early detected due to its sudden severe damages. The objective of this study is to present a survey of existing broken rotor bar fault detection techniques with new classification based on fault signature. Various monitoring conditions and signal processing techniques are considered for the detection process. A comprehensive list of references is reported for each fault signature and classified based on (i) loading level, (ii) the number of broken bars, (iii) validation and (vi) signal processing.

Use of a combined SVD-Kalman filter approach for induction motor broken rotor bars identification

This paper describes a new parametric spectral estimator for the identification of rotor bar fault of an induction motor using stator current analysis. This approach combines two methods: The first one, the Singular Value Decomposition method which allows the accurate detection and location of the fault's signature frequency. The second method allows the estimation of the fault amplitude. To this end, the Kalman filter is used for its efficient estimation of both amplitude and phase estimation using the frequencies estimated by the first method. This combination of both methods gives a better frequency resolution for a very short acquisition time, which cannot be obtained using the conventional method of the Periodogram. Moreover, in order to reduce the significant computation time resulting from the use of the Kalman filter, the proposed approach is applied only to the frequency band where the fault signature is able to appear. A series of tests will be carried out on real signals representing rotor faults.

Induction motor broken rotor bar fault location detection through envelope analysis of start-up current using Hilbert transform

Robustness, low running cost and reduced maintenance lead Induction Motors (IMs) to pioneerly penetrate the industrial drive system fields. Broken rotor bars (BRBs) can be considered as an important fault that needs to be early assessed to minimize the maintenance cost and labor time. The majority of recent BRBs’ fault diagnostic techniques focus on differentiating between healthy and faulty rotor cage. In this paper, a new technique is proposed for detecting the location of the broken bar in the rotor. The proposed technique relies on monitoring certain statistical parameters estimated from the analysis of the start-up stator current envelope. The envelope of the signal is obtained using Hilbert Transformation (HT). The proposed technique offers non-invasive, fast computational and accurate location diagnostic process. Various simulation scenarios are presented that validate the effectiveness of the proposed technique.

Induction Motors Broken Rotor Bars Diagnosis Through the Discrete Wavelet Transform of the Instantaneous Reactive Power Signal under Time-varying Load Conditions

—In this article, a method based on the application of the discrete wavelet transform to the instantaneous reactive power signal, for diagnosing the occurrence of broken rotor bars ininduction motors operating under time-varying load conditions, is presented. This method is based on the decomposition of the instantaneousreactive power signal, from which wavelet approximation and detail coefficients are extracted. The energy evaluation of known bandwidths permits to define a fault severity factor. This method has been tested through the simulation of an induction motor using a mathematical model based on the winding-function approach. These simulation results are complemented by experimental tests conductedon an induction motor with several faulty rotors that can be interchanged and both simulation and experimental results have shown the effectiveness of the proposed method for broken rotor bars diagnosis in induction motors even under time-varying load conditions.

Induction motor broken rotor bars detection using fuzzy logic: experimental research

This paper proposes a new automated practical method for the diagnosis and detection of broken rotor bars in induction motor. This method uses only one stator current sensor. It is based in spectral analysis of stator current envelope (SCE) obtained via Hilbert transform. According to the fault diagnosis objective, two features are selected from the SCE spectrum: the amplitude of the 2sf harmonic (s is the slip and f the fundamental harmonic) representing the broken bars defect and the DC value. These features will be used as inputs of fuzzy logic block, where the decision about the state of rotor is made. The results obtained are very satisfactory and the diagnostic system is capable to detect the correct number of broken bars.

Induction motors broken rotor bars detection using MCSA and neural network: experimental research

Early detection and diagnosis of incipient faults are desirable to ensure an improved operational effectiveness of induction motors. A novel practical method of detection and classification for broken rotor bars, using motor current signature analysis associated with a neural network technique is developed. The motor-slip is calculated via a new simple and very rigorous formula, based on (f s − f r ) mixed eccentricity harmonic. It can be seen from the experimental study, carried out on hundreds of observation, that the mixed eccentricity harmonic (f s − f r ) has the largest amplitude in its existence range, under different motor loads and conditions (healthy or defective). Since (f s − f r ) is related to the slip and the mechanical rotational frequency, it is obvious that the detection of the broken rotor bars harmonics (1 ± 2ks)f s becomes easy. The amplitude of these harmonics and the slip value (detection and discernment criterion) are used as the neural network inputs. The neural network provides a reliable decision on the machine condition. The experimental results obtained from 1.1 and 3 kW motors prove the effectiveness of the proposed method.

Sensorless Detection of Induction Motor Rotor Faults Using the Clarke Vector Approach

Sensorless Detection of Induction Motor Rotor Faults Using the Clarke Vector ApproachDue to their rugged build, simplicity and cost effective performance, induction motors are used in a vast number of industries, where they play a significant role in responsible operations, where faults and downtimes are either not desirable or even unthinkable. As different faults can affect the performance of the induction motors, among them broken rotor bars, it is important to have a certain condition monitoring or diagnostic system that is guarding the state of the motor. This paper deals with induction motor broken rotor bars detection, using Clarke vector approach.