Stator Winding Fault Diagnosis Research Articles

Microcontroller-Based Embedded System for the Diagnosis of Stator Winding Faults and Unbalanced Supply Voltage of the Induction Motors

Induction motors (IMs) are one of the most widely used motor types in the industry due to their low cost, high reliability, and efficiency. Nevertheless, like other types of AC motors, they are prone to various faults. In this article, a low-cost embedded system based on a microcontroller with the ARM Cortex-M4 core is proposed for the extraction of stator winding faults (interturn short circuits) and an unbalanced supply voltage of the induction motor drive. The voltage induced in the measurement coil by the axial flux was used as a source of diagnostic information. The process of signal measurement, acquisition, and processing using a cost-optimized embedded system (NUCLEO-L476RG), with the potential for industrial deployment, is described in detail. In addition, the analysis of the possibility of distinguishing between interturn short circuits and unbalanced supply voltage was carried out. The effect of motor operating conditions and fault severity on the symptom extraction process was also studied. The results of the experimental research conducted on a 1.5 kW IM confirmed the effectiveness of the developed embedded system in the extraction of these types of faults.

Condition Monitoring and Fault Diagnosis of Permanent Magnet Synchronous Motor Stator Winding Using the Continuous Wavelet Transform and Machine Learning

Abstract Applying the condition monitoring technology to industrial processes can help detect faults in time, minimise their impact and reduce the cost of unplanned downtime. Since the introduction of the Industry 4.0 paradigm, many companies have been investing in the development of such technology for drive systems. Permanent magnet synchronous motors (PMSMs) have recently been used in many industries. Therefore, the issues of condition monitoring of PMSM drives are important. This study proposes and compares diagnostic schemes based on the stator phase currents (SPCSCs) signal for condition monitoring and fault diagnosis of PMSM stator winding faults. The continuous wavelet transform (CWT) is used for the extraction of the symptoms of interturn short circuits in PMSM stator winding. Machine learning algorithms are applied to automate the detection and classification of the faults. The concept for an original and intelligent PMSM stator winding condition monitoring system is proposed.

Diagnosis of Stator Winding and Permanent Magnet Faults of PMSM Drive Using Shallow Neural Networks

This paper presents the application of shallow neural networks (SNNs): multi-layer perceptron (MLP) and self-organizing Kohonen maps (SOMs) to the early detection and classification of the stator and rotor faults in permanent magnet synchronous motors (PMSMs). The neural networks were trained based on the vector coming from measurements on a real object. The elements of the input vector of SNNs constituted the selected amplitudes of the diagnostic signal spectrum. The stator current and axial flux were used as diagnostic signals. The test object was a 2.5 kW PMSM motor supplied by a frequency converter operating in a closed-loop control structure. The experimental verification of the proposed diagnostic system was carried out for variable load conditions and values of the supply voltage frequency. The obtained results were compared with an approach based on a deep neural network (DNN). The research presented in the article confirm the possibility of detection and assessing the individual damage of stator winding and permanent magnets as well as the simultaneous faults of the PMSM stator and rotor using SNNs with simple signal preprocessing.

Short-Circuit Fault Diagnosis on Induction Motors through Electric Current Phasor Analysis and Fuzzy Logic

Online monitoring of induction motors has increased significantly in recent years because these devices are essential components of any industrial process. Incipient fault detection in induction motors avoids interruptions in manufacturing processes and facilitates maintenance tasks to reduce induction motor timeout. Therefore, the proposal of novel approaches to assist in the detection and classification of induction motor faults is in order. In this work, a reliable and noninvasive novel technique that does not require computational demanding operations, since it just performs arithmetic calculations, is introduced for detecting and locating short-circuit faults in the stator windings of an induction motor. This method relies on phasor analysis and the RMS values of line currents, followed by a small set of simple if-then rules to perform the diagnosis and identification of stator winding faults. Obtained results from different experimental tests on a rewound induction motor stator to induce short-circuit faults demonstrate that the proposed approach is capable of identifying and locating incipient and advanced deficiencies in the windings’ insulation with high effectiveness.

Machine Learning-Based Stator Current Data-Driven PMSM Stator Winding Fault Diagnosis

Permanent magnet synchronous motors (PMSMs) have become one of the most important components of modern drive systems. Therefore, fault diagnosis and condition monitoring of these machines have been the subject of many studies in recent years. This article presents an intelligent stator current-data driven PMSM stator winding fault detection and classification method. Short-time Fourier transform is applied in the process of fault feature extraction from the stator phase current symmetrical components signal. Automation of the fault detection and classification process is carried out with the use of three selected machine learning algorithms: support vector machine, naïve Bayes classifier and multilayer perceptron. The concept and online verification of the original intelligent fault diagnosis system with the potential of a real industrial deployment are demonstrated. Experimental results are presented to evaluate the effectiveness of the proposed methodology.

Diagnosis and Countermeasures of Stator Winding Faults of Hydrogenerators

Diagnosis and Countermeasures of Stator Winding Faults of Hydrogenerators

NI CompactRIO-based methodology for online detection of stator winding inter-turn insulation faults in 3-phase induction motors

An NI-CompactRIO-based online stator winding fault diagnosis technique has been proposed for discrimination and severity detection of partial degradation and complete breakdown of the insulation in stator winding turns of 3-phase induction motors. Principal Component Analysis (PCA) method was employed on 3-phase current signals to extract significant features. The variances of the first two principal components (PC1 & PC2) are found to be key features for fault detection. Inter-turn complete insulation breakdown has been discriminated from inter-turn partial insulation failure by analyzing the range of variance of PC2. Additionally, severity of both the faults is detected by noting the trend in variance of PC1. Faults involving a minimum of 0.27% of total phase winding turns can be successfully detected online within a few milliseconds with acceptable prediction accuracy by employing k-Nearest Neighbors classifier.

Stator Winding Fault Diagnosis Method Based on Dc Side Current of Inverter

This paper analyzes the influence of the fundamental negative sequence component of the grid voltage on the output voltage of the variable frequency power supply, and points out that the fundamental negative sequence component of the grid voltage will not generate the fundamental negative sequence current component in the stator current of the induction motor, so when the stator winding fault is diagnosed, the influence of the negative sequence voltage of the grid does not need to be compensated. Based on the characteristic that the fundamental negative sequence current component in the stator current is converted into two times of the inverter output frequency component in the DC side current of the inverter, a stator fault diagnosis method based on the DC side current of the inverter is proposed. The method of connecting the short-circuit resistance between the two phases of the motor is used to simulate the nonmetallic short-circuit fault of the stator coil. The experimental results show that this method does not need to compensate the negative sequence voltage, and only needs to collect one current signal, and the algorithm is relatively simple, which is a simple and effective method.

Stator winding fault diagnosis of induction motor operating under the field-oriented control with convolutional neural networks

Stator winding fault diagnosis of induction motor operating under the field-oriented control with convolutional neural networks

Performance of the Stator Winding Fault Diagnosis in Sensorless Induction Motor Drive

This paper deals with the diagnosis of stator winding inter-turn faults for an induction motor drive operating without a speed sensor in a speed-sensorless mode. The rotor direct field oriented control structure (DFOC) was applied, its reference current and voltage component values were analyzed, and their selected harmonics were applied as effective fault indicators. To ensure robust speed estimation, a sliding mode model reference adaptive system (SM-MRAS) estimator was selected. The influence of load torque, reference speed, proportional-integral (PI) controller parameters, and short-circuit current on fault diagnosis and speed estimation performance was verified. Experimental test results obtained for a 3 kW induction motor drive are included.

Early Diagnosis of Induction Machine Stator Winding Faults by Discrete Wavelet Transform

AbstractElectrical machines are useful in nuclear power plants, military applications, domestic appliances and industrial utilities. The relevant literature indicates that the induction machine takes about ninety percent of all electrical machine globally used in the industry. The risk of the failure of this machine can be avoided if the proper diagnostic scheme is designed and implemented to detect failure/impending faults at an incipient stage. This paper describes Discrete Wavelet Transform (DWT) based diagnosis technique that analyses stator currents of induction machine under healthy and faulty conditions. This enables the extraction of harmonic components caused by each signal for further analysis. On one hand, the maximum energy for each signal gives information about the time a certain fault occurs in the machine and the time it starts deviating from the normal (healthy) state. On the other hand, a Fault Index (FI) is generated for each situation in order to classify the state of the machine into normal, medium or high. The colours; green, yellow and red are used to represent the normal, medium and high states respectively. Should the faults at medium state are not detected on time, it may lead a more serious fault (high state). Thus, this technique is robust to identify a fault of an induction machine at the incipient state with a very minimal time.

Stator Winding Fault Diagnosis in Permanent Magnet Synchronous Generators Based on Short-Circuited Turns Identification Using Extended Kalman Filter

<p class="Abstract">This paper deals with an Extended Kalman Filter based fault detection for inter-turn short-circuit in Permanent Magnet Synchronous Generators. Inter-turn short-circuits are among the most critical faults in the PMSG. Indeed, due to permanent magnets, the short-circuit current is maintained as long as the machine is rotating. Thus, a specific faulty model in d-q frame is developed to estimate the number of short-circuited turns which are used to build a fault indicator. Simulation results demonstrate the sensitivity and the robustness of the proposed fault indicator against various operation points on an electrical network even for a few number of short-circuited turns.</p>

A Vibration-Based Approach for Stator Winding Fault Diagnosis of Induction Motors: Application of Envelope Analysis


 
 
 Induction motors are usually considered as one of the key components in various applications. To maintain the availability of induction motors, it calls for a reliable condition monitoring and prognostics strategy. Among the common induction motor faults, stator winding faults are usually diagnosed with current and voltage signals. However, if the same performance can be achieved, the use of vibration signal is favorable because the winding fault diagnostic method can be integrated with bearing fault diagnostic method which has been successfully proven with vibration signal. Existing work concerning vibration for winding faults often takes it either as auxiliary to magnetic flux, or is not able to detect the winding faults unless severity is already quite significant. This paper proposes a winding fault diagnostic method based on vibration signals measured on the mechanical structure of an induction motor. In order to identify the signature of faults, time synchronous averaging was firstly applied on the raw vibration signals to remove discrete frequency components originating from the dynamics of the shaft and/or gears, and the spectral kurtosis filtering was subsequently applied on the residual signal to emphasize the impulsiveness. For the purpose of enhancing the residual signal in practice, a demodulation technique was implemented with the help of kurtogram. A series of experiments have been conducted on a three-phase induction motor test bed, where stator inter-turn faults can be easily simulated at different loads, speeds and severity levels. The experimental results show that the proposed method was able to detect inter-turn faults in the induction motor, even when the fault is incipient.
 
 

Improving Stator Winding Fault Diagnosis in Induction Motor using Dempster-Shafer Theory

Due to the important role of induction motors in industry, reliability in fault detection of these motors is of great importance. In this paper, a method is proposed for increasing the reliability of stator winding fault diagnosis using Dempster-Shafer theory. Out of the measured current and vibration signals, some features are extracted and selected according to the method, and a neural network based on DempsterShafer theory is trained by the selected features. The proposed method is then tested for various fault. Finally it is shown how data fusion can increase the accuracy of fault diagnosis. The system performance is also evaluated on a laboratory motor showing satisfactory results.

Application of artificial intelligence to stator winding fault diagnosis in Permanent Magnet Synchronous Machines

This paper proposes a new methodology to solve the problem of fault diagnosis in electrical machines. The fault diagnosis method presented in this paper is, first, able to provide information about the location of a short-circuit fault in a stator winding. Secondly, the method enables the estimation of fault severity by specifying the number of short-circuited turns during a fault. A cluster of Focused Time-Lagged neural networks are combined with the Particle Swarm Optimization algorithm for proposed fault diagnosis method. This method is applied to the stator windings of a Permanent Magnet Synchronous Machine. Each neural network, in the cluster, is trained to correlate the zero-current component to the number of short-circuited turns in the stator windings. The zero-current component, different from the zero-sequence current, are obtained by summing the instantaneous values of current on all phases of the stator winding during the diagnosis procedure. The neural networks are trained offline with the Extended Kalman Filter method using fault data from both computer simulations and an actual Permanent Magnet Synchronous Machine. The use of the Extended Kalman Filter method, for training, ensures that the neural network cluster used can be re-trained online to make the fault diagnosis system adapt to changing operational conditions. Results from both computer simulation and actual machine data are presented to show the performance of the neural network cluster and the Particle Swarm Optimization algorithm.

Diagnosis of Stator Turn-to-Turn Fault and Stator Voltage Unbalance Fault Using ANFIS

An induction machine is a highly non-linear system that poses a great challenge because of its fault diagnosis due to the processing of large and complex data. The fault in an induction machine can lead to excessive downtimes that can lead to huge losses in terms of maintenance and production. This paper discusses the diagnosis of stator winding faults, which is one of the common faults in an induction machine. Several diagnostics techniques have been presented in the literature. Fault detection using traditional analytical methods are not always possible as this requires prior knowledge of the exact motor model. The motor models are also susceptible to inaccuracy due to parameter variations. This paper presents Adaptive Neuro-fuzzy Inference system (ANFIS) based fault diagnosis of induction motors. The distinction between the stator winding fault and supply unbalance is addressed in this paper. Experimental data is collected by shorting the turns of a health motor as well as creating unbalance in the stator voltage. The data is processed and fed to an ANFIS classifier that accurately identifies the faulted condition and unbalanced supply voltage conditions. The ANFIS provides almost 99% accurate and computationally efficient output in diagnosing the faults and unbalance conditions. DOI: http://dx.doi.org/10.11591/ijece.v3i1.1854

High-Frequency Carrier-Signal Voltage Selection for Stator Winding Fault Diagnosis in Inverter-Fed AC Machines

The diagnosis of stator winding faults in inverter-fed AC machines using an injected high-frequency carrier-signal voltage is analyzed in this paper. Measurement of the resulting carrier signals (either the negative-sequence carrier-signal current or the zero-sequence components) is used to detect turn faults at an incipient stage. The carrier frequency and magnitude are shown to have significant impact on the performance of the method, with the criteria for their selection being presented. The proposed technique shows low sensitivity to the working condition of the machine, i.e., torque level, flux levels, and fundamental excitation frequency.

Diagnosis of stator faults in induction motor based on zero sequence voltage after switch-off

To improve the accuracy of the stator winding fault diagnosis in induction motor, a new diagnostic method based on the Hilbert-Huang transform (HHT) was proposed. The ratio of fundamental zero sequence voltage to positive sequence voltage after switch-off was selected as the stator fault characteristic, which could effectively avoid the influence of the supply unbalance and the load fluctuation, and directly represent the asymmetry in the stator. Using the empirical mode decomposition (EMD) based on HHT, the zero sequence voltage after switch-off was decomposed and the fundamental component was extracted. Then, the fault characteristic can be acquired. Experimental results on a 4-kW induction motor demonstrate the feasibility and effectiveness of this method.

DSP Implementation of the Multiple Reference Frames Theory for the Diagnosis of Stator Faults in a DTC Induction Motor Drive

This paper deals with the use of a new diagnostic technique based on the multiple reference frames theory for the diagnosis of stator winding faults in a direct-torque-controlled (DTC) induction motor drive. The theoretical aspects underlying the use of this diagnostic technique are presented but a major emphasis is given to the integration of the diagnostic system into the digital-signal-processor (DSP) board containing the control algorithm. Taking advantage of the sensors already built in the drive for control purposes, it is possible to implement this diagnostic system at no additional cost, thus giving a surplus value to the drive itself. Experimental results show the effectiveness of the proposed technique to diagnose stator faults and demonstrate the possibility of its integration in the DSP board.

Online stator winding fault diagnosis in inverter-fed ac machines using high-frequency signal injection

The diagnosis of stator winding faults in inverter-fed AC machines using an injected high-frequency carrier signal is presented and analyzed in this paper. Measurement of the resulting high-frequency negative-sequence current (or alternatively of the negative-sequence impedance) is used to detect turn faults at an incipient stage. Though sharing the same physical principles of similar techniques applied to line-connected machines, the use of a high-frequency signal is shown to present important advantages, such as providing the same performance almost independently of the fundamental excitation frequency, and drastically reducing the sensitivity to the working condition of the machine, i.e., torque and flux levels.