Induction motor fault diagnosis based on neuropredictors andwavelet signal processing

Early detection and diagnosis of incipient faults is desirable for online condition assessment, product quality assurance and improved operational efficiency of induction motors running off power supply mains. In this paper, a model-based fault diagnosis system is developed for induction motors, using recurrent dynamic neural networks for transient response prediction and multi-resolution signal processing for nonstationary signal feature extraction. In addition to nameplate information required for the initial setup, the proposed diagnosis system uses measured motor terminal currents and voltages, and motor speed. The effectiveness of the diagnosis system is demonstrated through staged motor faults of electrical and mechanical origin. The developed system is scalable to different power ratings and it has been successfully demonstrated with data from 2.2-, 373-, and 597-kW induction motors. Incremental tuning is used to adapt the diagnosis system during commissioning on a new motor, significantly reducing the system development time     

Online Diagnosis of Induction Motors Using MCSA

In this paper, an online induction motor diagnosis system using motor current signature analysis (MCSA) with advanced signal-and-data-processing algorithms is proposed. MCSA is a method for motor diagnosis with stator-current signals. The proposed system diagnoses induction motors having four types of faults such as breakage of rotor bars and end rings, short-circuit of stator windings, bearing cracks, and air-gap eccentricity. Although MCSA is one of the most powerful online methods for diagnosing motor faults, it has some shortcomings, which degrade performance and accuracy of a motor-diagnosis system. Therefore, advanced signal-and-data-processing algorithms are proposed. They are composed of an optimal-slip-estimation algorithm, a proper-sample-selection algorithm, and a frequency auto search algorithm for achieving MCSA efficiently. The proposed system is able to ascertain four kinds of motor faults and diagnose the fault status of an induction motor. Experimental results obtained on 3.7-kW and 30-kW three-phase squirrel-cage induction motors and voltage-source inverters with a vector-control technique are discussed     

Induction Motor Bearing Failure Detection and Diagnosis: Park and Concordia Transform Approaches Comparative Study

This paper deals with the problem of bearing failure detection and diagnosis in induction motors. Indeed, bearing deterioration is now the main cause of induction motor rotor failures. In this context, two fault detection and diagnosis techniques, namely the Park transform approach and the Concordia transform, are briefly presented and compared. Experimental tests, on a 0.75 kW two-pole induction motor with artificial bearing damage, outline the main features of the aforementioned approaches for small- and medium-size induction motors bearing failure detection and/or diagnosis.     

Intelligent fault diagnosis system of induction motor based on transient current signal

This paper presents a method for induction motor fault diagnosis based on transient signal using component analysis and support vector machine (SVM). The start-up transient current signal is selected as features source for fault diagnosis. Preprocessing of transient current signal is performed using smoothing and discrete wavelet transform to highlight the salient features of faults. In this work, independent component analysis, principal component analysis and their kernel are performed to reduce the dimension of features and to extract the optimal features for classification process. In this work, the influence of the number of component analysis towards diagnosis accuracy is also studied. SVM multi-class classification using one against all strategy is selected for classification tool due to good generalization properties. Performance of the system is validated by applying the system to induction motor faults diagnosis. According to the result, the system has potential to serve an intelligent fault diagnosis system in real application.     

Neural speed filtering for induction motors with anomalies and incipient faults

Effective sensorless speed estimation is desirable for both on-line condition monitoring and assessment, and for efficiency calculation of induction motors running off the power supply mains. In this paper, a sensorless neural adaptive speed filter is developed for induction motors operating under normal and anomalous conditions, such as supply imbalance, as well as incipient faults, such as electrical, electromechanical, and mechanical faults. The filter is demonstrated by comparisons with experimental speed measurements and spectral speed estimates. In addition to nameplate information required for the initial setup, the proposed neural speed filter uses only measured motor terminal currents and voltages. Initial training of the speed filter is accomplished off-line, using rotor slot harmonic-based speed estimates. The developed speed filter is scalable and it has been used for speed estimation of induction motors with varying power ratings. Incremental tuning is used to further improve filter performance and reduce filter development time significantly.     

Induction motors' faults detection and localization using statorcurrent advanced signal processing techniques

The knowledge about fault mode behavior of an induction motor drive system is extremely important from the standpoint of improved system design, protection, and fault-tolerant control. This paper addresses the application of motor current spectral analysis for the detection and localization of abnormal electrical and mechanical conditions that indicate, or may lead to, a failure of induction motors. Intensive research effort has been for some time focused on the motor current signature analysis. This technique utilizes the results of spectral analysis of the stator current. Reliable interpretation of the spectra is difficult since distortions of the current waveform caused by the abnormalities in the induction motor are usually minute. This paper takes the initial step to investigate the efficiency of current monitoring for diagnostic purposes. The effects of stator current spectrum are described and the related frequencies determined. In the present investigation, the frequency signature of some asymmetrical motor faults are well identified using advanced signal processing techniques, such as high-resolution spectral analysis. This technique leads to a better interpretation of the motor current spectra. In fact, experimental results clearly illustrate that stator current high-resolution spectral analysis is very sensitive to induction motor faults modifying main spectral components, such as voltage unbalance and single-phasing effects     

Using a neural/fuzzy system to extract heuristic knowledge ofincipient faults in induction motors. Part I-Methodology

The use of electric motors in industry is extensive. These motors are exposed to a wide variety of environments and conditions which age the motor and make it subject to incipient faults. These incipient faults, if left undetected, contribute to the degradation and eventual failure of the motors. Artificial neural networks have been proposed and have demonstrated the capability of solving the motor monitoring and fault detection problem using an inexpensive, reliable, and noninvasive procedure. However, the major drawback of conventional artificial neural network fault detection is the inherent black box approach that can provide the correct solution, but does not provide heuristic interpretation of the solution. Engineers prefer accurate fault detection as well as the heuristic knowledge behind the fault detection process. Fuzzy logic is a technology that can easily provide heuristic reasoning while being difficult to provide exact solutions. The authors introduce the methodology behind a novel hybrid neural/fuzzy system which merges the neural network and fuzzy logic technologies to solve fault detection problems. They also discuss a training procedure for this neural/fuzzy fault detection system. This procedure is used to determine the correct solutions while providing qualitative, heuristic knowledge about the solutions     

FMM神经网络结合CART的感应电动机故障诊断方法

针对感应电动机存在多种故障问题,提出一种融合模糊极小-极大（FMM）神经网络和分类回归树（CART）的电机故障诊断方法（FMM-CART）,对转子断条、定子绕组和电压失衡三种常见电机故障进行诊断。通过采集电机三相的电流信号,并进行功率谱分析,提取特定谐波信号作为FMM-CART模型的输入特征。训练过的FMM神经网络根据输入特征计算置信因子,CART根据置信因子构建决策树,最终输出诊断结果。实验结果表明,FMM-CART能有效的诊断各种电机故障,且具有较少的检测时间和较低的网络复杂度。     

Fuzzy inference systems implemented on neural architectures formotor fault detection and diagnosis

Motor fault detection and diagnosis involves processing a large amount of information of the motor system. With the combined synergy of fuzzy logic and neural networks, a better understanding of the heuristics underlying the motor fault detection/diagnosis process and successful fault detection/diagnosis schemes can be achieved. This paper presents two neural fuzzy (NN/FZ) inference systems, namely, fuzzy adaptive learning control/decision network (FALCON) and adaptive network based fuzzy inference system (ANFIS), with applications to induction motor fault detection/diagnosis problems. The general specifications of the NN/FZ systems are discussed. In addition, the fault detection/diagnosis structures are analyzed and compared with regard to their learning algorithms, initial knowledge requirements, extracted knowledge types, domain partitioning, rule structuring and modifications. Simulated experimental results are presented in terms of motor fault detection accuracy and knowledge extraction feasibility. Results suggest new and promising research areas for using NN/FZ inference systems for incipient fault detection and diagnosis in induction motors     

Different indexes for eccentricity faults diagnosis in three-phase squirrel-cage induction motors: A review

In this paper, a short introduction about different types of eccentricity faults in three-phase squirrel-cage induction motors is presented and their effects and consequences on the health and behavior of the motor are reviewed. Two fault diagnosis techniques are discussed, namely: invasive and non-invasive techniques. The relative advantages of the non-invasive techniques are also discussed. Various indices used in the non-invasive techniques are then briefly introduced and some outlines for continuing the research on every index are given. The advantages and disadvantages of the indices under different operating conditions and for any type and eccentricity degree are then discussed together with some effective parameters of the motor. The results of this review are useful for manufacturers of fault diagnosis systems in selecting proper indices for existing conditions and also for researchers in determining further research areas.     

Hierarchical motor diagnosis utilizing structural knowledge and aself-learning neuro-fuzzy scheme

A fault diagnosis system contains a classification system that can distinguish between different faults based on observed symptoms of the process under investigation. Since the fault symptom relationships are not always known beforehand, a system is required which can be learned from experimental or simulated data. A fuzzy-logic-based diagnosis is advantageous. It allows an easy incorporation of a priori known rules and enables the user to understand the inference of the system. In this paper, a new diagnosis scheme is presented and applied to a DC motor. The approach is based on the combination of structural a priori knowledge and measured data in order to create a hierarchical diagnosis system that can be adapted to different motors. Advantages of the system are its transparency and an increased robustness over traditional classification schemes     

Using a neural/fuzzy system to extract heuristic knowledge ofincipient faults in induction motors: Part II-Application

The use of electric motors in industry is extensive. These motors are exposed to a wide variety of environments and conditions which age the motor and make it subject to incipient faults. These incipient faults, if left undetected, contribute to the degradation and eventual failure of the motors. This paper uses a hybrid neural/fuzzy fault detector to solve the motor fault detection problem. As an illustration, the neural/fuzzy fault detector is used to monitor the condition of a motor bearing and stator winding insulation. The initialization and training of this fault detector is in accordance with the procedures outlined in Part I of this paper. Once the neural/fuzzy fault detector is trained, the detector not only can provide accurate fault detector performance, but can also provide the heuristic reasoning behind the fault detection process and the actual motor fault conditions. With better understanding of the heuristics through the use of fuzzy rules and fuzzy membership functions, a better understanding of the fault detection process of the system is available, thus better motor protection systems can be designed     

Induction Motor Fault Diagnosis Based on Transfer Principal Component Analysis

This paper presents a transfer learning-based approach for induction motor fault diagnosis, where the Transfer principal component analysis (TPCA) is proposed to improve diagnostic performance of the induction motors under various working conditions. TPCA is developed to minimize the distribution difference between training and testing data by mapping cross-domain data into a shared latent space in which domain difference can be reduced. The trained model can achieve a good performance in testing data by using the learned features consisting of common latent principal components. Experimental results show that the proposed approach outperforms traditional machine learning techniques and can diagnose induction motor fault under various working conditions effectively.     

Induction Machine Condition Monitoring Using Neural Network Modeling

Condition monitoring is desirable for increasing machinery availability, reducing consequential damage, and improving operational efficiency. Model-based methods are efficient monitoring systems for providing warning and predicting certain faults at early stages. However, the conventional methods must work with explicit motor models, and cannot be applied effectively for vibration signal diagnosis due to their nonadaptation and the random nature of vibration signal. In this paper, an analytical redundancy method using neural network modeling of the induction motor in vibration spectra is proposed for machine fault detection and diagnosis. The short-time Fourier transform is used to process the quasi-steady vibration signals to continuous spectra for the neural network model training. The faults are detected from changes in the expectation of vibration spectra modeling error. The effectiveness of the proposed method is demonstrated through experimental results, and it is shown that a robust and automatic induction machine condition monitoring system has been produced     

A generic neurofuzzy model-based approach for detecting faults in induction motors

Many fault detection and diagnosis schemes are based on the concept of comparing the plant output with a model in order to generate residues. A fault is deemed to have occurred if the residue exceeds a predetermined threshold. Unfortunately, the practical usefulness of model-based fault detection schemes is limited because of the difficulty in acquiring sufficiently rich experimental data to identify an accurate model of the system characteristics. This paper aims at developing a generic neurofuzzy model-based strategy for detecting broken rotor bars, which is one of the most common type of faults that may occur in a squirrel-cage induction motor. A neurofuzzy model that captures the generic characteristics of a class of asynchronous motor is the key component of the proposed approach. It is identified using data generated by a simulation model that is constructed using information on the name plate of the motor. Customization for individual motors is then carried out by selecting the threshold for fault detection via an empirical steady-state torque-speed curve. Since data obtained from a practical motor are used to select the threshold and not to build a complete model, the objective of reducing the amount of experimental input-output data required to design a model-based fault detector may be realized. Experimental results are presented to demonstrate the viability of the proposed fault detection scheme.     

Detecting motor bearing faults

Three-phase induction motors are the workhorses of industry because of their widespread use. They are used extensively for heating, cooling, refrigeration, pumping, conveyors, and similar applications. They offer users simple, rugged construction, easy maintenance, and cost-effective pricing. These factors have promoted standardization and development of a manufacturing infrastructure that has led to a vast installed base of motors; more than 90% of all motors used in industry worldwide are ac induction motors. Causes of motor failures are bearing faults, insulation faults, and rotor faults. Early detection of bearing faults allows replacement of the bearings, rather than replacement of the motor. The same type of bearing defects that plague such larger machines as 100 hp are mirrored in lower hp machines which has the same type of bearings. Even though the replacement of defective bearings is the cheapest fix among the three causes of failure, it is the most difficult one to detect. Motors that are in continuous use cannot be stopped for analysis. We have developed a circuit monitor for these motors. Incipient bearing failures are detectable by the presence of characteristic machine vibration frequencies associated with the various modes of bearing failure. We will show that circuit monitors that we developed can detect these frequencies using wavelet packet decomposition and a radial basis neural network. This device monitors an induction motor's current and defines a bearing failure.     

Adaptive Neural Fuzzy Inference System for the Detection of Inter-Turn Insulation and Bearing Wear Faults in Induction Motor

The positive features of neural networks and fuzzy logic are combined together for the detection of stator inter-turn insulation and bearing wear faults in single-phase induction motor. The adaptive neural fuzzy inference systems (ANFISs) are developed for the detection of these two faults. These faults are created experimentally on a single-phase induction motor in the laboratory. The experimental data is generated for the five measurable parameters, viz, motor intakes current, speed, winding temperature, bearing temperature, and the noise of the machine. Earlier, the ANFIS fault detectors are trained for the two input parameters, i.e., speed and current, and the performance is tested. Later, the three remaining parameters are added and the five input ANFIS fault detector is trained and tested. It observed from the simulation results that the five input parameter system predicts more accurate results     

Neural-network-based motor rolling bearing fault diagnosis

Motor systems are very important in modern society. They convert almost 60% of the electricity produced in the US into other forms of energy to provide power to other equipment. In the performance of all motor systems, bearings play an important role. Many problems arising in motor operations are linked to bearing faults. In many cases, the accuracy of the instruments and devices used to monitor and control the motor system is highly dependent on the dynamic performance of the motor bearings. Thus, fault diagnosis of a motor system is inseparably related to the diagnosis of the bearing assembly. In this paper, bearing vibration frequency features are discussed for motor bearing fault diagnosis. This paper then presents an approach for motor rolling bearing fault diagnosis using neural networks and time/frequency-domain bearing vibration analysis. Vibration simulation is used to assist in the design of various motor rolling bearing fault diagnosis strategies. Both simulation and real-world testing results obtained indicate that neural networks can be effective agents in the diagnosis of various motor bearing faults through the measurement and interpretation of motor bearing vibration signatures     

Differential Diagnosis Based on Multivariable Monitoring to Assess Induction Machine Rotor Conditions

Multivariable supervision systems for online monitoring of induction motors allow large versatility and diagnosis robustness. As regards rotor faults, the diagnostic procedure based on sideband current components may fail due to the presence of interbar currents that reduce the degree of rotor asymmetry and, thus, the amplitude of these spectral components. On the other hand, the interbar currents produce core vibrations in the axial direction; these vibrations can be detected using a suitable vibration sensor. In this paper, a differential fault analysis based on traditional motor current signature analysis (MCSA) and on radial and axial vibration monitoring is proposed to discern cases in which the presence of interbar currents decreases the sensitivity of MCSA. The features of stator currents and of radial and axial core vibration signals are investigated in order to increase the reliability of the diagnostic system. Moreover, to explore the possibility of obtaining further information, stray flux signals are taken into account.      

Application of model-based fault detection to a brushless DC motor

In comparison to classical DC motors, brushless DC motors are very reliable, Nevertheless, they can also fail, caused by, e.g., overheating or mechanical wear. This paper proposes a parameter estimation technique for fault detection on this type of motor. Simply by measuring the motor's input and output signals, its parameters can be estimated. This method is based on a mathematical model of the process. In the presented work, a square-wave motor is considered. An appropriate model is derived. To be able to implement the method also on low-cost microcontroller-based control units, only the power inverter supply voltage, DC current, and the motor's angular velocity have to be measured. The parameter estimation technique provides information about the electrical resistance and the back-EMF constant as well as about the mechanical parameters. Comparing the nominal with the computed parameters, faults can be detected. The approach might be applied to both end-of-line and online fault detection. Results for simulated data demonstrate the capabilities of the proposed procedure. Finally, a real-world application-an actuation system with a brushless DC motor mounted to a gearbox-is given