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.     

A review of induction motors signature analysis as a medium forfaults detection

This paper is intended as a tutorial overview of induction motors signature analysis as a medium for fault detection. The purpose is to introduce in a concise manner the fundamental theory, main results, and practical applications of motor signature analysis for the detection and the localization of abnormal electrical and mechanical conditions that indicate, or may lead to, a failure of induction motors. The paper is focused on the so-called motor current signature analysis which utilizes the results of spectral analysis of the stator current. The paper is purposefully written without “state-of-the-art” terminology for the benefit of practising engineers in facilities today who may not be familiar with signal processing     

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     

Sensorless fault diagnosis of induction motors

Early detection and diagnosis of incipient faults is desirable for online condition assessment, product quality assurance, and improved operational efficiency of induction motors. In this paper, a speed-sensorless fault diagnosis system is developed for induction motors, using recurrent dynamic neural networks and multiresolution or Fourier-based signal processing for transient or quasi-steady-state operation, respectively. In addition to nameplate information required for the initial system setup, the proposed fault diagnosis system uses only motor terminal voltages and currents. The effectiveness of the proposed diagnosis system in detecting the most widely encountered motor electrical and mechanical faults is demonstrated through extensive staged faults. 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.     

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     

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 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     

Vibration analysis for bearing fault detection and classification using an intelligent filter

This paper proposes an intelligent method based on artificial neural networks (ANNs) to detect bearing defects of induction motors. In this method, the vibration signal passes through removing non-bearing fault component (RNFC) filter, designed by neural networks, in order to remove its non-bearing fault components, and then enters the second neural network that uses pattern recognition techniques for fault classification. Four different categories include; healthy, inner race defect, outer race defect, and double holes in outer race are investigated. Compared to the regular fault detection methods that use frequency-domain features, the proposed method is based on analyzing time-domain features which needs less computational effort. Moreover, machine and bearing parameters, and the vibration signal spectrum distribution are not required in this method. It is shown that better results are achieved when the filtered component of the vibration signal is used for fault classification rather than common methods that use directly vibration signal. Experimental results on three-phase induction motor verify the ability of the proposed method in fault diagnosis despite low quality (noisy) of measured vibration signal.     

基于MEMS加速度传感器的轴承故障检测

提出了一种通过利用低成本的MEMS加速度传感器进行振动分析,实现检测电动机深沟球轴承多重故障的简易方法。首先分析了轴承多故障特征频率,然后通过快速傅里叶变换算法对轴承出现故障的电动机振动频率进行了分析,从振动频谱中提取故障频率来诊断轴承多重故障的存在。同时,基频分量周围的边带频率分量表明由于故障轴承存在空气间隙。在空载、单相以及失衡电压条件下通过实验对提出的方法进行了研究,结果显示提取出的故障频率与理论值两者十分接近,表明提出的方法能够有效检测并识别出感应电动机的多故障特征。     

基于阻抗的匝间故障早期诊断系统设计与实现

提出了一种使用输入阻抗来诊断无刷直流电动机（brushless dc motors,BLDC）定子绕组匝间故障（inter-turn fault,ITF）的算法,并设计了相应的故障检测系统进行了实现。该系统的优势在于具有早期检测能力以及适用于各种速度范围检测。提出的故障检测技术通过使用输入电压和输入电流来计算输入阻抗,并将其与数据库中的数值比较。相比传统的方法,由于不需要快速傅里叶变换（FFT）,因此提出的算法更加迅速且简单。实验测试结果表明提出的检测方法在各种转速条件下均具有较高的精确度。     

Comparative investigation of diagnostic media for induction motors:a case of rotor cage faults

Results of a comparative experimental investigation of various media for noninvasive diagnosis of rotor faults in induction motors are presented. Stator voltages and currents in an induction motor were measured, recorded, and employed for computation of the partial and total input powers and of the estimated torque. Waveforms of the current, partial powers p_AB and p_CB, total power, and estimated torque were subsequently analyzed using the fast Fourier transform. Several rotor cage faults of increasing severity were studied with various load levels. The partial input power p_CB was observed to exhibit the highest sensitivity to rotor faults. This medium is also the most reliable, as it includes a multiplicity of fault-induced spectral components     

A comparison of external and internal methods of signal spectral analysis for broken rotor bars detection in induction motors

Like all mechanical devices, motors are subject to failures, which can sometimes lead to the shutting down of an entire industrial process. This paper looks at failure predictions in three-phase line-operated induction machines through spectral analysis or electric and electromagnetic signals. Fault characteristics frequencies generated in the estimated and the measured signal spectrum, as a result of mechanical abnormalities such as broken rotor bars, are analyzed. Spectral analyses of simple stator current, of the current's Park vector modulus, and or total and partial instantaneous electric powers are considered as external diagnosis. Internal methods of diagnosis are usually based on a mathematical model of the motor. This requires knowledge of the motor's electrical parameters, which are affected by a number of physical phenomena such as temperature variations, skin effects, core losses, and saturation. As internal diagnosis, we examine different approaches to the spectral analysis of electromagnetic torque computed by stator and rotor flux estimation. To this end, the open loop method, the Luenberger observer and the Kalman filter are employed. Finally, experimental results enable us to draw up a table of comparison of internal and external methods in the detection of rotor imperfections, using two criteria under different load levels.     

牵引电机的软硬件设计原理

机车牵引电机是机车运行重要的核心设备,同时又是保证行车安全和控制机车的关键设备。实现对机车牵引电机的实时监测,可以减少因牵引电机引起的故障率,提高铁路运输的安全和效率,为实现机务设备的状态控制打下良好基础。文中提出了机车牵引电机故障诊断系统的总体设计方案。通过理论研究与实践验证,采用单路直流电压隔离传感器完成了对6路牵...     

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     

Analysis and Application of Particular Current Signatures (Symptoms) for Cage Monitoring in Nonsinusoidally Fed Motors With High Rejection to Drive Load, Inertia, and Frequency Variations

In this paper, some original and effective fault indicators for broken-bar detection in power squirrel-cage induction motors are presented. A motor phase-current signature analysis can be performed by evaluating the typical ratios $I_{(7 - 2s)f}/I_{5f}$ and $I_{(5 + 2s)f}/I_{7f}$, $I_{(13 - 2s)f}/I_{11f}$ and $I_{(11 + 2s)f}/I_{13f}$, etc., which appear in the phase-current spectrum of faulted motors fed by nonsinusoidal voltage sources. The main advantages of the new indicators are the following: 1) accentuate insensitivity to disturbs such as load torque, drive inertia, and frequency variations; 2) low dependence with respect to machine parameters (except the pole number); and 3) linear dependence on fault gravity. They can be directly applied on motors fed by open-loop low-switching frequency gate turn-off/thyristor converters. Railway traction drives are possible targets. Application to mains-fed motors can be tried too, if suitable harmonics are present in the plant supply. A detailed analytical formulation for fault indicators is furnished, based on the multiphase symmetrical component theory; theoretical results have been supported by experimental work, performed by using a motor with an appositely prepared cage, and successively, method validation was achieved on three other industrial motors.      

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.     

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     

A neural network approach to real-time condition monitoring ofinduction motors

A neural network-based incipient fault detector for small and medium-size induction motors is developed. The detector avoids the problems associated with traditional incipient fault detection schemes by employing more readily available information such as rotor speed and stator current. The neural network design is evaluated in real time in the laboratory on a 3/4 hp permanent magnet induction motor. The results of this evaluation indicate that the neural-network-based incipient fault detector provides a satisfactory level of accuracy, greater than 95%, which is suitable for real-world applications     

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.