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     

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     

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。     

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。     

An Effective Neural Approach for the Automatic Location of Stator Interturn Faults in Induction Motor

This paper presents a neural approach to detect and locate automatically an interturn short-circuit fault in the stator windings of the induction machine. The fault detection and location are achieved by a feedforward multilayer-perceptron neural network (NN) trained by back propagation. The location process is based on monitoring the three-phase shifts between the line current and the phase voltage of the machine. The required data for training and testing the NN are experimentally generated from a three-phase induction motor with different interturn short-circuit faults. Simulation, as well as experimental, results are presented in this paper to demonstrate the effectiveness of the used method.      

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     

Fault detection and diagnosis of permanent-magnet DC motor based onparameter estimation and neural network

In this paper, fault detection and diagnosis of a permanent-magnet DC motor is discussed. Parameter estimation based on block-pulse function series is used to estimate the continuous-time model of the motor. The electromechanical parameters of the motor can be obtained from the estimated model parameters. The relative changes of electromechanical parameters are used to detect motor faults. A multilayer perceptron neural network is used to isolate faults based on the patterns of parameter changes. Experiments with a real motor validate the feasibility of the combined use of parameter estimation and neural network classification for fault detection and isolation of the motor     

Input Resistance Calculation for Circular Microstrip Antennas Using Adaptive Neuro-Fuzzy Inference System

This paper presents a new method based on adaptive neuro-fuzzy inference system (ANFIS) to calculate the input resistance of circular microstrip patch antennas. The ANFIS is a fuzzy inference system (FIS) implemented in the framework of an adaptive fuzzy neural network. It combines the explicit knowledge representation of FIS with learning power of neural networks. A hybrid learning algorithm based on the least square approach and the backpropagation algorithm is used to optimize the parameters of ANFIS. The input resistance results predicted by ANFIS are in excellent agreement with the experimental results reported elsewhere.     

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     

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     

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     

粗糙集神经网络在电机故障诊断中的应用

随着社会的进步,科学的发展,电力工程在日常生活中的重要性也日趋明显。在电力系统中,电机的稳定与否关乎到整个系统稳定。电机设备诊断中针对感应电机故障复杂、提取方法不足等问题,运用粗糙神经网络对变压器的故障进行诊断,通过分析电机单相瞬时功率,滤波后进行小波包分解,从得出故障特征变化率,并用以表征故障特征,以此作为电机故障的依据,运用粗糙集理论进行约简,将约简结果作为特征向量输入到RBF网络中。结果表明该方法诊断灵敏度高,可用于电机的故障诊断。     

Analysis of Performance of Adjustable-Speed Drives during Voltage Sags

The induction motors are the most common electric machines on industrial systems and with extended applications when adjustable speed drives (ASD) are used. The speed drives are based on power electronic devices and therefore they are highly sensitive to electric disturbances such as voltage sags, interruption, etc. Voltage sags has become one of most common power quality problems in the electrical systems, producing negative effects mainly in loads with power electronic technology. In this paper, the analysis of the effects produced by voltage sags in the ASD and the induction motor are presented. The electric system used for the analysis is conformed by an induction motor, an AC drive with V/Hz control scheme and a step down transformer connected in Yd. The voltage sags were produced by faults in the electric system with a time duration of 6 cycles (0.1 s). The whole electric system was modeled and simulated in Matlab/Simulink environment. The operating conditions of the induction motor was 80% of nominal speed and full load. The obtained results show high sensitivity of the drive, mainly to the dc-link voltage drop, resulting in a motor speed drop and overcurrents in the drive feeders at the ending sag. The adopted parameters used as a limit for the speed drive disruption were 5% of variation in the motor speed and 1.5 p.u. for the peak current. The most severe effects occur with sags type A and G due to three-phase and two-phase to ground faults respectively. The effect of these sags produced a dc-link voltage drop higher than 30% and therefore the drive disruption as a result of the operating limits exceeded. With voltage sags type C and D, caused by single-phase to ground and two-phase faults respectively, the effects produced in the drive and the motor are negligible.     

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.     

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MIV和BRBP神经网络的电路板红外诊断方法

针对BP神经网络对于海量数据训练及多维数据训练收敛困难的问题,在使用增加动力项、自适应学习速率等方法的基础上,引入均值影响度算法(MIV)构造了贝叶斯正则化反向传播(BRBP)神经网络,以此提高电子线路板红外故障诊断算法的效率。利用红外测温方式,获取了不同室温及运行状态下电路板中21个元器件温度数据。将此21个参数作为故障诊断模型的初始输入变量,经过MIV算法简约为12个参数输入至BRBP神经网络,进行故障评估和诊断。结果表明:相对于传统的BRBP神经网络,本文设计的基于MIV和BRBP神经网络模型诊断方法极大简化了数据训练的数据量并解决了数据收敛的困难,因此效率更高,用时更省。     

有记忆效应的功放实数延时模糊神经网络模型

描述了一种基于实数延时模糊神经网络的有记忆效应的功率放大器模型.该模糊神经系统即自适应模糊神经推理系统,采用模糊c类均值聚类方法来减少模型的规则数目和简化模型结构.在训练过程中,采用最小二乘和反向传播相结合的高效算法提取模型参数.在测试平台上用三载波WCDMA宽带信号对射频功率放大器进行测试,并借助矢量信号分析仪采样功率放大器输入和输出数据,成功地对模型进行了训练和验证.通过和实数延时神经网络模型(RVTDNN)比较,该模型的收敛速度远快于这些前馈结构的神经网络模型.比较和分析时域和频域结果表明模型有很好的性能,其归一化均方误差达-38dB.     

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.     

Low Order PWM Inverter Harmonics Contributions to the Inverter-Fed Induction Machine Fault Diagnosis

In this paper, the effects of inverter harmonics on motor current fault signatures are studied in detail. It is theoretically and experimentally shown that the fault signatures caused by the inverter harmonics are similar and comparable to those generated by the fundamental harmonic on the line current. Theoretically-derived extended relations including bearing fault, eccentricity, and broken rotor bar relations are found to match experimental results. Furthermore, it is observed and reported that the asymmetries on the rotor caused by broken rotor bars increase the amplitude of even harmonics. To confirm these claims, bearing, eccentricity, and broken rotor bar faults are tested and the line current spectrum of each faulty motor is compared with the healthy one. The proposed additional fault data are expected to contribute positively to the inverter-fed motor fault decision making algorithms.     

A Fuzzy-Based Approach for the Diagnosis of Fault Modes in a Voltage-Fed PWM Inverter Induction Motor Drive

This paper investigates the use of fuzzy logic for fault detection and diagnosis in a pulsewidth modulation voltage source inverter (PWM-VSI) induction motor drive. The proposed fuzzy technique requires the measurement of the output inverter currents to detect intermittent loss of firing pulses in the inverter power switches. For diagnosis purposes, a localization domain made with seven patterns is built with the stator Concordia current vector. One is dedicated to the healthy domain and the six others to each inverter power switch. The fuzzy bases of the proposed technique are extracted from the current analysis of the fault modes in the PWM-VSI. Experimental results on a 1.5-kW induction motor drive are presented to demonstrate the effectiveness of the proposed fuzzy approach.