Generally, there exist two major approaches in the feature engineering for motor fault diagnosis. These fault frequencies can be easily detected with the help of. Introduction induction motors square measure essential parts in several industrial processes. Convolutional discriminative feature learning for induction. The wide range oftheir use involves various electrical, magnetic, thermal and mechanical.
The results show that motor current signature analysis mcsa can effectively detect abnormal operating conditions in induction motor applications. Induction motors are the most widespread rotating electric machines in industry due to their ef. Current monitoring techniques are usually applied to detect various induction motor faults such as stator winding faults, bearing faults etc. Fault diagnosis of rotating electrical machines has. Mcsa instrument or spectrum analyzer to present the signature patterns. A comparison of different techniques for induction motor. Motor model and fault analysis system style in matlab 2015 simulink computer code. This presentation will focus on recent developments made in this field at aalto university, notably be the presenter. A thesis on condition monitoring and fault diagnosis of induction motors using motor current signature analysis by neelam mehala has discussed that fault frequencies that occur in motor current spectra are different for different motor faults. The complexity and automation level of machinery are continuously growing. Section presents the analysis of the experimental data for motor fault diagnosis using the proposed method. Download induction motor fault diagnosis ebook free in pdf and epub format. Pdf induction motors are one of the commonly used electrical machines in industry. Various techniques have been developed for broken rotor bar fault diagnosis.
Bearing fault detection in a 3 phase induction motor using stator current frequency spectral subtraction with various wavelet decomposition techniques. Bearing fault diagnosis of induction motor using time domain. Here the major faults in induction motor and different fault detection. Fault diagnosis of induction motors induction motors are still among the most reliable and important electrical machines. Introduction the fft fast fourier transform can be used for online failure detection of asynchronous motors. Review on fault diagnosis in threephase induction motor. Mechanical faults mechanical unbalance, bearing failures, shaft misalignment, airgap deformation and electrical faults rotor and stator faults of induction motors were analysed 48. The advantage of using these mother wavelets compared. This paper proposes an online fault diagnosis system for induction motors through the combination of discrete wavelet transform dwt, feature extraction, genetic algorithm ga, and neural network ann techniques. Mass production companies have become obliged to reduce their production costs and sell more products with lower profit margins in order to survive in competitive market conditions. The problem of failures in induction motors is a large concern due to its significant.
The faulty condition represents any number of broken bars. Bearing fault diagnosis of induction motor using time. Induction motor parameters estimation and faults diagnosis. Electrical current analysis is a very useful tool for the diagnosis of faults inducing torque or speed fluctuations, and ideally completes vibration analysis 1. The main purpose of this article is to revise the main alternatives in the detection of faults in induction machines and compare their contributions according to the. Pdf health monitoring and fault diagnosis in induction. Although, induction motors are highly reliable, they are susceptible to many types of faults that can became catastrophic and cause production shutdowns, personal injuries, and waste of raw material. A comprehensive list of references is reported and the faults are classified into the following main types.
Various damage types were found, such as interturn shortcircuit 1, broken rotor bar 2, bearing inner ring failure, bearing outer ring. Following a brief introduction, the second chapter. Scheme for three phase induction motors based on uncertainty bounds, published. Induction motor especially three phase induction motor plays vital role in the industry due to their advantages over other electrical motors. The first part deals with the electromagnetic modelling of faulty induction motors using finite element techniques. In this method, a set of mother wavelets, called frequency bspline, are used for tracking related fault harmonics in tf plane of the startup currents. If all the values are within the prescribed limit the output of the and gate will be true. A yet unreached goal is the development of a generalized, practical approach enabling industry to accurately diagnose different potential. Pdf induction motors are one of the commonly used electrical machines in industry because of various technical and economical reasons. One of the most commonly seen motor faults is the broken rotor bar, which can cause serious motor damage if not detected in time 3, 4. Induction motors are the mainstay for every industry. This book covers the diagnosis and assessment of the various faults which can.
A comprehensive list of induction motor fault conditions, viz. Therefore, fault diagnosis of ims has become an important area of conditionbased maintenance cbm programs. This book covers the diagnosis and assessment of the various faults which can occur in a three phase induction motor, namely rotor brokenbar faults, rotormass unbalance faults, stator winding faults, single phasing faults and crawling. A convolutional discriminative feature learning method is presented for induction motor fault diagnosis. Fundamental understanding of the design and operation of threephase induction motors. Vibration, electrical and thermal analyses were used for fault diagnosis of. Application of signal processing tools for fault diagnosis in. A vibration based approach for stator winding fault diagnosis of induction motors. This study describes an adaptive ordertracking fault diagnosis method using recursive kalman. Fault diagnosis has received significant attention in recent years, focusing on different aspects.
Victimization this computer code, motor parameter analysis, fault cases analyzed. A comparison of classifier performance for fault diagnosis of induction motor using multitype signals gang niu, jongduk son, achmad widodo, bosuk yang, donha hwang, and dongsik kang structural health monitoring 2007 6. Result can be compared with the fixed maximum and minimum values of voltage, current and temperature as shown in fig 8. Induction motors are now being used more as compared to before due to their certain advantages such as versatility, dependability and economy, good selfstarting capability, offers users simple, rugged construction easy maintenance. Induction motors condition monitoring system with fault diagnosis. The rotor faults were provoked interrupting the rotor bars by drilling into the rotor. However like any other machine, they will eventually fail because of heavy duty cycles, poor working environment, installation and manufacturing factors, etc. In the proposed method of bearing fault detection, the stator current is taken from the induction motor for both healthy and faulty conditions of the bearing and processed for spectral subtraction using different wavelet decomposition techniques. Introduction induction motors are most used types of motors industrial applications. In this paper, a deep learning approach based on deep belief networks dbn is developed to learn features from frequency distribution of. Pdf induction motor fault diagnosis download ebook for free.
To remove the dominant components in stator current, frequency spectral subtraction is. Acoustic based fault diagnosis of threephase induction motor. In this paper, a highresolution order tracking technique based on adaptive kalman. Automatic fault diagnostic system for induction motors under. Health monitoring and fault diagnosis in induction motor a. With escalating demands for reliability and efficiency, the field of fault diagnosis in induction motors is gaining importance.
Fault diagnosis of induction motors request pdf researchgate. The fft technique diagnoses almost all existing faults of the induction machine in the steady state. Fault diagnosis of induction motor using plc semantic scholar. A deep learning approach for fault diagnosis of induction. Health monitoring and fault diagnosis in induction motor. The development of power electronic devices and converter technologies has revo. Interturn stator winding fault diagnosis in threephase induction motors by parks vector approach. Read induction motor fault diagnosis online, read in mobile or kindle. Induction motor fault diagnosis approach through current. Fault diagnosis of lowpower threephase induction motor. The introduction of redundant element provides safety by.
The wavelet transform improves the signaltonoise ratio during a preprocessing. First works were focussed on motor fault diagnosis such as broken rotor bars or eccentricity faults 2. In this work a methodology is described for the most likely to happen faults in. Therefore, there is a strong demand for their reliable and safe operation. They used motor current with dsp techniques such as fast fourier transform fft, short term fourier transform stft and wavelet transform wt. Induction motor fault analysis, fuzzy logic control 1. Maaheritehrani 1 school of electrical and computer engineering, college of engineering, university of tehran, iran 2 department of electrical and computer engineering, concordia university, montreal, canada. Application of envelope analysis chao jin 1, agusmian p.
This development calls for some of the most critical issues that are reliability and dependability of automatic systems. A comparison of classifier performance for fault diagnosis. Fault diagnosis of induction motor using mcsa 17 different number of broken rotor bar. A comparison of different techniques for induction motor rotor fault diagnosis. The approach firstly utilizes backpropagation bpbased neural network to learn local filters capturing discriminative information. Induction motor faults can be detected in an initial stage in order to prevent the complete failure of the system and unexpected production costs. As for fault diagnosis of an induction motor, the literature has also indicated that approximately. Automatic fault diagnostic system for induction motors. Then, tests were carried out for full loads with faulty motors having up to 12 broken rotor bars.
Induction motors are still among the most reliable and important electrical machines. This diagnostic method can classify two types of induction motor faults. Telecommunication engineering, southwest jiaotong university, china, 2005 thesis submitted for the degree of masters of engineering science in school of electrical and electronic engineering the university of adelaide, australia august 2010. On fault detection, diagnosis and monitoring for induction motors. They used motor current with dsp techniques such as fast fourier transform fft, short term. A vibration based approach for stator winding fault. Induction motors applications, control and fault diagnostics. The results show that motor current signature analysis mcsa can effectively detect abnormal operating. A new method for fault diagnosis of induction motor broken bars has been presented in 6.
Oct 23, 2017 extracting features from original signals is a key procedure for traditional fault diagnosis of induction motors, as it directly influences the performance of fault recognition. Fault diagnosis of induction motor using plc open access. Convolutional discriminative feature learning for induction motor fault diagnosis abstract. The wide range of their use involves various electrical, magnetic, thermal and mechanical stresses which results in the need for fault diagnosis as part of the maintenance. Fault diagnosis of induction motor using neural networks. Fault diagnosis system of induction motors based on neural. Extracting features from original signals is a key procedure for traditional fault diagnosis of induction motors, as it directly influences the performance of fault recognition. Condition monitoring and fault diagnosis of induction motors has been a challenging task for engineers and researchers in many industries. This research proposes an intelligent diagnosis method for induction motor which utilizes deep learning model to automatically learn features from sensor data and realize working status recognition.
Fault diagnosis of rotating electrical motors has received intense research interest. Induction motors are one of the commonly used electrical machines in industry because of various technical and economical reasons. Research article fault diagnosis system of induction. Bearing fault detection in a 3 phase induction motor using. Fault diagnosis of induction motors iet digital library. Pdf fault diagnosis of induction motors using a recursive. Fault analysis and diagnosis system for induction motors.
Fault diagnosis of induction motors iet energy engineering. Diagnostics of rotor and stator problems in industrial. Fault diagnosis in induction motor using soft computing. Gear fault diagnosis by motor current analysis application. Request pdf fault diagnosis of induction motors induction motors are still among the most reliable and important electrical machines. Various fault monitoring techniques for induction motors can be broadly categorized as model based techniques, signal processing techniques, and soft computing techniques. Section describes the experimental setup of the induction motor fault simulation test rig. In the classifier design, the artificial ant clustering technique, inspired by the behavior of real ants, was used as an unsupervised classification method for optimizing fault diagnosis. In addition, this paper presents four case studies of induction motor fault diagnosis. The wide range oftheir use involves various electrical, magnetic, thermal and. Application of signal processing tools for fault diagnosis. Induction motors are used to mainly operate at the constant speed since the rotor speed depends on the supply frequency.
A new approach to intelligent fault diagnosis of threephase induction motors using a signalbased method was proposed in. Thus, the importance of condition monitoring and fault diagnosis of induction motors in auxiliary systems cannot be underestimated. Fault mechanisms and mcsa case histories figure 5 illustrates the key elements for the successful application of mcsa, these include. This book is organized into four sections, covering the applications and structural properties of induction motors, fault detection and diagnostics, control strategies, and the more recently developed topology based on the multiphase induction motors. Pdf fault diagnosis of induction motors using recurrence. Fault diagnosis of lowpower threephase induction motor in. Fault diagnosis of induction motor using plc semantic. International conference on electrical machines and systems, icems, pp. This paper investigates different types of faults for electrical machines with reference to an induction motor and to papers published in the last ten years. Isbn 9789535122074, pdf isbn 9789535163992, published 20151118. Features are extracted from motor stator current, while reducing data transfers and making online.
Fault diagnosis of induction motor using mcsa and fft khalaf salloum gaeid, hew wooi ping, mustafa khalid, atheer lauy salih department of electrical engineering, university of malaya, kuala lumpur, 50603, malaysia. Various damage types were found, such as interturn shortcircuit 1, broken rotor bar 2, bearing inner ring failure, bearing outer ring failure, ball failure, cage failure 3, and eccentricity 4. Induction machines ims power most modern industrial processes induction motors and generate an increasing portion of our electricity doubly fed induction generators. Diagnosis of electrical motors is discussed in many scienti. Plc and scada based fault diagnosis of induction motor.
Induction motors are used in many industrial applications in a wide range of operating areas as they have simple and robust structure, and low production costs. Centre for diagnostic engineering, university of huddersfield, queensgate, huddersfield hd1 3dh, uk. Induction motors are one of the reliable electrical machines but sometimes they undergo undesirable stress, causing faults in induction motor and its failure 1. The main purpose of this article is to revise the main alternatives in the detection of faults in induction machines and compare their contributions according to the information they require for the diagnosis, the number and relevance of the faults that can be detected, the speed to anticipate a fault and the accuracy in the diagnosis.
Fault diagnosis and identification, induction motor, artificial neural network, broken bars, rotor faults 1. Fault diagnosis of induction motor using mcsa and fft. Induction motors condition monitoring system with fault. Based on the method of current spectrum, a neural network method to diagnose the broken bar number of inductor motor. Fault detection and analysis of threephase induction. Diagnostics of rotor and stator problems in industrial induction motors by fang duan b.
The most prominent faults in case of induction motors,has been detected and diagnosed using plc. First, this is a robust technique, which is trained with datasets generated by timestepping finite element methods in order to monitor faults of real induction motors in operation. Research article fault diagnosis system of induction motors. However, high quality features need expert knowledge and human intervention. The test results demonstrated that the proposed induction motor fault diagnosis system is capable of fast algorithm, requires less data to train with, as well as has excellent power of identification. Induction motor fault diagnostic and monitoring methods.
595 1193 133 253 658 1126 347 1081 722 337 613 28 29 1087 309 1108 191 1616 1527 237 587 1616 1447 784 738 1075 1546 759 1264 1573 394 732 1098 1585 76 1257 214 704 463 52 518 609 1453 174 1090 176 316 1490