Induction Motor Fault Diagnosis Research Articles

Multi-agent decision fusion for motor fault diagnosis

Improvement of recognition rate is ultimate aim for fault diagnosis researchers using pattern recognition techniques. However, the unique recognition method can only recognise a limited classification capability which is insufficient for real-life application. An ongoing strategy is the decision fusion techniques. In order to avoid the shortage of single information source coupled with unique decision method, a new approach is required to obtain better results. This paper proposes a decision fusion system for fault diagnosis, which integrates data sources from different types of sensors and decisions of multiple classifiers. First, non-commensurate sensor data sets are combined using an improved sensor fusion method at a decision level by using relativity theory. The generated decision vectors are then selected based on correlation measure of classifiers in order to find an optimal sequence of classifiers fusion, which can lead to the best fusion performance. Finally, multi-agent classifiers fusion algorithm is employed as the core of the whole fault diagnosis system. The efficiency of the proposed system was demonstrated through fault diagnosis of induction motors. The experimental results show that this system can lead to super performance when compared with the best individual classifier with single-source data.

Vibration based Fault Diagnosis of induction Motor

All types of rotating machines even new ones generate some level of vibrations. Small level of machine vibration is acceptable, however higher level and increasing trends are symptoms of abnormal machine performance. Therefore, machine vibration analysis becomes one of the important tools for machine fault identification. This paper presents an integrated pattern recognition method based on Euclidean distance measure for vibration diagnostic of machine health. The overall process is subdivided into stages of data acquisition, preprocessing, feature extraction and calculation of distance index. A computerized on-line monitoring system has been developed to record the frame vibrations, temperature, speed, line voltages and line currents from a three-phase induction motor for different operating conditions. The proposed method is suitable for both off-line and online applications. The method has been successfully tested for a large number of vibration data collected from the set of five identical test motors under different operating conditions. The test results establish the accuracy, effectiveness and reliability of the method.

PCA와 비선형분류기에 기반을 둔 유도전동기의 고장진단

In this paper, we propose fault diagnosis of induction motor based on PCA and MLP. To resolve the main drawback of MLP, we calculate the reduced features by PCA in advance. Finally, we develop the diagnosis system based on nonlinear classifier by MLP rather than linear classifier by conventional k-NN. By various experiments, we obtained better classification performance in comparison to the results produced by linear classifier by k-NN.

MIXED FAULT DIAGNOSIS IN THREE-PHASE SQUIRREL-CAGE INDUCTION MOTOR USING ANALYSIS OF AIR-GAP MAGNETIC FIELD

In this paper fault diagnosis of induction motor under mixed fault is carried out using precise analysis of the air-gap magnetic field based on time stepping finite element method. By feeding voltage instead of current density to the finite element computation part, the drawbacks of the application of finite element method in fault diagnosis of induction motor are overcome. Normally static eccentricity and broken rotor bars faults have been individually diagnosed in the published papers. Here diagnosis of the mixed fault,including static eccentricity and broken rotor bars,is introduced which is considered as a novel part of the present work. Precise analysis of magnetic field in the air-gap of a faulty induction motor is carried and performance of the motor is predicted. Taking into account the magnetic core saturation is another advantage of the present work. This is required in the transient analysis of a faulty motor.

For an Accurate Diagnosis of Induction Motor Faults under Distorted Supply Voltage

For an Accurate Diagnosis of Induction Motor Faults under Distorted Supply Voltage

Application of Dempster–Shafer theory in fault diagnosis of induction motors using vibration and current signals

This paper presents an approach for the fault diagnosis in induction motors by using Dempster–Shafer theory. Features are extracted from motor stator current and vibration signals and with reducing data transfers. The technique makes it possible for on-line application. Neural network is trained and tested by the selected features of the measured data. The fusion of classification results from vibration and current classifiers increases the diagnostic accuracy. The efficiency of the proposed system is demonstrated by detecting motor electrical and mechanical faults originated from the induction motors. The results of the test confirm that the proposed system has potential for real-time applications.

진동 및 전류신호의 데이터융합을 이용한 유도전동기의 결함진단

진동 및 전류신호의 데이터융합을 이용한 유도전동기의 결함진단

Induction motor fault detection using vibration and stator current methods

Induction motors are widely used in industry as prime electromechanical energy conversion devices. Consequently, the condition monitoring and fault diagnosis of induction motors have received significant attention recently and become an integrated part of various maintenance strategies (for example preventive, condition-based and reliability-based maintenance). This paper presents a comparison of results of induction motor broken rotor bar fault detection using vibration and stator current methods. A broken rotor bar fault was induced into in a variable speed three-phase induction motor. Both the vibration and stator current signatures were acquired under different speed and load conditions. The fault detection sensitivities of vibration and stator current methods are evaluated. This paper also addresses the relationship between current and vibration signatures under normal and faulty motor conditions using correlation and frequency response methods. This relationship is desirable in order to determine the fault signature transmission mechanism and to exclude the irrelevant vibration sources so as to enhance fault detection accuracy. The relationship, studied during steady-state operation and start-up, enabled the identification of the vibrations from other sources.

Bearing and misalignment fault detection in induction motors by using the space vector angular fluctuation signal

This paper describes the use of the space vector angular fluctuation (SVAF) method for bearing and misalignment fault diagnosis in induction motors. The theoretical background for SVAF is presented and it is shown how bearing and misalignment faults can be effectively diagnosed by the use of this non-invasive method. The proposed algorithm uses only stator currents as the input, without any other sensors. Both simulation and experimental results carried out on different motors show that these faults could be easily detected and differentiated from each other by fault-related frequencies, which occur in the spectrum of the SVAF.

Case-based reasoning system with Petri nets for induction motor fault diagnosis

Abstract This paper presents an innovative approach for integrating case-based reasoning (CBR) with Petri net for the fault diagnosis of induction motors. In the CBR system, maintenance engineers can retrieve the information from previous cases which closely resemble the new problem and solve the new problem using the information from the previous cases. The proposed system has been used in fault diagnosis of electric motor to confirm the system performance. The result shows the proposed system performs better than the conventional CBR system.

Induction motor stator faults diagnosis by a current concordia pattern-based fuzzy decision system

This paper deals with the problem of detection and diagnosis of induction motor faults. Using the fuzzy logic strategy, a better understanding of heuristics underlying the motor faults detection and diagnosis process can be achieved. The proposed fuzzy approach is based on the stator current Concordia patterns. Induction motor stator currents are measured, recorded, and used for Concordia patterns computation under different operating conditions, particularly for different load levels. Experimental results are presented in terms of accuracy in the detection of motor faults and knowledge extraction feasibility. The preliminary results show that the proposed fuzzy approach can be used for accurate stator fault diagnosis if the input data are processed in an advantageous way, which is the case of the Concordia patterns.

Neural networks application for induction motor faults diagnosis

The paper deals with diagnosis problems of the induction motors in the case of rotor, stator and rolling bearing faults. Two kinds of neural networks (NN) were proposed for diagnostic purposes: multilayer perceptron networks and self organizing Kohonen networks. Neural networks were trained and tested using measurement data of stator current and mechanical vibration spectra. The efficiency of developed neural detectors was evaluated. Feedforward NN with very simple internal structure, used for the detection of all fault kinds, gave satisfactory results, which is very important in practical realization. Experiments with Kohonen networks indicated that they could be used for the initial classification of motor faults, as an introductory step before the proper neural detector based on multiplayer perceptron is used. The obtained results lead to a conclusion that neural detectors for rotor and stator faults as well as for rolling bearings and supply asymmetry faults can be developed based on measurement data acquired on-line in the drive system.

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.

Fault diagnosis in induction motors using radial magnetic field measurement withan antenna

In this paper the emf induced in a search coil is measured in order to detectfaults in an induction motor. Anomalous operations caused by a brokenrotor bar or a faulty stator cutting phase are analysed. Starting from atheoretical analysis of the radial field spectrum associated with these faults, themeasurement of the corresponding emf in the search antenna is examined.Thesaturation and harmonic components of the permeance produced by theslotting effect are taken into account. Their interactions are analysed,allowing the identification of the frequencies which are of interest for thedetection of stator cutting phase faults in a working induction motor.

Reducing the Impact of False Alarms in Induction Motor Fault Diagnosis

Early detection and diagnosis of incipient faults is desirable for on-line condition assessment, product quality assurance, and improved operational efficiency of induction motors. At the same time, reducing the probability of false alarms increases the confidence of equipment owners in this new technology. In this paper, a model-based fault diagnosis system recently proposed by the authors for induction motors is experimentally compared for fault detection and false alarm performance with a more traditional signal-based motor fault estimator. In addition to the nameplate information required for the initial set-up, the proposed model-based fault diagnosis system uses measured motor terminal currents and voltages, and motor speed. The motor model embedded in the diagnosis system is empirically obtained using dynamic recurrent neural networks, and the resulting residuals are processed using wavelet packet decomposition. The effectiveness of the model-based diagnosis system in detecting the most widely encountered motor electrical and mechanical faults, while minimizing the impact of false alarms resulting from power supply and load variations, is demonstrated through extensive testing with staged motor faults. The model-based fault diagnosis system is scalable to motors of different power ratings and it has been successfully tested with fault data from 2.2kW,373kW, and 597kW induction motors.

The HG Diagram Model for Induction Motors Analysis: Theoretical Approach and Applications

This article presents theory and applications of a practical approach for induction motors modeling under temperature and saturation effects. This approach is based on the so-called HG diagram that is established from the induction motor measurement analysis of the active and reactive power consumption for each operating point. In practice, this diagram is a circle plotted in the complex plane. The distinct feature of this circle is its diameter that is time-varying with the induction motor temperature and saturation states. In fact, these two effects are both interfering and conjugate, and only an online plotted circle will allow taking them into account. Since the HG diagram is characterized by three parameters, especially the rotor ones, it constitutes an interesting tool to achieve the identification of online motor parameters. This possibility has led us to apply this diagram for induction motor control and faults diagnosis, especially in the rotor. Moreover, it can easily be applied for modeling saturation, which will refine the control and diagnosis processes. Computer simulations and experimental tests, carried out on a 4-kW and a 0.75 four-pole squirrel cage induction motors, provide an encouraging validation of the HG diagram applications. Theresults obtained clearly point out the distinct features, simplicity and accuracy, of the proposed approach.

Analysis of induction motor fault diagnosis with fuzzy neural network

The online diagnosis of an electrical drive is the first step towards the application of an effective predictive maintenance plan on such electrical machines. The analysis of residual features corresponding to instrumentation faults of an induction motor lead to the design of a faults classification system. The training set is obtained by a faulted machine dynamical model as simulator. Two neuro-fuzzy structures will be conceived to learn the exact input-output relation of the fault detection process for induction motor, using measured data. The first neuro-fuzzy architecture maps the residuals into two classes: one of fixed direction residuals and another of faults belonging to velocity sensor. The second adaptive neuro-fuzzy network will provide updated membership functions of the sets of fixed oriented residuals that better describe the fault diagnosis map.

Induction motor fault diagnosis based on neuropredictors and wavelet 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 stator fault diagnosis in induction motors

This paper presents a noninvasive and online method for detection of stator winding faults in three-phase induction motors from observation of negative sequence supply current. A power decomposition technique (PDT) has been used to derive positive and negative sequence components of measured voltages and currents. A fault detection algorithm has been developed to characterise the effects of supply imbalance and nonlinear motor effects (motor iron saturation, winding imbalance, rotor static eccentricity), which also generate negative sequence current. The effects of motor heating and variation in negative sequence resistance with slip change are minimised by using only motor negative sequence reactance to calculate supply negative sequence current. Change in the motor negative sequence impedance under supply imbalance due to load variation (mainly because of closed rotor slots effect) has been included. Experimental results on several motors show that negative sequence impedance can vary between 10% to 50%. Semiempirical formulas based on theoretical and experimental results have been proposed to eliminate the effects of supply imbalance, load, and voltage variation. Compensation for this negative sequence current before making the fault decision enables a high fault sensitivity to be achieved.

Rotor Cage Fault Diagnosis in Three-Phase Induction Motors by Extended Park's Vector Approach

This paper introduces a new approach, based on the spectral analysis of the motor current Park's Vector modulus, for detecting the occurrence of rotor cage faults in operating three-phase induction machines. The major theoretical principles of the Extended Park's Vector Approach are described. Both simulation and laboratory test results demonstrate how the presence of rotor cage faults can be effectively detected by the application of this new approach. These results are also correlated with the ones obtained by the conventional motor current spectral analysis and by the classic Park's Vector Approach.