Neural classification method in fault detection and diagnosis for voltage source inverter in variable speed drive with induction motor

Farid, Kadri; Drid, Saïd; Djeffal, F.; Chrifi‐Alaoui, Larbi

doi:10.1109/ever.2013.6521549

Cited by 22 publications

(10 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Results proved that the designed fault detection and diagnosis system is more robust, accurate, systematic, effectual, and dynamic in detecting both single and multiple faults. This proposed technique is much better in comparison to previous techniques [7][8][9][10] as it can detect even multiple faults with 100% accuracy because of efficient feature extraction system as compared to 95% or lower accuracy of those techniques, and also it can detect single and multiple faults faster even in single current cycle. These simulated and hardware based system results prove the credibility and show the satisfactory performance of system.…”

Section: Introductionmentioning

confidence: 94%

“…In this paper, neural network based fault detection and diagnosis method [10,11] for three-phase inverter feeding an induction motor is designed to detect and localize failures in a set inverter-induction motor without the need of additional sensors or computational effort as shown in Figure 1. This technique can detect single or multiple switching device faults in three-phase inverter system by analyzing the stator current patterns and features extraction from that output current and then using these features in neural network method.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Neural Network Based Fault Detection and Diagnosis System for Three-Phase Inverter in Variable Speed Drive with Induction Motor

Asghar

Talha

Kim

2016

Journal of Control Science and Engineering

View full text Add to dashboard Cite

Recently, electrical drives generally associate inverter and induction machine. Therefore, inverter must be taken into consideration along with induction motor in order to provide a relevant and efficient diagnosis of these systems. Various faults in inverter may influence the system operation by unexpected maintenance, which increases the cost factor and reduces overall efficiency. In this paper, fault detection and diagnosis based on features extraction and neural network technique for three-phase inverter is presented. Basic purpose of this fault detection and diagnosis system is to detect single or multiple faults efficiently. Several features are extracted from the Clarke transformed output current and used in neural network as input for fault detection and diagnosis. Hence, some simulation study as well as hardware implementation and experimentation is carried out to verify the feasibility of the proposed scheme. Results show that the designed system not only detects faults easily, but also can effectively differentiate between multiple faults. These results prove the credibility and show the satisfactory performance of designed system. Results prove the supremacy of designed system over previous feature extraction fault systems as it can detect and diagnose faults in a single cycle as compared to previous multicycles detection with high accuracy.

show abstract

Section: Introductionmentioning

confidence: 94%

Section: Introductionmentioning

confidence: 99%

Neural Network Based Fault Detection and Diagnosis System for Three-Phase Inverter in Variable Speed Drive with Induction Motor

Asghar

Talha

Kim

2016

Journal of Control Science and Engineering

View full text Add to dashboard Cite

show abstract

“…In Ref. , a study of the feasibility of fault detection and diagnosis in a three‐phase inverter feeding an induction motor is presented using a neural network classification applied to the fault diagnosis of the field‐oriented drive of an induction motor. Multilayer perception (MLP) networks were used to identify the type and location of faults occurring using the stator Concordia mean current vector.…”

Section: Intorductionmentioning

confidence: 99%

Experimental investigation of a speed‐sensor‐less IM drive system under Inverter fault‐tolerant control

Elbarbary

Azazi

2016

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

This paper proposes an algorithm for fault tolerance of three-phase, inverter-fed, speed-sensor-less control of a three-phase induction motor drive system. The fault tolerance of the inverter when one switch is open or one leg of six-switch inverter is lost is considered. The control of the drive system is based on indirect rotor field-oriented control theory. Also, the speed estimator is based on model reference adaptive system (using stator current and rotor flux as state variables for estimating the speed). The fault-tolerant algorithm is able to adaptively change over from a six-switch inverter to a four-switch inverter topology when a fault occurs; also, it makes a smooth transition of the motor speed, torque, and current when changing over from a faulty condition to a new healthy status, which is four-switch three-phase inverter (FSTPI) topology; thus, the six-switch three-phase inverter (SSTPI) topology (pre-fault status) is almost retained for the medium-power range of induction motor applications. The proposed algorithm is simulated by using the MATLAB/SIMULINK package. Also, the proposed control system is tested experimentally using a digital signal processor (DSP1104). The obtained results from the simulation model and experimental system demonstrate the performance enhancement and good validity of the fault-tolerance control for the speed-sensor-less induction motor drive system. IntorductionThree-phase induction motors have been the workhorse for industrial and manufacturing processes. A high harmonic current content causes torque ripple on the load when variablespeed induction motor drives operate with an open-circuit phase fault. These effects result from the unbalanced nature of the faulted machine. Different diagnosis techniques for transistor opencircuit faults have been developed and analyzed [1][2][3]. A detection method that identifies the power switch in which the fault has occurred based on measurement of motor voltages is presented in Ref. [4]. It also investigates fault compensation via topologies that are able to maintain the system operation for a period. In Ref.[5], a modeling method for induction motor drives is proposed that includes machine saturation and space harmonics effects as well as inverter nonlinearity, which does not require significant computation times. Also, a descriptionon how the model was used to develop a fault ride-through control strategy for a voltage-fed vector-controlled drive is given. In Ref.[6], the effect of measurement failure error due to faulty sensors and power inverter malfunctions was investigated. Both software and hardware redundancies have been investigated during the occurrence of a failure. Software redundancy has been evaluated in the case of a speedsensor failure. In Ref.[7], a fault occurring when open-circuit winding faults appear on the induction motor drive is considered. A feed-forward compensation term is introduced into the a Correspondence to: Z. M. El-Barbary. E-mail: z_elbarbary@yahoo.com * Department of Electrical Engineering, Kafre...

show abstract

“…In this example, the classification accuracy of over 95% is reported. In [11], a multi-layered perceptron network is employed to classify open faults of a simulated voltage source inverter (VSI). Another study of BPNN application to a multi-level inverter fault classification is described in [2].…”

Section: Introductionmentioning

confidence: 99%

A Fast Classification Method of Faults in Power Electronic Circuits Based on Support Vector Machines

Cui

Shi

Gong

2017

Metrology and Measurement Systems

View full text Add to dashboard Cite

Fault detection and location are important and front-end tasks in assuring the reliability of power electronic circuits. In essence, both tasks can be considered as the classification problem. This paper presents a fast fault classification method for power electronic circuits by using the support vector machine (SVM) as a classifier and the wavelet transform as a feature extraction technique. Using one-against-rest SVM and one-against-one SVM are two general approaches to fault classification in power electronic circuits. However, these methods have a high computational complexity, therefore in this design we employ a directed acyclic graph (DAG) SVM to implement the fault classification. The DAG SVM is close to the one-against-one SVM regarding its classification performance, but it is much faster. Moreover, in the presented approach, the DAG SVM is improved by introducing the method of Knearest neighbours to reduce some computations, so that the classification time can be further reduced. A rectifier and an inverter are demonstrated to prove effectiveness of the presented design.

show abstract

Neural classification method in fault detection and diagnosis for voltage source inverter in variable speed drive with induction motor

Cited by 22 publications

References 10 publications

Neural Network Based Fault Detection and Diagnosis System for Three-Phase Inverter in Variable Speed Drive with Induction Motor

Neural Network Based Fault Detection and Diagnosis System for Three-Phase Inverter in Variable Speed Drive with Induction Motor

Experimental investigation of a speed‐sensor‐less IM drive system under Inverter fault‐tolerant control

A Fast Classification Method of Faults in Power Electronic Circuits Based on Support Vector Machines

Contact Info

Product

Resources

About