Detection Of Stator Inter-turn Short Circuit In Three-Phase Induction Motor Using Current Coordinate Transformation

Solodkiy, Evgeniy; Даденков, Д. А.; Сальников, С. В.

doi:10.1109/iwed.2019.8664353

Cited by 5 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To the best of our knowledge, although the are several works dealing with the on-line detection of inter-turn faults in different machine types such as induction motors [29], switched reluctance machines [30], brushless DC machines [31] or PM synchronous motors [13], among others, there are virtually no works dealing with the on-line detection of inter-turn faults in synchronous reluctance machines, thus this work contributing in this area, and specifically in the area of fault diagnosis in multi-phase machines, in which the research done is even less. Results presented when dealing with only one shorted turn, show the feasibility of the proposed strategy to perform a very fast detection of inter-turn faults in the very early stage.…”

Section: Introductionmentioning

confidence: 99%

Detection of Inter-Turn Faults in Multi-Phase Ferrite-PM Assisted Synchronous Reluctance Machines

et al. 2019

View full text Add to dashboard Cite

Inter-turn winding faults in five-phase ferrite-permanent magnet-assisted synchronous reluctance motors (fPMa-SynRMs) can lead to catastrophic consequences if not detected in a timely manner, since they can quickly progress into more severe short-circuit faults, such as coil-to-coil, phase-to-ground or phase-to-phase faults. This paper analyzes the feasibility of detecting such harmful faults in their early stage, with only one short-circuited turn, since there is a lack of works related to this topic in multi-phase fPMa-SynRMs. Two methods are tested for this purpose, the analysis of the spectral content of the zero-sequence voltage component (ZSVC) and the analysis of the stator current spectra, also known as motor current signature analysis (MCSA), which is a well-known fault diagnosis method. This paper compares the performance and sensitivity of both methods under different operating conditions. It is proven that inter-turn faults can be detected in the early stage, with the ZSVC providing more sensitivity than the MCSA method. It is also proven that the working conditions have little effect on the sensitivity of both methods. To conclude, this paper proposes two inter-turn fault indicators and the threshold values to detect such faults in the early stage, which are calculated from the spectral information of the ZSVC and the line currents.Energies 2019, 12, 2733 2 of 15 ripple in the output, although torque pulsations can be minimized by means of a suitable design, including rotor skewing, asymmetric flux barriers or selected rotor steps [5].Faults in electrical machines could produce loss of system reliability, unscheduled shutdowns [9], important economic losses or even harmful effects to humans. Therefore, there is a growing demand for improved fault diagnosis approaches in electrical machines, in particular for high-performance applications [10]. This strategy ensures the safe and reliable operation of the plant, while greatly reducing unexpected and unscheduled fault occurrences, thus improving system availability and minimizing economic losses and the likelihood of accidents [11].Rotating electric machines are designed with mechanical and electrical symmetry to maximize performance and efficiency and to minimize vibrations. When operating under faulty conditions this symmetry is lost, thus changing the magnitude or the shape of different machine signals, such as the electromotive force, line currents, vibrations profile or the temperature, among others [12]. Most of these faults generate specific patterns of such signals, so these changes can be used for fault diagnosis purposes.Different fault diagnosis techniques have been analyzed in the technical literature, based on on-line or off-line approaches. Whereas off-line methods require the disconnection of the machine and sometimes the removal of some components, on-line diagnosis methods require the addition of specific sensors to acquire data from the machine during normal operation, although in some cases no extra sensors are required. Due to the ex...

show abstract

Section: Introductionmentioning

confidence: 99%

Detection of Inter-Turn Faults in Multi-Phase Ferrite-PM Assisted Synchronous Reluctance Machines

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Layer 5 shows the overall output and defines defuzzification layer whose output is overall ANFIS output. The problems of continuous changes in mobile learning environments are solved by ANFIS[29]. The proposed ANFIS model can be used for modelling the learner context.…”

mentioning

confidence: 99%

Application of Machine Learning for Inter Turn Fault Detection in Pumping System

Dutta

Palanisamy

Shanmugam

2022

Preprint

View full text Add to dashboard Cite

Pump fault diagnosis is essential for maintenance and safety of the device as it is an important appliance used in various major sectors. Fault diagnosis at proper time can reduce maintenance cost and save energy. In this article a Simulink model based on mathematical equations has been built for analyzing the effects of parameter estimation of three phase induction motor based centrifugal pump in inter turn fault condition. The inter turn fault causes huge increase of current which severely affects the parameters of both motor and pump and these have been analysed by simulation through Matlab Simulink model. Later, the results are verified by hardware in loop (HIL) based simulator. In this paper machine learning (ML) based artificial neural network (ANN) and ANFIS (ANN and Fuzzy) models have been applied for fault detection ANN and ANFIS based models provide a satisfactory level of accuracy. These models provide accurate training and testing results. Based on root mean square error (RMSE), R2, prediction accuracy and mean validation value these models are compared to find out which is more suitable for this experiment. Various supervised algorithms are compared with ANN, ANFIS and lastly found which is the most suitable for this experiment.

show abstract

Application of machine learning for inter turn fault detection in pumping system

Dutta

Palanisamy

Shanmugam³

2022

Sci Rep

View full text Add to dashboard Cite

Pump fault diagnosis is essential for the maintenance and safety of the device as it is an important appliance used in various major sectors. Fault diagnosis at the proper time can reduce maintenance costs and save energy. This article uses a Simulink model based on mathematical equations to analyze the effects of parameter estimation of three-phase induction motor-based centrifugal pumps in inter-turn fault conditions. The inter-turn fault causes a massive in, a massive increase in current, which severely affects the parameters of both motor and pump. These have been analyzed by simulation through the Matlab Simulink model. Later, the results are verified by a hardware in loop (HIL) based simulator. In this paper, machine learning (ML) based artificial neural network (ANN) and ANFIS (ANN and Fuzzy) models have been applied for fault detection. ANN and ANFIS-based models provide a satisfactory level of accuracy. These models provide accurate training and testing results. Based on root mean square error (RMSE), R2, prediction accuracy, and mean validation value, these models are compared to find out which is more suitable for this experiment. Various supervised algorithms are compared with ANN, ANFIS, and lastly, found which is the most suitable for this experiment.

show abstract

Detection Of Stator Inter-turn Short Circuit In Three-Phase Induction Motor Using Current Coordinate Transformation

Cited by 5 publications

References 8 publications

Detection of Inter-Turn Faults in Multi-Phase Ferrite-PM Assisted Synchronous Reluctance Machines

Detection of Inter-Turn Faults in Multi-Phase Ferrite-PM Assisted Synchronous Reluctance Machines

Application of Machine Learning for Inter Turn Fault Detection in Pumping System

Application of machine learning for inter turn fault detection in pumping system

Contact Info

Product

Resources

About