Stator inter-turn fault diagnosis system for electric motors is of a considerable concern due to its significant effect on industrial production. In this paper, a new method for detecting the inter-turn fault and quantifying its severity in the line start permanent magnet synchronous motor (LSMPSM) is proposed. The new method depends on monitoring the stator current during steady-state period to detect the fault. The convolutional neural network (CNN) method is proposed to correlate the motor steady-state current with the status of the motor winding conditions and detect any presence of inter-turn faults. The data used in this study is extracted from both an experimental setup of a one-horsepower LSPMSM and the corresponding verified mathematical model through several testing cases under various loading conditions. One of the main features of the proposed technique is that it does not require separate feature extraction phase. The results indicate that the proposed technique is able to detect the inter-turn fault under different loading conditions varies from 0NM to 4NM with accuracy of 97.75% for all defined fault levels. The use of steady-state current for fault detection regardless of motor load enables the proposed technique to detect the fault online without disturbing the system functionality and reliability as well as without adding any extra hardware to the system. INDEX TERMS Convolutional neural network (CNN), diagnosis, fault detection, inter-turn fault, LSPMSM.
Three-phase line-start permanent magnet synchronous motors are considered among the most promising types of motors in industrial applications. However, these motors experience several faults, which may cause significant financial losses. This paper proposed a feed-forward neural network-based diagnostic tool for accurate and fast detection of the location and severity of stator inter-turn faults. The input to the neural network is a group of representative statistical and frequency-based features extracted from the steady-state three-phase stator current signals. The current signals with different numbers of shorted turns and loading conditions are captured using the developed finite element JMAG TM model for interior mount LSPMSM. In addition, an experimental set-up was built to validate the finite element model and the proposed diagnostics tool. The simulation and experimental test results showed an overall accuracy of 93.125% in detecting the location and the size of inter-turn, whereas, the accuracy in detecting the location of the fault is 100%.
Reliable and safe operation of electric motors in the industry is highly desirable. Accurate modelling is the first step in developing a diagnostic tool for different types of failures. This study presents a generalised dq-model for interior-mount line start permanent magnet synchronous motors under asymmetrical stator phase's windings. The presented dq-model has been derived using winding theorem. Implementation and simulation of the derived dq-model has been done using MATLAB/ SIMULINK software. For validation purposes, interior-mount line start permanent magnet synchronous motor (LSPMSM) under this fault condition is implemented using the JMAG TM-finite-element-based software. The performance of a 1-hp interior-mount LSPMSM motor under different loading levels and stator winding asymmetric conditions has been investigated using the simulated MATLAB and JMAG models. Simulation results of MATLAB and JMAG are in very good agreement and show that under asymmetrical stator winding condition, oscillations are obvious in the torque characteristics of the motor. In addition, the torque experience high oscillations at a steady state due to the asymmetry between stator phases. Finally, investigating torque frequency spectrum showed that they can be good signatures in diagnosing asymmetrical stator winding faults in interior-mount LSPMSM.
The application of line-start permanent magnet synchronous motors (LSPMSMs) is rapidly spreading due to their advantages of high efficiency, high operational power factor, being self-starting, rendering them as highly needed in many applications in recent years. Although there have been standard methods for the identification of parameters of synchronous and induction machines, most of them do not apply to LSPMSMs. This paper presents a study and analysis of different parameter identification methods for interior mount LSPMSM. Experimental tests have been performed in the laboratory on a 1-hp interior mount LSPMSM. The measurements have been validated by investigating the performance of the machine under different operating conditions using a developed qd0 mathematical model and an experimental setup. The dynamic and steady-state performance analyses have been performed using the determined parameters. It is found that the experimental results are close to the mathematical model results, confirming the accuracy of the studied test methods. Therefore, the output of this study will help in selecting the proper test method for LSPMSM.
Line start permanent magnet synchronous motors experience different types of failures, including static eccentricity. The first step in detecting such failures is the mathematical modeling of the motor under healthy and failed conditions. In this paper, an attempt to develop an accurate mathematical model for this motor under static eccentricity is presented. The model is based on the modified winding function method and coupled magnetic circuits approach. The model parameters are calculated directly from the motor winding layout and its geometry. Static eccentricity effects are considered in the motor inductances calculation. The performance of the line start permanent magnet synchronous motor using the developed mathematical model is investigated using MATLAB/SIMULINK ® software (2013b, MathWorks, Natick, MA, USA) under healthy and static eccentricity condition for different loading values. A finite element method analysis is conducted to verify the mathematical model results, using the commercial JMAG ® software (16.0.02n, JSOL Corporation, Tokyo, Japan). The results show a fine agreement between JMAG ® and the developed mathematical model simulation results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.