Search

Summary: The condition monitoring of squirrel cage induction motors (SCIMs) is vital for uninterrupted production and minimum downtime. Early fault detection can boost output with minimum effort. This article combines the application of transfer learning and convolution neural network (TL‐CNN) for developing an efficient model for bearing and rotor broken bars damage identification in SCIMs. A simple technique for the 1‐D current signal‐to‐image conversion is also proposed to provide input to the proposed deep learning‐based TL‐CNN technique. The proposed approach embodies the advantages of TL and CNN for effective fault identification in SCIMs. The developed technique has classified faults efficiently with an average accuracy of 99.40%. The complete analysis and data collection have been done on the experimental set‐up with a 5 kW SCIM and LabVIEW‐based data acquisition system. The propounded fault detection model has been created in python with the help of packages like Keras and TensorFlow. [ABSTRACT FROM AUTHOR]

Introduction. In various industrial processes, squirrel cage induction motors are widely employed. These motors can be used in harsh situations, such as non-ventilated spaces, due to their high strength and longevity. These machines are subject to malfunctions such as short circuits and broken bars. Indeed, for the diagnosis several techniques are offered and used. Novelty of the proposed work provides the use of wavelet analysis technology in a continuous and discrete system to detect faults affecting the rotating part of an induction motor fed by a three-phase inverter. Purpose. This paper aims to present a novel technique for diagnosing broken rotor bars in the low-load, stationary induction machine proposed. The technique is used to address the problem of using the traditional Techniques like Fourier Transforms signal processing algorithm by analyzing the stator current envelope. The suggested method is based on the use of discrete wavelet transform and continuous wavelet transform. Methods. A waveform can be monitored at any frequency of interest using the suggested discrete wavelet transform and continuous wavelet transform. To identify the rotor broken bar fault, stator current frequency spectrum is analyzed and then examined. Based on a suitable index, the algorithm separates the healthy motor from the defective one, with 1, 2 and 3 broken bars at no-load. Results. In comparison to the healthy conditions, the recommended index significantly raises under the broken bars conditions. It can identify the problematic conditions with clarity. The possibility of detecting potential faults has been demonstrated (broken bars), using discrete wavelet transform and continuous wavelet transform. The diagnostic method is adaptable to temporary situations brought on by alterations in load and speed. Performance and efficacy of the suggested diagnostic method are demonstrated through simulation in Simulink® MATLAB environment.

Introduction. In various industrial processes, squirrel cage induction motors are widely employed. These motors can be used in harsh situations, such as non-ventilated spaces, due to their high strength and longevity. These machines are subject to malfunctions such as short circuits and broken bars. Indeed, for the diagnosis several techniques are offered and used. Novelty of the proposed work provides the use of wavelet analysis technology in a continuous and discrete system to detect faults affecting the rotating part of an induction motor fed by a three-phase inverter. Purpose. This paper aims to present a novel technique for diagnosing broken rotor bars in the lowload, stationary induction machine proposed. The technique is used to address the problem of using the traditional Techniques like Fourier Transforms signal processing algorithm by analyzing the stator current envelope. The suggested method is based on the use of discrete wavelet transform and continuous wavelet transform. Methods. A waveform can be monitored at any frequency of interest using the suggested discrete wavelet transform and continuous wavelet transform. To identify the rotor broken bar fault, stator current frequency spectrum is analyzed and then examined. Based on a suitable index, the algorithm separates the healthy motor from the defective one, with 1, 2 and 3 broken bars at no-load. Results. In comparison to the healthy conditions, the recommended index significantly raises under the broken bars conditions. It can identify the problematic conditions with clarity. The possibility of detecting potential faults has been demonstrated (broken bars), using discrete wavelet transform and continuous wavelet transform. The diagnostic method is adaptable to temporary situations brought on by alterations in load and speed. Performance and efficacy of the suggested diagnostic method are demonstrated through simulation in Simulink® MATLAB environment. [ABSTRACT FROM AUTHOR]

Short-circuit in three-phase engines are highly destructive faults, which overheat and damage internal elements reducing efficiency and lifetime. New multi-class approaches are best trained with measurements from three-phase motors instrumented with short-circuit faults because it offers natural and physical signal behavior. This work overcomes the lack of datasets by acquiring current signals from an instrumented induction motor to create a dataset of inter-turn short-circuit (ITSC) faults at four levels per phase. The dataset generated consists of 13 categories with five repetitions per trial for a squirrel cage motor induction. The proposed classification method is based on quaternions that simultaneously model the three-phase signals as pure quaternions. Three statistical features are extracted from quaternions, and a decision tree classifier is trained per feature. Thereby, a boosting scheme is used to calculate the resulting category. Boosting method improves the classification results of decision tree models, showing fast, accurate, and robust performance. • Classification of Inter-turn short circuit faults in induction motors. • Modeling and characterizing three-phase currents in quaternion space. • Detection of four levels of inter-turn short circuit faults per phase and healthy. • The decision tree and the boosting scheme predict the fault category. • A multiclass dataset with raw and filtered three-phase currents of an induction motor. [ABSTRACT FROM AUTHOR]

The condition monitoring of the rotor bar in the squirrel cage induction motors (SCIMs) is performed with various contact methods and non-contact methods. The various contact methods are zero sequence current spectrum measurement, non-uniform time resampling of current, motor current spectrum analysis, vibration measurement, etc. Non-contact methods are infrared thermography, stray flux measurement, acoustic emission measurement, temperature measurement, etc. The contact methods execute via vibration, instantaneous frequency, rotor speed and flux signal analysis. Whereas, non-contact method accomplishes via acoustic, current, temperature and stray flux measurement. The existing methods suffer from the influence of adjoining machines, surrounding environmental changes; require human expertise to mount sensors and analysing the signals. In this paper, a novel low-cost and non-invasive method proposed for rotor bar fault identification in SCIMs with Software Phase Locked Loop (SPLL). The proposed method uses a high-frequency signal projected on the motor and the reflected signal captured. The captured signal analysed by Fast Fourier Transform (FFT) and Wavelet transforms to identify the fault. The performance of these transforms compared in term of accuracy to identify the rotor bar faults of SCIM. The experimental results show that the proposed method achieves better accuracy than the existing methods..

• The rotor temperature estimation methods are preferred to direct measurement methods. • These methods are classified into the parameter, thermal model and hybrid estimation methods. • The rotor temperature estimation methods are described and analyzed comprehensively. • The assumptions, requirements, advantages, and drawbacks of these methods are discussed. • The review can be useful to find novel methods with more advantage and less drawback. In order to ensure the stable and reliable operation of the squirrel cage induction motors (SCIMs), it is very important to know their rotor temperature. The rotor overheating causes serious damages on rotor bars and end rings. The direct measurement of the rotor temperature by means of thermal sensors is expensive and the installation and utilization process of their corresponding data acquisition devices is difficult. Therefore, the estimation methods of the SCIM's rotor temperature are proposed which are classified into three main methods: parameter estimation methods, thermal model-based estimation methods, and hybrid methods. The present paper describes and analyses and compares the assumptions, requirements, advantages, and drawbacks of these methods comprehensively. This review could be useful to advance the path of the previous researches in the field of the SCIM's rotor temperature estimation and could be effective to find the novel methods with more advantages and less drawbacks in the future. [ABSTRACT FROM AUTHOR]

The condition monitoring of the rotor bar in the squirrel cage induction motors (SCIMs) is performed with various contact methods and non-contact methods. The various contact methods are zero sequence current spectrum measurement, non-uniform time resampling of current, motor current spectrum analysis, vibration measurement, etc. Non-contact methods are infrared thermography, stray flux measurement, acoustic emission measurement, temperature measurement, etc. The contact methods execute via vibration, instantaneous frequency, rotor speed and flux signal analysis. Whereas, non-contact method accomplishes via acoustic, current, temperature and stray flux measurement. The existing methods suffer from the influence of adjoining machines, surrounding environmental changes; require human expertise to mount sensors and analysing the signals. In this paper, a novel low-cost and non-invasive method proposed for rotor bar fault identification in SCIMs with Software Phase Locked Loop (SPLL). The proposed method uses a high-frequency signal projected on the motor and the reflected signal captured. The captured signal analysed by Fast Fourier Transform (FFT) and Wavelet transforms to identify the fault. The performance of these transforms compared in term of accuracy to identify the rotor bar faults of SCIM. The experimental results show that the proposed method achieves better accuracy than the existing methods.. [ABSTRACT FROM AUTHOR]

EVs (Electric Vehicles) have been rejuvenated over the last decades while the motor drive technologies are still evolving. This paper provides a review of electrical motor drive technologies used in EV applications, with a performance comparison of candidate machines and their drive topologies. EV applications demand high efficiency, high torque density, high reliability, and wide speed range while reducing weight, complexity, total costs and environmental impact. In the literature, DC (Direct Current) motors, IMs (Induction Motors) and PM (Permanent Magnet) motors can be generally found in marketplace whilst RMs (Reluctance Motors) have been researched for some time and are nearing commercial availability. This paper evaluates the performance of these four main types of electrical motor drives for EV propulsion applications using analytical methods. PM motors may offer the best performance in terms of torque density and compactness but the cost is the highest (primarily dominated by rare-earth permanent magnets), limiting their widespread application in mass production EVs. DC motors have their own merits but suffer from limited power density and necessity for maintenance. Induction motor drives are a mature and proven technology. In particular, squirrel-cage IMs are robust, reliable and inexpensive, striking a balance between system cost and complexity, power density and extended speed range. Reluctance motors can provide a good torque density and cost effective EV drive solutions. Their drawbacks can also be overcome by the use of power electronic converters and advanced control strategies. Induction and reluctance motor drives are well suited for cost sensitive mass production EV applications. Looking to the future, increased hybridization may be a way forward in industry which combines attractive features of different electrical machines and control algorithms and still offer much promise in performance and total cost. At last, reliability study on EVs requires historical information and driving patterns, demanding research expertise in eco-sociology, human behaviors as well as human-machine interface. [ABSTRACT FROM AUTHOR]

Detection of broken rotor bars has been an important but difficult job in the detection area of induction motor faults. The characteristic frequency component of a faulty rotor in the stator current spectrum is very close to the power frequency component but by far less in amplitude, which brings about great difficulty for accurate detection, In this paper a new detection technique based on the α, β instantaneous active power signature analysis is proposed for the diagnosis of rotor cage faults in operating squirrel cage three-phase induction motors (IMs). Experimental results are presented to show the merits of this novel approach. [ABSTRACT FROM AUTHOR]

This study addresses the detection of air-gap eccentricity based on hearing damage in 5 hp induction machines. The faulty condition of the bearing is caused by accelerated aging processes in seven aging cycles. For the faulty case, the spectra of vibration signals are computed for initial and final aging processes under 100% load condition. Subsequently, the spectra of the current signals for a single phase are also obtained for the initial and aged cases and cross-power spectral coherences between the vibration and current signals are computed [ABSTRACT FROM PUBLISHER]