Multiple Fault Detection in Induction Motors through Homogeneity and Kurtosis Computation

Martinez-Herrera, Ana L.; Ferrucho-Alvarez, Edna R.; Ledesma-Carrillo, Luis M.; Mata-Chavez, Ruth I.; Lopez–Ramirez, Misael; Cabal-Yépez, Eduardo

doi:10.3390/en15041541

Cited by 30 publications

(22 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is possible in some cases to not be able to ensure treatment in a steady state, in particular, when the load or the speed varies in time. In this case, as shown in [ 15 ], it is necessary to analyse a non-stationary signal. This represents perspectives on the work present in this article.…”

Section: Discussionmentioning

confidence: 99%

“…In some cases, the analysis needs more tools and techniques, such as the Hilbert transform [ 1 ], kurtosis selection of sub-bands [ 13 ], autogram selection of sub-bands [ 14 ], other than a simple Fourier transform. In recent works [ 15 ], the approach is based on the analysis of the startup transient current signal through the current signal homogeneity and the fourth central moment (kurtosis) analysis.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparative Study between Physics-Informed CNN and PCA in Induction Motor Broken Bars MCSA Detection

Boushaba

Cauët

Chamroo

et al. 2022

Sensors

View full text Add to dashboard Cite

In this article, two methods for broken bar detection in induction motors are considered and tested using data collected from the LIAS laboratory at the University of Poitiers. The first approach is Motor Current Signature Analysis (MCSA) with Convolutional Neural Networks (CNN), in which measurements have to be processed in the frequency domain before training the CNN to ensure that the resulting model is physically informed. A double input CNN has been introduced to perform a 100% detection regardless of the speed and load torque value. A second approach is the Principal Components Analysis (PCA), in which the processing is undertaken in the time domain. The PCA is applied on the induction motor currents to eventually calculate the Q statistic that serves as a threshold for detecting anomalies/faults. Even if obtained results show that both approaches work very well, there are major differences that need to be pointed out, and this is the aim of the current paper.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Comparative Study between Physics-Informed CNN and PCA in Induction Motor Broken Bars MCSA Detection

Boushaba

Cauët

Chamroo

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…They collect 2000 samples of both 20 kHz sampling rate and 5 kHz sampling rate, and they vary the proportion of test to train ratios. The authors also tried with different pump speed pairs (30)(31)(32)(33)(34)(35)(36)(37)(38)(39)(40)(40)(41)(42)(43)(44)(45)(46)(47)(48)(49)(50)etc) to test intermediate speeds as an alternative option in case no specific fault data are available. Finally, the final obtained test classification accuracy for the same speed training/testing is 83.2% which gets worse if based on a different speed instead or gets better if more resolution is used [32].…”

Section: Machine Learning Methods 1) Non-deep Learningmentioning

confidence: 99%

“…There are five types of cavitation: vaporization, turbulence, vane syndrome, internal recirculation, air aspiration cavitation [8]. According to [35], if run for a long period of time, the cavitation also creates unsteady flow that causes following internal surfaces' failure such as volute, bearing, shaft, seal and etc.…”

Section: D: Cavitationmentioning

confidence: 99%

Review of Machine Learning Based Fault Detection for Centrifugal Pump Induction Motors

2022

View full text Add to dashboard Cite

Centrifugal pumps are an integral part of many industrial processes and are used extensively in water supply, sewage, heating and cooling systems. While there are several review papers on machine learning-based fault diagnosis on induction motors, its application to centrifugal pumps has received relatively little attention. This work attempts to summarize and review recent research and development in machine learning-based pump condition monitoring and fault diagnosis. The paper starts with a brief explanation of pump operation including common pump faults and the main principles of the motor current signature analysis (MCSA) method. This is followed by a detailed explanation of various machine learning-based methods including the types of detected faults, experimental details and reported accuracies. The performances of different approaches are then presented systematically in a unified table. Finally, the authors discuss practical aspects and challenges related to data collection, storage and real-world implementation.

show abstract

“…The unbalanced supply voltage and inter-turns short circuits are studied in [18] through thermal behavior of the motors. The analysis of supply current signals under faulty condition of specific number of rotor bars as time-frequency features is commonly used in recent work [19].…”

Section: Introductionmentioning

confidence: 99%

Faults Feature Extraction Using Discrete Wavelet Transform and Artificial Neural Network for Induction Motor Availability Monitoring—Internet of Things Enabled Environment

Zuhaib¹,

Shaikh²,

Tanweer³

et al. 2022

Energies

View full text Add to dashboard Cite

This paper presents the high contact resistance (HCR) and rotor bar faults by an extraction method for an induction motor using Discrete Wavelet Transform (DWT) and Artificial Neural Network (ANN). The root mean square (RMS) and mean features are obtained using DWT, and ANN is used for classification using activation functions. Activation provides output by assigning the specific input with respect to the transfer function according to the nature and type of the activation function. Method: The faulty conditions are induced using MATLAB by adopting the motor current signature analysis (MCSA) method to achieve current signature signals of the healthy and faulty motors. Results: The DWT technique has been applied to obtain fault-specific features of the average continuously varying signal (RMS) and an average of the data points (mean) at levels 5, 7, 8, and 9, followed by ANN to classify the faults for condition monitoring. Utility: The utility of the results is to reduce unscheduled downtime in the industry, thus saving revenue and reducing production losses. This work will help provide support to ensure early indication of faults in induction motors under operating conditions, enabling in-service engineers to take timely preventive measures as part of the availability of resources in IoT-enabled systems. Application: Resource availability and cybersecurity are becoming vital in an environment that supports the Internet of Things (IoT) as the essential components of Industry 4.0 scenarios. The novelty of this research lies in the implementation of high contact resistance and rotor bar faults using DWT and ANN with different activation functions to achieve accuracy up to 98%.

show abstract

Multiple Fault Detection in Induction Motors through Homogeneity and Kurtosis Computation

Cited by 30 publications

References 34 publications

Comparative Study between Physics-Informed CNN and PCA in Induction Motor Broken Bars MCSA Detection

Comparative Study between Physics-Informed CNN and PCA in Induction Motor Broken Bars MCSA Detection

Review of Machine Learning Based Fault Detection for Centrifugal Pump Induction Motors

Faults Feature Extraction Using Discrete Wavelet Transform and Artificial Neural Network for Induction Motor Availability Monitoring—Internet of Things Enabled Environment

Contact Info

Product

Resources

About