This study presents a novel deep neural network–based method for fault detection in induction motors. The focus was on identifying five types of mechanical cases: normal operation, shaft/load breakage, misalignment, mounting bolt looseness, and cooling fan problems. To increase the realism of the results, a laboratory-collected dataset of stereo microphone recordings was augmented with real factory noise. The audio data was transformed into image data using Mel-frequency cepstral coefficients as the feature extraction method and then processed with image-based classifiers. A comparison was made among 12 different networks in terms of accuracy and number of parameters, revealing that Mobilenet_v2, EfficientNetV2B0, and NASNetMobile had the best performance in terms of both network size and accuracy.
BelloIFedusWDuX, et al. (2021) Revisiting ResNets: Improved training and scaling strategies. Advances in Neural Information Processing Systems34: 22614–22627.
2.
ChenWYuMFangM (2021) Research on identification and localization of rotor–stator rubbing faults based on AF-VMD-KNN. Journal of Vibration Engineering and Technologies9: 2213–2228.
CuiLWangXXuY, et al. (2019) A novel switching unscented Kalman filter method for remaining useful life prediction of rolling bearing. Measurement135: 678–684.
5.
DengWZhangSZhaoH, et al. (2018) A novel fault diagnosis method based on integrating empirical wavelet transform and fuzzy entropy for motor bearing. IEEE Access6: 35042–35056.
6.
ErenL (2017) Bearing fault detection by one-dimensional convolutional neural networks. Mathematical Problems in Engineering2017: 8617315.
7.
FaizJEbrahimiBMSharifianMBB (2006) Different faults and their diagnosis techniques in three-phase squirrel-cage induction motors—A review. Electromagnetics26(7): 543–569.
8.
GangsarPTiwariR (2020) Signal based condition monitoring techniques for fault detection and diagnosis of induction motors: A state-of-the-art review. Mechanical Systems and Signal Processing144: 106908.
9.
GlowaczA (2018) Acoustic based fault diagnosis of three-phase induction motor. Applied Acoustics137: 82–89.
10.
GlowaczAGlowaczZ (2017) Diagnosis of stator faults of the single-phase induction motor using acoustic signals. Applied Acoustics117: 20–27.
11.
HeKZhangXRenS, et al. (2016a) Identity mappings in deep residual networks. In: Computer vision–ECCV 2016: 14th European conference, Amsterdam, 11–14 October, pp. 630–645. Berlin: Springer.
12.
HeXWangDLiY, et al. (2016b) A novel bearing fault diagnosis method based on Gaussian restricted Boltzmann machine. Mathematical Problems in Engineering2016: 2957083.
JalayerMOrsenigoCVercellisC (2021) Fault detection and diagnosis for rotating machinery: A model based on convolutional LSTM, fast Fourier and continuous wavelet transforms. Computers in Industry125: 103378.
15.
JiangHLiXShaoH, et al. (2018) Intelligent fault diagnosis of rolling bearings using an improved deep recurrent neural network. Measurement Science and Technology29(6): 065107.
16.
Jiménez-RomeroFGuijo-RubioDLara-RayaF, et al. (2020) Validation of artificial neural networks to model the acoustic behaviour of induction motors. Applied Acoustics166: 107332.
17.
JúniorAMSilvaVVBaccariniLM, et al. (2018) The design of multiple linear regression models using a genetic algorithm to diagnose initial short-circuit faults in 3-phase induction motors. Applied Soft Computing63: 50–58.
18.
KrizhevskyASutskeverIHintonGE (2012) Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems25: 1097–1105.
19.
LiuHZhouJZhengY, et al. (2018) Fault diagnosis of rolling bearings with recurrent neural network-based autoencoders. ISA Transactions77: 167–178.
20.
MaraabaLAl-HamouzZAbidoM (2018) An efficient stator inter-turn fault diagnosis tool for induction motors. Energies11(3): 653.
21.
MaraabaLSMemonAMAbidoM, et al. (2021) An efficient acoustic-based diagnosis of inter-turn fault in interior mount LSPMSM. Applied Acoustics173: 107661.
22.
MengZZhanXLiJ, et al. (2018) An enhancement denoising autoencoder for rolling bearing fault diagnosis. Measurement130: 448–454.
23.
NandiSBharadwajRToliyatH (2002) Performance analysis of a three-phase induction motor under mixed eccentricity condition. IEEE Transactions on Energy Conversion17(3): 392–399.
24.
NeupaneDSeokJ (2020) Bearing fault detection and diagnosis using case Western Reserve university dataset with deep learning approaches: A review. IEEE Access8: 93155–93178.
25.
OrtombinaLTinazziFZigliottoM (2018) Magnetic modeling of synchronous reluctance and internal permanent magnet motors using radial basis function networks. IEEE Transactions on Industrial Electronics65(2): 1140–1148.
26.
PandyaDHUpadhyaySHHarshaSP (2014) Fault diagnosis of rolling element bearing by using multinomial logistic regression and wavelet packet transform. Soft Computing18(2): 255–266.
SaufiSRAhmadZABLeongMS, et al. (2019) Challenges and opportunities of deep learning models for machinery fault detection and diagnosis: A review. IEEE Access7: 122644–122662.
29.
SeeraMLimCPNahavandiS, et al. (2014) Condition monitoring of induction motors: A review and an application of an ensemble of hybrid intelligent models. Expert Systems with Applications41(10): 4891–4903.
30.
ShifatTAHurJW (2021) Ann assisted multi sensor information fusion for BLDC motor fault diagnosis. IEEE Access9: 9429–9441.
TanMLeQ (2019) Efficientnet: Rethinking model scaling for convolutional neural networks. In: International conference on machine learning, pp. 6105–6114. Available at: https://arxiv.org/pdf/1905.11946.pdf
35.
TanMLeQ (2021) Efficientnetv2: Smaller models and faster training. In: International Conference on Machine Learning1: 10096–10106.
36.
TangSShenCWangD, et al. (2018) Adaptive deep feature learning network with Nesterov momentum and its application to rotating machinery fault diagnosis. Neurocomputing305: 1–14.
37.
TranVTYangBSOhMS, et al. (2009) Fault diagnosis of induction motor based on decision trees and adaptive neuro-fuzzy inference. Expert Systems with Applications36(2 Pt 1): 1840–1849.
38.
WenLLiXGaoL, et al. (2018) A new convolutional neural network-based data-driven fault diagnosis method. IEEE Transactions on Industrial Electronics65(7): 5990–5998.
39.
XueYDouDYangJ (2020) Multi-fault diagnosis of rotating machinery based on deep convolution neural network and support vector machine. Measurement156: 107571.
40.
YanKChongAMoY (2020) Generative adversarial network for fault detection diagnosis of chillers. Building and Environment172: 106698.
41.
YiakopoulosCGrylliasKAntoniadisI (2011) Rolling element bearing fault detection in industrial environments based on a k-means clustering approach. Expert Systems with Applications38(3): 2888–2911.
42.
YuJDingBHeY (2018) Rolling bearing fault diagnosis based on mean multigranulation decision-theoretic rough set and non-naive Bayesian classifier. Journal of Mechanical Science and Technology32(11): 5201–5211.
43.
ZhangJTianJLiM, et al. (2023a) A parallel hybrid neural network with integration of spatial and temporal features for remaining useful life prediction in prognostics. IEEE Transactions on Instrumentation and Measurement72: 1–12.
44.
ZhangJZhangKAnY, et al. (2023b) An integrated multitasking intelligent bearing fault diagnosis scheme based on representation learning under imbalanced sample condition. IEEE Transactions on Neural Networks and Learning Systems. Epub ahead of print 6January. DOI: 10.1109/TNNLS.2022.3232147.
