Accurate fault diagnosis technology is essential for ensuring reliable operation of rotating machinery. However, complex conditions and various damage forms bring challenges to present diagnosis technology. In this study, a novel fault diagnosis method is proposed utilizing the newly developed adaptive resize-residual deep neural networks. The usage of the proposed method consists of three steps. First, the continuous wavelet transform is used to transfer the acquired vibration signals into time–frequency images. Second, the histogram equalization algorithm is applied to enhance the contrast of these images. Finally, the enhanced images are used as the input of newly proposed adaptive resize-residual networks, in which the adaptive resize block can deduce the dimensions of input data by self-learning and feed them into the residual block for pattern recognition. Two experimental cases are designed to evaluate the performance of proposed method. The experimental results indicate that the proposed adaptive resize-residual network obtains superior recognition accuracy and outperforms many state-of-the-art methods.
HanGZhuB. Virtual current coefficients based power transistors fault diagnosis for small power EV-SRM drives. IEEE Trans Transp Electrif2021; 7(4): 2881–2891.
2.
XiaoYXueJLiM, et al. Low-pass filtering empirical wavelet transform machine learning based fault diagnosis for combined fault of wind turbines. Entropy (Basel)2021; 23(8): 975.
3.
ZhangKSuJSunS, et al. Compressor fault diagnosis system based on PCA-PSO-LSSVM algorithm. Sci Prog2021; 104(3): 368504211026110.
4.
HeCWuTGuR, et al. Rolling bearing fault diagnosis based on composite multiscale permutation entropy and reverse cognitive fruit fly optimization algorithm – extreme learning machine. Measurement2021; 173: 108636.
5.
JiDYaoXLiS, et al. Model-free fault diagnosis for autonomous underwater vehicles using sequence convolutional neural network. Ocean Eng2021; 232: 108874.
6.
AhmadiSPourePSaadateS, et al. Open-switch and open-clamping diode fault diagnosis for single-phase five-level neutral-point-clamped inverters. IEEE J Emerging Sel Top Power Electron2021; 9(4): 4676–4686.
7.
ZhangZLiSLuJ, et al. Intrinsic component filtering for fault diagnosis of rotating machinery. Chin J Aeronaut2021; 34(1): 397–409.
8.
ZhengYZhouWYangW, et al. Multivariate/minor fault diagnosis with severity level based on Bayesian decision theory and multidimensional RBC. J Process Control2021; 101: 68–77.
9.
LeeHJeongHKooG, et al. Attention recurrent neural network-based severity estimation method for interturn short-circuit fault in permanent magnet synchronous machines. IEEE Trans Ind Electron2021; 68(4): 3445–3453.
10.
ZhongTQuJFangX, et al. The intermittent fault diagnosis of analog circuits based on EEMD-DBN. Neurocomputing2021; 436: 74–91.
11.
RuanHWangYLiX, et al. A relation-based semi-supervised method for gearbox fault diagnosis with limited labeled samples. IEEE Trans Instrum Meas2021; 70: 1–1.
12.
ShiJHeQWangZ. An LSTM-based severity evaluation method for intermittent open faults of an electrical connector under a shock test. Measurement2021; 173: 108653.
13.
ZhengHLiZChenX. Gear fault diagnosis based on continuous wavelet transform. Mech Syst Signal Process2002; 16(2–3): 447–457.
14.
ChengYLinMWuJ, et al. Intelligent fault diagnosis of rotating machinery based on continuous wavelet transform-local binary convolutional neural network. Knowl Based Syst2021; 216: 106796.
15.
LiYZouLJiangL, et al. Fault diagnosis of rotating machinery based on combination of deep belief network and one-dimensional convolutional neural network. IEEE Access2019; 7: 165710–165723.
16.
ChenXQiXWangZ, et al. Fault diagnosis of rolling bearing using marine predators algorithm-based support vector machine and topology learning and out-of-sample embedding. Measurement2021; 176: 109116.
17.
ShiQZhangH. Fault diagnosis of an autonomous vehicle with an improved SVM algorithm subject to unbalanced datasets. IEEE Trans Ind Electron2021; 68(7): 6248–6256.
18.
SunSZhangTLiQ, et al. Fault diagnosis of conventional circuit breaker contact system based on time–frequency analysis and improved AlexNet. IEEE Trans Instrum Meas2021; 70: 1–12.
19.
WangZHuangHWangY. Fault diagnosis of planetary gearbox using multi-criteria feature selection and heterogeneous ensemble learning classification. Measurement2021; 173: 108654.
20.
WangGZhaoBXiangL, et al. Information interval spectrum: A novel methodology for rolling-element bearing diagnosis. Measurement2021; 183: 109899.
21.
HangJDingSRenX, et al. Integration of interturn fault diagnosis and torque ripple minimization control for direct-torque-controlled SPMSM drive system. IEEE Trans Power Electron2021; 36(10): 11124–11134.
22.
HuangTZhangQTangX, et al. A novel fault diagnosis method based on CNN and LSTM and its application in fault diagnosis for complex systems. Artif Intell Rev2021; 55: 1289–1315.
23.
WenXXuZ. Wind turbine fault diagnosis based on ReliefF-PCA and DNN. Expert Syst Appl2021; 178: 115016.
24.
JiH. Statistics mahalanobis distance for incipient sensor fault detection and diagnosis. Chem Eng Sci2021; 230: 116233.
25.
LeeCKShinYJ. Detection and assessment of I&C cable faults using time–frequency R-CNN-based reflectometry. IEEE Trans Ind Electron2021; 68(2): 1581–1590.
26.
ZhangKWangJShiH, et al. A fault diagnosis method based on improved convolutional neural network for bearings under variable working conditions. Measurement2021; 182: 109749.
27.
WangBLeiYLiN, et al. Multiscale convolutional attention network for predicting remaining useful life of machinery. IEEE Trans Ind Electron2021; 68(8): 7496–7504.
28.
ZhuJHuTJiangB, et al. Intelligent bearing fault diagnosis using PCA–DBN framework. Neural Comput Appl2019; 32(14): 10773–10781.
29.
SunJWenJYuanC, et al. Bearing fault diagnosis based on multiple transformation domain fusion and improved residual dense networks. IEEE Sens J2021; 22(2): 1541–1551.
30.
SunKHuangZMaoH., et al. Multi-scale cluster-graph convolution network with multi-channel residual network for intelligent fault diagnosis. IEEE Trans Instrum Meas2021; 71: 1–12.
31.
ZhaoMTangBDengL, et al. Multiple wavelet regularized deep residual networks for fault diagnosis. Measurement2020; 152: 107331.
32.
WangZLiGYaoL, et al. Data-driven fault diagnosis for wind turbines using modified multiscale fluctuation dispersion entropy and cosine pairwise-constrained supervised manifold mapping. Knowl Based Syst2021; 228: 107276.
33.
WuYJinWLiY, et al. A novel method for simultaneous-fault diagnosis based on between-class learning. Measurement2021; 172: 108839.
34.
XiaoBYinS. A deep learning based data-driven thruster fault diagnosis approach for satellite attitude control system. IEEE Trans Ind Electron2021; 68(10): 10162–10170.
35.
XuLChattertonSPennacchiP. Rolling element bearing diagnosis based on singular value decomposition and composite squared envelope spectrum. Mech Syst Signal Process2021; 148: 107174.
36.
ZhangKJiangBChenF. Multiple-model-based diagnosis of multiple faults with high-speed train applications using second-level adaptation. IEEE Trans Ind Electron2021; 68(7): 6257–6266.
37.
ZouFZhangHSangS, et al. Bearing fault diagnosis based on combined multi-scale weighted entropy morphological filtering and bi-LSTM. Appl Intell2021; 51(10): 6647–6664.
38.
TalebiHMilanfarP. Learning to resize images for computer vision tasks. In: IEEE/CVF international conference on computer vision (ICCV), Montreal, QC, Canada, 2021, pp. 497–506. New York: IEEE.
39.
WangQJinTWangM. A hierarchical minimum hitting set calculation method for multiple multiphase faults in power distribution networks. IEEE Trans Ind Electron2021; 68(1): 4–14.
40.
HanJHYangSLeeBU. A novel 3-D color histogram equalization method with uniform 1-D gray scale histogram. IEEE Trans Image Process2011; 20(2): 506–512.
41.
ZhaoGPangBXuZ, et al. Urban flood susceptibility assessment based on convolutional neural networks. J Hydrol2020; 590: 125235.
42.
ZhangKSunMHanTX, et al. Residual networks of residual networks: multilevel residual networks. IEEE Trans Circuits Syst Video Technol2018; 28(6): 1303–1314.
43.
AlomMZHasanMYakopcicC, et al. Improved inception-residual convolutional neural network for object recognition. Neural Comput Appl2018; 32(1): 279–293.
44.
ShaGRadzienskiMSomanR, et al. Delamination imaging in laminated composite plates using 2D wavelet analysis of guided wavefields. Smart Mater Struct2021; 30(1): 15001.
45.
SbertMAncutiCAncutiCO, et al. Histogram ordering. IEEE Access2021; 9: 28785–28796.
PengHZhuWDengC, et al. Enhancing firefly algorithm with courtship learning. Inf Sci2021; 543: 18–42.
48.
ZhouQLiYTianY, et al. A novel method based on nonlinear auto-regression neural network and convolutional neural network for imbalanced fault diagnosis of rotating machinery. Measurement2020; 161: 107880.
49.
ChenZChenYWuL, et al. Deep residual network based fault detection and diagnosis of photovoltaic arrays using current-voltage curves and ambient conditions. Energy Convers Manage2019; 198: 111793.
50.
WangBLeiYLiN, et al. A hybrid prognostics approach for estimating remaining useful life of rolling element bearings. IEEE Trans Reliab2020; 69(1): 401–412.
