The operating time of rotating impellers in different faulty conditions is much shorter than its normal operating condition, and obtaining signals of faulty impellers is extremely difficult due to safety and cost. Therefore, the issue of highly imbalanced data between normal and fault status samples of rotating impellers frequently arises, which significantly obstructs the application of intelligent fault recognition and classification models. This paper addresses this challenge by proposing a novel approach that integrates improved denoising diffusion probabilistic models (IDDPM) with improved convolutional neural networks (ICNN) to solve extremely imbalanced data in fault diagnosis. IDDPM is built to synthesize one-dimensional time-domain signals stably to augment the original training set. Meanwhile, a nonlinear denoising strategy and a non-autoregressive network suitable for time-domain signal generation were introduced to enhance the quality of the generated signal. In addition, an ICNN with strong feature extraction and identification capability is designed to classify mixed datasets. The experimental results indicate that the IDDPM stably generates data that closely resembles actual data, and the ICNN can more effectively extract features from the mixed dataset, leading to a significant improvement in fault diagnosis performance. Accordingly, the proposed approach can effectively solve the low accuracy issue in extremely imbalanced data fault diagnosis of rotating impellers.
VashishthaGChauhanSYadavN, et al. A two-level adaptive chirp mode decomposition and tangent entropy in estimation of single-valued neutrosophic cross-entropy for detecting impeller defects in centrifugal pump. Appl Acoust2022; 197: 108905.
2.
LiHHuangQLiS, et al. Study on flow characteristics of a single blade breakage fault in a centrifugal pump. Processes2023; 11(9): 2695.
3.
YuTShuaiZJianJ, et al. Numerical study on hydrodynamic characteristics of a centrifugal pump influenced by impeller-eccentric effect. Eng Fail Anal2022; 138: 106395.
4.
VashishthaGKumarR.Centrifugal pump impeller defect identification by the improved adaptive variational mode decomposition through vibration signals. Eng Res Express2021; 3: 035041.
5.
ZhangYDingJLiY, et al. Multi-modal data cross-domain fusion network for gearbox fault diagnosis under variable operating conditions. Eng Appl Artif Intell2024; 133: 108236.
6.
FengKSmithWRandallR, et al. Vibration-based monitoring and prediction of surface profile change and pitting density in a spur gear wear process. Mech Syst Signal Process2022; 165: 108319.
7.
ZhangYYuKLeiZ, et al. Integrated intelligent fault diagnosis approach of offshore wind turbine bearing based on information stream fusion and semi-supervised learning. Expert Syst Appl2023; 232: 120854.
8.
XuYFengKYanX, et al. CFCNN: a novel convolutional fusion framework for collaborative fault identification of rotating machinery. Inf Fusion2023; 95: 1–16.
9.
ManikandanSDuraiveluK.Vibration-based fault diagnosis of broken impeller and mechanical seal failure in industrial Mono-Block centrifugal pumps using deep convolutional neural network. J Vib Eng Technol2023; 11: 141–152.
10.
FanZLiHCaoH, et al. Research on running status monitoring and rotating blade crack detection of large-scale centrifugal compressor based on blade tip timing technique. IEEE Trans Instrum Meas2023; 72: 3501011.
11.
FanZXuXWangR, et al. CF-HSACNN: a joint anti-noise learning framework for centrifugal fan state recognition. Measurement2022; 202: 111902.
12.
XieTZhangWZhangY, et al. Marine current turbine multifault diagnosis based on optimization resampled modulus feature and 1-D-CNN. IEEE Trans Instrum Meas2023; 72: 3515910.
13.
ZhouKLuNJiangB.Information fusion-based fault diagnosis method using synthetic indicator. IEEE Sens J2023; 23(5): 5124–5133.
14.
ChenZYuWWangL, et al. A Dual-View Style Mixing Network for unsupervised cross-domain fault diagnosis with imbalanced data. Knowl Based Syst2024; 278: 110918.
15.
ShiMDingCWangR, et al. Graph embedding deep broad learning system for data imbalance fault diagnosis of rotating machinery. Reliab Eng Syst Safe2023; 240: 109601.
16.
SunSHuWLiuY, et al. Matching contrastive learning: an effective and intelligent method for wind turbine fault diagnosis with imbalanced SCADA data. Expert Syst Appl2023; 223: 119891.
17.
ZhangTChenJLiF, et al. Intelligent fault diagnosis of machines with small & imbalanced data: a state-of-the-art review and possible extensions. ISA Trans2022; 119: 152–171.
18.
RenZLinTFengK, et al. A systematic review on imbalanced learning methods in intelligent fault diagnosis. IEEE Trans Instrum Meas2023; 72: 3508535.
19.
WangYYaoQKwokJ, et al. Generalizing from a few examples: a survey on few-shot learning. ACM Comput Surv2020; 53(3): 1–34.
20.
ZhangYLiXGaoL, et al. Imbalanced data fault diagnosis of rotating machinery using synthetic oversampling and feature learning. J Manuf Syst2018; 48: 34–50.
21.
XiaoDHuangYQinC, et al. Transfer learning with convolutional neural networks for small sample size problem in machinery fault diagnosis. Proc IMechE, Part C: J Mechanical Engineering Science2019; 233(14): 5131–5143.
22.
PanTChenJXieJ, et al. Deep feature generating network: a new method for intelligent fault detection of mechanical systems under class imbalance. IEEE Trans Ind Inf2021; 17(9): 6282–6293.
23.
GuoQLiYLiuY, et al. Data augmentation for intelligent mechanical fault diagnosis based on local shared multiple-generator GAN. IEEE Sens J2022; 22(10): 9598–9609.
24.
YangSZhouYChenX, et al. Fault diagnosis of wind turbines with generative adversarial network-based oversampling method. Meas Sci Technol2023; 34: 044004.
25.
LiuSJiangHWuZ, et al. Rolling bearing fault diagnosis using variational autoencoding generative adversarial networks with deep regret analysis. Measurement2021; 168: 108371.
26.
ZhaoDLiuSGuD, et al. Enhanced data-driven fault diagnosis for machines with small and unbalanced data based on variational auto-encoder. Meas Sci Technol2020; 31: 035004.
27.
XieYZhangT. Imbalanced learning for fault diagnosis problem of rotating machinery based on generative adversarial networks. In: 37th Chinese control conference, China, Wuhan, 25–27 July 2018, pp.6017–6022. New York: IEEE.
28.
WangRChenZZhangS, et al. Dual-attention generative adversarial networks for fault diagnosis under the class-imbalanced conditions. IEEE Sens J2022; 22(2): 1474–1485.
29.
LiZZhengTWangY, et al. A novel method for imbalanced fault diagnosis of rotating machinery based on generative adversarial networks. IEEE Trans Instrum Meas2021; 70: 3500417.
30.
LiXYueCLiuX, et al. ACWGAN-GP for milling tool breakage monitoring with imbalanced data. Robot Comput Integr Manuf2024; 85: 102624.
31.
LiJLiuTWuX.Research on bearing vibration signal generation method based on filtering WGAN-GP with small samples. Proc IMechE, Part C: J Mechanical Engineering Science2023; 237(20): 4911–4929.
32.
YiHHouLJinY, et al. Time series diffusion method: a denoising diffusion probabilistic model for vibration signal generation. Mech Syst Signal Process2024; 216: 111481.
33.
WangDDongYWangH, et al. Limited fault data augmentation with compressed sensing for bearing fault diagnosis. IEEE Sens J2023; 23(13): 14499–14511.
34.
Sohl-DicksteinJWeissEMaheswaranathanN, et al. Deep unsupervised learning using nonequilibrium thermodynamics. In: 32nd international conference on machine learning, France, Lille, 7–9 July 2015, pp.2256–2265. PMLR.
35.
HoJJainAAbbeelP.Denoising diffusion probabilistic models. In: Proceedings of the 34th international conference on neural information processing systems, Vancouver, BC, Canada, December 2020, pp.6840–6851. Curran Associates Inc.
36.
NicholADhariwalP.Improved denoising diffusion probabilistic models. In: International conference on machine learning, Virtual Event, 18–24 July 2021, pp.8162–8171. Electr network.
37.
SongJMengCErmonS.Denoising diffusion implicit models. In: International conference on learning representations, Vienna, Austria, 3–7 May 2021.
38.
ZhouXZhangYRenZ, et al. DiffDD: a surface defect detection framework with diffusion probabilistic model. Adv Eng Inform2024; 62: 102637.
39.
CroitoruFHondruVLonescuR, et al. Diffusion models in vision: a survey. IEEE Trans Pattern Anal Mach Intell2023; 45(9): 10850–10869.
40.
TashiroYSongJSongY, et al. CSDI: conditional score-based diffusion models for probabilistic time series imputation. In: 35th conference on neural information processing systems, 6–14 December 2021, Electr network.
41.
KongZPingWHuangJ, et al. Diffwave: a versatile diffusion model for audio synthesis. In: International conference on learning representations, 3–7 May 2021, Vienna, Austria.
42.
LimHKimMParkS, et al. Regular time-series generation using SGM. arXiv preprint arXiv:2301.08518, 2023.
43.
ZhangYRenZFengK, et al. Universal source-free domain adaptation method for cross-domain fault diagnosis of machines. Mech Syst Signal Process2023; 191: 110159.
44.
ZhangYJiJRenZ, et al. Digital twin-driven partial domain adaptation network for intelligent fault diagnosis of rolling bearing. Reliab Eng Syst Saf2023; 234: 109186.
45.
HouQLuCChengM, et al. Conv2former: a simple transformer-style convnet for visual recognition. arXiv preprint arXiv:2211.11943, 2022.
46.
ZhengTSongLWangJ, et al. Data synthesis using dual discriminator conditional generative adversarial networks for imbalanced fault diagnosis of rolling bearings. Measurement2020; 158: 107741.
47.
DaiJWangJYaoL, et al. Categorical feature GAN for imbalanced intelligent fault diagnosis of rotating machinery. IEEE Trans Instrum Meas2023; 72: 3525212.
48.
ShaoSYanRBaldiP.Highly accurate machine fault diagnosis using deep transfer learning. IEEE Trans Ind Inf2019; 15(4): 2446–2455.
