Deep learning has advanced machinery fault diagnosis, yet performance remains constrained by scarce and imbalanced labeled vibration data. We present ACS-DM, an adaptive conditional sampling diffusion framework that synthesizes frequency-faithful yet temporally diverse signals for few-shot regimes. ACS-DM couples a Nested U-Net denoiser with 1D Omni-Dimensional dynamic convolution and shuffle attention to capture multiscale temporal–spectral patterns while reducing parameters by 15–20% without loss of fidelity. Lightweight conditioning via classifier-free guidance and time-step embeddings steers generation toward class-discriminative attributes without auxiliary classifiers. Trained with the standard DDPM noise-prediction objective, ACS-DM is evaluated under 5/10/20-shot settings on CWRU, PU, and a field BJTU-RAO metro-bogie dataset. Classifiers trained solely on ACS-DM-augmented datasets and tested on held-out real signals achieve consistent gains. In the experiments on the PU dataset, with five real samples per class, accuracy reaches 98.8% under our configurations. The synthesized signals preserve diagnostic spectral characteristics while maintaining time-domain diversity, yielding robust generalization across machines and operating conditions and offering a practical route to mitigate scarcity and imbalance in industrial fault diagnosis.
BatzolisGStanczukJSchönliebC-B, et al. (2021) Conditional image generation with score-based diffusion models. Available at:. https://arxiv.org/abs/2111.13606
2.
ChenYQiangYChenJ, et al. (2024) FMRGAN: feature mapping reconstruction GAN for rolling bearings fault diagnosis under limited data condition. IEEE Sensors Journal24(15): 25116–25131.
3.
DingAQinYWangB, et al. (2024) Evolvable graph neural network for system-level incremental fault diagnosis of train transmission systems. Mechanical Systems and Signal Processing210: 111175.
4.
DingPZhangCZhangJ, et al. (2025) Frequency diffusion-based vibration signal generation for machinery fault identification under limited data. Structural Health Monitoring, Epub ahead of print September 2025. DOI: 10.1177/14759217251378244.
5.
FajardoVAFindlayDJaiswalC, et al. (2020) On oversampling imbalanced data with deep conditional generative models. Expert Systems with Applications169: 114463.
6.
FuWYangKWenB, et al. (2024) Rotating machinery fault diagnosis with limited multisensor fusion samples by fused attention-guided wasserstein GAN. Symmetry16(3): 285.
7.
FuZLiuZPingS, et al. (2024) TRA-ACGAN: a motor bearing fault diagnosis model based on an auxiliary classifier generative adversarial network and transformer network. ISA Transactions149: 381–393.
8.
GaoXDengFYueX (2019) Data augmentation in fault diagnosis based on the Wasserstein generative adversarial network with gradient penalty. Neurocomputing396: 487–494.
9.
GaoHZhangXGaoX, et al. (2023) ICOT-GAN: Integrated convolutional transformer GAN for rolling bearings fault diagnosis under limited data condition. IEEE Transactions on Instrumentation and Measurement72: 1–14.
10.
GuoZYinQWangT, et al. (2025) Mechanism-constrained decomposition diffusion network for compound bearing fault diagnosis in rotating machinery. Measurement Science and Technology36(6): 066133.
HuangYWenBLiaoW, et al. (2024) Image enhancement based on dual-branch generative adversarial network combining spatial and frequency domain information for imbalanced fault diagnosis of rolling bearing. Symmetry16(5): 512.
KhanAHwangHKimHS (2021) Synthetic data augmentation and deep learning for the fault diagnosis of rotating machines. Mathematics9(18): 2336.
15.
KongZPingWHuangJ, et al. (2020) DiffWave: a versatile diffusion model for audio synthesis. Available at:. https://arxiv.org/abs/2009.09761
16.
LessmeierCKimothoJKZimmerD, et al. (2016) ConDition monitoring of bearing damage in electromechanical drive systems by using motor current signals of electric motors: a benchmark data set for data-driven classification. PHM Society European Conference3(1): 05–08.
17.
LiXiangLiXuHuiMa (2020) Deep representation clustering-based fault diagnosis method with unsupervised data applied to rotating machinery. Mechanical Systems and Signal Processing143(106825).
18.
LiYShiZLiuC, et al. (2021) Augmented time regularized generative adversarial network (ATR-GAN) for data augmentation in online process anomaly detection. IEEE Transactions on Automation Science and Engineering19(4): 3338–3355.
LiXYueCLiuX, et al. (2023) ACWGAN-GP for milling tool breakage monitoring with imbalanced data. Robotics and Computer-Integrated Manufacturing85: 102624.
21.
LiCLiSFengY, et al. (2024) Small data challenges for intelligent prognostics and health management: a review. Artificial Intelligence Review57(8): 214.
22.
LiJWeiYGuX (2024) MTC-GAN bearing fault diagnosis for small samples and variable operating conditions. Applied Sciences14(19): 8791.
23.
LuSHeQWangJ (2018) A review of stochastic resonance in rotating machine fault detection. Mechanical Systems and Signal Processing116: 230–260.
24.
MuellerPN (2024) Attention-enhanced conditional-diffusion-based data synthesis for data augmentation in machine fault diagnosis. Engineering Applications of Artificial Intelligence131: 107696.
25.
NicholADhariwalPRameshA, et al. (2021) GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. Available at:. https://arxiv.org/abs/2112.10741
26.
PingZWangDZhangY, et al. (2025) Few-shot aero-engine bearing fault diagnosis with denoising diffusion based data augmentation. Neurocomputing622: 129327.
27.
RameshADhariwalPNicholA, et al. (2022) Hierarchical text-conditional image generation with CLIP latents. Available at:. https://arxiv.org/abs/2204.06125
28.
RombachRBlattmannALorenzD, et al. (2021) High-resolution image synthesis with latent diffusion models. Available at:. https://arxiv.org/abs/2112.10752
29.
SahariaCChanWSaxenaS, et al. (2022) Photorealistic text-to-image diffusion models with deep language understanding. Available at:. https://arxiv.org/abs/2205.11487
30.
ShaoHLaiYLiuH, et al. (2025) LSFConvformer: a lightweight method for mechanical fault diagnosis under small samples and variable speeds with time-frequency fusion. Mechanical Systems and Signal Processing236: 113016.
31.
SmithWARandallRB (2015) Rolling element bearing diagnostics using the case Western reserve university data: a benchmark study. Mechanical Systems and Signal Processing64–65: 100–131.
Sohl-DicksteinJWeissEAMaheswaranathanN, et al. (2015) Deep unsupervised learning using nonequilibrium thermodynamics. Available at:. https://arxiv.org/abs/1503.03585
34.
SunSHuXLiuY (2021) An imbalanced data learning method for tool breakage detection based on generative adversarial networks. Journal of Intelligent Manufacturing33(8): 2441–2455.
35.
SunDFanYWangG (2024) Enhancing fault diagnosis in industrial processes through adversarial task augmented sequential meta-learning. Applied Sciences14(11): 4433.
36.
WangHLiPLangX, et al. (2023) FTGAN: a novel GAN-based data augmentation method coupled time–frequency domain for imbalanced bearing fault diagnosis. IEEE Transactions on Instrumentation and Measurement72: 1–14.
37.
WangHZhangWHanC, et al. (2024) A bearing fault diagnosis method with an improved residual Unet diffusion model under extreme data imbalance. Measurement Science and Technology35(4): 046113.
38.
XiaoYShaoHLiuB (2025) Evaluating calibration of deep fault diagnostic models under distribution shift. Computers in Industry171: 104334.
39.
YanSShaoHLongZ, et al. (2025) Incremental few-shot fault diagnosis with cosine-represent real-time evolved network of transmission systems. IEEE Transactions on Transportation Electrification11(4): 9544–9554.
40.
YangXLiuBXiangL, et al. (2022) A novel intelligent fault diagnosis method of rolling bearings with small samples. Measurement203: 111899.
41.
YiHHouLJinY, et al. (2024) Time series diffusion method: a denoising diffusion probabilistic model for vibration signal generation. Mechanical Systems and Signal Processing216: 111481.
42.
ZhangQ-LYangY-B (2021) SA-Net: Shuffle attention for deep convolutional neural networks. In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing, Toronto, Canada, 6–11 June 2021, 2235–2239.
43.
ZhangPLinYCuiH, et al. (2024) Channel attention-based conditional diffusion model applied to fault diagnosis under imbalanced data. Electronics13(23): 4807.
44.
ZhangTLinJJiaoJ, et al. (2024) An interpretable latent denoising diffusion probabilistic model for fault diagnosis under limited data. IEEE Transactions on Industrial Informatics20(8): 10354–10365.
45.
ZhaoZLiTWuJ, et al. (2020) Deep learning algorithms for rotating machinery intelligent diagnosis: an open source benchmark study. ISA Transactions107: 224–255.
