Sage Journals: Discover world-class research

Abstract

This paper tackles the challenge of accurately diagnosing rolling bearing faults under limited data conditions by introducing an integrated deep learning framework that synergistically combines Temporal Convolutional Networks (TCN), Bidirectional Gated Recurrent Unit (BiGRU), Attention mechanism, and Deep Q-Network (DQN)-based reinforcement learning. Conventional approaches frequently exhibit overfitting and poor generalization when labeled fault data is scarce. To address this limitation, our model leverages TCN’s capacity for parallelized long-term dependency modeling, BiGRU’s capability to capture bidirectional contextual features, and the Attention mechanism’s adaptive feature weighting capability. Unlike traditional methods that rely on static architectures or manual tuning, this study innovatively introduces a Deep Q-Network (DQN) agent as an external controller. This design theoretically enables the dynamic self-optimization of hyperparameters and network structures during training, ensuring robust convergence even under severe data scarcity. Additionally, a reinforcement learning strategy dynamically optimizes hyperparameters and network architecture during training, thereby enhancing convergence and robustness under data scarcity. The framework integrates advanced signal processing techniques, including Variational Mode Decomposition (VMD) for noise-resistant signal decomposition and maximum singular value energy entropy for effective feature fusion. Experimental results on benchmark bearing fault datasets demonstrate that the proposed model achieves a detection rate (DR) exceeding 80% with an error threshold of 0.195 and 90% with an error threshold of 0.2, significantly outperforming comparative models including LVQ, CNN, LSTM, and standalone TCN-BiGRU-Attention. Notably, at a 30% training sample size, the model improves DR by 3.21% and reduces the false alarm rate (FAR) by 4.13% compared to baseline methods. These results validate the method’s efficacy in achieving high diagnostic accuracy and stability under data-limited scenarios, providing a practical solution for intelligent fault diagnosis in industrial applications.

Keywords

rolling bearing fault diagnosis small-sample learning reinforcement learning temporal convolutional network (TCN)attention mechanism

Get full access to this article

View all access options for this article.

References

Cheng

Wang

Chen

, et al. (2019) An improved complementary ensemble empirical mode decomposition with adaptive noise and its application to rolling element bearing fault diagnosis. ISA Transactions 91: 218–234. https://doi.org/10.1016/j.isatra.2019.01.038

Choi

Kim

(2007) Fault detection in a ball bearing system using minimum variance cepstrum. Measurement Science and Technology 18(5): 1433–1440. https://doi.org/10.1088/0957-0233/18/5/031

Dyer

Stewart

(1978) Detection of rolling element bearing damage by statistical vibration analysis. Journal of Mechanical Design 100(2): 229–235. https://doi.org/10.1115/1.3453905

Gan

Wang

Zhu

(2016) Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings. Mechanical Systems and Signal Processing 72: 92–104. https://doi.org/10.1016/j.ymssp.2015.11.014

Han

Pan

(2015) A fault diagnosis method combined with LMD, sample entropy and energy ratio for roller bearings. Measurement 76: 7–19. https://doi.org/10.1016/j.measurement.2015.08.019

Janssens

Slavkovikj

Vervisch

, et al. (2016) Convolutional neural network based fault detection for rotating machinery. Journal of Sound and Vibration 337: 331–341. https://doi.org/10.1016/j.jsv.2016.05.027

Fan

(2019) Fault diagnosis of rolling bearings based on Hilbert resonance demodulation method. Journal of Physics: Conference Series 1168(2): 022100. https://doi.org/10.1088/1742-6596/1168/2/022100

Liu

Yan

Liu

, et al. (2023) Multiscale residual antinoise network via interpretable dynamic recalibration mechanism for rolling bearing fault diagnosis with few samples. IEEE Sensors Journal 23: 31425–31439. https://doi.org/10.1109/jsen.2023.3328007

Liu

Yan

Wang

, et al. (2023) Fault diagnosis of rolling bearing under limited samples using joint learning network based on local-global feature perception. Journal of Mechanical Science and Technology 37: 3409–3425. https://doi.org/10.1007/s12206-023-0607-2

10.

Wang

Qin

, et al. (2017) Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification. Signal Processing 130: 377–388. https://doi.org/10.1016/j.sigpro.2016.07.028

11.

Pandya

Upadhyay

Harsha

(2013) Fault diagnosis of rolling element bearing with intrinsic mode function of acoustic emission data using APF-KNN. Expert Systems with Applications 40(10): 4137–4145. https://doi.org/10.1016/j.eswa.2013.01.033

12.

Ren

Zhu

, et al. (2019) ISVD-based in-band noise reduction approach combined with envelope order analysis for rolling bearing vibration monitoring under varying speed conditions. IEEE Access 7: 32072–32084. https://doi.org/10.1109/access.2019.2902851

13.

Wang

Gao

Song

, et al. (2019) Application of multiscale learning neural network based on CNN in bearing fault diagnosis. Journal of Signal Processing Systems 91: 1205–1217. https://doi.org/10.1007/s11265-019-01461-w

14.

Yang

Qiao

Zhu

, et al. (2023) An intelligent fault diagnosis method enhanced by noise injection for machinery. IEEE Transactions on Instrumentation and Measurement 72: 1–11. https://doi.org/10.1109/tim.2023.3322488

15.

Yang

Qiao

Liu

(2025) Positive-incentive noise in artificial intelligence-enabled machine fault diagnosis. Structural Health Monitoring. 2025:1-15. https://doi.org/10.1177/14759217251370358

16.

Yao

Zhang

Yang

, et al. (2020) Learning attention representation with a multi-scale CNN for gear fault diagnosis under different working conditions. Sensors 20: 1233. https://doi.org/10.3390/s20041233

17.

Zhao

Zhang

(2020) Intelligent fault diagnosis of rolling bearings based on normalized CNN considering data imbalance and variable working conditions. Knowledge-Based Systems 34(10): 359–371.

An integrated deep learning model with reinforcement learning for rolling bearing fault diagnosis under small-sample conditions

Abstract

Keywords

Get full access to this article

References