In industrial scenarios, bearing operating conditions are complex and unknown faults may occur unexpectedly, which usually reflect some new modes. This can result in the recognition failure of traditional intelligent algorithms based on the closed set assumption. To address this issue of open set fault diagnosis (OSFD), an OSFD approach of rolling bearing is proposed based on adversarial reciprocal point learning (ARPL) and efficient multi-scale attention (EMA). First, ARPL is introduced to diagnose the bearing faults under open set scenarios, which considers the deep distribution of unknown classes in learners by using an adversarial mechanism, achieving better open set recognition ability. Then, the EMA is employed to improve the open set classification performance of the ARPL model by interacting with information without channel dimensionality reduction. Finally, the effectiveness of the proposed method is evaluated on the bearing datasets. The experimental results show that the proposed ARPL-EMA model can effectively identify the unknown faults and its OSFD performance is superior to the comparative methods.
BendaleABoultT (2016) Towards open set deep networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA, 27–June 30 2016, 1563–1572.
2.
ChenGPengPWangX, et al. (2022) Adversarial reciprocal points learning for open set recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence44(11): 8065–8081.
3.
ChenJWangGLvJ, et al. (2023a) Open-set classification for signal diagnosis of machinery sensor in industrial environment. IEEE Transactions on Industrial Informatics19(3): 2574–2584.
4.
ChenYZhangDZhuK, et al. (2023b) An adaptive activation transfer learning approach for fault diagnosis. IEEE28(5): 2645–2656.
5.
ChenYTaoLLiuX, et al. (2024) Open-Set Fault Recognition and inference for rolling bearing based on open fault semantic subspace. IEEE Transactions on Instrumentation and Measurement73: 1–11.
6.
GengCHuangSChenS (2020) Recent advances in open set recognition: a survey. IEEE Transactions on Pattern Analysis and Machine Intelligence43(10): 3614–3631.
7.
HanTJiangDZhaoQ, et al. (2018) Comparison of random forest, artificial neural networks and support vector machine for intelligent diagnosis of rotating machinery. Transactions of the Institute of Measurement and Control40(8): 2681–2693.
8.
HeDZouXJinZ, et al. (2023) Intelligent fault diagnosis of train bearing based on ISTOA-VMD and SE-WDCNN. Journal of Vibration and Control30(15–16): 3572–3583.
9.
IoffeSSzegedyC (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning, Lille, France, 6 – 11 July 2015, 448–456.
10.
JiaoRLiSDingZ, et al. (2024) Fault diagnosis of rolling bearing based on BP neural network with fractional order gradient descent. Journal of Vibration and Control30(9-10): 2139–2153.
11.
LiJLiuYLiQ (2022) Intelligent fault diagnosis of rolling bearings under imbalanced data conditions using attention-based deep learning method. Measurement189: 110500.
12.
LiuYDengADengM, et al. (2023) Transforming the open set into a pseudo-closed set: a regularized GAN for domain adaptation in open set fault diagnosis. IEEE Transactions on Instrumentation and Measurement72: 1–12.
13.
MeiJZhuMLiuW, et al. (2024) Conditional variational encoder classifier for open set fault classification of rotating machinery vibration signals. IEEE Transactions on Industrial Informatics20: 3038–3049.
14.
MenZLiYTangW, et al. (2024) A new multi-modal time series transformation method and multi-scale convolutional attention network for railway wagon bearing fault diagnosis. Journal of Vibration and Control10775463241276024.
15.
OuyangDHeSZhangG, et al. (2023) Efficient multi-scale attention module with cross-spatial learning. In: ICASSP 2023-2023 IEEE international conference on acoustics, speech and signal processing (ICASSP), Rhodes Island, Greece, 4–10 June 2023: IEEE, 1–5.
16.
PengPLuJXieT, et al. (2022) Open-set fault diagnosis via supervised contrastive learning with negative out-of-distribution data augmentation. IEEE Transactions on Industrial Informatics19(3): 2463–2473.
17.
RenHWangJShenC, et al. (2023) Dual classifier-discriminator adversarial networks for open set fault diagnosis of train bearings. IEEE Sensors Journal23: 22040–22050.
18.
RuddEJainLPScheirerWJ, et al. (2017) The extreme value machine. IEEE Transactions on Pattern Analysis and Machine Intelligence40(3): 762–768.
19.
SunHYangBLinS (2023) An open set diagnosis method for rolling bearing faults based on prototype and reconstructed integrated network. IEEE Transactions on Instrumentation and Measurement72: 1–10.
20.
TangTWangJYangT, et al. (2023) An improved prototypical network with L2 prototype correction for few-shot cross-domain fault diagnosis. Measurement217: 113065.
21.
TianYWangZZhangL, et al. (2018) A subspace learning-based feature fusion and open-set fault diagnosis approach for machinery components. Advanced Engineering Informatics36: 194–206.
22.
TongJLiuCZhengJ, et al. (2023) Multi-sensor information fusion and coordinate attention-based fault diagnosis method and its interpretability research. Engineering Applications of Artificial Intelligence124: 106614.
23.
WangXShiZSunS, et al. (2024) Open-set domain adaptation via feature clustering and separation for fault diagnosis. IEEE Sensors Journal24: 16347–16361.
24.
WuKXuWShuQ, et al. (2024) Unknown-class recognition adversarial network for open set domain adaptation fault diagnosis of rotating machinery. Journal of Intelligent Manufacturing1–19.
25.
XieJLiuJDingT, et al. (2023) Self-attention metric learning based on multi-scale feature fusion for few-shot fault diagnosis. IEEE Sensors Journal23: 19771–19782.
26.
YuXZhaoZZhangX, et al. (2021) Deep-learning-based open set fault diagnosis by extreme value theory. IEEE Transactions on Industrial Informatics18(1): 185–196.
27.
ZhangHPatelVM (2016) Sparse representation-based open set recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence39(8): 1690–1696.
28.
ZhangBZhouCLiW, et al. (2022) Intelligent bearing fault diagnosis based on open set convolutional neural network. Mathematics10(21): 3953.
29.
ZhangZNieGShaoM, et al. (2023a) Multi-sample-distances-fusion-and generalized-Pareto-distribution-based open-set fault diagnosis of rolling bearing. Nonlinear Dynamics111(12): 11407–11428.
30.
ZhangZZhouFZhangC, et al. (2023b) A personalized federated learning-based fault diagnosis method for data suffering from network attacks. Applied Intelligence53(19): 22834–22849.
31.
ZhangYZhangHChenB, et al. (2024) Integrating intrinsic information: a novel open set domain adaptation network for cross-domain fault diagnosis with multiple unknown faults. Knowledge-Based Systems299: 112100.
32.
ZhaoZLiTWuJ, et al. (2020) Deep learning algorithms for rotating machinery intelligent diagnosis: an open source benchmark study. ISA Transactions107: 224–255.
