基于IDANN的跨工况齿轮箱故障诊断

PDF(1823 KB)

振动与冲击 ›› 2025, Vol. 44 ›› Issue (9) : 282-289.

故障诊断分析

基于IDANN的跨工况齿轮箱故障诊断

赵玲*，邹杰，秦佳继，王航

作者信息 +

Fault diagnosis of cross-condition gearbox based on IDANN

ZHAO Ling*, ZOU Jie, QIN Jiaji, WANG Hang

Author information +

文章历史 +

摘要

迁移学习的方法在解决齿轮箱无监督故障诊断问题上取得了极大的进展。然而，由于齿轮箱数据分布差异、噪声和干扰以及模型的局限性影响，大多方法在面对复杂的齿轮箱数据集迁移效果不佳，同时对于网络输入的可解释性研究仍然很少。本文提出了一种改进的域对抗网络（Improve Domain-Adversarial Neural Network, IDANN）。首先使用改进的时频网络作为特征提取器，在信号输入网络的时候提供可解释性和降噪功能，然后在域对抗网络中添加目标域的类级对齐方法，使用两个分类器来检测靠近决策边界的目标样本，以增强迁移性能。在东南大学齿轮箱和跨座式单轨齿轮箱数据集上验证了IDANN的有效性和可靠性，并在凯斯西储大学轴承数据集上测试IDANN在噪声条件下的性能，实验证明IDANN具有优秀的诊断性能和鲁棒性。

Abstract

The transfer learning method has made great progress in solving the problem of unsupervised fault diagnosis of gearbox. However, due to the differences in the distribution of gearbox data, noise and interference, and the limitations of the model, most of the methods are not effective in migrating complex gearbox datasets, and there are still few studies on the interpretability of network inputs. In this paper, we propose an improved domain-adversarial neural network (IDANN). The improved time-frequency network is used as a feature extractor to provide interpretability and noise reduction when the signal is fed into the network, and then the class-level alignment method of the target domain is added to the domain adversarial network, and two classifiers are used to detect the target samples close to the decision boundary to enhance the migration performance. The effectiveness and reliability of IDANN are verified on the Southeast University gearbox dataset and straddle-type monorail gearbox, and the performance of IDANN under noise conditions is tested on the Case Western Reserve University bearing dataset, and the experimental results show that IDANN has excellent diagnostic performance and robustness.

导出引用

赵玲, 邹杰, 秦佳继, 王航. 基于IDANN的跨工况齿轮箱故障诊断[J]. 振动与冲击, 2025, 44(9): 282-289

ZHAO Ling, ZOU Jie, QIN Jiaji, WANG Hang. Fault diagnosis of cross-condition gearbox based on IDANN[J]. Journal of Vibration and Shock, 2025, 44(9): 282-289

参考文献

[1] Li Tianfu, Zhao Zhibin, Sun Chuang, et al. WaveletKernelNet: An interpretable deep neural network for industrial intelligent diagnosis[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2021, 52(4): 2302-2312.
[2] Yuan Jing, Cao Shuwei, Ren Gangxing, et al. LW-Net: an interpretable network with smart lifting wavelet kernel for mechanical feature extraction and fault diagnosis[J]. Neural Computing and Applications, 2022, 34(18): 15661-15672.
[3] Dai Le, Guo Junyu, Wan Jia-Lun, et al. A reliability evaluation model of rolling bearings based on WKN-BiGRU and Wiener process[J]. Reliability Engineering & System Safety, 2022, 225: 108646.
[4] Wang Dong, Chen Yikai, Shen Changqing, et al. Fully interpretable neural network for locating resonance frequency bands for machine condition monitoring[J]. Mechanical Systems and Signal Processing, 2022, 168: 108673.
[5] Wang Huan, Liu Zhiliang, Peng Dandan, et al. Interpretable convolutional neural network with multilayer wavelet for Noise-Robust Machinery fault diagnosis[J]. Mechanical Systems and Signal Processing, 2023, 195: 110314.
[6] Zhou Kai, Diehl Edward, Tang Jiong. Deep convolutional generative adversarial network with semi-supervised learning enabled physics elucidation for extended gear fault diagnosis under data limitations[J]. Mechanical Systems and Signal Processing, 2023, 185: 109772.
[7] Brito Lucas C, Susto Gian Antonio, Brito Jorge N, et al. An explainable artificial intelligence approach for unsupervised fault detection and diagnosis in rotating machinery[J]. Mechanical Systems and Signal Processing, 2022, 163: 108105.
[8] Xia Jingyan, Huang Ruyi, Chen Zhunyun, et al. A novel digital twin-driven approach based on physical-virtual data fusion for gearbox fault diagnosis[J]. Reliability Engineering & System Safety, 2023, 240: 109542.
[9] Wang Haitao, Dai Xiyang, Shi Lichen, et al. Data-Augmentation Based CBAM-ResNet-GCN Method for Unbalance Fault Diagnosis of Rotating Machinery[J]. IEEE Access, 2024.
[10] Dai Baorui, Frusque Gaetan, Li Tianfu, et al. Smart filter aided domain adversarial neural network for fault diagnosis in noisy industrial scenarios[J]. Engineering Applications of Artificial Intelligence, 2023, 126: 107202.
[11] Zhao Zhibin, Zhang Qiyang, Yu Xiaolei, et al. Applications of unsupervised deep transfer learning to intelligent fault diagnosis: A survey and comparative study[J]. IEEE Transactions on Instrumentation and Measurement, 2021,70:1-28.
[12] 王鹏,李丹青,王恒. 基于改进交替迁移学习的滚动轴承故障诊断算法 [J]. 振动与冲击, 2024, 43 (05): 239-249.
Wang Peng, Li Danqing, Wang Heng. Rolling bearing fault diagnosis algorithm based on improved alternating transfer learning [J]. Journal of Vibration and Shock. 2024, 43 (05): 239-249.
[13] 姜烨飞,王华,潘裕斌,等.基于GADF-MDSC的特大型轴承深度迁移故障诊断方法[J].振动与冲击,2024,43(19):10-18.
Jiang Yefei, Wang Hua, Pan Yunbin, et al. Deep transfer fault diagnosis method for extra-large bearings based on GADF-MDSC[J]. Journal of Vibration and Shock. 2024,43(19):10-18.
[14] Zheng Bo, Huang Jianhao, Ma Xin, et al. An unsupervised transfer learning method based on SOCNN and FBNN and its application on bearing fault diagnosis[J]. Mechanical Systems and Signal Processing, 2024, 208: 111047.
[15] Tang Guiting, Yi Cai, Liu Lei, et al. Integrating adaptive input length selection strategy and unsupervised transfer learning for bearing fault diagnosis under noisy conditions[J]. Applied Soft Computing, 2023, 148: 110870.
[16] Shang Zuogang, Zhao Zhibin, Yan Ruqiang. Denoising fault-aware wavelet network: A signal processing informed neural network for fault diagnosis[J]. Chinese Journal of Mechanical Engineering, 2023, 36(1): 9.
[17] 王海涛,郭一帆,史丽晨. 基于SC-ResNeSt及频域格拉姆角场的滚动轴承故障诊断方法 [EB/OL]. (2023-02-08).．https://kns.cnki.net/kcms/detail//11.5946.TP.20230207.1619.002.html.
[18] He Kaiming, Zhang Xianyu, Ren Shaoqing, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770-778.
[19] Chen Qian, Dong Xingjian, Tu Guowei, et al. TFN: An interpretable neural network with time-frequency transform embedded for intelligent fault diagnosis[J]. Mechanical Systems and Signal Processing, 2024, 207: 110952.
[20] Ganin Yaroslav, Ustinova Evgeniya, Ajakan Hana, et al. Domain-adversarial training of neural networks[J]. Journal of machine learning research, 2016, 17(59): 1-35.
[21] He Chao, Shi Hongmei, Si Jin, et al. Physics-informed interpretable wavelet weight initialization and balanced dynamic adaptive threshold for intelligent fault diagnosis of rolling bearings[J]. Journal of Manufacturing Systems, 2023, 70: 579-592.
[22] Huo Chunran, Jiang Quansheng, Shen Yehu, et al. A class-level matching unsupervised transfer learning network for rolling bearing fault diagnosis under various working conditions[J]. Applied Soft Computing, 2023, 146: 110739.
[23] Jiao Jinyang, Lin Jing, Zhao Ming, et al. Double-level adversarial domain adaptation network for intelligent fault diagnosis[J]. Knowledge-Based Systems, 2020, 205: 106236.
[24] Lee Chen-Yu, Batra Tanmay, Baig Mohammad Haris, et al. Sliced wasserstein discrepancy for unsupervised domain adaptation[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019: 10285-10295.
[25] Shao Siyu, McAleer Stephen, Yan Ruqiang, et al. Highly accurate machine fault diagnosis using deep transfer learning[J]. IEEE Transactions on Industrial Informatics, 2018, 15(4): 2446-2455.