Zhong Zhidan, Xie Hao, Wang Zhenxin, Zhang Zhihui
School of Mechanical and Electrical Engineering, Henan University of Science and Technology, Luoyang 471023, China.
Sensors (Basel). 2025 Mar 17;25(6):1851. doi: 10.3390/s25061851.
With the improvement in industrial equipment intelligence and reliability requirements, bearing fault diagnosis has become a key technology to ensure the stable operation of mechanical equipment. Traditional bearing fault diagnosis methods are ineffective in diagnosing complex faults and mostly rely on the manual adjustment of hyperparameters. To this end, this paper proposes a domain adversarial migratory learning bearing fault diagnosis model incorporating structural adjustment modules. First, the pre-trained model of the source domain is applied to the target domain dataset through an adversarial domain adaptation technique. Then, the network depth and width are dynamically adjusted in the Optuna optimization framework to accommodate more complex fault types in the target domain. Finally, the performance of the model is further improved by automatically optimizing the hyperparameters. The experimental results show that the model exhibits high accuracy in the diagnosis of different fault types, especially in the face of complex and variable industrial environments, demonstrating strong adaptability and robustness. The method provides an effective solution for fault diagnosis of intelligent devices.
随着工业设备智能化和可靠性要求的提高，轴承故障诊断已成为确保机械设备稳定运行的关键技术。传统的轴承故障诊断方法在诊断复杂故障时效果不佳，且大多依赖于人工调整超参数。为此，本文提出了一种结合结构调整模块的域对抗迁移学习轴承故障诊断模型。首先，通过对抗域适应技术将源域的预训练模型应用于目标域数据集。然后，在Optuna优化框架中动态调整网络深度和宽度，以适应目标域中更复杂的故障类型。最后，通过自动优化超参数进一步提高模型性能。实验结果表明，该模型在不同故障类型的诊断中具有较高的准确率，尤其是在面对复杂多变的工业环境时，展现出强大的适应性和鲁棒性。该方法为智能设备的故障诊断提供了一种有效的解决方案。
