Xue Fangyong, Liu Chang, He Feifei, Bai Zeping
Key Laboratory of Advanced Equipment Intelligent Manufacturing Technology of Yunnan Province, Kunming University of Science &Technology, Kunming 650500, China.
Faculty of Mechanical & Electrical Engineering, Kunming University of Science &Technology, Kunming 650500, China.
Sensors (Basel). 2025 Aug 21;25(16):5190. doi: 10.3390/s25165190.
Although contact-based vibration signal methods for mechanical equipment fault diagnosis demonstrate superior performance, their practical deployment faces significant limitations. In contrast, acoustic signals offer notable deployment flexibility due to their non-contact nature. However, acoustic diagnostic methods are susceptible to environmental noise interference, and fault samples are typically scarce, leading to insufficient model generalization capability and robustness. To address this, this paper proposes an acoustic-vibration feature fusion strategy based on heterogeneous transfer learning, further integrated with a knowledge distillation framework. By doing so, it aims to achieve efficient transfer of vibration diagnostic knowledge to acoustic models. In the proposed approach, a teacher model learns diagnostic knowledge from highly reliable vibration signals and uses this to guide the training of a student model on acoustic signals. This process significantly enhances the diagnostic capability of the acoustic-based student model. Experimental studies conducted on a custom-built test rig and public datasets demonstrate that the proposed method exhibits excellent diagnostic accuracy and robustness under unseen working conditions.
尽管基于接触的振动信号方法在机械设备故障诊断中表现出卓越性能，但其实际应用面临重大限制。相比之下，声学信号因其非接触特性而具有显著的部署灵活性。然而，声学诊断方法易受环境噪声干扰，且故障样本通常稀缺，导致模型泛化能力和鲁棒性不足。为解决这一问题，本文提出一种基于异构迁移学习的声振特征融合策略，并进一步集成知识蒸馏框架。通过这样做，旨在实现振动诊断知识向声学模型的高效迁移。在所提出的方法中，教师模型从高度可靠的振动信号中学习诊断知识，并以此指导学生模型对声学信号的训练。这一过程显著提高了基于声学的学生模型的诊断能力。在定制测试平台和公共数据集上进行的实验研究表明，该方法在未知工作条件下具有出色的诊断准确性和鲁棒性。
