School of Reliability and Systems Engineering, Beihang University, Beijing 100191, China.
School of Mechanical Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi 710049, China.
Neural Netw. 2022 Jan;145:331-341. doi: 10.1016/j.neunet.2021.11.003. Epub 2021 Nov 11.
Driven by industrial big data and intelligent manufacturing, deep learning approaches have flourished and yielded impressive achievements in the community of machine fault diagnosis. Nevertheless, current diagnosis models trained on a specific dataset seldom work well on other datasets due to the domain discrepancy. Recently, adversarial domain adaptation-based approaches have become an emerging and compelling tool to address this issue. Nonetheless, existing methods still have a shortcoming since they cannot guarantee sufficient feature similarity between the source domain and the target domain after adaptation, resulting in unguaranteed performance. To this end, a Cycle-consistent Adversarial Adaptation Network (CAAN) is advanced to realize more effective fault diagnosis of machinery. In CAAN, specifically, an adversarial game formed by the feature extractor and the domain discriminator is constructed to induce transferable feature learning. Meanwhile, the feature translators and discriminators between source and target domains are further designed to build a more comprehensive cycle-consistent generative adversarial constrain, which can more reliably ensure domain-invariant and class-separate characteristics of learned features. Extensive experiments constructed on three datasets from different mechanical systems demonstrate the effectiveness and superiority of CAAN.
在工业大数据和智能制造的推动下，深度学习方法在机器故障诊断领域蓬勃发展，取得了令人瞩目的成果。然而，由于领域差异，当前在特定数据集上训练的诊断模型很少能在其他数据集上很好地工作。最近，基于对抗性域自适应的方法已成为解决这一问题的新兴有力工具。然而，现有的方法仍然存在一个缺点，因为在适应后它们不能保证源域和目标域之间有足够的特征相似性，从而导致不可靠的性能。为此，提出了一种循环一致的对抗性自适应网络（CAAN），以实现更有效的机器故障诊断。在 CAAN 中，具体来说，通过特征提取器和域鉴别器构建对抗性博弈，以诱导可转移的特征学习。同时，还进一步设计了源域和目标域之间的特征翻译器和鉴别器，以构建更全面的循环一致生成对抗约束，从而更可靠地保证学习特征的域不变性和类别可分性。在来自不同机械系统的三个数据集上构建的广泛实验证明了 CAAN 的有效性和优越性。
