Hei Zhendong, Yang Haiyang, Sun Weifang, Zhong Meipeng, Wang Gonghai, Kumar Anil, Xiang Jiawei, Zhou Yuqing
College of Mechanical and Electrical Engineering, Jiaxing Nanhu University, Jiaxing, China; College of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou, China.
College of Mechanical and Electrical Engineering, Jiaxing Nanhu University, Jiaxing, China; Jiaxing Key Laboratory of Intelligent Manufacturing and Operation & Maintenance of Automotive Parts, Jiaxing, China.
ISA Trans. 2024 Nov;154:352-370. doi: 10.1016/j.isatra.2024.08.027. Epub 2024 Sep 2.
Deep learning has been increasingly used in health management and maintenance decision-making for rotating machinery. However, some challenges must be addressed to make this technology more effective. For example, the collected data is assumed to follow the same feature distribution, and sufficient labeled training data are available. Unfortunately, domain shifts occur inevitably in real-world scenarios due to different working conditions, and acquiring sufficient labeled samples is time-consuming and expensive in complex environments. This study proposes a novel domain adaptive framework called deep Multiscale Conditional Adversarial Networks (MCAN) for machinery fault diagnosis to address these shortcomings. The MCAN model comprises two key components. Constructed by a novel multiscale module with an attention mechanism, the first component is a shared feature generator that captures rich features at different internal perceptual scales, and the attention mechanism determines the weights assigned to each scale, enhancing the model's dynamic adjustment and self-adaptation capabilities. The second component consists of two domain classifiers based on Bidirectional Long Short-Term Memory (BiLSTM) leveraging spatiotemporal features at various levels to achieve domain adaptation in the output space. The deep domain classifier also captures the cross-covariance dependencies between feature representations and classifier predictions, thereby improving the predictions' discriminability. The proposed method has been evaluated using two publicly available fault diagnosis datasets and one condition monitoring experiment. The results of cross-domain transfer tasks demonstrated that the proposed method outperformed several state-of-the-art methods in terms of transferability and stability. This result is a significant step forward in deep learning for health management and maintenance decision-making for rotating machinery, and it has the potential to revolutionize its future application.
深度学习在旋转机械的健康管理和维护决策中得到了越来越广泛的应用。然而，要使这项技术更有效，还必须解决一些挑战。例如，假设收集到的数据遵循相同的特征分布，并且有足够的带标签训练数据。不幸的是，由于工作条件不同，在实际场景中不可避免地会出现域转移，并且在复杂环境中获取足够的带标签样本既耗时又昂贵。本研究提出了一种名为深度多尺度条件对抗网络（MCAN）的新型域自适应框架，用于机械故障诊断，以解决这些缺点。MCAN模型由两个关键组件组成。第一个组件是一个共享特征生成器，由一个带有注意力机制的新型多尺度模块构建，它在不同的内部感知尺度上捕获丰富的特征，注意力机制确定分配给每个尺度的权重，增强了模型的动态调整和自适应能力。第二个组件由两个基于双向长短期记忆（BiLSTM）的域分类器组成，利用不同层次的时空特征在输出空间中实现域自适应。深度域分类器还捕获特征表示与分类器预测之间的交叉协方差依赖性，从而提高预测的可辨别性。所提出的方法已使用两个公开可用的故障诊断数据集和一个状态监测实验进行了评估。跨域转移任务的结果表明，所提出的方法在可转移性和稳定性方面优于几种现有方法。这一结果是深度学习在旋转机械健康管理和维护决策方面向前迈出的重要一步，并且有可能彻底改变其未来应用。
