[论文解读] Controlled Generation of Unseen Faults for Partial and Open-Partial Domain Adaptation

Katharina Rombach, Gabriel Michau+1 more|arXiv (Cornell University)|Apr 29, 2022

Machine Fault Diagnosis Techniques被引用 2

一句话总结

本文提出了一种基于Wasserstein GAN的框架，用于在部分域适应（Partial Domain Adaptation）和开放部分域适应（Open-Partial Domain Adaptation）设置下，可控生成未见过的故障特征。在源域与目标域之间仅共享健康数据的情况下，通过条件控制故障类型和严重程度，该方法能够合成逼真且多样化的故障数据，显著提升诊断性能，即使在较大的域偏移下也表现优异。

ABSTRACT

New operating conditions can result in a significant performance drop of fault diagnostics models due to the domain shift between the training and the testing data distributions. While several domain adaptation approaches have been proposed to overcome such domain shifts, their application is limited if the fault classes represented in the two domains are not the same. To enable a better transferability of the trained models between two different domains, particularly in setups where only the healthy data class is shared between the two domains, we propose a new framework for Partial and Open-Partial domain adaptation based on generating distinct fault signatures with a Wasserstein GAN. The main contribution of the proposed framework is the controlled synthetic fault data generation with two main distinct characteristics. Firstly, the proposed methodology enables to generate unobserved fault types in the target domain by having only access to the healthy samples in the target domain and faulty samples in the source domain. Secondly, the fault generation can be controlled to precisely generate distinct fault types and fault severity levels. The proposed method is especially suited in extreme domain adaption settings that are particularly relevant in the context of complex and safety-critical systems, where only one class is shared between the two domains. We evaluate the proposed framework on Partial as well as Open-Partial domain adaptation tasks on two bearing fault diagnostics case studies. Our experiments conducted in different label space settings showcase the versatility of the proposed framework. The proposed methodology provided superior results compared to other methods given large domain gaps.

研究动机与目标

• 解决在源域与目标域之间仅共享健康数据时，故障诊断中因域偏移带来的挑战。
• 在安全关键型工业系统中常见的极端域适应场景下实现迁移学习。
• 在无需目标域故障数据的前提下，生成逼真且多样的未见故障类型与严重程度的故障特征。
• 克服现有域适应方法对共享标签空间的假设限制。
• 提升诊断模型在现实场景中面对罕见或未观测到的故障类型时的泛化能力。

提出的方法

• 采用条件Wasserstein GAN结合梯度惩罚（WGAN-GP）生成合成故障信号。
• 通过表示故障类型和严重程度的类别潜变量进行生成条件控制。
• 采用三元组编码器学习域不变表示，实现特征对齐。
• 通过将生成信号添加到基础数据集中的真实健康样本，引入重构损失。
• 使用多头分类头实现早停和模型评估。
• 端到端联合训练生成器与判别器，损失函数包含对抗损失、重构损失和分类损失。

实验结果

研究问题

• RQ1 当源域与目标域之间仅共享健康数据时，可控的合成故障生成是否能提升域适应性能？
• RQ2 所提出方法在源域中未出现的未见故障类型上，其泛化能力达到何种程度？
• RQ3 在源域与目标域均存在私有类别的开放部分域适应（Open-Partial DA）设置下，该框架的有效性如何？
• RQ4 对故障严重程度的可控生成是否能增强诊断模型在大域偏移下的鲁棒性？
• RQ5 与现有域适应基线方法相比，该方法在准确率和泛化能力方面表现如何？

主要发现

• 在部分域适应和开放部分域适应设置下，该方法在两个滚动轴承故障诊断数据集上的表现优于当前最先进基线方法。
• 该框架仅利用源域故障数据和目标域健康数据，成功生成了逼真的未见故障类型的故障特征。
• 对故障严重程度的可控生成显著提升了模型在多种域偏移下的泛化能力。
• 即使目标域包含源域中完全不存在的故障类别，该方法仍保持了高诊断准确率。
• 实验结果表明，模型在不同标签空间差异和大域偏移下均表现出良好的性能鲁棒性。
• 消融实验验证了条件生成与重构模块对实现最优性能的关键作用。