Controlled Generation of Unseen Faults for Partial and Open-Partial Domain Adaptation

TL;DR

This paper introduces a Wasserstein GAN-based framework for generating synthetic fault data to improve partial and open-partial domain adaptation in fault diagnostics, especially when only healthy data is shared between source and target domains.

Contribution

It presents a novel controlled fault data generation method that creates unobserved fault types and severity levels, enhancing transferability in extreme domain adaptation scenarios.

Findings

Outperforms existing methods in large domain gap settings.

Effectively generates unobserved fault types in target domains.

Demonstrates versatility across different fault diagnostics case studies.

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.