Domain-Aware Hierarchical Contrastive Learning for Semi-Supervised Generalization Fault Diagnosis

TL;DR

This paper introduces DAHCL, a novel semi-supervised fault diagnosis framework that improves pseudo-label accuracy and sample utilization by capturing domain-specific features and employing hierarchical contrastive learning.

Contribution

The paper proposes a unified domain-aware hierarchical contrastive learning framework that addresses pseudo-label bias and sample imbalance in semi-supervised fault diagnosis.

Findings

DAHCL outperforms existing methods on three benchmark datasets.

Incorporating engineering noise enhances evaluation realism.

Hierarchical contrastive learning improves representation quality.

Abstract

Fault diagnosis under unseen operating conditions remains highly challenging when labeled data are scarce. Semi-supervised domain generalization fault diagnosis (SSDGFD) provides a practical solution by jointly exploiting labeled and unlabeled source domains. However, existing methods still suffer from two coupled limitations. First, pseudo-labels for unlabeled domains are typically generated primarily from knowledge learned on the labeled source domain, which neglects domain-specific geometric discrepancies and thus induces systematic cross-domain pseudo-label bias. Second, unlabeled samples are commonly handled with a hard accept-or-discard strategy, where rigid thresholding causes imbalanced sample utilization across domains, while hard-label assignment for uncertain samples can easily introduce additional noise. To address these issues, we propose a unified framework termed domain-aware hierarchical contrastive learning (DAHCL) for SSDGFD. Specifically, DAHCL introduces a domain-aware learning (DAL) module to explicitly capture source-domain geometric characteristics and calibrate pseudo-label predictions across heterogeneous source domains, thereby mitigating cross-domain bias in pseudo-label generation. In addition, DAHCL develops a hierarchical contrastive learning (HCL) module that combines dynamic confidence stratification with fuzzy contrastive supervision, enabling uncertain samples to contribute to representation learning without relying on unreliable hard labels. In this way, DAHCL jointly improves the quality of supervision and the utilization of unlabeled samples. Furthermore, to better reflect practical industrial scenarios, we incorporate engineering noise into the SSDGFD evaluation protocol. Extensive experiments on three benchmark datasets demonstrate that...