Work

Two-Stage Self-Supervised Meta-Learning for Few-Shot Cross-Condition Fault Diagnosis of Air Conditioning Compressors

Year: 2026

Type: article

Abstract: The air conditioning compressor serves as the primary power unit in refrigeration systems, and its reliable fault diagnosis is critical for ensuring safe and stable system operation. However, existing data-driven approaches face two fundamental bottlenecks: the prohibitive cost of acquiring large-scale labeled fault samples in industrial settings, and the degradation of model generalization caused by domain shift in vibration signals across different operating conditions (e.g., high-pressure vs. low-pressure modes). To address these challenges, this paper proposes a Two-Stage Self-Supervised Meta-Learning (TS-SSML) framework. In Stage 1, we perform self-supervised contrastive pre-training on large-scale unlabeled vibration signals using the NT-Xent loss, enabling the encoder to learn condition-agnostic fault representations. In Stage 2, the pre-trained encoder is frozen, and an Attention-Weighted Prototypical Network (AWPN) is trained via episodic meta-learning to dynamically assess the contribution of each support sample to class prototypes, thereby enhancing discriminability in few-shot classification. We conduct systematic evaluations on a self-collected AC compressor fault dataset across two tasks: cross-condition transfer (Task T1, 10-way) and open-set novel fault detection (Task T2, 6→4-way). Experimental results demonstrate that the proposed method achieves 96.50% (T1) and 94.10% (T2) classification accuracy under the 5-shot setting, outperforming standard Prototypical Networks by 1.20% and 4.92%, respectively. Compared to SCM-FD, our method reduces training time by 93.75% while achieving superior or comparable accuracy. These results highlight the substantial advantages of the proposed framework in industrial fault diagnosis scenarios with scarce labeled data.

Source: Sensors

DOI: 10.3390/s26216802

Authors: Tao Feng, Jiewen Wen, Jing Wang, Kun Chen, Haonan Guo

Institution: Beijing Technology and Business University

Language: English

Topic: Machine Fault Diagnosis Techniques

Subfield: Control and Systems Engineering

Field: Engineering

Domain: Physical Sciences

SDG: Industry, innovation and infrastructure

Open Access status: gold

Estimated APC paid: $3,137