Temporal Cross-Modal Knowledge-Distillation-Based Transfer-Learning for Gas Turbine Vibration Fault Detection

TL;DR

This paper introduces a novel transfer learning framework using cross-modal knowledge distillation with temporal context to improve gas turbine fault detection, balancing accuracy and real-time constraints.

Contribution

It proposes a temporal cross-modal knowledge distillation transfer-learning framework that enhances fault detection accuracy while maintaining computational efficiency.

Findings

Achieves superior feature separability and diagnostic accuracy over conventional models.

Enables high-performance, unsupervised anomaly detection on resource-constrained hardware.

Demonstrates effectiveness on experimental and industrial gas turbine datasets.

Abstract

Preventing machine failure is inherently superior to reactive remediation, particularly for critical assets like gas turbines, where early fault detection (FD) is a cornerstone of industrial sustainability. However, modern deep learning-based FD models often face a significant trade-off between architectural complexity and real-time operational constraints, often hindered by a lack of temporal context within restricted vibration signal windows. To address these challenges, this study proposes a Temporal Cross-Modal Knowledge-Distillation Transfer-Learning (TCMKDTL) framework. The framework employs a "privileged" teacher model trained on expansive temporal windows incorporating both past and future signal context to distill latent feature-based knowledge into a compact student model. To mitigate issues of data scarcity and domain shift, the framework leverages robust pre-training on benchmark datasets (such as CWRU) followed by adaptation to target industrial data. Extensive evaluation using experimental and industrial gas turbine (MGT-40) datasets demonstrates that TCMKDTL achieves superior feature separability and diagnostic accuracy compared to conventional pre-trained architectures. Ultimately, this approach enables high-performance, unsupervised anomaly detection suitable for deployment on resource-constrained industrial hardware.