A Maintenance-Aware Temporal Contrastive Autoencoder for Health Index Learning of Marine Turbochargers Under Real-Ship Operation

Health monitoring of marine turbochargers under real-ship operation is complicated by operating-condition variability, recurrent online cleaning, and limited fault labels. This study presents a maintenance-aware temporal contrastive autoencoder (TCCL-AE) for health index (HI) learning from multivariate real-ship monitoring data. The framework aims to learn an HI that tracks degradation while reducing sensitivity to short-term operating-condition fluctuations by incorporating maintenance information into latent-state evolution and introducing temporal contrastive learning. The model includes a temporal encoder for window-level feature extraction, a latent decomposition module for separating degradation-related and condition-related information, and a Health Coupling Module for representing maintenance-induced recovery. The training objective combines temporal contrastive learning, observation reconstruction, and maintenance consistency. Experiments on multi-voyage real-ship data indicate that the learned HI reflects long-term degradation evolution and maintenance-related recovery, while remaining comparatively smooth under variable operating conditions. The resulting HI provides a continuous representation for condition tracking and maintenance-related interpretation during long-horizon monitoring.