Lubricating oil degradation directly impacts friction coefficient, wear rate, and lubrication regime transitions, making precise health quantification essential for predictive tribological maintenance. However, conventional evaluation methods fail to capture subtle tribological changes preceding lubrication failure, often oversimplifying complex multi-parameter relationships critical to friction and wear performance. To address this challenge, this study proposes Seasonal–Trend decomposition using Loess, a Factor Attention Network, a Temporal Convolutional Network, and an Informer with Long Short-Term Memory Variational Autoencoder (SFTI-LVAE) framework for continuous tribological health assessment of diesel engine lubricants. The approach integrates Seasonal–Trend decomposition using Loess (STL) for trend–seasonal separation, a Factor Attention Network (FAN) for multidimensional feature fusion, and a Temporal Convolutional Network (TCN)-enhanced Informer for capturing long-term tribological dependencies. By combining Long Short-Term Memory (LSTM) temporal modeling with Variational Autoencoder (VAE) reconstruction, the method quantifies lubricant health through reconstruction error, establishing a direct correlation between data deviation and tribological performance degradation. Additionally, permutation importance-based feature evaluation and parameter contribution quantification techniques enable deep mechanistic analysis and fault source tracing of lubricant health degradation. Experimental validation using multi-sensor monitoring data demonstrates that SFTI-LVAE achieves a 96.67% fault detection accuracy with zero false alarms, providing early warning 6.47 h before lubrication failure. Unlike traditional anomaly detection methods that only classify conditions as abnormal or normal, the proposed continuous health index reveals gradual tribological degradation processes, capturing subtle viscosity–temperature relationships and wear particle evolution indicating early lubrication regime transitions. The health index correlates strongly with tribological performance indicators, enabling a transition from reactive maintenance to predictive tribological management, providing an innovative solution for equipment health evaluation in the digital tribology era.

Lubricating oil monitoring provides continuous health information for early fault warning and maintenance decision-making in industrial gas turbines. However, real-world multi-sensor monitoring streams exhibit pronounced nonstationary thermodynamic drifts that often obscure subtle high-frequency residuals containing critical incipient degradation signatures. Prevailing data-driven monitoring models typically struggle to separate these macroscopic trends from stochastic wear-related fluctuations, and their restrictive distributional assumptions are often inadequate for the heteroscedastic and heavy-tailed nature of industrial residuals. To address these challenges, this study proposes ResAD-Net, a framework for early fault warning in nonstationary multi-sensor oil monitoring that combines trend–residual decoupling, trend-conditioned residual modeling, and residual-domain dependency learning. Specifically, a signal trend–residual decoupling strategy is adopted to separate slowly varying operational trends from stochastic residual fluctuations captured by the sensors, thereby exposing residual information that is more sensitive to incipient degradation. On this basis, a trend-conditioned diffusion model is introduced to characterize state-dependent, skewed residual distributions and generate residual sample ensembles for nonstationary monitoring. Meanwhile, a graph-based variational autoencoder is employed to learn latent intersensor dependency structures from the residual domain, providing diagnostic cues for temporal risk evolution analysis and sensor-level inspection. Experiments on a real-world industrial oil-monitoring record show that the proposed framework achieves an average F1-score of 0.985 with no observed false positives in the predefined pre-alarm reference interval of the finite test set. In addition to accurate anomaly detection, ResAD-Net captures early residual distributional shifts before clear macroscopic deviations emerge and provides diagnostic association cues for interpreting oil-monitoring changes around the system-level alarm.

Online detection of wear particles in marine machinery lubricants is critical for effective condition monitoring. However, current methods encounter significant difficulties in accurately identifying microscale wear debris owing to the high-frequency background noise and motion blur inherent in online ferrographic images. To address these challenges, this study proposes YOLO-RSMA, a novel detection framework based on YOLOv8 architecture. The model systematically integrates a Residual Efficient Multi-scale Attention (REMA) mechanism to retrieve global contextual features that are frequently attenuated in deep convolutional layers. Furthermore, the framework employs the Sophia optimizer to mitigate gradient instability within nonconvex loss landscapes, and incorporates the MPDIoU loss function to ensure precise geometric alignment for irregular particle morphologies. Validated on a custom dataset against industrial baselines and state-of-the-art methods, YOLO-RSMA demonstrated superior robustness under complex imaging conditions. The model achieves a mAP0.5 of 99.30%, representing a substantial improvement of 16.63% over the baseline, thereby offering an efficient and accurate solution for intelligent fault diagnosis.

Driven by the escalating requirements for efficiency and operational safety in power-generation units, data-driven forecasting of generator output has emerged as a critical research frontier. Generator performance is governed by a complex interplay between mechanical operating conditions and stochastic human factors. In this study, we performed online monitoring of turbine lubricating oil to assemble a comprehensive time-series dataset integrating oil wear signatures and unit power metrics. We propose a synergistic deep-learning architecture, the Transformer–LSTM, which leverages an LSTM-based auxiliary extractor to capture fine-grained local temporal patterns. Concurrently, positional encodings, timestamp embeddings, and value embeddings are employed to characterize global contextual features. By fusing these local and global representations, the model achieves a joint perception of short-term dynamics and long-range dependencies. Empirical results demonstrate that the proposed hybrid model significantly outperforms standalone LSTM and Transformer baselines across diverse evaluation metrics in terms of both predictive accuracy and robustness. This framework provides robust technical decision support for condition-based maintenance and optimized power-generation scheduling.