In the present paper, temperature measurements are utilized to develop health indicators based on principal component analysis towards the probabilistic estimation of the Remaining Useful Life (RUL) of reciprocating compressors in service. Temperature degradation histories obtained from thirteen actual valve failure cases constitute the training data in a data-driven prognostic approach. Two data-driven prognostic methodologies are presented and proposed based on probabilistic mathematical models i.e. Gradient Boosted Trees (GBTs) and Non-Homogeneous Hidden Semi Markov Models (NHHSMM). The training and testing process of all models is described in detail. RUL prognostics in unseen data are obtained for all models. Beyond the mean estimates of the RUL, the uncertainty associated with the point prediction is quantified and upper/lower confidence bounds are also estimated. Prediction estimates for twelve real-life failure cases are presented and the pros and cons of each model's performance are highlighted. Several metrics are utilized to assess the performance of the prognostic algorithms and conclusions are drawn regarding the prognostic capabilities of each of them.

Prognostics and health management (PHM) is becoming increasingly important as engineering structures and systems grow more complex. Many of these systems lack accurate physical models to describe their degradation, especially in unpredictable scenarios. To meet safety regulations, robust prognostic models are needed to transform sensor data into reliable predictions about a system’s remaining useful life (RUL). This study presents the adaptive hidden semi-Markov model (AHSMM), a novel probabilistic approach that enhances RUL prediction accuracy, uncertainty quantification (UQ), and reliability assessment compared to a long short-term memory (LSTM) model. A key contribution is an in-house experimental campaign involving glass fiber-reinforced polymer specimens subjected to fatigue loading and multiple impact events at different locations and time intervals. Unlike traditional models that rely on data from similar damage histories, the AHSMM is trained exclusively on unimpacted specimens and tested on multiply impacted ones, showcasing its adaptability to previously unseen conditions. The study also introduces a new prognostic performance measure tailored to AHSMM and develops a conditional reliability analysis for both AHSMM and LSTM predictions. Results demonstrate that AHSMM consistently outperforms LSTM across all evaluation metrics. It achieves a 24% lower RMSE over the full lifetime and superior UQ, with an average coverage of 0.79 compared to 0.17 for LSTM. Conditional reliability analysis further shows that AHSMM provides more accurate and stable reliability estimates as data accumulates. By capturing the degradation process and adapting to evolving conditions, AHSMM strengthens prognostic robustness. This study highlights the need for robust PHM models that can handle real-world uncertainties and contribute to advancements in the aerospace, automotive, and defense industries.

Prognostics and Health Management (PHM) plays a key role in predicting the Remaining Useful Life (RUL) of systems, which is essential for enabling decision-making for Predictive Maintenance (PdM) and operations. While most research has traditionally focused on improving the accuracy of RUL predictions, this paper argues that four essential characteristics, uncertainty, robustness, interpretability, and feasibility, are key for real-world PHM applications. This study explores these characteristics through a comparative analysis of two data-driven models (DDMs): the probabilistic Bidirectional Long Short-Term Memory (BiLSTM) model and the Adaptive Hidden Semi-Markov Model (AHSMM). Deep Learning (DL) models such as the BiLSTM often achieve high prediction accuracy but struggle with uncertainty quantification and adaptability across varying operating conditions. In contrast, stochastic models like AHSMM offer stronger robustness and feasibility, performing well even with limited or noisy data. Using the C-MAPSS dataset, the models are evaluated through the lens of the four proposed characteristics. This more holistic approach clarifies each model’s strengths, limitations, and practical trade-offs in PHM settings. The findings highlight that while accuracy remains important, focusing solely on it can overlook critical factors that affect model performance in real operational environments. Balancing all four characteristics is essential for deploying reliable and effective decision-making for predictive maintenance and operations.

The procedure of fatigue damage accumulation in composite structures, is a complex phenomenon due to the multiphase nature of composites, the variation of inherent manufacturing defects, the randomness of loads, the stochastic activation of different damage mechanisms and an incomplete knowledge about the physics behind the evolution and interaction of damage mechanisms. In order to develop a robust model, which will reliably estimate the remaining useful life of the structure, we hypothesize that the damage accumulation process is of a stochastic nature and we propose a framework that combines a stochastic model with structural health monitoring data. In this study, the Non-Homogenous Hidden Semi Markov model and acoustic emission and strain data extracted from fatigue tests of open-hole quasi-isotropic carbon fibre reinforced polymers are selected. The damage accumulation is a hidden process and the goal of the framework is to correlate the structural health monitoring data with the parameters of the model and identify the hidden relationship. In conclusion, the remaining useful life estimations of each structural health monitoring technique are compared with the actual remaining useful life and based on performance metrics it was found that the strain data provided more accurate predictions.