Marcia L. Baptista

The viability and extended lifetime of proton‐exchange membrane (PEM) fuel cells are essential to enable hydrogen electric aviation. Their reliability, that is, the ability to maintain stable performance over long operational periods under varying environmental and load conditions, is a critical factor for their adoption in aviation systems. Prognostics and Health Management (PHM) is a popular strategy used extensively in aero engines. This data‐driven approach is used to estimate the best maintenance times and to prevent utilisation of equipment beyond its end‐of‐life. Despite being considerably well established in classical aeronautics, PHM is not yet mature for PEM fuel cells. Currently PHM for PEM fuel cells face three technical problems: (1) reliance on multi‐sensor datasets that limit applicability when only voltage and current measurements are available, (2) short‐term prediction windows of typically below 100 h, and (3) limited linkage between physics models and machine learning models for RUL predictions. This study presents a hybrid long short‐term memory (LSTM) and echo state network (ESN) framework to address gaps (1) and (2) under static and quasi‐dynamic conditions. Using seasonal and trend decomposition using LOESS (STL), voltage and current are separated into components, enabling medium‐term prediction up to 125 h. Existing membrane degradation models are utilised to establish a foundation for future linkage with a machine learning model to improve remaining useful life (RUL) predictions. Our results suggest that the hybrid LSTM–ESN framework enables 125‐h degradation predictions using only voltage and current measurements.

Accurately estimating a Health Index (HI) from condition monitoring data (CM) is essential for reliable and interpretable prognostics and health management (PHM) in complex systems. In most scenarios, complex systems operate under varying operating conditions and can exhibit different fault modes, making unsupervised inference of an HI from CM data a significant challenge. Hybrid models combining prior knowledge about degradation with deep learning models have been proposed to overcome this challenge. However, previously suggested hybrid models for HI estimation usually rely heavily on system-specific information, limiting their transferability to other systems. In this work, we propose an unsupervised hybrid method for HI estimation that integrates general knowledge about degradation into the convolutional autoencoder's model architecture and learning algorithm, enhancing its applicability across various systems. The effectiveness of the proposed method is demonstrated in two case studies from different domains: turbofan engines and lithium batteries. The results show that the proposed method outperforms other competitive alternatives, including residual-based methods, in terms of HI quality and their utility for Remaining Useful Life (RUL) predictions. The case studies also highlight the comparable performance of our proposed method with a supervised model trained with HI labels.

Developing Health Indicators (HI) is a crucial aspect of prognostics and health management of complex systems. Previous research has demonstrated the benefits of accurately determining the HI, which can lead to better performance of prognostic models. However, the existing methodologies for determining HI in complex systems are mostly semi-supervised and rely on assumptions that may not hold in real-world scenarios. The existing methods usually involve using a reference set of healthy sensor readings or run-to-failure data to infer HI. But the unsupervised inference of HI from sensor readings, which is challenging in scenarios where diverse operating conditions can mask the effect of degradation on sensor readings, has not been extensively researched. In this paper, we propose a novel physics-informed unsupervised model for determining HI. Unlike previous methods, constrained by assumptions, the proposed method uses prior general knowledge about degradation to infer HI, thereby eliminating the need for a reference set of healthy sensor readings. The proposed unsupervised model is an Autoencoder that incorporates constraints on its latent space to ensure consistency with knowledge about degradation. We assess the efficacy of the proposed model by analyzing a prevalent prognostic case study, specifically the turbofan engine dataset (N-CMAPSS). Our analysis considers the model's sensitivity to data availability and the resulting Health Index's quality, including trendability and monotonicity. Additionally, we investigate the impact of incorporating the Health Index in predicting Remaining Useful Life (RUL). We demonstrate that our proposed method generates a Health Index that exhibits greater monotonicity and trendability than the current state-of-the-art semi-supervised approach. Moreover, our approach for identifying the Health Index leads to enhanced prognostic performance compared to the existing semi-supervised approach.

Prognostics and health management is an engineering discipline that aims to support system operation while ensuring maximum safety and performance. Prognostics is a key step of this framework, focusing on developing effective maintenance policies based on predictive methods. Traditionally, prognostics models forecast the degradation process using regression techniques that approximate a mapping function from input to continuous remaining useful life estimates. These models are typically of high complexity and low interpretability. Classification approaches are an alternative solution to these types of models. We propose a predictive classification model that translates the input into discrete output variables instead of mapping the input to a single remaining useful life estimate. Each discrete output variable corresponds to a range of remaining useful life values. In other words, each output class variable represents the likelihood or risk of failure within a specific time range. We apply this model to a real-world case study involving the unscheduled and scheduled removals of a set of engine bleed valves from a fleet of Boeing 737 aircraft. The model can reach an area under the (micro-average) receiver operating characteristic curve of 72%. Our results suggest that the proposed multiclass gated recurrent unit network can provide valuable information about the different fault stages (corresponding to intervals of residual lives) of the studied valves.

Prognostics and health management is an engineering discipline that aims to support system operation while ensuring maximum safety and performance. Prognostics is a key step of this framework, focusing on developing effective maintenance policies based on predictive methods. We propose a predictive classification model that translates the input into discrete output variables instead of mapping the input to a single remaining useful life estimate. We apply this model to a real-world case study involving the unscheduled and scheduled removals of a set of engine bleed valves from a fleet of Boeing 737 aircraft. Our results suggest that the proposed multiclass gated recurrent unit network can provide valuable information about the different fault stages (corresponding to intervals of residual lives) of the studied valves. The model can reach an area under the (micro-average) receiver operating characteristic curve of 72%.