PrognosticsAircraft Prognostics and Health Management (PHM) is a multidisciplinary framework that provides vital information to operators to ensure maximum system uptime and system safety. It does this by estimating the current and future condition (health) of engineering systems and providing decision support. In recent years, PHM has evolved from being a post hoc maintenance support tool to an essential system that should be integrated throughout all stages of the equipment lifecycle. This chapter describes the essential steps of how PHM can be used in the design and manufacturing of future aircraft. There are many benefits in adopting and evaluating PHM in the design stage. This includes a system that is ultimately easier to monitor and maintain, has better logistics, has reduced overall costs, and has less unplanned downtime. As such, it is argued here that PHM should be designed together with the aircraft. Therefore, this chapter proposes a methodology that includes PHM considerations at all stages of aircraft design. By promoting the integration of these disciplines − PHM, engineering design and manufacturing −, we hope to contribute to more reliable and safe aircraft that can achieve more cost-effective operations and a more sustainable future.

Prognostics and Health Management (PHM) is critical for predicting the Remaining Useful Life (RUL) of systems, a key enabler of Predictive Maintenance (PdM). This paper reviews state-of-the-art data-driven prognostic models, emphasizing four essential characteristics: uncertainty, robustness, interpretability, and feasibility. While traditional research has focused on enhancing RUL prediction accuracy, this review argues that these additional characteristics are equally vital for addressing the demands of PHM applications. The review examines Machine Learning (ML) techniques, stochastic models, and Bayesian filters (BFs), analyzing their strengths, limitations, and trade-offs. ML models excel in accuracy but often lack robust uncertainty quantification and adaptability across varying operational conditions. Stochastic models demonstrate greater robustness and feasibility, performing reliably with limited or variable data. Bayesian filters provide high interpretability and do not require run-to-failure data but face challenges in adapting to diverse environments. To bridge these gaps, this paper proposes a structured Model Evaluation Framework that integrates users’ specific needs with key model characteristics identified in the review. By quantifying the importance of the four characteristics, the framework enables systematic evaluation and selection of prognostic models. The findings underscore the need for advancements in uncertainty quantification, adaptive methods to improve robustness, and enhanced interpretability to meet practical and regulatory requirements. While current models offer valuable insights, further improvements are necessary to unlock their full potential for PHM and PdM applications, ensuring more reliable and actionable predictions.

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.

Hybrid models combining physical knowledge and machine learning show promise for obtaining accurate and robust prognostic models. However, despite the increased interest in hybrid models in recent years, the proposed solutions tend to be domain-specific. As a result, there is no compelling strategy of what, where, and how physics-derived knowledge can be integrated into deep learning models depending on the available representation of physical knowledge and the quality of data for the development of prognostic models for complex systems. This Ph.D. project aims to develop a general strategy for hybridizing prognostic models by exploring multiple methods to incorporate physical knowledge at various stages of the learning algorithm. The project will prioritize general expert knowledge as the primary source of information, while domain-specific knowledge will serve as an additional feature when applicable.

Discovering health indicators (HI) is essential for prognostics and health management of complex systems, as an HI enables timely interventions and effective maintenance strategies. However, most of the existing methodologies for HI discovery rely on labeled data which is expensive and complicated to obtain in the real world. In this paper, we propose a novel, unsupervised physics-informed model structured after expert knowledge in the form of a graphical representation of the expected relationships between sensor readings, operating conditions, and degradation. In addition, a soft constraint is used to guide the representation of the HI according to generally available expert knowledge about degradation. We evaluated the model on a turbofan engine dataset and conducted four experiments by manipulating the original data to create realistic real-world scenarios. The proposed method discovers an HI that exhibits better intrinsic qualities than the current state-of-the-art methodologies, leading to enhanced prognostic performance. Notably, in situations where the initial health state of each system varies, the proposed method achieves an average prognostic performance improvement of approximately 20% compared to existing state-of-the-art methods.

Maintenance decisions in domains such as aeronautics are becoming increasingly dependent on being able to predict the failure of components and systems. When data-driven techniques are used for this prognostic task, they often face headwinds due to their perceived lack of interpretability. To address this issue, this paper examines how features used in a data-driven prognostic approach correlate with established metrics of monotonicity, trendability, and prognosability. In particular, we use the SHAP model (SHapley Additive exPlanations) from the field of eXplainable Artificial Intelligence (XAI) to analyze the outcome of three increasingly complex algorithms: Linear Regression, Multi-Layer Perceptron, and Echo State Network. Our goal is to test the hypothesis that the prognostics metrics correlate with the SHAP model's explanations, i.e., the SHAP values. We use baseline data from a standard data set that contains several hundred run-to-failure trajectories for jet engines. The results indicate that SHAP values track very closely with these metrics with differences observed between the models that support the assertion that model complexity is a significant factor to consider when explainability is a consideration in prognostics.

When the influence of changing operational and environmental conditions, such as temperature and external loading, is not factored out from sensor data it can be difficult to observe a clear deterioration path. This can significantly affect the task of engineering prognostics and other health management operations. To address this problem of dynamic operating regimes, it is necessary to baseline the data, typically by first finding the operating regimes and then normalizing the data within each regime. This paper describes a baselining solution based on neural networks. A self-organizing map is used to identify the regimes, and a multi-layer perceptron is used to normalize the sensor data according to the detected regimes. Tests are performed on public datasets from a turbofan simulator. The approach can produce similar results to classical methods without the need to specify in advance the number of regimes and the explicit computation of the statistical properties of a hold-out dataset. Importantly, the techniques can be integrated into a deep learning system to perform prognostics in a single pass.

Prior to failure, most systems exhibit signs of changed characteristics. The early detection of this change is important to remaining useful life estimation. To have the ability to detect the inflection point or “elbow point” of an asset, i.e. the point of the degradation curve that marks the transition from nominal to faulty condition, can enable more sophisticated prognostics because this divide and conquer tactic allows the prediction to focus on the window before failure when significant changes are being expected. In this work, we compare prognostics with and without change point detection. We use different recurrent neural network techniques (standard recurrent neural network, long short-term memory and gated recurrent unit) to find the elbow point location. The actual estimation of the remaining time to failure is based on the echo state network, a state-of-the-art approach in prognostics. Two different experiments are performed on simulated data obtained from NASA Ames prognostics repository. We first compare the performance of the elbow point detectors based on recurrent neural networks against three baseline models: the Z-test, multi-layer perceptron and random forests. Results indicate that recurrent neural networks can outperform the baseline approaches. In the second experiment, the best elbow detection model, the gated recurrent unit, is integrated within an echo state network, with a significant increase in overall performance in terms of remaining useful life estimation.