The complexity of airline operations requires operations planning to be divided into multiple problems solved sequentially by the respective departments. This is particularly the case for (1) network planning and (2) maintenance planning. Despite the close interaction of these two departments, airlines typically evaluate plans from both domains separately. However, an integrated perspective is necessary to develop robust plans and effective recovery policies in this intrinsically uncertain environment. This paper presents a new modular, stochastic, discrete event simulation model of airline operations named ANEMOS (Airline Network and Maintenance Operations Simulation). ANEMOS contains both network and maintenance dynamics, allowing the evaluation of plans, policies, and scenarios from both domains. The model is validated using data from a major European airline. We show that the simulated results closely resemble the airline's historical operational performance. ANEMOS is tested with a use-case investigating the effects of adding a second reserve aircraft to a fleet of fifty wide-body aircraft. The results show that the second reserve is capable of reducing cancellations by 55%. However, such does not cover the lost revenue associated with keeping an aircraft non-operational for a part of the time.

Machine learning has contributed to the advancement of maintenance in many industries, including aviation. In recent years, many neural network models have been proposed to address the problems of failure identification and estimating the remaining useful life (RUL). Nevertheless, the black-box nature of neural networks often limits their transparency and interpretability. Interpretability (or explainability) in maintenance refers to the ability of a predictive model to provide insights into its decision-making process for predicting failures or estimating metrics like RUL. Counterfactual Explanations (CFEs) from Explainable AI (XAI) addresses this problem by explaining model decisions through hypothetical scenarios leading to alternative outcomes. A kind of neural network that could benefit from increased interpretability is Bayesian networks. In general, Bayesian models improve interpretability by quantifying uncertainty. However, incorporating Bayesian uncertainty into neural networks adds complexity because we often need a statistical distribution for each network parameter. This study investigates the use of CFEs within a Bayesian framework to achieve two key objectives simultaneously: (1) enhance the interpretability of RUL estimations and (2) improve model accuracy. We generate two types of CFEs: (1) RUL CFEs that increase/decrease the RUL estimation and (2) uncertainty CFEs with reduced estimation uncertainty, which we use to augment the dataset and increase model accuracy. We apply this method to a classical case study, the C-MAPSS dataset, using a Bayesian Long Short-Term Memory (B-LSTM) model. We demonstrate that CFEs can help identify critical features and fine-tune corrective actions to achieve specific outcomes. For example, following a maintenance action that increased the temperature by 1°F, CFEs can reveal that this adjustment extended the equipment's useful life by 30 cycles. This ability to correlate specific actions with effects enhances both decision-making and maintenance efficiency. Additionally, our data augmentation approach results in a 5% improvement in α−λ accuracy for a strict α of 20%. The root mean square error (RMSE) of the B-LSTM model decreases from 9.56 to 8.47 cycles, demonstrating the potential of Uncertainty CFEs to improve accuracy in aircraft maintenance. The code is publicly available at Github.

As the volume of telemetry data generated by satellites and other complex systems continues to grow, there is a pressing need for more efficient and accurate anomaly detection methods. Current techniques often rely on human analysis and preset criteria, presenting several challenges including the necessity for expert interpretation and continual updates to match the dynamic mission environment. This paper critically examines the use of deep anomaly detection (DAD) methods in addressing these challenges, evaluating their efficacy on real-world spacecraft telemetry data. It exposes limitations in current DAD research, highlighting the tendency for performance results to be overestimated and suggesting that simpler methods can sometimes outperform more complex DAD algorithms. By comparing established metrics for anomaly detection with newly proposed ones, this paper aims to improve the evaluation of DAD algorithms. It underscores the importance of using less accuracy-inflating metrics and offers a comprehensive comparison of DAD methods on popular benchmark datasets and real-life satellite telemetry data. Among the DAD methods examined, the LSTM algorithm demonstrates considerable promise. However, the paper also reveals the potential limitations of this approach, particularly in complex systems that lack a single, clear predictive failure channel. The paper concludes with a series of recommendations for future research, including the adoption of best practices, the need for high-quality, pre-split datasets, and the investigation of other prediction error methods. Through these insights, this paper contributes to the improved understanding and application of DAD methods, ultimately enhancing the reliability and effectiveness of anomaly detection in real-world scenarios.

Over the past years, advanced prognostic models and approaches have been developed. Most existing approaches are tailored to one specific system and cannot adaptively be used on different systems. This can lead to years of research and expertise being put into implementing prognostic models without the capacity to predict system failures, either because of a lack of data or data quality or because failure behavior cannot be captured by data-driven models. In addition, prognostic models are often evaluated using metrics only related to the correctness of predictions, preventing meaningful evaluation of operational performance. This paper makes use of a framework that can automatically choose prognostic settings based on specific system data. It simultaneously optimizes the choice of methodologies using metrics that capture multiple aspects of prediction quality. We apply this framework to both a simulated data set and a real aircraft data set to characterize the impact of metrics on the choice of prognostic methodologies. The results show that the choice of optimization metric greatly impacts the output of the generic prognostic framework and the overall performance. In addition, a definition for data suitability is provided and assessed on the aircraft system data sets.

In the Condition-Based Maintenance (CBM) context, the definition of optimal maintenance plans for an aircraft fleet depends on an efficient integration of : (i) the probabilistic predictions of the health condition of the components and (ii) the stochastic arrival of the corrective maintenance tasks, together with consideration of the preventive maintenance tasks as defined in the Maintenance Planning Document (MPD). To this end, in this paper, we present a two-stage dynamic scheduling framework to solve the aircraft fleet maintenance scheduling problem under a CBM strategy in a disruptive environment. In the first stage of the framework, we address the uncertainty in the predicted health state of the monitored components by planning the optimal maintenance policy based upon the belief state-space of the health of the components. The decision-making process is formulated as a Partially Observable Markov Decision Process (POMDP) and is solved using the Partially Observable Monte Carlo Planning (POMCP) algorithm, considering the aircraft maintenance scheduling problem requirements. In the second stage, a Deep Q-Network (DQN) is developed, that integrates the defined maintenance policy of the monitored components within the scheduling of the aircraft fleet's preventive and corrective maintenance tasks. Our model, through a rolling horizon approach, continuously creates and adjusts the maintenance schedule, reacting to new updated task information, where the availability of maintenance resources constraints the execution of each task. The proposed framework was tested on a case study from a large airline and the performance was evaluated against the current state practice of the airline. The results show that our model can schedule 96.4% of monitored components on-time. As a consequence of this, a 46.2% maintenance cost reduction is achieved for the considered monitored components relative to a corrective maintenance approach.

Artificial Intelligence (AI) is transforming the future of industries by introducing new paradigms. To address data privacy and other challenges of decentralization, research has focused on Federated Learning (FL), which combines distributed Machine Learning (ML) models from multiple parties without exchanging confidential information. However, conventional FL methods struggle to handle situations where data samples have diverse features and sizes. We propose a Hybrid Federated Learning solution with label synchronization to overcome this challenge. Our FedLabSync algorithm trains a feed-forward Artificial Neural Network while alerts that it can aggregate knowledge of other ML architectures compatible with the Stochastic Gradient Descent algorithm by conducting a penalized collaborative optimization. We conducted two industrial case studies: product inspection in Bosch factories and aircraft component Remaining Useful Life predictions. Our experiments on decentralized data scenarios demonstrate that FedLabSync can produce a global AI model that achieves results on par with those of centralized learning methods.

Prognostics is used in predictive maintenance to estimate the remaining time to the end of the life of a system or component. Among the many challenges of prognostics is the need for model verification and validation. Over the years, several objective metrics have been utilized by the community. Some of these metrics came from statistics, others from forecasting, and others have been proposed specifically for prognostics. A single “perfect” metric has not yet been put forward. Finding one metric that can excel in all evaluation dimensions and case studies is an open question. In this review, we analyze the most important metrics of prognostics. A set of 19 metrics is subject to analysis and implementation. The metrics are implemented on a public GitHub project. Our analysis focuses only on metrics for deterministic predictions. Stochastic predictions are out of the scope. The paper describes properties, advantages, disadvantages, and industrial applicability of each metric. We also discuss potential modifications to the existing metrics and the development of new metrics. A final table summarizes the main properties of the metrics. Our goal is to raise awareness about prognostics metrics and help establish a common evaluation procedure. Code available at: MetricsForPrognostics.

This paper proposes using reinforcement learning (RL) to schedule maintenance tasks, which can significantly reduce direct operating costs for airlines. The approach consists of a static algorithm for long-term scheduling and an adaptive algorithm for rescheduling based on new maintenance information. To assess the performance of both approaches, three key performance indicators (KPIs) are defined: Ground Time, representing the hours an aircraft spends on the ground; Time Slack, measuring the proximity of tasks to their due dates; and Change Score, quantifying the similarity level between initial and adapted maintenance plans when new information surfaces. The results demonstrate the efficacy of RL in producing efficient maintenance plans, with the algorithms complementing each other to form a solid foundation for routine tasks and real-time responsiveness to new information. While the static algorithm performs slightly better in terms of Ground Time and Time Slack, the adaptive algorithm excels overwhelmingly in terms of Change Score, offering greater flexibility in handling new maintenance information. The proposed RL-based approach can improve the efficiency of aircraft maintenance and has the potential for further research in this area.