This study assesses classification-based predictive maintenance (PdM) for aircraft engines on the NASA Commercial Modular Aero-Propulsion System Simulation dataset and addresses the lack of wide-scope, unified benchmarks. PdM is cast as a short-term binary task – predicting whether an engine will fail within the next 30 cycles – and a comparison is conducted across 10 machine-learning models (Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, k-Nearest Neighbor, Naïve Bayes, Extreme Gradient Boosting, LightGBM, CatBoost, and Gradient Boosting) and 3 deep-learning models (Multilayer Perceptron, Gated Recurrent Unit, and Long Short-Term Memory). A leakage-aware pipeline applies Min–Max scaling; class imbalance is handled with Synthetic Minority Over-sampling Technique where appropriate; hyperparameters are tuned via GridSearchCV/BayesSearchCV; and performance is reported with accuracy, precision, recall, F1-score, and receiver operating characteristic–area under the curve (ROC–AUC), complemented by Shapley Additive Explanations (SHAP) explainability and nonparametric significance tests. Sequence models delivered the strongest performance: LSTM achieved Accuracy = 0.981 (Macro-F1 = 0.92; ROC–AUC = 0.96), and GRU achieved ROC–AUC = 0.97 with Accuracy = 0.975. Among classical learners, LightGBM reached Accuracy = 0.972 (Macro-F1 = 0.86; ROC–AUC = 0.93). These gains over weaker baselines were statistically significant across folds. Framing PdM as near-term failure classification yields operationally interpretable alerts. Models that explicitly capture temporal dependencies (GRU/LSTM) best track short-horizon failure dynamics, while gradient-boosted trees offer competitive, lightweight alternatives. The benchmark and analysis (including SHAP) provide a reproducible reference for model selection in aviation PdM.

The rapid development of AI has resulted in an unprecedented paradigm shift across various industries, with aerospace among the laureates of this transformation. This review paper attempts to explore and provide comprehensive overview of the aerospace research imperatives from the AI perspective, detailing the technical sides of the full lifecycle from vehicle design and operational optimisation to advanced air traffic management systems. By examining real-world engineering implementations, the review demonstrates how AI-driven solutions are directly addressing longstanding challenges in aerospace, such as optimising flight performance, reducing operational costs and improving system reliability. A significant emphasis is placed on the crucial roles of AI in health monitoring and predictive maintenance, areas that are pivotal for ensuring the safety and longevity of aerospace endeavors, and which are now increasingly adopted in industry for remaining useful life (RUL) forecasting and condition-based maintenance strategies. The paper also discusses AI embedded in quality control and inspection processes, where it boosts accuracy, efficiency and fault detection capability. The review provides insight into the state-of-the-art applications of AI in planetary exploration, particularly within the realms of autonomous scientific instrumentation and robotic prospecting, as well as surface operations on extraterrestrial bodies. An important case study is India’s Chandrayaan-3 mission, demonstrating the application of AI in both autonomous navigation and scientific exploration within the challenging environments of space. By furnishing an overview of the field, the paper frames the ever-important, increasing domains of AI as the forefront in the advancement of aerospace engineering and opens avenues for further discussion regarding the limitless possibilities at the juncture of intelligent systems and aerospace innovation.

Turbofan engines are having a growing role in modern aircraft maintenance. Due to this increase, estimation of remaining useful life (RUL) of these engines is an important area of study in the field of reliability and maintenance optimisation. In this work, we propose a hybrid approach that combines deep learning models with similarity-based methods for accurate RUL estimation. For a better comparison, we evaluate four architectures: dropout long short-term memory (LSTM), bidirectional LSTM, convolutional neural network 1D (CNN 1D), and multi-layer LSTM. The FD002 subset of NASA’s Commercial Modular Aero-Propulsion System Simulation dataset is used in the case study. Root mean square error (RMSE) and mean absolute error (MAE) were used for performance metrics. The main output of the study suggests that the dropout LSTM model achieves the best prediction accuracy with an RMSE score of 26.547 and a MAE score of 18.749. It is worth noting that these are achieved despite requiring higher computational resources compared to multi-layer LSTM. Furthermore, all models had difficulties with smaller test trajectory lengths such as 50–100 due to training data imbalance. Overall, the findings highlight the promise of hybrid deep learning and similarity-based approaches for RUL prediction. However, potential advancements such as hyperparameter optimisation and data augmentation still hold potential for further improvements.

Predictive maintenance attempts to prevent unscheduled downtime by scheduling maintenance before expected failures and/or breakdowns while maximally optimizing uptime. However, this is a non-trivial problem, which requires sufficient data analytics knowledge and labeled data, either to design supervised fault detection models or to evaluate the performance of unsupervised models. While today most companies collect data by adding sensors to their machinery, the majority of this data is unfortunately not labeled. Moreover, labeling requires expert knowledge and is very cumbersome. To solve this mismatch, we present an architecture that guides experts, only requiring them to label a very small subset of the data compared to today’s standard labeling campaigns that are used when designing predictive maintenance solutions. We use auto-encoders to highlight potential anomalies and clustering approaches to group these anomalies into (potential) failure types. The accompanied dashboard then presents the anomalies to domain experts for labeling. In this way, we enable domain experts to enrich routinely collected machine data with business intelligence via a user-friendly hybrid model, combining auto-encoder models with labeling steps and supervised models. Ultimately, the labeled failure data allows for creating better failure prediction models, which in turn enables more effective predictive maintenance. More specifically, our architecture gets rid of cumbersome labeling tasks, allowing companies to make maximum use of their data and expert knowledge to ultimately increase their profit. Using our methodology, we achieve a labeling gain of 90% at best compared to standard labeling tasks.

Cost efficiency is a critical factor in the competitive aviation sector. These efficiency factors force airline operators to develop new approaches in their organizations. Predictive maintenance helps to build scheduling maintenance programs for airline operators or MROs. Scheduled maintenance programs benefit cost efficiency in the aviation sector. Predictive maintenance methods predict the failure time of any equipment. Predictions can be made by analyzing the sensor values from equipment.

In this paper, we predicted the remaining useful life (RUL) of turbofan engines using machine learning models and a similarity-based approach. Sensor datasets from the Prognostics Data Repository of NASA, called CMAPPS, were utilized. Using the FD0002 sub-dataset, a health index (HI) was created, and models were trained. Once the models were trained, train and test HIs were estimated. The predicted test HI was matched with the predicted train HI based on a similarity-based approach, and then a RUL prediction was made. The results obtained were compared with the actual results to calculate the accuracy, and the algorithm that resulted in the maximum accuracy was identified.

We selected six machine learning algorithms and also created an ensemble model by averaging the predictions of six machine learning algorithms for comparing prediction accuracy. The different algorithms were compared to obtain the prediction model with the closest prediction of remaining useful lifecycle in terms of the number of life cycles. This experiment showed us the effect of the similarity-based approach on the basic version of machine learning models for RUL prediction.

Gas turbines play a vital role in various industries. Timely and accurately predicting their degradation is essential for efficient operation and optimal maintenance planning. Diagnostic and prognostic outcomes aid in determining the optimal compressor washing intervals. Diagnostics detects compressor fouling and estimates the trend up to the current time. If the forecast indicates fast progress in the fouling trend, scheduling offline washing during the next inspection event or earlier may be crucial to address the fouling deposit comprehensively. This approach ensures that compressor cleaning is performed based on its actual health status, leading to improved operation and maintenance costs. This paper presents a novel prognostic method for gas turbine degradation forecasting through a time-series analysis. The proposed approach uses the Temporal Fusion Transformer model capable of capturing time-series relationships at different scales. It combines encoder and decoder layers to capture temporal dependencies and temporal-attention layers to capture long-range dependencies across the encoded degradation trends. Temporal attention is a self-attention mechanism that enables the model to consider the importance of each time step degradation in the context of the entire degradation profile of the given health parameter. Performance data from multiple two-spool turbofan engines is employed to train and test the method. The test results show promising forecasting ability of the proposed method multiple flight cycles into the future. By leveraging the insights provided by the method, maintenance events and activities can be scheduled in a proactive manner. Future work is to extend the method to estimate remaining useful life.

With the wide application of quadrotor unmanned aerial vehicles (UAVs), the requirements for their safety and reliability are becoming increasingly stringent. In this paper, based on the feedback of airframe performance health perception information and the predictive function control strategy, the autonomous maintenance of a quadrotor UAV with multi-actuator degradation is realised. Autonomous maintenance architecture is constructed by the predictive maintenance (PdM) idea and the Laguerre function model predictive pontrol (LF-MPC) strategy. Using the two-stage Kalman filter (TSKF) method, based on the established UAV degradation model, the aircraft state and actuator degradation state are predicted simultaneously. For the predictive perception of system health, on the one hand, the system health degree (HD) based on Mahalanobis distance is defined by the degree of airframe state deviation from the expected state, and then the failure threshold of the UAV is obtained. On the other hand, according to the degradation state of each actuator, a comprehensive degradation variable fused with different weight coefficients of multiple actuators degradation is used to obtain the probability density function (PDF) of remaining useful life (RUL) prediction. For the autonomous maintenance of system health, the LF-MPC weight matrixes are adjusted adaptively in real-time based on the HD evaluation, to achieve a compromise balance between UAV performance and control effect, and greatly extend the working time of UAV. Simulation results verified the effectiveness of the proposed method.

Prognostics and Health Management (PHM) models aim to estimate remaining useful life (RUL) of complex systems, enabling lower maintenance costs and increased availability. A substantial body of work considers the development and testing of new models using the NASA C-MAPSS dataset as a benchmark. In recent work, the use of ensemble methods has been prevalent. This paper proposes two adaptations to one of the best-performing ensemble methods, namely the Convolutional Neural Network – Long Short-Term Memory (CNN-LSTM) network developed by Li et al. (IEEE Access, 2019, 7, pp 75464–75475)). The first adaptation (adaptable time window, or ATW) increases accuracy of RUL estimates, with performance surpassing that of the state of the art, whereas the second (sub-network learning) does not improve performance. The results give greater insight into further development of innovative methods for prognostics, with future work focusing on translating the ATW approach to real-life industrial datasets and leveraging findings towards practical uptake for industrial applications.

The bearing is one of the most important components of rotating machines. Nevertheless,in normal conditions of use, it is subject to fatigue which creates a defect called arolling fatigue spalling. In this work, we present a follow-up of the thrust bearingfatigue on a test bench. Vibration analysis is a method used to characterize the defect.In order to obtain the fatigue curve more adjusted, we have studied the vibration levelaccording to statistical indicators: the Root Mean Square value (RMS value), which is oneof the best indicators to show the evolution of the bearing degradation. The approachfollows the working of the bearing until the degradation with an on line acquisition ofvibration statements in form of time signals. With the signal treatment, we obtain thevalues of the vibration amplitudes which characterize the vibration state of the bearing.Consequently, these values allow us to plot the fatigue curves. During our experimentalwork, this operation is applied for a batch of thrust bearings for which we have obtainedsimilar fatigue curves where the evolution trend follows a regression model from thedetection of the onset of the first spall. The result of this work will contribute topredict the working residual time before failure.

Le travail que nous présentons dans cet article a pour but de montrerles avantages liés à la mise en place d'une maintenance prédictive,relative aux outils de coupe pour les usinages à enlèvement de matière.Nous décrivons la méthode de détection des fautes basée sur l'utilisationdu modèle analytique de la rugosité des pièces usinées. Ce modèleest établi sous des conditions de coupe données, calculées en fonctionde la rugosité maximale souhaitée. Deux types de fautes, d'une partl'usure prématurée de l'outil de coupe et d'autre part le bris del'outil sont injectées lors de l'usinage des pièces et permettentainsi de valider la méthode de détection proposée. Le principe decette méthode est de comparer la rugosité mesurée à la rugosité calculéeà partir du modèle analytique. En l'absence de faute, les deux valeurstraduisant ces rugosités sont identiques, tandis que l'occurrence d'unefaute se traduit par une différence entre ces deux signaux, cettedifférence étant appelée résidu. Une maintenance systématique estégalement proposée pour pallier à l'usure normale de l'outil. La duréede vie de l'outil de coupe est calculée en utilisant le modèle dela rugosité couplé à la rugosité maximale spécifiée.

Les électrobroches UGV sont des systèmes complexes et fortement sollicités qui sont la cause de frais d'exploitation élevés : défaillance prématurée initiée par des incidents d'utilisation (chocs, surcharges) ou provoquée par une fuite de fluide de coupe ou de refroidissement ; dégradation du cône et des éléments de serrage des porte-outils ; dégradation des roulements... Le problème a été étudié conjointement par le LSIS, le LARAMA, COMAU et PCI. Une analyse statistique a été conduite, conjointement à une analyse technologique. La première visait à déterminer les causes principales de défaillance et la deuxième, à identifier les éléments les plus sensibles et les plus critiques. Cet article présente le point de vue statistique ainsi que les orientations de travaux qui en ont résulté, visant à évaluer l'évolution de la dégradation par des mesures in situ, afin de déclencher les interventions de maintenance à bon escient.