Engine health monitoring in the aeronautical domain is crucial. Aircraft engines operate under crucial conditions, and their failure can have major safety and operational consequences. The prognostic and health management (PHM) of engines plays an important role in keeping the operation of engines steady and secure. The main purpose of PHM is to predict future machinery faults by estimating their remaining useful life (RUL). To do so, PHM methods could apply machine learning methods using monitoring data to predict industrial machinery RUL. However, these predictions could differ from one source (predictor) to another, which is not totally reliable. In addition, this imperfection is due to data imprecision that needs to be managed. In this investigation, the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset is used, as engine health monitoring is highly critical and has a great impact on the maintenance of aeronautical systems. To tackle this challenge, we combine the process of studying sliding windows on time series data and taking advantage of the integration of learning algorithms. Specifically, we merge the convolutional neural network (CNN) with multi-layer perceptron, and CNN with long short-term memory. To further enhance the performance, we employ an ensemble learning approach to manage imprecision by applying fuzzy concepts embedded within the adaptive neuro-fuzzy inference system model and a decision tree as a meta-learner. Experimental errors are reduced compared to predictions offered by hard prediction models.

In flight safety monitoring, risk prediction demands high accuracy for rare but critical events such as engine failures and weather-related hazards. However, the limited sample size of such extreme cases within a single dataset poses a significant challenge to achieving precise predictions. Aggregating data across sources is a potential solution, but datasets are often not independently and identically distributed. Transfer learning can improve target performance by leveraging related sources, yet classical methods struggle with heavy-tailed data due to the lack of robust loss functions. This paper proposes a transfer learning algorithm based on composite quantile regression (CQR). It identifies and transfers information from similar sources and constructs pseudo response variables to linearise the CQR loss, enabling robust computation under heavy-tailed noise. Extensive simulation studies demonstrate the superior performance of the proposed method. The practical utility of the algorithm is further illustrated through its application to quick access recorder (QAR) flight data for hard landing risk prediction. This work aims to identify and quantify key controllable factors influencing landing safety through a data-driven approach. Our research provides quantitative analytical tools for multiple core safety aspects, including flight operation standardisation, aircraft condition monitoring, operational environment assessment and support resource allocation, thereby enabling more precise and proactive risk mitigation strategies.

Recent trends in the context of aircraft propulsion and systems electrification are met with challenges, as new sources of on-board waste heat generation are introduced. The development and optimisation of innovative thermal management systems (TMS) for aviation is a key asset in addressing those challenges. Leveraging the intrinsic thermal capacity of Jet-A fuel appears as a promising solution to provide heat source cooling for both conventional and hybrid-electric aircraft configurations. In this paper, the feasibility of a fuel-based thermal management system (F-TMS) is investigated to support thermal control of fuel cells in the context of hybrid-propulsion electrification for a regional transport aircraft. A modelling approach is proposed for the dynamic simulation of the stored fuel mass and temperature, along with a preliminary investigation of the passive heat rejection through the tank walls. The performance of the F-TMS is simulated for two primary cooling architectures, and their thermal endurance is compared across some realistic flight mission profiles. Finally, the influence of altitude, range and alternate flight is investigated to identify critical scenarios of F-TMS utilisation and derive the maximum degree of supported hybridisation.

To meet the requirement of refined airspace risk assessment under the autonomous operation mode, this paper proposes an airspace risk calculation method based on potential field theory. First, an aircraft ellipsoidal risk zone is established to define the risk influence range. Based on the airspace grid and potential field function, a risk assessment model is constructed that considers the real-time impacts of distance, speed, heading, and other factors to model the radiation effect of aircraft operation risk. Second, two simulation scenarios are set up to validate the model’s effectiveness and analyze differences in the spatio-temporal distribution of airspace risk. Additionally, multiple conflict scenarios are established. The correlation coefficients between conflict indicators and average airspace risk values for different flights are calculated to demonstrate the model’s reasonableness. Finally, an airspace hotspot grid marking method is developed. Hotspot distributions are visualized across various grid scales, realizing multi-granularity awareness of the airspace safety situation from a spatial geographic perspective. Simulation results show the model effectively characterizes the real-time spatio-temporal distribution of airspace risk. As the number of simulated aircraft increases, the correlation between conflict indicators and average risk values becomes increasingly strong and stable, verifying the model’s validity. Furthermore, multi-granularity grids reveal hotspot distribution details at different spatial resolutions, providing a reference for on-board auxiliary decision-making systems to make trajectory adjustments.

This study presents a hybrid energy management system (EMS) for unmanned aerial vehicles (UAVs), integrating flexible photovoltaic (PV) panels with a high-capacity lithium-polymer (Li-Po) battery to enhance flight endurance and energy resilience. The proposed EMS features a multi-layered adaptive control architecture, combining fuzzy logic-based decision-making, short-term solar irradiance prediction using machine learning and closed-loop proportional-integral-derivative (PID) motor control. This architecture dynamically allocates power based on real-time solar irradiance, battery state of charge (SOC) and propulsion load. The approach aims to minimise battery stress while ensuring stable UAV operation under variable environmental conditions. Simulation results indicate that, without PV support, the UAV battery depletes in approximately 28 min. However, incorporating an 80 W PV panel extends the endurance to 37 min, and a 160 W effective PV configuration increases the flight time to over 50 min, while maintaining the SOC above 20%. This corresponds to a 79% improvement in endurance and nearly a 50% reduction in net battery energy consumption. The EMS effectively mitigates deep discharge cycles, improving battery health and operational lifespan. These findings demonstrate that the proposed hybrid EMS provides a scalable, adaptive and computationally efficient solution for balancing renewable and stored energy. It outperforms conventional static or single-source control strategies, particularly under fluctuating solar conditions.

A novel fixed-time cooperative guidance law is developed to enable multiple flight vehicles to simultaneously intercept various target motions with desired impact angle, including stationary, constant-velocity moving and manoeuvring targets, with a unified guidance structure that requires no mode switching or target motion classification. First, a fixed-time distributed cooperative guidance law is developed using the theory of multi-intelligence cooperative control, which is formulated along the line of sight (LOS) direction. This approach ensures that the impact time is regulated, enabling multiple flight vehicles to intercept the target simultaneously within a fixed time. In the second phase, employing a sliding manifold and a fixed-time reaching law, the normal acceleration of each flight vehicle is designed to ensure that the LOS angle converges to its target value within a fixed duration. Unknown components of the target’s acceleration are estimated via fixed-time observers and incorporated into the guidance commands, enhancing precision and robustness in the guidance process. In conclusion, the proposed approach proves the effectiveness and superiority through numerical simulations, including various target motions, switching communication topology, robustness against uncertainties based on Monte Carlo experiment and comparative studies.

This study investigates the nonlinear dynamics and control strategies for a Cessna-182 unmanned aerial vehicle (UAV). The longitudinal and lateral dynamic models were derived using aerodynamic analysis conducted in ANSYS Fluent. Various control methodologies, including PID (proportional, integral, derivative) tuning with genetic algorithm (GA), root locus (RL), MATLAB tuned (MT), Ziegler Nichols (ZN), the model reference adaptive controller (MRAC), linear quadratic regulator (LQR) and linear quadratic Gaussian (LQG), were implemented and compared through simulations. Due to the inadequacy of PID control under variable environmental and noise conditions, LQR and LQG controllers, including the full state-space model required for real-time applications, are simulated for both longitudinal and lateral motions in addition to the PID controller. Although the LQR controller has acceptable simulation results for noiseless conditions, the superiority and stable structure of the LQG controller under noise and disturbance effects are highlighted. The results, including noise Dryden turbulence effects, highlight the advantages of proposed MRAC and LQG for robust stability and precise flight performance. Experimental flight tests validate the theoretical findings, demonstrating the practical viability of the proposed control approaches. The results obtained for the Cessna-182 mini-UAV will be effective for future researchers in terms of obtaining UAV dynamics and also evaluating different control strategies of the UAV.

In this article, a new triple-loop recurrent neural network and observer-based two-stage fast terminal sliding mode controller (TRNNO-TFTSMC) is proposed for a quadrotor unmanned aerial vehicle (UAV) with nonlinear dynamics and external disturbances. The two-stage fast terminal sliding mode control scheme is designed to guarantee fast convergence of trajectory tracking within a finite time. In the architecture of the flight control system, the triple-loop recurrent neural network (TRNN) is designed to approximate the nonlinear dynamics, which include system uncertainties and known nominal terms. Furthermore, to mitigate the impact of external disturbances and the approximation error of TRNN on the performance of the control system, an observer is employed. Finally, the closed-loop stability of the quadrotor system is ensured based on Lyapunov theory, and the outperformance of the proposed flight control scheme is clearly demonstrated through a comparative study with other techniques.

The introduction of advanced automation and human-artificial intelligence (AI) teaming is expected to permit more efficient use of airspace in the face of increasing air transport demand. Additionally, the development of next-generation aircraft to support net-zero has introduced more complexity into the future flight deck and informational requirements. This study evaluates a design for an ‘intelligent assistant’ system that could share tasks with the pilot during engine failure and pilot incapacitation events, promoting greater reliance on system interaction as workload increases. Four professional pilots were split into two groups to perform six and eight scenarios, respectively. The aim was to identify the task-related information for the designed system to promote transparency to the pilots. Three modalities varied across each scenario (visual, auditory and physical) to evaluate the combination of modality to increase pilot monitoring and interaction with the system. Analysis of participant feedback indicated key limitations to existing human-machine-interaction design, with current operational procedures creating disparity between the system and pilots’ authority to handle the scenario. Additionally, the use of audio narration was negatively received by participants, primarily due to the potential overlap between other audio stimuli, masking the perception of task-critical audio prompts and delaying critical flight tasks from being performed. Design considerations were generated for future ‘intelligent assistant’ systems, with further research required to understand the effect of each modality on pilot reliance on these ‘intelligent assistant’ systems.

Accurate estimation of an aircraft cruise range is a critical challenge in aeronautical engineering that directly influences fuel efficiency, operational costs and environmental sustainability. Traditional analytical models, such as the Bréguet range equation, provide simplified range estimates but often fail to capture the nonlinear dependencies between flight parameters, fuel consumption and aerodynamic efficiency. In this study, machine learning-based regression methods have been employed to model the aircraft cruise range using the cruise flight data of Boeing 737–400, which is one of the most widely used commercial aircraft. Based on the calculated performance metrics, it is determined that the Gaussian process regression model exhibits superior validation and test performance compared to the other models. The developed models provide deeper insight into range variations under various flight conditions by performing accurate and robust predictions.

The paper presents a detailed study on the transonic buffeting phenomenon and related active control problems via a novel nonlinear aeroservoelastic model of reduced-order. An important feature of the study is the reconstruction of the unsteady aerodynamics in transonic buffeting flows via a modified nonlinear state-space identification scheme. Based on the aerodynamic model reduction, the paper gives a nonlinear aeroservoelastic model of reduced-order by coupling the structural dynamics of a wing section with a control surface. To demonstrate the accuracy and efficiency of the above model and the control design for transonic buffeting, the study deals with detailed numerical simulations of a wing section of an NACA0012 aerofoil system with a control surface. The case studies cover the dynamic behaviours of such an aerofoil system, including flutter, limit-cycle oscillations, nodal-shaped oscillations and open/closed-loop aeroservoelastic buffeting oscillations. The numerical results demonstrate that the novel nonlinear reduced-order modeling approach provides an efficient way to synthesise the active buffeting control system. Based on the nonlinear aeroservoelastic model of reduced-order, the control gains of the buffeting controller can be efficiently determined and the unstable buffeting behaviours can also be controlled effectively.

Dynamic soaring (DS) enables unmanned aerial vehicles (UAVs) to extend endurance by extracting energy from atmospheric wind gradients. While prior DS research has primarily focused on fixed-wing platforms using nonlinear optimal control and trajectory optimisation, these methods typically require solving computationally demanding optimisation problems online. In contrast, deep reinforcement learning (DRL) allows computationally intensive training to be performed offline, with real-time deployment requiring only lightweight policy inference. This study investigates autonomous dynamic soaring in a hybrid tricopter UAV, where the two forward-facing rotors provide limited thrust assistance and the rear rotor remains inactive during soaring. A six-degree-of-freedom nonlinear flight model is implemented in MATLAB/Simulink to capture aerodynamic forces and wind-gradient energy interactions. The DS task is formulated as a DRL problem, and three representative algorithms – DDPG, PPO and TRPO – are evaluated. Simulation results demonstrate distinct performance characteristics: proximal policy optimisation (PPO) yields the most stable and repeatable cycles, trust region policy optimisation (TRPO) produces smoother control inputs, and deep deterministic policy gradient (DDPG) converges rapidly but relies more heavily on propulsive thrust. Compared to DDPG, TRPO and PPO improve net energy gain by approximately 42.0% and 30.3%, respectively. These findings demonstrate the feasibility of DS in a tricopter-based hybrid UAV and highlight DRL as an effective framework for autonomous, energy-aware flight.