Browsing by Author "Zammit-Mangion, David"
Now showing 1 - 7 of 7
Results Per Page
Sort Options
Item Open Access AI for real-time tolerance to critical flight data errors in large aircraft(AIAA, 2023-06-08) Koopman, Cynthia; Zammit-Mangion, DavidThe environment in the cockpit of large transport aircraft is currently highly complex due to an increasing amount of automation systems. This complexity can cause pilots to become less aware of how all systems work and interact. It becomes a severe issue when sensor or data failures occur, as such failures can contribute to a situation in which it is difficult for a pilot to assess what actually is happening and, possibly, where the fault originated from and how to resolve the problem. Erroneous sensor information is known to cause automation to fail or malfunction and there are several instances where such errors led to fatal accidents. This paper presents a method, based on artificial intelligence, for detecting and identifying incorrect critical flight control data in real-time. The aim of this method is to help the pilot assess the state of the aircraft and reduce the risk of confusion due to automation. A novel combination of Reinforcement Learning and an auxiliary denoising autoencoder is proposed to identify where the failures are occurring and to provide command inputs to the aircraft’s flight control and guidance systems, allowing the aircraft to perform the correct manoeuvre to counter the failure and/or to avoid or recover from flight upsets and loss of control. Tests in nominal as well as stall conditions with a partially blocked Pitot tube were conducted. These tests show that the proposed combination of Machine Learning methods creates a system to accurately detect failures (2.5s average detection time), reconstruct input data (RMSE < 6 ft/s for airspeed), and provide stable directions for the flight controls. Due to the specifically designed architecture and training schedule it is possible for the proposed system to achieve this level of performance using only a single neural network. To conclude, a comparison with the performance of the system trained without the auxiliary denoising autoencoder was made to highlight the significant advantages of the proposed architecture for learning meaningful neural connections and how this relates to creating systems with AI to improve situational awareness for pilots and execute appropriate automatic manoeuvres to successfully counter the effect of sensor failures.Item Open Access Concept of operations of an ATC tool for trajectory optimization(International Council of the Aeronautical Sciences, 2016-09) Zammit-Mangion, DavidThis paper presents the Concept of Operations (Con-Ops) associated with integrating a quasi-real-time ground-based trajectory optimization tool in the Air Traffic Control system. The tool is intended to be used a few minutes before a climb or descent to generate trajectories with minimual fuel burn which take into account the latest operational considerations.Item Open Access Design and development of an algorithm for a take-off performance monitor(Cranfield University, 2001-02) Zammit-Mangion, David; Eshelby, M. E.A take-off performance monitor is an instrument that is intended to monitor the progress of the take-off manoeuvre in real-time in order to ensure that the aircraft will meet the various distance constraints of the airfield. Several designs have to date been proposed but none have been successful commercially. This work has involved the development of a novel design concept based on the consideration of the time history of the run to obtain an accurate prediction of the distance required to VI. Scheduled post-VI distances are then allowed for in the estimate of the actual distances required to complete the manoeuvre. A performance standard complementing SAE aerospace standard AS-8044 has also been established to ensure system reliability during operation. The algorithms developed were validated using the College of Aeronautics' Jetstream-100 flying laboratory and take-off data of B747 and B737 aircraft. A fixed-base simulator was also used to evaluate the algorithm in adverse operating conditions. The algorithm was demonstrated to meet the named performance standards and is shown to have the potential of being utilised in a successful commercial performance monitor. A novel display design concept is also proposed, providing a basis on which an attractive display can be further developed.Item Open Access Experimental flight testing of night vision imaging systems in military fighter aircraft(ASTM International, 2013-10-26) Sabatini, Roberto; Richardson, Mark A.; Cantiello, Maurizio; Toscano, Mario; Fiorini, Pietro; Zammit-Mangion, David; Gardi, AlessandroThis paper describes the research and experimental flight test activities conducted by the Italian Air Force Official Test Centre (RSV), in collaboration with Alenia Aermacchi and Cranfield University, in order to confer night vision imaging systems (NVIS) capability to the Italian TORNADO Interdiction and Strike and Electronic Combat and Reconnaissance aircraft. The activities included design, development, test, and evaluation activities, including night vision goggle (NVG) integration, cockpit instruments, and external lighting modifications, as well as various ground test sessions and a total of 18 flight test sorties. RSV and Litton Precision Products were responsible for coordinating and conducting the installation of the internal and external lights. Particularly, an iterative process was established allowing in-site rapid correction of the major deficiencies encountered during the ground and flight test sessions. Both single-ship (day/night) and formation (night) flights were performed, with testing activities shared among the test crews involved, allowing for a redundant examination of the various test items by all participants. An innovative test matrix was developed and implemented by RSV for assessing the operational suitability and effectiveness of the various modifications implemented. Also important was the definition of test criteria for Pilot and Weapon Systems Officer workload assessment during the accomplishment of various operational tasks during NVG missions. Furthermore, the specific technical and operational elements required for evaluating the modified helmets were identified, allowing an exhaustive comparative evaluation of the two proposed solutions (i.e., HGU-55P and HGU-55G modified helmets). The initial compatibility problems encountered were progressively mitigated by incorporating modifications in both front and rear cockpits at various stages of the test campaign. This process allowed considerable enhancement of the TORNADO NVIS configuration, giving good medium- to high-level NVG operational capability to the aircraft. Further developments also include the internal/external lighting for the Italian TORNADO “Mid-Life Update” and other programs such as AMX aircraft internal/external light modification/testing and the activities addressing low-altitude NVG operations with fast jets (e.g., TORNADO, AMX, MB-339CD), with a major issue being the safe ejection of aircrew with NVG and NVG modified helmets. Two options have been identified for solving this problem, namely, the modification of the current Gentex HGU-55 helmets and the design of a new helmet incorporating a reliable NVG connection/disconnection device (i.e., a mechanical system fully integrated in the helmet frame) with embedded automatic disconnection capability in case of ejection. Other relevant issues to be accounted for in these new developments are the helmet dimensions and weight, the NVG usable field of view as a function of eye-relief distance, and the helmet's center of gravity (moment arms) with and without NVG (effect on aircrew fatigue during training and real operational missions)Item Open Access Increasing predictability in the response of an AI-assisted stall recovery system in complex stall conditions by expanding the knowledge-base of AI(IOP Publishing, 2024-03-13) Koopman, Cynthia; Zammit-Mangion, DavidThe environment in the cockpit of commercial aircraft is becoming increasingly complex due to the introduction of automation systems. This complexity is especially evident when malfunctions take place, making it difficult for pilots to comprehend the interconnectedness of the systems and potentially leading to loss of control. This paper investigates a novel method for creating an Artificial Intelligence-based stall recovery assistant using Reinforcement Learning by training the agent to generate a stall and subsequently recover from it. This enables training in a large training space with a simple reward function, where the agent has the ability to develop a deep understanding of the environment. Tests show that the agent is able to recover from stall at a variety of altitudes while experiencing unreliable airspeed information originating from a blocked Pitot tube system and with a better response than all baseline agents. The results indicate that restricting AI is not always necessary and, further, that too many restrictions can lead to a system that learns only shallow features, causing it to be unreliable in unforeseen circumstances.Item Open Access Theoretical optimal trajectories for reducing the environmental impact of commercial aircraft operations(Institute of Aeronautics and Space, 2014-03-01) Celis, Cesar; Sethi, Vishal; Zammit-Mangion, David; Singh, Riti; Pilidis, PericlesThis work describes initial results obtained from an ongoing research involving the development of optimization algorithms which are capable of performing multi-disciplinary aircraft trajectory optimization processes. A short description of both the rationale behind the initial selection of a suitable optimization technique and the status of the optimization algorithms is firstly presented. The optimization algorithms developed are subsequently utilized to analyze different case studies involving one or more flight phases present in actual aircraft flight profiles. Several optimization processes focusing on the minimization of total flight time, fuel burned and oxides of nitrogen (NOx) emissions are carried out and their results are presented and discussed. When compared with others obtained using commercially available optimizers, results of these optimization processes show atisfactory level of accuracy (average discrepancies ~2%). It is expected that these optimization algorithms can be utilized in future to efficiently compute realistic, optimal and ‘greener’ aircraft trajectories, thereby minimizing the environmental impact of commercial aircraft operations.Item Open Access A traffic surveillance function and conflict detection method for runway manoeuvres(AIAA, 2012-06-15) Sammut, Andrew; Zammit, Brian; Zammit-Mangion, DavidRunway conflicts continue to occur regularly in commercial aviation. There have been several initiatives worldwide to implement new systems capable of detecting such conflicts. For example, ground based systems have been implemented in several airports improving the air traffic controller situational awareness. Unfortunately, however, these systems fail to provide support in situations where the time to conflict is very short. This paper discusses the implementation of an algorithm for traffic surveillance and runway conflict detection on board the aircraft to provide the necessary information directly to the crew. The rules on which the detection algorithm is based and the alert suppression logic to reduce the number of nuisance alerts are discussed. A description of the multi-threaded software architecture is also included.