Flight envelope prediction is a challenging task where one of the difficulties is that widely used methods, like the level set methods, are impractical for systems with more than four coupled state dimensions due to the “curse of dimensionality”. Monte-Carlo simulation based approach suffers less from this, however a large number of simulations is needed to predict a flight envelope, while not all simulations directly contribute towards estimating its boundary. This paper proposes a new approach to alleviate this with the use of machine learning techniques that can distinguish more valuable control sequences within the random samples; this knowledge could be used to reduce the number of simulations required to predict the boundary.
An artificial neural network containing a long short-term memory is trained to map a randomly sampled control sequence to the relative position of the resultant end state of the trajectory compared to a predetermined reference reachable set. This trained network is applied for Monte-Carlo based reachability analysis of a dynamic model with model parameter changes compared to the reference model, which is able to reject 50% of randomly sampled sequences while at most 95% of the rejected samples would not have contributed towards reachable set boundary estimation.

Sustainability has become an increasingly important issue, and several different governments around the world have been working towards more environmentally friendly approaches throughout different industries. This has led to measures such as the European Green Deal, which aims to make Europe climate neutral by 2050. For the aircraft industry, however, this goal creates a so-called circular causality problem. This is because there may be limited investment in increasing production of alternative energy sources due to the limited availability of aircraft that use them. On the other hand airlines may hesitate due to the limited availability of fuel to buy such aircraft. In order to solve this problem, the carbon neutral ready aircraft has been proposed. The carbon neutral ready aircraft is designed such that it initially is powered by fossil fuels and can then be converted to be powered by a carbon neutral energy source. The carbon neutral energy source that is chosen for this aircraft design is synthetic kerosene. The carbon neutral aircraft has a high wing configuration with a high aspect ratio wing. To cope with the large span of the aircraft it was decided to give the aircraft the ability of the wing tips to be folded up. Furthermore, the wing has support struts which connect the wing to the lower part of the fuselage. The propulsion system of the aircraft has two novel features: two wing mounted ultra high bypass ratio turbofan engines and an electrically powered ducted fan, which ingests the boundary layer at the aft of the fuselage. An additional five-gear configuration was chosen for the landing gear to provide the aircraft with stable ground operations while not creating a need for a fairing which interferes with the boundary layer being ingested by the aft ducted fan. Carrying out the design of this aircraft shows that the aircraft is financially feasible and performs as well as the baseline A320 aircraft in terms of payload and range, while allowing sustainability goals such as the European Grean Deal to be met. The aircraft has a 17 % emission reduction compared to the A320neo, while still employing fossil fuel based kerosene. Furthermore, at least 90% by mass of the primary structure of the aircraft is recyclable. From the recommendations however, it is clear that a lot still needs to be done before the carbon neutral aircraft can enter into service in 2030.