LD
L. De Malsche
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
2 records found
1
Master thesis
(2025)
-
L. De Malsche, V. Yaghoubi Nasrabadi, D. Zarouchas, A. Grammatikopoulos, E. Lemmens
Protecting sensitive objects during a rocket launch is imperative. For equipment going to the ISS this is done through packing them in polymer foam or bubble wrap. Simulating how well an object is packaged is computationally intensive and difficult to implement. To solve this, this thesis examines the performance of three surrogate models, LSTM, LSTM-FC-GP, and LSTM-PCA-GP, to predict the response of a foam packed object when it is subjected to a vibration. The results show that the models can accurately predict the response of the system in both the time and frequency domain. Furthermore, the LSTM models that are augmented with a GP can accurately predict the uncertainty of the system in addition to having better performance.
...
Protecting sensitive objects during a rocket launch is imperative. For equipment going to the ISS this is done through packing them in polymer foam or bubble wrap. Simulating how well an object is packaged is computationally intensive and difficult to implement. To solve this, this thesis examines the performance of three surrogate models, LSTM, LSTM-FC-GP, and LSTM-PCA-GP, to predict the response of a foam packed object when it is subjected to a vibration. The results show that the models can accurately predict the response of the system in both the time and frequency domain. Furthermore, the LSTM models that are augmented with a GP can accurately predict the uncertainty of the system in addition to having better performance.
Bachelor thesis
(2022)
-
Y. Birol, W.L.C.P. Boullart, M.D. Byelov, D.E.S. Hotters, M.J.W.G. van Hugten, A.O. Kıreşi, L. De Malsche, T. Middendorp, M. Moravčík, J.W. Vallinga, A.C. in 't Veld, E.C. Radcliff, G. van Helden, Jacco Dominicus, Harmen Bronkhorst, Tom Pruijsers, Dennis van Oorspronk, Joep Wezel
Training in realistic conditions is crucial for fighter pilots. During this training, a red air team is used to represent adversary threats. Currently, the red air team is made up of friendly aircraft that mimic the tactics of the expected adversaries. However, this method has its limitations, such as that these friendly aircraft do not correctly mimic the performance and detectable emissions of the real adversary aircraft. Furthermore, using real combat aircraft has other downsides. They require active fighters and pilots that require expensive training, and using real aircraft means that these expensive combat aircraft need to spend a lot of their service life filling the role of red air instead of flying real missions. As red air flying hours are not considered to be useful training for the pilots flying them, there is no need for using combat-ready aircraft that can carry real armament, nor for a pilot in the cockpit. Using real combat aircraft has other extensive costs attached to it and is unsustainable looking at its real intended purpose. Just to have a real combat aircraft in the red air fleet requires acquisition of the aircraft, taking it away from active service that it was designed for. It needs a (ground)crew to operate it. It also needs lots of maintenance, requiring mechanics, engineers, tools, hardware, and much more. All of this and the combat aircraft is not used for its designed capabilities in flag missions when it is part of the red team. Therefore, there is a desire for a UAV that can match the performance of the real adversaries, is less expensive to operate, and is more sustainable than the current alternatives to fill the role of red air...
...
Training in realistic conditions is crucial for fighter pilots. During this training, a red air team is used to represent adversary threats. Currently, the red air team is made up of friendly aircraft that mimic the tactics of the expected adversaries. However, this method has its limitations, such as that these friendly aircraft do not correctly mimic the performance and detectable emissions of the real adversary aircraft. Furthermore, using real combat aircraft has other downsides. They require active fighters and pilots that require expensive training, and using real aircraft means that these expensive combat aircraft need to spend a lot of their service life filling the role of red air instead of flying real missions. As red air flying hours are not considered to be useful training for the pilots flying them, there is no need for using combat-ready aircraft that can carry real armament, nor for a pilot in the cockpit. Using real combat aircraft has other extensive costs attached to it and is unsustainable looking at its real intended purpose. Just to have a real combat aircraft in the red air fleet requires acquisition of the aircraft, taking it away from active service that it was designed for. It needs a (ground)crew to operate it. It also needs lots of maintenance, requiring mechanics, engineers, tools, hardware, and much more. All of this and the combat aircraft is not used for its designed capabilities in flag missions when it is part of the red team. Therefore, there is a desire for a UAV that can match the performance of the real adversaries, is less expensive to operate, and is more sustainable than the current alternatives to fill the role of red air...