Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Indonesian Journal of Aerospace

Optimization of Powered Landing Control for Reusable Rockets Using Softmax DDGN Rafika Arum Sari; Muhammad Hadi Widanto; Imron Rosadi
Indonesian Journal of Aerospace Vol. 22 No. 2 (2024): Indonesian Journal Of Aerospace
Publisher : BRIN Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This research presented a novel approach to optimize powered landing control on reusable rockets by using Softmax Double Deep Q-Networks (DDQN). We combined the advantages of Double DQN with Softmax exploration and curriculum learning to achieve precise and efficient landing control. Through extensive experiments in a specially developed 2D simulation environment, our method achieves improved landing accuracy by 37% (reduced final position error from 2.4 m to 1.5 m), better fuel efficiency by 28% (reduced average fuel consumption from 850 kg to 612 kg per landing), and improved adaptability to initial conditions (improved successful landing rate from 76% to 94% across a wide range of altitudes and initial orientations) compared to traditional PID control methods. The results showed that the curriculum learning method significantly outperformed the non-curriculum approach, achieving 27% higher average awards (11.97 vs. 8.61) and 60% better performance consistency as measured by standard deviation (0.92 vs. 2.29). Both Softmax and ε-greedy exploration strategies proved effective with curriculum learning, with ε-greedy DDQN achieving the highest average award of 11.97. This approach allows for higher precision rocket landings while reducing operational costs through.
The Effect of Cross-section and Elliptical Hole Ratio on Crashworthiness Parameters of Crash-Box Structure Warsiyanto, Budi Aji; Widanto, Muhammad Hadi; Musthofa, Ilham; Maulana, Ichsan; Sitompul, Sahril Afandi; Yuniarti, Endah
Indonesian Journal of Aerospace Vol. 19 No. 1 (2021)
Publisher : BRIN Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30536/j.jtd.2021.v19.a3408

Abstract

The thin-walled column structure or crash-box with metal material and consisting of multi-cell were found to be much more efficient in energy absorption than single-cell under axial impact loads. In this study, a numerical analysis was performed using the Abaqus finite element method for the cross-section differences in thin-walled column structures. The cross-section differences are compared to get a configuration that complies with the indicator parameters using the complex proportional assessment (COPRAS) method. The chosen cross-section configuration is further enhanced by creating elliptical holes with different diameter ratios. The results show that the thin-walled column structure with nine-cell cross-section accompanied by an elliptical hole ratio of 0.3 indicates the potential corresponding to the indicator parameters for the crashworthiness application.
Dynamic response of the wing during UAV collision Warsiyanto, Budi Aji; Widanto, Muhammad Hadi; Musthofa, Ilham; Maulana, Ichsan
Indonesian Journal of Aerospace Vol. 19 No. 1 (2021)
Publisher : BRIN Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30536/j.jtd.2021.v19.a3514

Abstract

An airborne collision between civil Unmanned Aerial Vehicles (UAVs) and manned aircraft is a potential threat to aircraft operation safety. In this paper, the UAV collision test was performed on a commuter aircraft wing section to investigate the dynamic response of this primary operation component. The projectile was a 735 g drone named ‘Mavic’. Explicit dynamic code ABAQUS was employed to simulate the collision process based on the difference of collision scenarios to assess the hazard. The results showed that 735 g drone impact at the aircraft maximum approach flap and cruising speed could cause some damage on the wing front spar and the situation is more serious than 910 g bird strike in which the hardness of drone components rather than kinetic energy is a decisive factor. The lithium-ion battery penetrated the airframe which may be a potential source of ignition.