Abstract
Neural networks are one of the methods used in system identification problems. In this study, a NARX network with a serial-parallel structure was used to identify an unknown aerial delivery system with a ram-air parachute. The dataset was created using the software-in-the-loop method (Software in the loop). Gazebo was used as the simulator and PX4 was used as the autopilot software. The performance of the NARX network differed according to parameters used, such as the selected training algorithm, input and output delays, the hidden layer, and the number of neurons. Within the scope of this study, each parameter was examined independently. Models were trained using MATLAB 2020a. The results demonstrated that the model with one hidden layer and five neurons, which was trained using the Bayesian regularization algorithm, was sufficient for this problem.
Reference37 articles.
1. Precision Aerial Delivery Systems: Modeling, Dynamics, and Control;Yakimenko,2015
2. Evolution of flight vehicle system identification
3. System Identification of a Parafoil-Load Vehicle-Lessons Learned;Jann;Proceedings of the 18th AIAA Aerodynamic Decelerator Systems Technology Conference and Seminar,2005
4. Real-Time Parameter Estimation using Output Error;Grauer;Proceedings of the AIAA Atmospheric Flight Mechanics Conference,2014
5. Aerodynamic model identification and GNC design for the parafoil-load system ALEX;Jann;Proceedings of the 16th AIAA Aerodynamic Decelerator Systems Technology Conference and Seminar,2001
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献