System identification of an unmanned quadcopter system using MRAN neural

AEROS Conference 2017

Pairan, M.F.^1 ; Shamsudin, S.S.^1

Department of Aeronautical Engineering, Faculty of Mechanical and Manufacturing, Universiti Tun Hussein Onn Malaysia, Parit Raja, Johor

86400, Malaysia^1

关键词: Accurate prediction;    Data sampling;    Hidden neurons;    Minimal resource allocating networks;    Performance analysis;    Prediction accuracy;    Radial basis function neural networks;    Real-time identification;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/270/1/012019/pdf
DOI  :  10.1088/1757-899X/270/1/012019

来源: IOP

【 摘 要 】

This project presents the performance analysis of the radial basis function neural network (RBF) trained with Minimal Resource Allocating Network (MRAN) algorithm for real-time identification of quadcopter. MRAN's performance is compared with the RBF with Constant Trace algorithm for 2500 input-output pair data sampling. MRAN utilizes adding and pruning hidden neuron strategy to obtain optimum RBF structure, increase prediction accuracy and reduce training time. The results indicate that MRAN algorithm produces fast training time and more accurate prediction compared with standard RBF. The model proposed in this paper is capable of identifying and modelling a nonlinear representation of the quadcopter flight dynamics.