Research of the 3-DOF Helicopter System Based on Adaptive Inverse Control

Abstract

For the flight control problem occurred in 3-DOF Helicopter System, reference adaptive inverse control scheme based on Fuzzy Neural Network model is designed. Firstly, fuzzy inference process of identifier and controller is achieved by using the network structure. Meanwhile, the neural network connection weights are used to express parameters of fuzzy inference. Then, back-propagation algorithm is adopted to amend the network connection weights in order to automatically identify the fuzzy model and adjust its membership functions and parameters, so that the actual system output of adaptive inverse controller control which is adjusted can track the reference model output. Finally, the simulation result of 3-DOF Helicopter System based on the scheme shows that the method is effective and feasible.

Metodologia de Controle Inverso Adaptativo Indireto via Algoritmo FASS-NLMS

“…Para as técnicas de AIC, o vetor de pesos da função de transferência inversa da planta é atualizado em função da minimização de um índice de performance por um algoritmo de otimização baseado, por exemplo, no método do gradiente descendente estocástico. Na literatura, para o projeto de AIC, já foram utilizados os seguintes algoritmos adaptativos baseados no método do gradiente descendente estocástico: Least Mean Square (LMS) [11], Normalized Least Mean Square (NLMS) [7] e Affine Projection (AP) [3]. O algoritmo NLMS ao contrário do LMS, soluciona o problema de sensibilidade à dimensão do vetor de entrada pela normalização com a potência desse sinal.…”

Direct and Indirect Adaptive Inverse Control Design for Non-Minimum Phase EHA System with Periodic Disturbance via FASS-NLMS Algorithm

“…The weights vector of a DAIC and IAIC is updated through the minimization of a given performance index described as a function of the error used to update the estimate of the weights vector. Due to this, in the literature some proposals for the DAIC and IAIC design via opti-mization algorithms based on stochastic gradient descent can be found using the following algorithms: Least Mean Square (LMS) (Wang et al, 2013) and Normalized Least Mean Square (NLMS) (Shafiq et al, 2017;Ghazali et al, 2015). In this paper, only the NLMS algorithm is discussed for the DAIC and IAIC design, since this algorithm is less sensitive to variations in the input signal power and performs well on correlated signals (Benesty et al, 2006).…”