Modeling and Identification of Spacecraft Systems Using Adaptive Neuro Fuzzy Inference Systems (ANFIS)
Tharwat O. S. Hanafy · IOSR Journal of Engineering · 2014
This paper concentrates on the identification of Multiple Inputs Multiple Outputs (MIMO) system data with and without noise by means of a hybrid-learning rule, which combines the back propagation and the Least Mean Squared (LMS) to identify parameters.We construct a neuro fuzzy model structure, and generate the membership function from the measured data based on deterministic and soft computing.The four cases has been done.The first two cases for deterministic without and with noise have done.The second two cases for ANFIS without and with noise also have been done..The MIMO system model is represented as a set of coupled input-output MISO models of the Takagi-Sugeno type.Neuro fuzzy model of the system structure is incorporated easily in the structure of the model.The simulation is used to implement a MIMO spacecraft system using Matlab for moment_yaw, moment_pitch, and moment_roll as input, and velocity in inertial axis as output.Experimental results are given to show the effectiveness of this Adaptive Neuro Fuzzy System (ANFIS) model.This paper attempts to present ANFIS control design framework for a class of nonlinear multiple-input multiple-output (MIMO) system with uncertainties.This research effort is motivated by the following considerations: (a) An appropriate reference model that accurately represents the desired system dynamics is usually assumed to exist and to be available, and yet in reality this is not the case often times; (b) In real world applications, there are many cases where controls are constrained within a physically allowable range, which presents another layer of difficulties to directly apply the reference model based inverse control; (c) It is difficult to consider optimal control even for the reference model as in general the analytic solution to the optimal control problem is not available.The simulation study has been focused on the identification of Multiple Input, Single Output (MISO) non-linear complex systems.