Intelligent robust tracking control for multi-arm mobile manipulators using a fuzzy cerebellar model articulation controller neural network

Abstract

This article originally analyses intelligent robust tracking for multi-arm fruit-harvesting mobile manipulators (MAFHMMs) with delayed angle-velocity uncertainties. The MAFHMMs are composed of two parts: a crawler-type mobile platform and a four-arm harvesting manipulator. The method proposed here does not require a matching condition for the non-linear uncertainties. A fuzzy cerebellar model articulation controller (CMAC) neural network system is used to approximate an unknown controlled system from the strategic manipulation of the model following the tracking errors. In addition, an adaptive robust compensator is presented to compensate for the uncertainties. Based on the Lyapunov stability theory and neural network approximation capability, several sufficient conditions are derived, which guarantee the convergence of the closed-loop error system. Both simulation and experimental results show the superior control performance of the proposed intelligent control method.

The modeling and controlling of electrohydraulic actuator for quadruped robot based on fuzzy Proportion Integration Differentiation controller

“…To obtain the smooth rule surface, five variables are set with Gaussian membership function 15 for generating outputs. Rules are set based on the experience and the experimental results conducted before.…”

Extracting fuzzy rules for modeling of complex processes using neural networks

“…[1][2][3][4][5][6][7] In the current type of GMDH algorithm, the structure of the model is more complicated, in which selecting neurons for new layers can be obtained from all former layers. 11-13 GA has been applied to obtain optimum structure of GMDH-type neural network.…”

“…In classical GMDH algorithm, there are different methods in selecting neurons for the next layer that are explained completely in previous studies. 1–7 In the current type of GMDH algorithm, the structure of the model is more complicated, in which selecting neurons for new layers can be obtained from all former layers. 11–13 GA has been applied to obtain optimum structure of GMDH-type neural network.…”

“…2 Fuzzy-logic, neural network and genetic algorithm (GA), as the main components of soft computing, have shown significant ability in solving complex non-linear system identification in real world complex modeling. [3][4][5][6][7] Chien et al 8 proposed a new approach to provide the architecture of the neural network and the weights among the layers in order to guarantee stability of the nonlinear ball and beam system without using any learning or adaptive algorithms. Neural network was used in the study of Parhi and Dash 9 to predict the relative crack locations and relative crack depths of a beam structure using the first three natural frequencies and mode shapes.…”

Fractional order controllers tuning strategy for permanent magnet synchronous motor servo drive system based on genetic algorithm–wavelet neural network hybrid method

“…Neural network-based integer order PID (NNbased PID) is a well-known online tuning control technique which has drawn considerable interest in the past years. [17][18][19][20] The two most popular types of NN in NN-based PID are the back propagation neural network (BPNN) 19 and radial basis function neural network (RBFNN). 18,21 However, the training of the BPNN is time consuming and it could fail to converge when high nonlinearities exist.…”