Modelling of neurofuzzy control of a flexible link

Abstract

A modelling approach for neuro-fuzzy control of a single-link flexible robot manipulator that uses a computer-aided design (CAD) program is proposed. Initially, a CAD model of the flexible link is created using experimentally determined values of system parameters. This CAD model is then exported to MATLAB software and the Simulink/ SimMechanics toolbox. An adaptive-network-based fuzzy logic controller is used for position and vibration control of the flexible link.Experimental and simulation results are presented that validate the proposed approach.

Robust tracking control design and its application to balance a two-wheeled robot steering on a bumpy road

“…Therefore, the conventional direct adaptive law does not necessarily lead to parameter convergence. This indicates that the adaptive fuzzy SMC (equations ( 15) and ( 23)) does not necessarily approach the optimal SMC law in equation (5).…”

“…However, the conventional direct adaptive mechanism partially adjusts the controller parameters and the optimal values cannot be achieved, which increases tracking time. To promote the adaptive ability, several other approaches, such as the adaptive neuro-control scheme, 3 the genetic algorithm-based fuzzy-neural sliding-mode controller, 4 the adaptive-network-based fuzzy controller, 5 and the wavelet-neural-network bound observer, 6 have been proposed for nonlinear dynamic systems such as electrical servo drive, robotic, manipulator, and electromechanical systems. A major advantage of these schemes is that the adaption laws are derived based on the Lyapunov synthesis method; therefore, the stability of the controlled systems can be guaranteed.…”

A composite controller for manipulator with flexible joint and link under uncertainties and disturbances

“…In the last years, the controller design for the flexible link or flexible joint manipulator has been extensively studied. Many advanced technologies have been applied in the flexible link, such as sliding mode control (Xu et al, 2000; Mujumdar et al, 2015), boundary control (Jiang et al, 2018; Mamani et al, 2012), neural network (NN) control (Gao et al, 2019; Hu et al, 2020a, 2020b; Xu, 2018), fuzzy control (Jnifene and Andrews, 2005; Lin and Lewis, 2003; Tinkir et al, 2010), robust control (Lee and Lee, 2002; Shafei et al, 2020), and singular perturbation (SP) approach (El-Badawy et al, 2010; Siciliano and Book, 1988). In Choi and Cheon (2004), a sliding mode controller was already reported.…”

Decreasing infinite-mode vibrations in single-link flexible manipulators by a continuous function

“…The feedback control strategies, which use measurements of system states to control vibrations in a closed loop, include the proportional–integral–derivative control, 9,10 delayed feedback control, 11 positive position feedback control, 12 linear quadratic regulator, 13 adaptive control, 14,15 sliding-mode control, 16,17 fuzzy control, 18,19 and artificial neural network–based control. 20,21 The open-loop control strategies, which filter the inputs to produce a desirable motion that results in minimal vibrations, include the optimal trajectory planning 22–24 and input shaping. 25–28 More works for dynamics and control of flexible link manipulators might be found from the literature review.…”