Identification of pneumatic artificial muscle manipulators by a MGA-based nonlinear NARX fuzzy model

Modeling of pneumatic artificial muscle using a hybrid artificial neural network approach

“…The proposed approach shows improvement over a similar work by Chang and Lilly that 23,340 iterations were required to achieve a MSE of 0.0011 [27]. Three strategies were introduced in the MGA based NARX fuzzy model, and these strategies can ensure a global optimal solution, but they do not enhance the local search capabilities of GA. Their proposed best approach can provide a MD of 10% [28]. It is clear that the modeling performance for PAM using ANN model trained by hybrid approach is much better than these three strategies.…”

Modeling and control of a pneumatic artificial muscle manipulator joint – Part I: Modeling of a pneumatic artificial muscle manipulator joint with accounting for creep effect

“…These two phenomena lead to a nonlinear and time-varying behavior and to an increased complexity in the associated control systems. In previous studies on PAMs or PAM manipulators, these drawbacks were mostly left as uncertainties or disturbances to the associated control systems, and the efforts to overcome them were mainly put into the control algorithms, such as sliding mode control [7], nonlinear PID control using neural networks [8], adaptive sliding mode control [9], or NAX fuzzy model by means of genetic algorithm [22].…”

An iterative fuzzy controller for pneumatic muscle driven rehabilitation robot

“…However, the work was based on constant load, and it cannot be used for hybrid control applications. Recently, modified GA based non-linear ARX (NARX) fuzzy model (Anh & Ahn, 2009) was proposed to model PMA behavior. Four different approaches, GA based fuzzy model (max.…”