English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

For any newly developed mechanism the most challenging task is the controller. The controller is an algorithm that organizes the mechanism input energy to perform a specified task. Robot control usually requires the directing of signals or fluid paths of power elements to indicate robot end-effector dynamic behaviour. Furthermore, robot control can be divided into two main areas: kinematic control (the coordination of the links of the kinematic chain to produce desired motions of the robot) and dynamic control (driving the actuators of the mechanism to follow the commanded position velocities). These control strategies are widely used in most robots involving position coordination in Cartesian space by a direct kinematic method (Karlik and Aydin, 2000). In this chapter, an artificial neural network (ANN) adaptive learning algorithm has been implemented for dynamic behaviour control of a new two-degreeof-freedom (2DOF) serial ball-and-socket actuator. The ANN provides computer simulation of human brain activity that gives computers the ability to learn and predict a decision for a specific task. The ANN requires a specific network design followed by a training process. A variety of modifications could be carried out for the network design during the training process. For a robot control scheme there are many uncertainties in the parameters of both the actuators (hydraulic, pneumatic, and electric drivers) and the mechanical parts of the manipulators (Cheah et al., 2003, Tso & Law, 1993, Mills, 1994, Yang & Chu, 1993, Tsao & Tomizuka, 1994, Park & Cho, 1992, Ambrosino et al., 1998). Therefore, to cover the overall complexity of the robot control problem and the quest for a truly autonomous robot system, the application of an ANN to the robot control scheme has been considered (Ananthraman, 1991, Cruse & Bruwer, 1990, Kuperstein & Wang, 1990, Miller et al., 1990, Hasan et al., 2007, Abdelhameed, 1999, Sharkey & Noel, 1997, Brun-Picard et al., 1999). In addition, the proposed hydraulic power system is one with highly non-linear behaviour. Variations in parameters affect the hydraulic system operation and performance, e.g. the laminar and turbulent flows, channel geometry, friction results in the system equation, the relation between flow velocity and pressure, and oil viscosity (Knohl & Unbehauen, 2000). Hence, to 5

Development of Adaptive Learning Control Algorithm for a Two-Degree-of-Freedom Serial Ball And Socket Actuator