On using fuzzy logic to integrate learning mechanisms in an electro-hydraulic system. II. Actuator's position control

For pt.I see ibid., p.305-16 (2000). In Part I of this paper, fuzzy modeling showed its potential to describe the behavior of the electro-hydraulic system. To verify the possibilities of its application for the system's learning control, two inverse-model compensation schemes were implemented. This paper describes and discusses the experimental results obtained, showing the feasibility and effectiveness of the learning controllers in: generalizing their previously acquired knowledge to possible new trajectories; their ability to learn new rules and update their fuzzy models while functioning; and how they compensate changes in the system's dynamics caused by the variation of the parameters and/or environment perturbations on it.