M. Sturm et al., HYBRIDIZATION OF NEURAL AND FUZZY-SYSTEMS BY A MULTI AGENT ARCHITECTURE FOR MOTOR GEARBOX CONTROL, Fuzzy sets and systems, 89(3), 1997, pp. 309-319
Citations number
23
Categorie Soggetti
Computer Sciences, Special Topics","System Science",Mathematics,"Statistic & Probability",Mathematics,"Computer Science Theory & Methods
In this paper a hybrid system for motor control on testbeds, consistin
g of neural networks with a self-organizing process state detection an
d fuzzy rulebases, is proposed. The basic mechanism used for hybridiza
tion is a multiagent system composed from loosely interconnected subsy
stems for the different control tasks to be accomplished. The major ai
ms taken into account are: using standard - and approved - subsystems,
realize an easily expandable system, which can handle the exchange or
even failure of a component. The proposed system is implemented as a
first stage using a simple motor and car simulation. First results sho
w the system's capability to control the car simulation precisely foll
owing a given speed profile using knowledge acquisition from the fuzzy
system to the neural network. Published by Elsevier Science B.V.