IMPLEMENTATION OF AN ONLINE ADAPTIVE FUZZY CONTROLLER IN LOW-END HARDWARE

The implementation of art on-line adaptive fuzzy control algorithm in low-end hardware is described. The adaptive controller starts with a v acuous control policy, i.e. its initial control surface is derived fro m a vacuous rule base. The control surface is adapted autonomously in real time using control meta-knowledge and basic learning constructs. Limited system-dependent information is incorporated to tailor the Int el-8031-based hardware to specific applications. This information incl udes input and output signal magnitudes and time-scale information. Si mulations and actual experiments indicate that the on-line adaptive co ntroller is very robust and fault-tolerant. A relatively high learning rare enables the controller to learn to control plants in real time e ven while it is controlling them.