Microprocessor implementation of fuzzy systems and neural networks
J. Binfet, Bogdan M. Wilamowski · 2002
Systems were implemented on an 8-bit Motorola 68HC711E9 microcontroller. The on-board features of the HC711 are 512 bytes of RAM and EEPROM and 12 K bytes of UV erasable EPROM. The processor was used with an 8 MHz crystal, allowing an internal clock frequency of 2 MHz. ICC11 for Windows V5 was the compiler used to program the HC711E9. In the case of fuzzy systems three different membership functions were used: trapezoidal, triangular, and Gaussian and two different defuzzification processes: Zadeh and Tagagi-Sugeno. In the case of neural networks all architectures were developed and optimized with a help of SNNS. Both, layered and fully connected structures were investigated. In the case of neural controllers implemented on a microprocessor the code is simpler, much shorter; the processing time is comparable with fuzzy controllers. Control surfaces obtained from neural controllers also do not exhibit the roughness of fuzzy controllers.