A Comparison of FAM and CMAC for Nonlinear Control

Arit Thammano
Cihan H. Dagli, Missouri University of Science and Technology

This document has been relocated to http://scholarsmine.mst.edu/engman_syseng_facwork/236

There were 6 downloads as of 28 Jun 2016.


This article compares a neural network-based controller, both local and global networks, with fuzzy associative memories (FAM) on a nonlinear problem. CMAC and FAM are chosen as representatives of local generalization networks. CMAC controller is trained off-line, therefore, it can response to the incoming input immediately. CMAC can interpolate its memory and give a reasonable control signal even the input has not been trained on. Backpropagation is picked as a representative of global generalization networks. All three systems are studied on a simple simulated control problem. This preliminary research will be adapted later to control the laser cutting machine. A performance measure that depends on the transient response and the steady state response of the controlled system is used. The results indicate that CMAC and FAM are comparable