Adaptive Control of Nonlinear Systems Represented by Extreme Learning Machine (ELM) and the Fuzzy Logic Control (FLC)
Abdunaser M. Abdusamad, Mohamed Aburakhis · 2021 IEEE 1st International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering MI-STA · 2021
Extreme learning machine (ELM) has been used in many fields due to its flexibility to approximate highly nonlinear functions. This is because the hidden node parameters are randomly generated and the outputs weights are computed analytically. The idea is based on producing high accuracy function approximation that can follow the system path in the appropriate time. One of the best approaches that work in this area for a long time is the Fuzzy Logic Control (FLC) but the problem of the FLC is that it needs a high volume of data to develop a fuzzy system and the approximation accuracy is related to the number of membership functions. In this paper, we present an adaptive control single-input-single-output (SISO) nonlinear system using ELM and FLC and analyze the results obtained in both cases. Our focus is to decrease the overall MSE produced and the control energy needed.