Abstract
The unknown nonlinear system identification is an identification method used in the area of the automatic control. However, most methods for system identification and parameter adjustment are based on linear analysis, thus, it is difficult to extend them to nonlinear systems. In this paper, particle swarm optimization (PSO) is studied and is applied to modify the performance of feedback neural network (FNN) and forms MFNN algorithm for identifying nonlinear system. Comparing with hybrid algorithm of FNN, MFNN has less parameters needed to be adjusted, faster convergence speed and higher identification precision in the numerical experiment. The effectivness of this intelligent method is verified by engineering examples, widely application of MFNN for nonlinear system identification could be expected.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
