Identification of Nonlinear Time Lag Systems by Improved Genetic Algorithm

概要

論文の詳細を見る
In this paper. a new identification method is proposed which can obtain a good accuracy of identification of nonlinear time lag system on the basis of combination of genetic algorithm and sequence method. The nonlinear system may be described as a discrete model of a polynomial type with unknown parameters using Kolmogorov-Gabor's method. The task of system identification is to determine these parameters. Though the system parameters can be obtained through the search of GA. there is a potential risk. in using a simple GA, that a solution is usually stuck at a local minimum. In order to solve this problem. a new GA search method is proposed by adding a sequence search. which is carried out nearby the value of each estimated parameter coming from a simple GA. By this method. the individual whose fitness is larger can be found. As a result. the solution escapes from a local minimum and converges to the optimum one. The effectiveness of the proposed method is demonstrated through simulation of the identification of nonlinear time lag systems. As an application. the proposed identification method is applied to explosion-proof pneumatic robots, which are modeled as nonlinear time lag systems because the controller links with an actuator by a long pneumatic tube to prevent explosion.
福井大学の論文