System inductive modeling using genetic programming with a genetic algorithm for parameter adjustment
Antonio M. López, H. Lopez, G. Ojea, Víctor M. González · 2003
System modeling is highly relevant in the automation and simulation processes. Until now, there have been two main ways to deal with the problem. The first is to collect the equations, normally differential, which direct the dynamics of the system and to solve them mainly by the S transform. The other way is to collect enough data from the process and, based on a predefined structure of the model, use a method for the parameter adjustment such as the least mean squares technique. In this paper an alternative method is presented. Based on the technique like genetic programming, a particular application of genetic algorithms where the structures under adaptation are "computer programs", a tray for the induction of models in the block diagram representation using simple discretized systems is made. The genetic program needs a way of performing parameter adjustment. For this purpose, a genetic algorithm has been applied with highly convincing results.