Intelligent PID Control for Linear SISO System with Random Communication Delay by Using Online Genetic Algorithms

In this paper we propose an intelligent control strategy for linear SISO systems in the presence of communication delay. We call this control strategy as being intelligent because it has the capability to learn from past events and is able to behave as expected in new situations. We have included the communication delay in the process model. Our control strategy is able, in the same sampling time, to determine the new value of the communication delay and, by using genetic algorithms, to tune the PID controller. The new parameters of the PID controller are memorized and, if in the future there will be again the same communication delay, the parameters for the PID controller will be fetched from memory. This control strategy is able to behave as expected for a new value of the communication delay because the genetic algorithms are used to find the new parameters for the PID controller. Simulation and implementation results are presented. The results show performance improvement when is used our intelligent control strategy. The authors present the implementation for an axis of a 3D crane and using the Ethernet communication.