Using Linear Genetic Programming to Develop a C/C++ Simulation Model of a Waste Incinerator

To evaluate whether this is feasible for complex industrial processes, we test the approach on data obtained from the operation of a hazardous waste incinerator. This process is a difficult problem to model. Previously, in a well-conducted study, the popular machine learning technique, analytic neural networks, was unable to derive useful solutions to this problem. The present study used various mutation rates (95%, 50%, and 10%), ten random initial seeds per mutation rate, and a large number (1,280 to 4,461) of generations. The GP system evolved excellent solutions to this problem -the best validation data measure of fitness, R, was 0.961.