CHAOTIC DIFFERENTIAL EVOLUTION ALGORITHM BASED ON COMPETITIVE COEVOLUTION AND ITS APPLICATION TO DYNAMIC OPTIMIZATION OF CHEMICAL PROCESSES

A chaotic differential evolution algorithm based on competition coevolution is proposed to improve the performance of the differential evolution (DE) algorithm. In the proposed algorithm (named CO-CDE), at first the population is divided into several sub-populations, each sub-population evolves individually, using different differential schemes. At the end of the evolution each sub-population will have one individual with best fitness. After that all the individuals with best fitness compete with each other, at this time the fitness of one individual is defined as the number of times one individual is superior to others. Therefore one individual with best fitness is picked out and its information is shared by the whole population. To avoid premature convergence and raise the probability of escaping from local optima, a chaotic evolutionary operation based on chaotic variables is introduced into the algorithm and implemented to the whole population. The simulation experiment shows that the CO-CDE algorithm generally outperforms the original differential evolution algorithm for a suite of benchmark functions. Furthermore, the CO-CDE algorithm is applied to a dynamic optimization of chemical process. Experimental results have proved the proposed approach effective, statistically consistent, and promising.