Optimization of Thermal Cracking Operation Using Differential Evolution

This paper presents the application of Differential Evolution (DE), an Evolutionary Computation method, for the optimization of Thermal Cracking operation. The objective in this problem is the estimation of optimal flow rates of different feeds to the cracking furnace under the restriction on ethylene and propylene production. Thousands of combinations of feeds are possible. Hence an efficient optimization strategy is essential in searching for the global optimum. In the present study LP Simplex method and DE, an improved version of Genetic Algorithms (GA), have been successfully applied with different strategies to find the optimum flow rates of different feeds. In the application of DE, various combinations of the key parameters are considered. It is found that DE, an exceptionally simple evolution strategy, is significantly faster and yields the global optimum for a wide range of the key parameters. The results obtained from DE are compared with that of LP Simplex method.