Multipopulation differential evolution algorithm based on the opposition-based learning for heat exchanger network synthesis

Multipopulation differential evolution combined with opposition-based learning is developed to improve the convergence efficiency and optimization accuracy for heat exchanger network synthesis. The algorithm is based on a stagewise superstructure simultaneous optimization model without considering stream splitting. The candidate population and its opposite population are searched in parallel. Mutation operations are implemented on both populations to provide a full information exchange among populations at each generation. A regrouping schedule is introduced to avoid premature convergence. The algorithm is applied to five heat exchanger network cases of different sizes. More economic networks are found using this method with less computational time.