Efficient integration of optimal solvent and process design using molecular clustering

We present a molecular clustering approach for the efficient incorporation of solvent design information into process synthesis in the integrated design of solvent/process systems. The approach is to be used in conjunction with an integrated solvent/process design approach where the solvent design stage utilises multi-objective optimisation in order to identify Pareto optimal solvent candidates that are subsequently evaluated in a process synthesis stage. We propose to introduce the solvent design information into the process synthesis stage through the use of molecular clusters. The partitioning of the original Pareto optimal set of solvents leads to smaller compact groups of similar solvent molecules from which representative molecules are introduced into the process synthesis model as discrete options to determine the optimal process performance associated with the optimal solvent. We investigate two clustering strategies, serial and parallel clustering, that allow to effectively exploit the solvent-process design interactions to minimise the computational demands of the process synthesis stage. We further propose a clustering heuristic probability that can aid decision making in clustering and can significantly accelerate the search for the best integrated solvent-process systems. The presented method is illustrated with case studies in the design of solvents for liquid-liquid extraction, gas-absorption and extractive distillation systems.