Reverse engineering is applied to identify optimum polymerization conditions for the synthesis of polymers with pre-defined properties. The proposed approach uses multi-objective optimization (MOO) and provides multiple candidate polymerization procedures to achieve the targeted polymer property. The objectives for optimization include the maximal similarity of molar mass distributions (MMDs) compared to the target MMDs, a minimal reaction time, and maximal monomer conversion. The method is tested for vinyl acetate radical polymerizations and can be adopted to other monomers. The data for the optimization procedure are generated by an in-house-developed kinetic Monte-Carlo (kMC) simulator for a selected recipe search space. The proposed reverse engineering algorithm comprises several steps: kMC simulations for the selected recipe search space to derive initial data, performing MOO for a targeted MMD, and the identification of the Pareto optimal space. The last step uses a weighted sum optimization function to calculate the weighted score of each candidate polymerization condition. To decrease the execution time, clustering of the search space based on MMDs is applied. The performance of the proposed approach is tested for various target MMDs. The suggested MOO-based reverse engineering provides multiple recipe candidates depending on competing objectives.
This work proposes a multi-objective optimization (MOO) approach for reverse engineering of vinyl acetate polymerization processes. Our method leverages machine learning (ML) models trained on data from kinetic Monte Carlo (kMC) simulations to replace expensive laboratory experiments. We employ a genetic algorithm (GA) as the MOO optimizer, considering reaction time, monomer conversion, and molar mass distribution (MMD) similarity as objectives. The trained ML models assist the optimization process and predict key polymer properties for candidate recipes generated by the GA, enabling rapid fitness function evaluation. The proposed framework involves: (1) training ML models for monomer concentration and MMD prediction using kMC simulation data; (2) performing GA-based MOO to identify optimal recipes (Pareto front) for a target MMD (3) selecting the most suitable recipe based on user priorities from the resulting Pareto front, considering user-defined weights for each objective (reaction time, conversion, MMD). Our experiments demonstrate that the GA, coupled with simulation-supported ML, efficiently identifies optimal recipes with high accuracy. Notably, the ML models achieve good performance even with limited training data. This approach offers a rapid and cost-effective solution for reverse engineering of vinyl acetate polymerization processes