Artificial intelligence-based optimization for ring-opening metathesis polymerization of proton exchange membrane

Abstract

Abstract The proton exchange membrane (PEM) is one of the significant components in PEM fuel cells. However, conventional synthesis experiments for proton exchange membrane (PEM) require considerable workload and time due to complicated conditions and various influencing factors. Here we initially utilized artificial intelligence (AI) techniques based on the artificial wolf pack algorithm (AWPA) to optimize the synthesis reaction conditions of the ring-opening metathesis polymerization (ROMP) reaction of norbornene derivatives for PEM preparation. An empirical model was established based on four variables, including temperature, reaction time, catalyst amount and ratio of reactants, with two fitness functions, including molecular weight (MW) and molecular weight distribution (MWD). Four trend indices were used, including the mean average precision (mAP), the mean, standard deviation (mSTD), the moving mean of the average precision (mmAP) and the moving mean of standard derivation (mmSD). The theoretical optimum values of operating conditions were obtained successfully, including reactant ratio (0.71), temperature (41.23 oC), catalyst content (0.20) and reaction time (47.94 min). The method in this paper helps optimize PEM preparation conditions and guides a database for AI-aid ROMP reactions.