Search for: All records

Abstract Identifying sustainable chemical processes often depends on the choice of enabling materials that directly influence the overall performance. Matching property targets while incorporating adequate process knowledge is essential for optimal material selection. Multi‐scale decisions need to be taken simultaneously to determine the optimal process configurations, operating conditions, and material structures. Integrating molecular to process scale decisions within an equation‐oriented optimization framework leads to large‐scale mixed‐integer nonlinear programs (MINLP). Over the years, several solution approaches have been suggested to tackle this issue. Here, the current state‐of‐the‐art in the field of computer‐aided molecular and process design (CAMPD) is discussed and key challenges and open questions are highlighted that may stimulate future research. 

Group contribution (GC) models are powerful, simple, and popular methods for property prediction. However, the most accessible and computationally efficient GC methods, like the Joback and Reid (JR) GC models, often exhibit severe systematic bias. Furthermore, most GC methods do not have uncertainty estimates associated with their predictions. The present work develops a hybrid method for property prediction that integrates GC models with Gaussian process (GP) regression. Predictions from the JR GC method, along with the molecular weight, are used as input features to the GP models, which learn and correct the systematic biases in the GC predictions, resulting in highly accurate property predictions with reliable uncertainty estimates. The method was applied to six properties: normal boiling temperature (Tb), enthalpy of vaporization at Tb (ΔHvap), normal melting temperature (Tm), critical pressure (Pc), critical molar volume (Vc), and critical temperature (Tc). The CRC Handbook of Chemistry and Physics was used as the primary source of experimental data. The final collected experimental data ranged from 485 molecules for ΔHvap to 5640 for Tm. The proposed GCGP method significantly improved property prediction accuracy compared to the GC-only method. The coefficient of determination (R2) values of the testing set predictions are ≥ 0.85 for five out of six and ≥ 0.90 for four out of six properties modeled, and compare favorably with other methods in the literature. Tm was used to demonstrate one way the GCGP method can be tuned for even better predictive accuracy. The GCGP method provides reliable uncertainty estimates and computational efficiency for making new predictions. The GCGP method proved robust to variations in GP model architecture and kernel choice.