Robust chemical product design via fuzzy optimisation approach

Product superiority is usually the only factor considered while designing optimal products using molecular design techniques for specific applications. It is to be noted that the accuracy of property prediction model can affect the effectiveness of this approach. Thus, the effect of property prediction uncertainty has to be addressed while designing optimal products. This paper presents a systematic methodology for the design of optimum molecules used in chemical processes by considering both product superiority and robustness. Product superiority is quantified by property optimality while product robustness is measured by the deviation of product property from the expected property prediction range. Standard deviation of a property prediction model is used to address the uncertainty of the model. Fuzzy optimisation approach is applied into the molecular design techniques in this work. To illustrate the proposed method, a case study is presented where optimal solution is selected based on how much the solution satisfied the criteria of product superiority and robustness.