Extension of Probability-Based Multi-objective Optimization in Condition of the Utility with Desirable Value
摘要
It represents the extension of probability-based multi-objective optimization in condition of the utility with desirable value, which includes the types of “one side desirability problem” and “one range desirability problem”; thereafter, the evaluations of partial and total preferable probabilities of the multi-objective optimization experiment design are conducted according to the common procedure of the probability multi-objective optimization. Finally, regression analysis is employed for the total preferable probability to get its maximum and optimal status with desirable response variable. Application examples of the experimental designs of maximizing yield with constraints of viscosity and molecular weight and the maximizing conversion rate with constraints of desirable thermal activity are given in detail; satisfied results are obtained.