Discretization of Simplified Evaluation in Probability-Based Multi-objective Optimization by Means of GLP and Uniform Experimental Design

Discretization treatment of evaluation in probability-based multi-objective optimization by means of GLP and uniform experimental design is illuminated, which provides efficient simplification with low discrepancy. Some examples of application of multi-objective optimization with complicated integrals and estimation of extreme value are given, including evaluations of multi-objective optimization in structure and material designs for tower crane boom tie rods, optimal design for the composition of rubber, linear and nonlinear programming problems with domain in non-regular area, and multi-objective optimization of numerical control machining parameters for high efficiency and low carbon.