An Intelligent Optimization Algorithm Based on Adaptive Change Mechanism

Aiming at the urgent need and existing bottleneck of model parameter optimization in data enrichment in engine design and application, the problem of large dispersion of data enrichment results caused by the uncertainty of data input was carried out. A self-optimization algorithm with the goal of minimizing global deviation was developed in the uncertainty interval by combining multiple input parameters, and the multi-objective problem was converted into a single objective problem by adding weights, The adaptive weight change mechanism is introduced to balance the optimization intensity of each objective. In the end, the algorithm gets only one solution, which eliminates the difficulty of engineers’ selection of solutions and greatly improves the efficiency of optimization.