A novel sequential approximate optimization approach using data mining for engineering design optimization

For most engineering design optimization problems, it is hard or even impossible to find the global optimum owing to the unaffordable computational cost. To overcome this difficulty, a sequential approximate optimization (SAO) approach that integrates the hybrid optimization algorithm with data mining and surrogate models is proposed to find the global optimum in engineering design optimization. The surrogate model is used to replace expensive simulation analysis and the data mining is applied to obtain the reduced search space. Thus, the efficiency of finding and quality of the global optimum will be increased by reducing the search space using data mining. The validity and efficiency of the proposed SAO approach are examined by studying typical numerical examples.