Dynamic reduction method of hierarchical design space and its application in hull form optimization

Objectives Due to high-dimensional, computationally expensive and "black-box" characteristics, hull form optimization based CFD usually lead to low efficient and poor quality. Methods Based on address the above problems, hierarchical space reduction method(HSRM) based on self-organizing maps(SOM) method and K-means clustering is proposed. Data mining is used to extract the knowledge implicit in the sample simulation data during the hull form optimization. These knowledge can be used to guide the hull form optimization, thus improving the efficiency and quality of the optimization. The proposed method was applied to the optimization of the 7500t bulk carrier shape line. Results The results show that the total drag of the optimised ship type obtained using traditional PSO and HSRM is reduced by 1.854% and 2.266%, respectively, and HSRM leads to a higher quality