An automated approximate model generation platform integrating the vehicle type generation, grid division and CFD resistance calculation is established, and the approximate model is obtained based on underwater vehicle resistance. Three approximate models of RSM model, RBF model and Kriging model were compared, and the error results were analyzed. The four-order RSM model with different speed is established, and the different speed model is weighted fitting and the approximate model of multi-speed fitting is obtained, which can be applied to the resistance optimization of multi-speed interval. Based on the intelligent optimization platform of fitting approximation model, MIGA algorithm is adopted to optimize the displacement volume, the longitudinal position of the floating center and the resistance, and get the optimal underwater vehicle type.
For some highly nonlinear problems, the general second-order response surface method (RSM) cannot satisfy the accuracy requirement. To improve accuracy, the highest order number has to be determined in advance. Thus, a progressive trigonometric mixed response surface method (PTMRSM) was proposed to enhance the approximation accuracy and define the highest order number, rather than determining it in advance. After that, a double-loop interval optimization process could be constructed using this PTMRSM to save time while maintaining accuracy when compared to other experimental or computational methods. Unfortunately, the traditional double-loop interval optimization method had issues with the probability of reliable constraints. Then, for the construction of this double-loop interval optimization process, the modified reliable constraints were introduced. A more reliable and effective double-loop interval optimization was introduced for addressing practical engineering problems using the effective approximate method of the PTMRSM and the amended reliable constraints. Two numerical test functions and a composite submersible hull were performed to verify the accuracy and effectiveness of the PTMRSM and the double-loop interval optimization.