采用回归分析法研究船型主尺度参数对阻力性能的敏感度。首先确定船型参数及其变化范围;然后,通过均匀试验设计方法在设计空间选取样本点,并采用流体分析软件(Shipflow)对每个样本点进行阻力性能数值计算,进而构建样本集,再采用径向基神经网络生成近似模型,并验证近似模型的精度;最后,利用回归分析法得到船型主尺度参数对阻力性能的敏感度排序。通过研究可确定对总阻力性能影响显著的主尺度参数,从而为船型主尺度优化的顺利进行打下基础。
The paper uses regression analysis to study the sensitivity of ship's main parameters on the resistance properties. Firstly, the ship's parameters and their ranges are determined Secondly, the uniform design method is used to select the sample points in the design space, and the fluid analysis software (Shipflow) is used to calculate the resistance performance for each sample point, after which the sample set is built. Then the radial basis function neural network is used to generate the approximate model and its accuracy is verified Finally, the regression analysis is used to get the sort of the ship's main dimensions based on the sensitivity on the resistance performance. Through the research, the main dimension parameter which greatly" influences the total resistance properties is confirmed. It lays foundation for the development of the optimization on ship type main dimensions.