基于代理模型的仿真模型近似替代方法及其在船舶操纵性建模中的应用

Chapter 1 Introduction 1.1 Surrogate Model 1.2 Design of Experiments 1.3 Global Sensitivity Analysis 1.4 Book Overview Chapter 2 Optimal Latin Hypercube Design Using Local Search-based Genetic Algorithm 2.1 Optimal Latin Hypereube Design 2.2 Local Search-based Genetic Algorithm for LHD Optimization 2.3 Performance Comparison of Optimization Methods 2.4 Summary Chapter 3 Active Learning of Multi-kernel Kriging Surrogate Models Using Regional Discrepancy and Space-ffiling Criteria 3.1 Formulation of Ensemble Surrogate Model 3.2 Ensemble Learning for Kriging Surrogate Models 3.3 Experimental Study 3.4 Summary Chapter 4 Derivative-based Global Sensitivity Measure Using Radial Basis Function 4.1 Estimation of Kernel Width for RBF 4.2 DGSM Estimator Using RBF 4.3 Experimental Study 4.4 Summary Chapter 5 Polynomial Chaos Expansion-enhanced Gaussian Process Regression for Global Sensitivity Analysis 5.1 GPR Surrogate Model 5.2 Global Sensitivity Analysis Using PCEGPR 5.3 Experimental Study 5.4 Summary Chapter 6 Multi-fidelity Kriging Method for Global Sensitivity Analysis 6.1 Cokriging Surrogate Model 6.2 Sobol Indices Based on Cokriging Model 6.3 Experimental Study 6.4 Summary Chapter 7 Reliability-based Design Optimization Using Polynomial Chaos Expansion-enhanced Radial Basis Function Method 7.1 Formulation of RBDO Problem 7.2 Extended Radial Basis Function 7.3 PCE-RBF for RBDO 7.4 Experimental Study 7.5 Summary Chapter 8 Application of Surrogate Model for Ship Maneuvering Motion Modelling 8.1 Formulation of Ship Dynamic Model 8.2 Nonparametric Modelling 8.3 Parametric Identification 8.4 Summary Reference