Search

In this study, a surrogate assisted hybrid aggressive space mapping method is suggested to optimize buckling loads of cylinder variable stiffness composites made by fiber steering. Compared with other popular space mapping algorithms, both of surrogate and coarse FE model are integrated to obtain the coarse FE model-based solution. Moreover, the accuracy of surrogate can be enhanced by the sample points evaluated by the fine FE model. Therefore, the suggested method is easy to converge. After optimization by using the suggested algorithm, the buckling load of the variable stiffness cylinder optimized by the method has 43.12% improvement than the constant stiffness cylinder and 32.12% improvement than the quasi-isotropic cylinder, respectively. Therefore, it suggests that the suggested method has potential capability to handle complicated design for composites and can be extended to other complicated disciplines. [ABSTRACT FROM AUTHOR]

Differential Evolution (DE) is one of the most powerful stochastic real parameter optimizers. An alternative adaptive DE algorithm called Expected Improvement (EI)-High Dimensional Model Representation (HDMR)-DE is suggested. The EI criterion and the Kriging-HDMR are used to adjust scale factor F and crossover constant C r , respectively. Considering the expensive computational cost of evaluation, the Kriging is integrated to evaluate the objective function when an accuracy criterion is met. To compare the performance, the suggested method, it has been compared with four popular adaptive DE algorithms over 25 standard numerical benchmarks derived from the IEEE Congress on Evolutionary Computation 2005 competition. To verify the feasibility of the suggested algorithm, a real-world application, time-dependent variable Blank Hold Force (BHF) optimization problem is also carried out by the EI-HDMR-DE. The results show that the EI-HDMR-DE improves the performance of adaptive DE and has potential capability to solve some complicated real-world applications. [ABSTRACT FROM AUTHOR]

Abstract: A metamodeling optimization system for nonlinear problems was developed in this study. Boundaries and best neighbors searching (BBNS) intelligent sampling method and fuzzy based progressive metamodeling for space reduction were integrated and applied for this system. The BBNS scheme generates new samples derived from information of boundaries and the best samples of initial sparse distributed samples. It is easy to obtain better samples and avoid local convergence due to boundary information. In order to construct accuracy metamodel, the fuzzy based progressive metamodeling method was implemented to cluster samples generated by BBNS several patches in optimization domain. Only better sets of them are involved in construction of metamodels in each patch by response surface and kriging method. The nonlinear problems with multi-humps as test functions were used for proving accuracy and efficiency of developed system. The practical nonlinear engineering problems were also successfully optimized by this system. [Copyright &y& Elsevier]

The main limits of reanalysis method using CUDA (Compute Unified Device Architecture) for large-scale engineering optimization problems are low efficiency on single GPU and memory bottleneck of GPU. To breakthrough these bottlenecks, an efficient parallel independent coefficient (IC) reanalysis method is developed based on multiple GPUs platform. The IC reanalysis procedure is reconstructed to accommodate the use of multiple GPUs. The matrices and vectors are successfully partitioned and prepared for each GPU to achieve good load balance as well as little communication between GPUs. This study also proposes an effective technique to overlap the computation and communication by using non-blocking communication strategy. GPUs would continue their succeeding tasks while communication is still carried out simultaneously. Furthermore, the CSR format is used in each GPU for saving the memory. Finally, large-scale vehicle design problems are implemented by the developed solver. According to the test results, the multi-GPU based IC reanalysis method has potential capability for handling the real large scale problem and reducing the design cycle. [ABSTRACT FROM AUTHOR]

A novel semi-analytic method for interval-based uncertainty analysis is suggested to calculate the uncertainty measure index in this study. As nonlinear problems commonly cannot be solved analytically, an analytic interval-based uncertainty analysis method for linear problems is deduced, and an explicit expression of the measure index of uncertainty is given. To extend this form to nonlinear analysis, a semi-analytic uncertainty analysis (SAUA) method is suggested by integrating gradient-based optimization methods and Taylor expansion. Initially, a pseudo optimal solution is obtained. Sequentially, a Taylor expansion is used to calculate the performance function based on the pseudo optimal solution. In this way, the uncertainty measure index can be obtained analytically. Considering the bottleneck of surrogate model, an efficient reanalysis assisted material nonlinear analysis (RAMNA) method is integrated. Thus, the efficiency and accuracy of the suggested method are both enhanced. The SAUA method has been applied to large-scale reliability analysis of vehicle components. The results show that the SAUA is effective and efficient, especially for large-scale problems. Furthermore, the SAUA method can also be extended for other mechanical design, and contribute to shortening the design period. [ABSTRACT FROM AUTHOR]