基于可靠度的海上风机基础结构优化设计方法研究

RBDO METHOD RESEARCH OF OFFSHORE WIND TURBINE FOUNDATION STRUCTURE

该文推荐了一种基于可靠度的优化设计方法,该方法利用支持向量回归机进行两级响应面近似策略,将双层优化问题转换为一个单层优化问题,第一级称为分析响应面,用来拟合极限状态方程的近似表达式,第二级称为设计响应面,用来拟合设计变量和失效概率的关系式,然后借助一种全局的优化方法——粒子群算法求解该确定性的优化问题,该方法的有效性可以从三脚架基础算例中验证。

Traditional reliability- based design optimization （RBDO） requires a double-loop iteration process, solving such nested optimization problems is extremely expensive for a complex structure. For handling the difficulties associated with the problem, a new RBDO approach was presented. In this approach, a two-tier response surface approximation strategy was carried out based on support vector regression machine and converted the nested optimization problem to single-loop optimization problem, the first-tier of response surface was analysis response surface, which was fitted to limit state functions in terms of both design variables and random variables. The second tier was design response surface that was fitted to probability as a function of design variables. Following the reliability analysis, the optimization problem was solved by a global algorithm-particle swarm optimization. The efficiency of the method compared to classical method was illustrated with the tripod foundation.