论文部分内容阅读
在对涡轮叶片低循环疲劳寿命概率分析的基础上,将广义回归型神经网络(generalized regression neural network,GRNN)与果蝇优化算法(fruit fly optimization algorithm,FFOA)结合,利用果蝇优化算法的多点全局的快速搜索能力来优化影响疲劳寿命的随机变量,进行涡轮叶片低循环疲劳寿命健壮性优化设计.优化结果表明:疲劳寿命的概率区间减小17.9%,对随机变量的敏感度降低,从而可以更精确地对疲劳寿命进行估计.计算结果验证了该方法在工程应用中的可行性.
Based on the analysis of the low cyclic fatigue life of turbine blades, the generalized regression neural network (GRNN) was combined with fruit fly optimization algorithm (FFOA) Point global fast search ability to optimize the random variables that affect the fatigue life to optimize the robustness of low cycle fatigue life of turbine blades.The optimization results show that the probability range of fatigue life decreases by 17.9% and the sensitivity to random variables decreases, The fatigue life can be estimated more accurately.The calculation results verify the feasibility of this method in engineering application.