摘要
针对门式起重机主梁隐式极限状态函数的非概率可靠性分析,提出了一种基于支持向量机回归的主梁非概率可靠性分析方法。调试核函数,优化回归参数,使用训练后的支持向量机替代隐式极限状态函数。利用非概率集合理论中的区间分析法,引入尺寸比例因子,提出了基于支持向量机的起重机主梁非概率可靠性分析方法。最后用1个算例来验证本文方法,结果表明,该方法具有可行性、正确性和高精度的优点,并对其它工程结构的非概率可靠性分析具有一定的参考价值。
For non-probabilistic reliability analysis of main girder of gantry crane with implicit limit state function, a method of non-probabilistic reliability analysis for main girder is presented on the basis of support vector regression. Debugging kernel function and optimizing support vector regression parameters, the post-training support vector machine is used to replace implicit limit state function. Using the interval analysis method of non-probabilistic set theory and introducing the size scale factor, a method of non-probabilistic reliability analysis of main girder based on support vector machines is presented. Finally, one example is used to test the presented method. The results show that the presented method has three virtues of feasibility, correctness and high accuracy, and it has a certain useful value for non-probabilistic reliability analysis of other engineering structure.
出处
《机械设计与研究》
CSCD
北大核心
2012年第3期51-54,共4页
Machine Design And Research
基金
国家自然科学基金资助项目(51175442)
关键词
支持向量机回归
非概率可靠性分析
主梁
隐式极限状态函数
区间分析
support vector regression
non -probabilistic reliability analysis
main girder
implicit limit statefunction
interval analysis
