摘要
以7种常用航空金属材料的疲劳试验数据为基础,首次利用最小二乘法支持向量机确定了材料的应力-寿命关系及相应的S-N曲线,并将所得结果与传统的幂函数式和三参数式的结果进行了比较,发现:支持向量机不仅能够描述材料的应力寿命关系,而且与现有的幂函数和三参数表达式相比,支持向量机最好;利用支持向量机描绘的S-N曲线,不仅能够精确确定任意交变名义应力作用下材料的疲劳寿命,而且还可精确确定材料的疲劳极限,为保证结构设计和使用的可靠性打下了基础。
Based on the seven conventional aero-metals fatigue test data,the relationship between cyclic stress-fatigue life and the S-N curve are obtained by the Least Squares Support Vector Machine(LSSVM) firstly.The S-N curves got by LSSVM and by the power function and the three-parameter equation are compared.It is found that the LSSVM not only can be used to describing the relationship between the cyclic stress-fatigue life,but also is the best method compared with the power function and the three-parameter equation.Using the S-N curve got by LSSVM,the fatigue life under the cyclic stress can be precisely obtained,and the fatigue limit can be obtained too.So,the security can be ensured for the structure design and using.
出处
《空军工程大学学报(自然科学版)》
CSCD
北大核心
2012年第2期90-94,共5页
Journal of Air Force Engineering University(Natural Science Edition)
基金
国家自然科学基金资助项目(10804130)
关键词
支持向量机
应力-寿命关系
S-N曲线
疲劳极限
support vector machine
relationship between cyclic stress-fatigue life
S-N curve
fatigue limit