摘要
针对预测机械设备疲劳裂纹的扩展进程,在分析灰色预测方法和支持向量机各自的优缺点基础上,提出将二者相结合的一种新的预测模型——灰色支持向量机裂纹扩展预测模型.新模型发挥了灰色预测方法中"累加生成"的优点,弱化了原始序列中随机扰动因素的影响,增强了数据的规律性,同时避免了灰色预测方法及模型存在的理论缺陷.工程实例表明,裂纹扩展测模型较传统的GM(1,1)模型、传统支持向量机模型精度都有所提高.
Accurately and rapidly forecasting the fatigue crack propagation is of practical significance and remarkable economic benefit. The advantages and disadvantages of grey forecasting methods and support vector machine（SVM） are analyzed respectively, a new fatigue crack propagation forecasting model of grey support vector machine is presented. The new model develops the advantages of accumulation generation in the grey forecasting method, weakens the effect of stochastic disturbing factors in original sequence, strengthens the regularity of data and avoids the theoretical defects existing in the grey forecasting model. The analysis of engineering practice indicates that the entropy weight combined forecasting model can forecast accurately with obvious advantages.
出处
《湖北工业大学学报》
2008年第4期55-58,共4页
Journal of Hubei University of Technology
关键词
灰色预测
支持向量
时间序列
疲劳裂纹扩展
. grey theory
support vector machine
time sequence
fatigue crack propagation
