摘要
在分析了灰色预测方法和支持向量机各自的优缺点基础上,提出了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,文章所提出的裂纹扩展预测模型较传统的GM(1,1)模型、等维GM(1,1)模型精度都有所提高,为预测疲劳裂纹扩展提供了一种新的方法.
The advantages and disadvantages of grey forecasting methods and support vector machines（SVM） were analyzed respectively. A new fatigue crack propagation forecasting model of grey support vector machines is proposed. The new model develops the advantages of accumulation generation in the grey forecasting method, weakens the effect of stochastic disturbing factors in the 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 forecasts well with obvious advantages.
出处
《中国计量学院学报》
2008年第3期229-232,共4页
Journal of China Jiliang University
基金
浙江省教育厅科研基金资助项目(No.Y200702680)
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
