摘要
分析了GM(1,1)预测模型存在的理论缺陷和禁区,指出在形成预测模型时规定X^(1)(1)为已知条件是不合理的,应根据实际情况选用其他数据.构建了基于时间响应函数的优化模型,按照变化系数阀值,界定了优化模型的有效区.经过数值模拟,发现优化的GM(1,1)模型优于传统GM(1,1)模型,因此,提出的新的优化模型,为提高GM(1,1)模型预测精度提供了新的途径.
This paper Analyzes the theoretical defect and the prohibited area of GM (1,1) model, and point out that X^(1)(1) shouldn't be limited as the only known condition when forming the prediction model. Instead, other data could be used. Then, the optimum model is established based on time response function. By constrasting the optimum one to the GM (1,1) about the numerical simulation. This paper propose new optimum model, and gives new way to improve the prediction accuracy of GM (1,1) model.
出处
《数学的实践与认识》
CSCD
北大核心
2009年第9期214-219,共6页
Mathematics in Practice and Theory
基金
江苏省高校自然科学基础研究资助项目(08KJD630001)
关键词
GM(1
1)模型
时间响应函数
优化模型
变化系数阀值
GM (1, 1 ) model
time response function
optimum model
threshold of the changing coefficients