论文部分内容阅读
合金疲劳强度随温度变化关系是金属加工过程中需要考虑的重要因素,需要合理选择方法对其进行预测。根据三次样条插值一致收敛性、精度较高等特点,提出了一种基于三次样条插值的非等间距的GM(1,1)模型灰色预测方法。该方法通过三次样条插值法处理原始非等间距采样数据,将其转变为等间距序列,继而用传统等间距GM(1,1)模型进行预测。在预测试验结果中,均方差比值为0.0014,小误差概率为1,精度等级为一级,得到了良好的预测效果。
The relationship between the fatigue strength and the temperature of the alloy is an important factor to be considered in the metalworking process. It needs a reasonable selection method to predict it. According to the cubic spline interpolation uniform convergence and high accuracy, a non-equidistant GM (1,1) model gray forecasting method based on cubic spline interpolation is proposed. The method processes the original non-equidistant sampling data by cubic spline interpolation and transforms it into an equidistant sequence, and then uses the traditional equal-interval GM (1,1) model to predict. In the prediction test results, the mean square deviation ratio is 0.0014, the small error probability is 1, the accuracy level is one level, and the good prediction result is obtained.