表6
j t 100 200 300 400 500 600 700 800 900 1000
j c 4.54 4.99 5.35 5.65 5.90 6.10 6.26 6.39 6.50 6.59
解 该问题即解最优化问题:
Σ=
− = + −姿饥
10
1
0.02 2 min ( , , ) ( )
i
j
kt F a b k a be j c
(1)编写M文件fun1.m定义函数F(x,tdata):
function f=fun1(x,tdata)
f=x(1)+x(2)*exp(-0.02*x(3)*tdata)%其中x(1)=a,x(2)=b,x(3)=k
(2)调用函数lsqcurvefit,编迹缺返写程序如下:
td=100:100:1000
cd=[4.54 4.99 5.35 5.65 5.90 6.10 6.26 6.39 6.50 6.59]
x0=[0.2 0.05 0.05]
x=lsqcurvefit(@fun1,x0,td,cd)
直接使用CFTOOL工具箱命令行输入cftool即可,然后选择拟合类型
x=[6.69:0.02:7.53]
y=[4.2,3.7,3.3,2.95,2.63,2.33,2.11,1.87,1.65,1.47,1.32,1.17,1.04,0.925,0.82,0.735,0.653,0.582,0.52,0.462,0.412,0.366,0.325,0.289,0.258,0.23,0.205,0.182,0.162,0.145,0.129,0.115,0.102,0.091,0.081,0.072,0.064,0.057,0.051,0.0455,0.0403,0.036,0.032]
直接输入滑芹辩cftool进入曲线拟合工具箱界面首滑“Curve Fitting tool”
(1)点击“Data”按钮,d出“Data”窗口;
(2)利用X data和Y data的下拉菜单读入数据x,y,然后点击“Create data set”按钮,退出“Data”窗口,返回工具箱界面,这时会自动画出数据集的曲线图;
(3)点击“Fitting”按钮,d出“Fitting”窗口;
(4)点击“New fit”按钮,可修改拟合项目名称“Fit name”,通过“Data set”下拉菜单选择数据集,然后通过下拉菜单“Type of fit”选择拟合曲线的类型,选择类信缺型Power:幂逼近,有2种类型,a*x^b 、a*x^b + c
【代码】
x=[200 300 400 500 600 700 800 900 1000 1100 1200 1300 1400 1500 1600 1700 1800 1900 2000]
y=[0.1 0.25 0.49 0.65 0.7 0.91 1.15 1.26 1.37 1.46 1.52 1.60 1.65 1.67 1.68 1.68 1.69 1.69 1.71]
cftool(x,y)
【拟合方式一:指数拟合】
General model Power2:
f(x) = a*x^b+c
Coefficients (with 95% confidence bounds):
a = -44.95 (-570, 480.1)
b = -0.02049 (-0.297, 0.2561)
c = 40.3 (-490, 570.6)
Goodness of fit:
SSE: 0.1527
R-square: 0.9708
Adjusted R-square: 0.9672
RMSE: 0.0977
【拟合方式二:最高三次多项式】
Linear model Poly3:
f(x) = p1*x^3 + p2*x^2 + p3*x + p4
Coefficients (with 95% confidence bounds):
p1 = -1.208e-011 (-1.778e-010, 1.536e-010)
桐棚祥 p2 = -6.613e-007 (-1.214e-006, -1.088e-007)
p3 = 0.002397 (0.001855, 0.00294)
p4 = -0.388 (-0.5376, -0.2384)
Goodness of fit:
SSE: 0.02784
R-square: 0.9947
Adjusted R-square: 0.9936
RMSE: 0.04308
【拟合方式三:最高四次多项式】
Linear model Poly4:
f(x) = p1*x^4 + p2*x^3 + p3*x^2 + p4*x + p5
Coefficients (with 95% confidence bounds):
p1 = 4.099e-013 (1.256e-013, 6.942e-013)
p2 = -1.815e-009 (-3.073e-009, -5.575e-010)
p3 = 2.001e-006 (1.018e-007, 3.9e-006)
p4 = 0.0009045 (-0.0002188, 0.002028)
p5 = -0.1391 (-0.3494, 0.07117)
Goodness of fit:
SSE: 0.01654
R-square: 0.9968
Adjusted R-square: 0.9959
RMSE: 0.03437
【小结和粗】
实际上多项式拟合经度(SSE,RMSE)四次高于三次,因为四次包含了三次,需要根据物理模型来确定选择多项式最高次数。
指数模型精度低于三次多项式。
本文希望你局搏能认识一个新的有用的函数,曲线拟合工具箱
希望你学习进步。
欢迎分享,转载请注明来源:内存溢出
评论列表(0条)