How to plot the least square method?

2 次查看（过去 30 天）
RoBoTBoY
RoBoTBoY 2021-4-24
评论： Star Strider 2021-4-24
Hello!
I have these measurements of an experiment where Kp and Kd are the coefficients of PD controller and model displays critical damping at these measurements.
I want to find the ideal curve with respect to least sqruare method.
How to do that?
I tried that but I don't know if is true.
plot(Kd,Kp,'go')
hold on
f = fit(Kd,Kp,'poly2');
plot(f,Kd,Kp,'b--')
xlim([0.2,1.3])
ylim([-2,22])
legend('Location','NorthWest');
hold off
  3 个评论
显示 1更早的评论
RoBoTBoY
RoBoTBoY 2021-4-24
How do I connect these points with a curve?
So this diagram I drew is wrong?
Star Strider
Star Strider 2021-4-24
Ran in:
'How do I connect these points with a curve?’
Whatever works, unless you have a mathematical model of the process that created them, and in that instance, use that mathematical model with a linear or nonlinear parameter estimation function. Then, using that function and the estimated parameters, calculate the fit and plot the line using those data.
One option is a spline fit —
Kd_Kp = readtable('https://www.mathworks.com/matlabcentral/answers/uploaded_files/595780/Kd_Kp.xlsx')
Kd_Kp = 4×2 table
Kp Kd __ ___ 1 0.3 5 0.6 10 0.8 20 1.2
Kd_v = linspace(min(Kd_Kp.Kd), max(Kd_Kp.Kd));
Kp_v = spline(Kd_Kp.Kd, Kd_Kp.Kp, Kd_v);
figure
scatter(Kd_Kp.Kd, Kd_Kp.Kp, 'filled')
hold on
plot(Kd_v, Kp_v, '-r')
hold off
xlabel('K_d')
ylabel('K_p')
grid
legend('Data','Spline Fit', 'Location','best')
It all depends on the result you want, and the process that created the data.

请先登录，再进行评论。

请先登录，再回答此问题。

回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Smoothing 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by