The Origin Forum
File Exchange
Try Origin for Free
The Origin Forum
Home | Profile | Register | Active Topics | Members | Search | FAQ | Send File to Tech support
Username:
Password:
Save Password
Forgot your Password? | Admin Options

 All Forums
 Origin Forum
 Origin Forum
 Defined fitting function does not work well
 New Topic  Reply to Topic
 Printer Friendly
Author Previous Topic Topic Next Topic Lock Topic Edit Topic Delete Topic New Topic Reply to Topic

bitalien

China
13 Posts

Posted - 03/10/2014 :  09:29:31 AM  Show Profile  Edit Topic  Reply with Quote  View user's IP address  Delete Topic
Hi,

i need an defined fitting function to make a fitting curve for some data,and i created the function by User Defined Function Organizer,and the function like "y=A/sqrt(x)*(1-exp(-B*x^2))",A and B are parameters.
But the function seems working badly,and the fitting curve does not match the original curve.Where am i wrong?Please give some tips I would be very grateful.

Thanks guys.

bitalien

China
13 Posts

Posted - 03/10/2014 :  09:31:35 AM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Go to Top of Page

lkb0221

China
497 Posts

Posted - 03/10/2014 :  11:37:15 AM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Hi,

So what is your function exactly?
Looks like you have three versions of the function (the forum text, the Fitting Function Organizer and the fitting result table in the graph).
I tried all three of them, none of which can recreate the shape (curve go up after 3).
So I guess you need to find the correct function first.

Zheng
OriginLab
Go to Top of Page

bitalien

China
13 Posts

Posted - 03/11/2014 :  02:34:48 AM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Thank you firstly!

I am sorry for my mistake,but the function in the graph is what i needed,i put a wrong picture to explain it.
Actually,i want to fit the curve by using an equation in the attached picture,and the result should be like the subsequent graph.As you see,t is the variable,I is the dependent variable,and the others are parameters.
I tried to edit a simple function to fit it,but the function did not work well,i also tried to adjust some parameters,but i failed!So what should i do to alter the fitting curve's shape,particularly shift the peak's horizontal position of the fitting curve,making it fit the original curve?Should i add another parameters?Or change the function?



Go to Top of Page

lkb0221

China
497 Posts

Posted - 03/11/2014 :  10:00:59 AM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Hi,

It's obvious that your curve does not match the function, at least not all of it. So I masked part of the curve to do a partial fit, here is the result (green part of the line is what I masked):


The fitting is functional, but you can see the curve is still not a prefect match. Maybe that's because you have some other elements that effected your experiments?

Zheng
OriginLab

Edited by - lkb0221 on 03/11/2014 10:07:14 AM
Go to Top of Page

bitalien

China
13 Posts

Posted - 03/11/2014 :  10:26:36 PM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Thanks a lot!

The problem has been solved.
Go to Top of Page
  Previous Topic Topic Next Topic Lock Topic Edit Topic Delete Topic New Topic Reply to Topic
 New Topic  Reply to Topic
 Printer Friendly
Jump To:
The Origin Forum © 2020 Originlab Corporation Go To Top Of Page
Snitz Forums 2000