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
 Get convergence from two Non-linear curve fittings
 New Topic  Reply to Topic
 Printer Friendly
Author Previous Topic Topic Next Topic Lock Topic Edit Topic Delete Topic New Topic Reply to Topic

edwardclhuang

Taiwan
9 Posts

Posted - 05/21/2014 :  07:52:06 AM  Show Profile  Edit Topic  Reply with Quote  View user's IP address  Delete Topic
Origin Ver. and Service Release (Select Help-->About Origin):9.1
Operating System:Win7

Hello,

I have two sets of data y1=f1(x) and y2=f2(x). I established two non-linear curve fitting functions for each set of data with several fitting coefficients. For f1(x) the coefficients are A, t1, t2..., and for f2(x) the coefficients are A, r1, r2, and etc. The A coefficient has to be the same value for both fits and the others (t1, t2, r1, r2) are mutual independent. However, since the solutions for A are many, i.e., a lot of local minima in the solution space, the A value I get from the least-square fit on f1(x) cannot be applied to get reasonable fit on f2(x).

In a word, one needs to apply a "simultaneous" fit on f1(x) and f2(x) to get a single A value, which leads to comprised fits for two sets of data. Could you please give me some instructions about how I can do it in Origin Pro 9.1?

With best regards,

edward

JacquelineHe

287 Posts

Posted - 05/22/2014 :  07:26:51 AM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Hi,

To fit multiple functions with multiple variables with shared parameters, you can refer to this tutorial page:

http://www.originlab.com/doc/Tutorials/Fitting-NLFit-MultiVar

Thanks
Jacqueline
OriginLab
Go to Top of Page

edwardclhuang

Taiwan
9 Posts

Posted - 05/27/2014 :  08:19:25 AM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Dear Jacqueline,

I thank for your instruction. I do look at the example on the page "Nonlinear Multiple Variables Fitting". It shows me how to fit a single set of data by two different functions with shared parameters.

I also look at the example on the page "Global Fitting with Parameter Sharing". It shows me how to fit two sets of data by one function with shared parameter.

However, what I need is to fit two sets of data by two different functions with shared parameter. Can I do this in OriginPro 9.1 Sr1?

I thank for your help in advance,

Chien-Lung
Go to Top of Page

JacquelineHe

287 Posts

Posted - 05/27/2014 :  10:59:57 PM  Show Profile  Edit Reply  Reply with Quote  View user's IP address  Delete Reply
Dear Chien-Lung,

If your two Y datasets with the same x value (XYY datasets), you can select the 3 columns and use Multiple Variables function to fit the datasets as the "Nonlinear Multiple Variables Fitting".

But if your two Y datasets with the different x value (XYXY datasets), you will need to set two functions with different "Independent Variables: x1,x2".

About how to create the User Defined Fitting Function, please refer to the simple sample in this page: http://www.originlab.com/doc/Tutorials/UserDef-FitFunc


Also, if you do not mind, you can send your project file and the fitting function formula to us, when you define the fitting function with any problem.

Tech Support department Email: tech@originlab.com
(Please send us with your detailed version and serial number information. You can check it by selecting ''Help: About Origin'' in the menu.)

Thanks
Jacqueline
OriginLab
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