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
 All Forums
 Origin Forum
 Origin Forum
 [emerg]Fitting xyz data to find a,b,c BUT ERROR

Note: You must be registered in order to post a reply.
To register, click here. Registration is FREE!

Screensize:
UserName:
Password:
Anti-Spam Code:
Format Mode:
Format: BoldItalicizedUnderlineStrikethrough Align LeftCenteredAlign Right Horizontal Rule Insert HyperlinkUpload FileInsert Image Insert CodeInsert QuoteInsert List
   
Message:

* HTML is OFF
* Forum Code is ON
Smilies
Smile [:)] Big Smile [:D] Cool [8D] Blush [:I]
Tongue [:P] Evil [):] Wink [;)] Clown [:o)]
Black Eye [B)] Eight Ball [8] Frown [:(] Shy [8)]
Shocked [:0] Angry [:(!] Dead [xx(] Sleepy [|)]
Kisses [:X] Approve [^] Disapprove [V] Question [?]

 
Check here to subscribe to this topic.
   

T O P I C    R E V I E W
leejuyeon Posted - 06/10/2022 : 02:11:22 AM
Origin Ver. and Service Release (Select Help-->About Origin): OriginPro 2019(64-bit) SR2
Operating System: window 10

Emergency! Help!



Hi, this is juyeon.
I have the following problem:

z=a+bx+cy
I have a xyz-dataset and i need to find a,b,c parameter.


I tried to do 'nonlinear curve fit' by referring to this post and the link to the post is (https://www.originlab.com/doc/Tutorials/Fitting-Datasets) .

But, i got some error : Fit did not converge - reason unknow & Fit status code: 27 fit did not converge - reason unknowm.
Does anyone know why I got an error??

I think that I do not know how to do a non-linear fitting. Someone tell me how to do it.
What I have is xyz-data, and what I need to get is ABC(parameter).
z=a+bx+cy



[The settings I used are as follows]
-function model: explict
- independent variables: x,y
- dependent variables: z
- parameter name: a,b,c
- fuction : z= a+bx+cy

Here is the link to my previous-forum-post(THE SAME QUESTION) https://my.originlab.com/forum/topic.asp?TOPIC_ID=47516


Ask me again if there's anything you don't understand.
To solve this problem, I am willing to send you the data excel file, original opj file, or fit function file by email.
Or, I would appreciate it if someone could tell me how to ask the original lab-tech directly.
I'll be waiting for your answer. Thank you.


I'm in a hurry. This problem is killing me. This problem is an emergency for me. Give me an answer me ASAP.




leejuyeon
2   L A T E S T    R E P L I E S    (Newest First)
Shirley_GZ Posted - 06/10/2022 : 05:39:51 AM
Hi leejuyeon,
Let me take back my previous suggestion.
I think that the best way to get the parameter values is to perfrom multiple linear regression on your data.
https://www.originlab.com/doc/Origin-Help/Multi-Regression-Dialog
https://www.originlab.com/doc/Quick-Help/Multiple-Linear-Regression

Thanks,
Shirley
Originlab Technical Service Team
Shirley_GZ Posted - 06/10/2022 : 02:31:10 AM
Hi leejuyeon,

Usally if you didn't give the good inital values, you would get the error "Fit did not converge", even if you defined the function correctly and did the fitting with correct steps.

The initial values for the parameters should depend on your experimental model.

If you still have problem to figure this out, please send us the function file(fdf file) and the project you are working. Please also tell us the initial values for the parameters.

You can attach the files here,
or submit a ticket with
https://www.originlab.com/restricted/support/newticket.aspx?c=3
,or start a chat with the Chat Now button on our website page.

Thanks,
Shirley


Originlab Technical Service Team

The Origin Forum © 2020 Originlab Corporation Go To Top Of Page
Snitz Forums 2000