defining fitting curve to measured data

Question

Elisbeth Brandner 2021-8-26

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1441449-defining-fitting-curve-to-measured-data

编辑： Roshan Hingnekar 2021-9-2

Hi, i try to find a fitting function for my measured data. Sadly i do not come to a good result. my last try was based on defining a fitting type. but i just get errors. the matrix distance_data contains the measurement results. in the first colum is stored the distance and the ones after are the measurment values. the value of the measurment results decrease by increasing distance. this means the measurement curve goes from high value at low distance and low measurment value at high distance. for this behavioure i am looking for a estimation method/ fitting function.

fo = fitoptions('Method','NonlinearLeastSquares',...
               'Lower',[0,0],...
               'Upper',[Inf,max(distance_data(:,1))],...
               'StartPoint',[1 1]);
Unrecognized function or variable 'distance_data'.
ft = fittype('(a/(x+b))^n','problem','n','options',fo);
fitobject = fit(distance_data(:,1),distance_data(:,material_index),'ft');
[curve2,gof2] = fit(distance_data(:,1),distance_data(:,material_index),ft,'problem',2)
[curve3,gof3] = fit(distance_data(:,1),distance_data(:,material_index),ft,'problem',3)
hold on
plot(curve2,'m')
plot(curve3,'c')
legend('Data','n=2','n=3')
hold off

by performing the code in this way i get following error:

>> fo = fitoptions('Method','NonlinearLeastSquares',...
               'Lower',[0,0],...
               'Upper',[Inf,max(distance_data(:,1))],...
               'StartPoint',[1 1]);
ft = fittype('(a/(x+b))^n','problem','n','options',fo);
fitobject = fit(distance_data(:,1),distance_data(:,material_index),'ft');
Error using fittype>iCreateFromLibrary (line 414)
Library function ft not found.
Error in fittype>iCreateFittype (line 345)
    obj = iCreateFromLibrary( obj, varargin{:} );
Error in fittype (line 330)
                obj = iCreateFittype( obj, varargin{:} );
Error in fit>iFit (line 165)
    model = fittype( fittypeobj, 'numindep', size( xdatain, 2 ) );
Error in fit (line 116)
[fitobj, goodness, output, convmsg] = iFit( xdatain, ydatain, fittypeobj, ...
 
>> 