Tuning of box jenkins model parameters to improve accuracy

11 次查看(过去 30 天)
i am using bj function to identify my system using
sys = bj(data, nb, nc, nd, nf, nk);
after getting reduced order model using Akaike information criteria AIC, i am unable to achieve accurate results.
Is there any method to "tune the model parameters of bj model to improve the accuracy of the model fit, as we manaually tune the parameters in OE and ARX model.

回答(1 个)

Sumukh
Sumukh 2024-8-23,9:53
Hi John,
The model obtained from “bj” function can be tuned in the same way as the models obtained from “oe” and “arx” functions. The “bj” model returns a “idpoly” object that has the “Fit” struct present in its “Report” property. This provides a quantitative assessment of the model estimated. This can be used to iteratively tune the options passed to the “bj” function, such as the parameters in the array “[nb nc nd nf nk]” and the initial system parameter “init_sys”, to improve the accuracy of the model obtained. You can refer to the following documentation to learn more about the “bj” function input arguments:
Additional estimation options can be passed to the “opt” input argument as “bjOptions” option to further improve the accuracy of the estimated model. You can find more about the various options available here:
I hope this helps with improving your model accuracy.

类别

Help CenterFile Exchange 中查找有关 Linear Model Identification 的更多信息

Community Treasure Hunt

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

Start Hunting!

Translated by