~ Nonlinear Adaptive Filtering as a Form of Artificial Intelligence ~

The real life example 2

Identification of physical object code and data
This page shares an experience of identification of Urysohn object with two inputs. The object is physical system, which is F-16 aircraft structure. The details are provided by the site holding the public dataset - http://www.nonlinearbenchmark.org/. The recommended reference is:

J.P. Noël and M. Schoukens, F-16 aircraft benchmark based on ground vibration test data, 2017 Workshop on Nonlinear System Identification Benchmarks, pp. 19-23, Brussels, Belgium, April 24-26, 2017.

The data is complex. It consists of multiple implementations with two samples, one of which is recommended for training and another is recommended for validation. The errors for validation samples are between 1 and 2 percent. The code and data can be downloaded from the link above.