Wiener-Hammerstein System

The Wiener-Hammerstein system is a well-known block-oriented structure. It contains a static nonlinearity that is sandwiched in between two linear time-invariant (LTI) blocks. The presence of the two LTI blocks results in a problem that is harder to identify. This benchmark can be considered to be the predecessor of the Parallel Wiener-Hammerstein and the Wiener-Hammerstein with Process Noise datasets (though the system parameters are different).

The provided data is part of a previously published benchmark available online at IFAC website. The benchmark description can be found here. All the provided files (.mat file format) and information on the Wiener-Hammerstein system are available for download here. This .mat file contains the estimation and test dataset as specified in the benchmark document. A .csv version of the benchmark dataset is available for download here.

Special thanks to Johan Schoukens for creating this benchmark, to Gerd Vandersteen for designing the benchmark system and to the IFAC Technical Committee 1.1 on Modelling, Identification and Signal Processing for hosting this benchmark. 

Previously published results on the Wiener-Hammerstein benchmark are listed here and below. You can submit your own results through this form. Note that the reported results are curated, only complete submissions with meaningful contributions will be included. Candidate entries should make use of the Python dataloader functionalities and figure of merit calculation functions provided through this link. 

Cite

Please refer to the Wiener-Hammerstein benchmark as:

J. Schoukens, J. Suykens, L. Ljung. Wiener-Hammerstein Benchmark. 15th IFAC Symposium on System Identification (SYSID 2009), July 6-8, 2009, St. Malo, France.

Benchmark Results

Benchmark Results

You can submit your own results through this form. Note that the reported results are curated, only complete submissions with meaningful contributions will be included. Candidate entries should make use of the Python dataloader functionalities and figure of merit calculation functions provided through this link.