摘要：AbstractNonlinear system identification is a fast evolving field of research with contributions from different communities. It is not always straightforward to compare different models and identification approaches. Therefore it is of high importance to offer well chosen benchmarks to the nonlinear system identification community. The interaction generated by such a benchmark can push the state of the art in nonlinear system identification forward.This paper discusses some challenges that are present nowadays in the nonlinear system identification community. Three benchmarks are presented, a hysteretic benchmark, a Wiener-Hammerstein benchmark, and a cascaded tanks benchmark, each addressing one or more of these challenges.
关键词：KeywordsNonlinear System IdentificationBenchmark SystemsHysteresisWiener-HammersteinProcess NoiseCascaded TanksShort Data Record
