Review of results and perspectives of nonlinear process identification from experimental data Original Research Article

Mathematical models are an essential part of most branches of science and engineering. A mathematical model can be used to unveil fundamental properties of the system it describes, which are not apparent otherwise, leading to a better understanding of the system. The mathematical models of the fundamental processes in nature have become physical laws based on which the models of most systems in the real world are derived. For many real systems, however, the axiomatic approach to modelling cannot be applied either because the. modeller does not have access to the internal structure of the system or because of the extremely high complexity of the system, which precludes the application of elementary laws to derive the systems equations. In such cases an experimental approach, where the model of a system or process is derived solely from experimental input/output measurements, is the only alternative solution. This approach is known as system identification. This paper provides an overview of nonlinear system identification methods with an emphasis on space physics related applications.