TY - DATA
T1 - Wiener-Hammerstein Process Noise System Time Series
PY - 2020/09/21
AU - Maarten Schoukens
AU - Jean-Philippe Noël
UR - https://data.4tu.nl/articles/dataset/Wiener-Hammerstein_Process_Noise_System_Time_Series/12952124/1
DO - 10.4121/12952124.v1
KW - Wiener-Hammerstein
KW - System Identification
KW - Process Noise
KW - Nonlinear
KW - Machine Learning
KW - Dynamical System
KW - Electronic Circuit
KW - Time Series
N2 - The Wiener-Hammerstein system structure 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. The LTI blocks are realized as active filters while the static nonlinearity is implemented as a diode-resistor electronic circuit.<br>The Wiener-Hammerstein system proposed here as a benchmark contains dominant process noise. The process noise enters the system before the static nonlinearity. Two much less significant noise sources are present in the measurement channels of the input and output.<br>All the provided files, data and information on the Wiener-Hammerstein system are available for download here together with an in-depth description of the measured input-output time series. This zip-file contains a detailed system description, an example estimation data set, the test data sets, the datasets measured during the past measurement campaign(s), pictures of the measurement setup, and an indicative electrical circuit schematic of the system. It is possible that the actual implemented Wiener-Hammerstein system deviates at some points (resistor values, opamp type) from the electrical circuit provided here. The data is available in the .csv and .mat file format.<br><br>
ER -