TY - GEN
T1 - Identification of decoupled polynomial narx model using simulation error minimization
AU - Karami, Kiana
AU - Westwick, David
AU - Schoukens, Johan
N1 - Funding Information:
*Supported by the Natural Sciences and Engineering Research Council of Canada (NSERC) through grant RGPIN/06464-2015.
PY - 2019/7
Y1 - 2019/7
N2 - The Polynomial Nonlinear Auto-Regressive eXogenous input (P-NARX) model, a multivariable polynomial of past input and output values, is a widely used equation error nonlinear system model. The number of model parameters grows rapidly with the polynomial degree, and with the number of past inputs and outputs, but can be reduced significantly by adopting a decoupled structure, consisting of a transformation matrix followed by a bank of single-input single-output polynomials whose outputs are summed to produce the final output. Prediction Error Minimization (PEM) is a classical approach for the identification of both linear and nonlinear systems. Models trained using PEM may not be suitable for system simulation, where the model only has access to the system's inputs. In this paper, an identification method based on Simulation Error Minimization (SEM) for Decoupled P-NARX models is proposed. The proposed algorithm is applied to data from two nonlinear system identification benchmarks and the performance is compared to a previous PEM based algorithm.
AB - The Polynomial Nonlinear Auto-Regressive eXogenous input (P-NARX) model, a multivariable polynomial of past input and output values, is a widely used equation error nonlinear system model. The number of model parameters grows rapidly with the polynomial degree, and with the number of past inputs and outputs, but can be reduced significantly by adopting a decoupled structure, consisting of a transformation matrix followed by a bank of single-input single-output polynomials whose outputs are summed to produce the final output. Prediction Error Minimization (PEM) is a classical approach for the identification of both linear and nonlinear systems. Models trained using PEM may not be suitable for system simulation, where the model only has access to the system's inputs. In this paper, an identification method based on Simulation Error Minimization (SEM) for Decoupled P-NARX models is proposed. The proposed algorithm is applied to data from two nonlinear system identification benchmarks and the performance is compared to a previous PEM based algorithm.
UR - http://www.scopus.com/inward/record.url?scp=85072296301&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85072296301&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85072296301
T3 - Proceedings of the American Control Conference
SP - 4362
EP - 4367
BT - 2019 American Control Conference, ACC 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 American Control Conference, ACC 2019
Y2 - 10 July 2019 through 12 July 2019
ER -