NNARX networks on didactic level system identification
Research output: Journal contributions › Journal articles › Research › peer-review
Standard
In: WSEAS Transactions on Systems and Control, Vol. 15, 19, 11.05.2020, p. 184-190.
Research output: Journal contributions › Journal articles › Research › peer-review
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - NNARX networks on didactic level system identification
AU - Santos Neto, A. F.
AU - Santos, M. F.
AU - Santiago, A. C.
AU - Vidal, V. F.
AU - Mercorelli, Paolo
PY - 2020/5/11
Y1 - 2020/5/11
N2 - This work has as main objective to propose the identification of a small scale non-linear system through the Neural Network AutoRegressive with eXternal input. The use of this network requires an adequate methodol-ogy for its configuration and, consequently, a good training set. Then, it is proposed that the main definitions of the network parameters be obtained through the analysis of nonintrusive performance indices. Additionally, using a database based on the system’s response, excited by the Pseudo-Random Binary Sequence signal. The method-ology will be applied in two specific open-loop identification situations: numerical simulation of a fourth order polynomial system (Case 01), and an experimental system that controls a nonlinear water tank level (Case 02). The results of the identified models were able to represent the system dynamics with high fidelity, presenting an average identification error of less than 0.14 and 0.34% for Case 1 and 2, respectively. Also, it is observed that the learning and generalization evidence could represent the process intrinsic nonlinearities satisfactorily. Besides, it will be possible to find the potentiality and usefulness of the developed network in nonlinear system identification.
AB - This work has as main objective to propose the identification of a small scale non-linear system through the Neural Network AutoRegressive with eXternal input. The use of this network requires an adequate methodol-ogy for its configuration and, consequently, a good training set. Then, it is proposed that the main definitions of the network parameters be obtained through the analysis of nonintrusive performance indices. Additionally, using a database based on the system’s response, excited by the Pseudo-Random Binary Sequence signal. The method-ology will be applied in two specific open-loop identification situations: numerical simulation of a fourth order polynomial system (Case 01), and an experimental system that controls a nonlinear water tank level (Case 02). The results of the identified models were able to represent the system dynamics with high fidelity, presenting an average identification error of less than 0.14 and 0.34% for Case 1 and 2, respectively. Also, it is observed that the learning and generalization evidence could represent the process intrinsic nonlinearities satisfactorily. Besides, it will be possible to find the potentiality and usefulness of the developed network in nonlinear system identification.
KW - Level system
KW - NNARX
KW - System identification
KW - Engineering
UR - http://www.scopus.com/inward/record.url?scp=85084839177&partnerID=8YFLogxK
UR - https://wseas.org/wseas/cms.action?id=23195
U2 - 10.37394/23203.2020.15.19
DO - 10.37394/23203.2020.15.19
M3 - Journal articles
AN - SCOPUS:85084839177
VL - 15
SP - 184
EP - 190
JO - WSEAS Transactions on Systems and Control
JF - WSEAS Transactions on Systems and Control
SN - 1991-8763
M1 - 19
ER -