hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.7225/toms.v04.n02.001

System Identification in Difficult Operating Conditions Using Artificial Neural Networks

Petar Matić   ORCID icon orcid.org/0000-0002-1799-5257 ; University of Split, Faculty of Maritime Studies in Split, Split, Croatia
Ivana Golub Medvešek ; University of Split, Faculty of Maritime Studies in Split, Split, Croatia
Tina Perić   ORCID icon orcid.org/0000-0002-9531-0065 ; University of Split, Faculty of Maritime Studies in Split, Split, Croatia

Puni tekst: engleski, pdf (431 KB) str. 105-112 preuzimanja: 323* citiraj
APA 6th Edition
Matić, P., Golub Medvešek, I. i Perić, T. (2015). System Identification in Difficult Operating Conditions Using Artificial Neural Networks. Transactions on Maritime Science, 04 (02), 105-112. https://doi.org/10.7225/toms.v04.n02.001
MLA 8th Edition
Matić, Petar, et al. "System Identification in Difficult Operating Conditions Using Artificial Neural Networks." Transactions on Maritime Science, vol. 04, br. 02, 2015, str. 105-112. https://doi.org/10.7225/toms.v04.n02.001. Citirano 20.01.2020.
Chicago 17th Edition
Matić, Petar, Ivana Golub Medvešek i Tina Perić. "System Identification in Difficult Operating Conditions Using Artificial Neural Networks." Transactions on Maritime Science 04, br. 02 (2015): 105-112. https://doi.org/10.7225/toms.v04.n02.001
Harvard
Matić, P., Golub Medvešek, I., i Perić, T. (2015). 'System Identification in Difficult Operating Conditions Using Artificial Neural Networks', Transactions on Maritime Science, 04(02), str. 105-112. https://doi.org/10.7225/toms.v04.n02.001
Vancouver
Matić P, Golub Medvešek I, Perić T. System Identification in Difficult Operating Conditions Using Artificial Neural Networks. Transactions on Maritime Science [Internet]. 2015 [pristupljeno 20.01.2020.];04(02):105-112. https://doi.org/10.7225/toms.v04.n02.001
IEEE
P. Matić, I. Golub Medvešek i T. Perić, "System Identification in Difficult Operating Conditions Using Artificial Neural Networks", Transactions on Maritime Science, vol.04, br. 02, str. 105-112, 2015. [Online]. https://doi.org/10.7225/toms.v04.n02.001

Sažetak
To investigate an ability of system identification in difficult operating conditions. A simulation based experiment was performed on a simple second order system with white noise signal superimposed to the output signal. Interferences are added to the output signal in order to simulate difficult operating conditions present in a real system environment. Based on system simulation measurements, the system was identified using conventional method with least squares estimate and an alternative method, a multi-layer perceptron (MLP) network. Graphical evaluation of simulation results showed that MLP network produced better results than conventional model, with significantly better results in case of interferences in the output signal. To model dynamic system, a simple two-layer perceptron network with external dynamic members was trained in Matlab using Levenberg-Marquardt algorithm.

Ključne riječi
System identification; Difficult operating conditions; Artificial neural network; Multy-layer perceptron; Levenberg-Marquardt

Hrčak ID: 147237

URI
https://hrcak.srce.hr/147237

Posjeta: 486 *