Identification of measurable dynamics of a nuclear research reactor using differential neural networks

J. Humberto Pérez-Cruz; Alexander Poznyak

doi:10.1109/CCA.2007.4389276

Identification of measurable dynamics of a nuclear research reactor using differential neural networks

J. Humberto Pérez-Cruz, Alexander Poznyak

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

Complete modeling of a nuclear reactor is a difficult task because dynamic behavior of this system depends on many factors. So, a complete description of the reactor dynamics implies necessarily the employment of high order nonlinear models. To overcome this problem, in this paper, we propose to use a low order differential neural network for the identification on-line of the uncertain measurable dynamics of a nuclear research reactor. As in real situations many variables associated with the nuclear process are not available for measurement, the identification is performed based on only the input and two states: the fuel temperature and the neutron power. In spite of that, the obtained low order model still shows a good behavior.

Original language	English
Title of host publication	16th IEEE International Conference on Control Applications, CCA 2007. Part of IEEE Multi-conference on Systems and Control
Pages	473-478
Number of pages	6
DOIs	https://doi.org/10.1109/CCA.2007.4389276
State	Published - 2007
Externally published	Yes
Event	16th IEEE International Conference on Control Applications, CCA 2007. Part of IEEE Multi-conference on Systems and Control - , Singapore Duration: 1 Oct 2007 → 3 Oct 2007

Publication series

Name	Proceedings of the IEEE International Conference on Control Applications

Conference

Conference	16th IEEE International Conference on Control Applications, CCA 2007. Part of IEEE Multi-conference on Systems and Control
Country/Territory	Singapore
Period	1/10/07 → 3/10/07

Access to Document

10.1109/CCA.2007.4389276

Cite this

Pérez-Cruz, J. H., & Poznyak, A. (2007). Identification of measurable dynamics of a nuclear research reactor using differential neural networks. In 16th IEEE International Conference on Control Applications, CCA 2007. Part of IEEE Multi-conference on Systems and Control (pp. 473-478). Article 4389276 (Proceedings of the IEEE International Conference on Control Applications). https://doi.org/10.1109/CCA.2007.4389276

Pérez-Cruz, J. Humberto ; Poznyak, Alexander. / Identification of measurable dynamics of a nuclear research reactor using differential neural networks. 16th IEEE International Conference on Control Applications, CCA 2007. Part of IEEE Multi-conference on Systems and Control. 2007. pp. 473-478 (Proceedings of the IEEE International Conference on Control Applications).

@inproceedings{0bb9a56af5bb4902933c59b9cd08a378,

title = "Identification of measurable dynamics of a nuclear research reactor using differential neural networks",

abstract = "Complete modeling of a nuclear reactor is a difficult task because dynamic behavior of this system depends on many factors. So, a complete description of the reactor dynamics implies necessarily the employment of high order nonlinear models. To overcome this problem, in this paper, we propose to use a low order differential neural network for the identification on-line of the uncertain measurable dynamics of a nuclear research reactor. As in real situations many variables associated with the nuclear process are not available for measurement, the identification is performed based on only the input and two states: the fuel temperature and the neutron power. In spite of that, the obtained low order model still shows a good behavior.",

author = "P{\'e}rez-Cruz, {J. Humberto} and Alexander Poznyak",

year = "2007",

doi = "10.1109/CCA.2007.4389276",

language = "Ingl{\'e}s",

isbn = "1424404436",

series = "Proceedings of the IEEE International Conference on Control Applications",

pages = "473--478",

booktitle = "16th IEEE International Conference on Control Applications, CCA 2007. Part of IEEE Multi-conference on Systems and Control",

note = "16th IEEE International Conference on Control Applications, CCA 2007. Part of IEEE Multi-conference on Systems and Control ; Conference date: 01-10-2007 Through 03-10-2007",

}

Pérez-Cruz, JH & Poznyak, A 2007, Identification of measurable dynamics of a nuclear research reactor using differential neural networks. in 16th IEEE International Conference on Control Applications, CCA 2007. Part of IEEE Multi-conference on Systems and Control., 4389276, Proceedings of the IEEE International Conference on Control Applications, pp. 473-478, 16th IEEE International Conference on Control Applications, CCA 2007. Part of IEEE Multi-conference on Systems and Control, Singapore, 1/10/07. https://doi.org/10.1109/CCA.2007.4389276

Identification of measurable dynamics of a nuclear research reactor using differential neural networks. / Pérez-Cruz, J. Humberto; Poznyak, Alexander.
16th IEEE International Conference on Control Applications, CCA 2007. Part of IEEE Multi-conference on Systems and Control. 2007. p. 473-478 4389276 (Proceedings of the IEEE International Conference on Control Applications).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Identification of measurable dynamics of a nuclear research reactor using differential neural networks

AU - Pérez-Cruz, J. Humberto

AU - Poznyak, Alexander

PY - 2007

Y1 - 2007

N2 - Complete modeling of a nuclear reactor is a difficult task because dynamic behavior of this system depends on many factors. So, a complete description of the reactor dynamics implies necessarily the employment of high order nonlinear models. To overcome this problem, in this paper, we propose to use a low order differential neural network for the identification on-line of the uncertain measurable dynamics of a nuclear research reactor. As in real situations many variables associated with the nuclear process are not available for measurement, the identification is performed based on only the input and two states: the fuel temperature and the neutron power. In spite of that, the obtained low order model still shows a good behavior.

AB - Complete modeling of a nuclear reactor is a difficult task because dynamic behavior of this system depends on many factors. So, a complete description of the reactor dynamics implies necessarily the employment of high order nonlinear models. To overcome this problem, in this paper, we propose to use a low order differential neural network for the identification on-line of the uncertain measurable dynamics of a nuclear research reactor. As in real situations many variables associated with the nuclear process are not available for measurement, the identification is performed based on only the input and two states: the fuel temperature and the neutron power. In spite of that, the obtained low order model still shows a good behavior.

UR - http://www.scopus.com/inward/record.url?scp=43049175097&partnerID=8YFLogxK

U2 - 10.1109/CCA.2007.4389276

DO - 10.1109/CCA.2007.4389276

M3 - Contribución a la conferencia

AN - SCOPUS:43049175097

SN - 1424404436

SN - 9781424404438

T3 - Proceedings of the IEEE International Conference on Control Applications

SP - 473

EP - 478

BT - 16th IEEE International Conference on Control Applications, CCA 2007. Part of IEEE Multi-conference on Systems and Control

T2 - 16th IEEE International Conference on Control Applications, CCA 2007. Part of IEEE Multi-conference on Systems and Control

Y2 - 1 October 2007 through 3 October 2007

ER -

Pérez-Cruz JH, Poznyak A. Identification of measurable dynamics of a nuclear research reactor using differential neural networks. In 16th IEEE International Conference on Control Applications, CCA 2007. Part of IEEE Multi-conference on Systems and Control. 2007. p. 473-478. 4389276. (Proceedings of the IEEE International Conference on Control Applications). doi: 10.1109/CCA.2007.4389276

Identification of measurable dynamics of a nuclear research reactor using differential neural networks

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this