Title :
Neural identification of failed fuel rods in nuclear reactors [PWRs]
Author :
Seixas, J.M. ; Soares-Filho, W. ; Bossan, M.C. ; Thome, Z.D. ; Pereira, WC A.
Author_Institution :
COPPE, Univ. Fed. do Rio de Janeiro, Brazil
Abstract :
Ultrasonic pulses were used for automatic detection of failed nuclear fuel rods. The detection is based on processing the received echoes of the emitted ultrasonic pulses by means of a neural network, which achieves an efficiency of 98% and outperforms classical discriminating methods. Additional studies on the correlation of the neural and the best nonneural discriminating methods evaluate whether a hybrid detection approach could improve the overall performance of the system
Keywords :
fission reactor monitoring; fission reactor safety; neural nets; nuclear engineering computing; ultrasonic materials testing; automatic detection; failed fuel rods; hybrid detection approach; neural identification; nonneural discriminating methods; nuclear reactors; received echoes; ultrasonic pulses; Assembly; Inductors; Inspection; Neural networks; Nuclear fuels; Pulse generation; Safety; Structural rods; Testing; Ultrasonic imaging;
Conference_Titel :
Circuits and Systems, 2000. Proceedings. ISCAS 2000 Geneva. The 2000 IEEE International Symposium on
Conference_Location :
Geneva
Print_ISBN :
0-7803-5482-6
DOI :
10.1109/ISCAS.2000.857052
