Traditional signal pattern recognition versus artificial neural networks for nuclear plant diagnostics

Abstract This paper introduces a new tool based on a traditional noise analysis techniques for monitoring reactor components' signal condition. It also presents the performance of artificial neural networks for pattern recognition to the same set of reactor signals and provides a comparison of these two techniques. Reactor pump signals from the Experimental Breeder Reactor (EBR-II) are utilized here. Collected signals such as pump power, pump speed, and pump pressure are obtained from already installed sensors in the reactor. The signals utilized are collected signals as well as generated signals simulating the pump shaft degradation progress. From the study of time series analysis and regression modeling of these signals, a parameter related to degradation and material buildup in the shaft is identified and used in the development of a monitoring tool. The results are then used as a benchmark against which to test the performance of artificial neural networks as a tool for reactor diagnostics. Several neural networks are examined in this study, including Restricted Coulomb Energy (RCE), Cascade Correlation, and Backpropagation paradigms of artificial neural networks. RCE is selected due to its unique design and speed, Backpropagation is selected because it is widely used and well accepted in the neural network research community, and Cascade correlation is selected because it overcomes some of the problems associated with the Backpropagation paradigm. Similar study is performed using the Adaptive Resonance Theory (ART) family of neural network paradigms. The results of this study indicate that artificial neural networks are simpler techniques for pattern recognition than noise analysis techniques such as the one introduced here. Neural networks do not require prior fault related parameter identification; they generate their own rules by learning from being shown examples. On the other hand, noise analysis and regression modeling can provide very sensitive techniques for monitoring of a detected problem in a component.

[1]  Lefteri H. Tsoukalas,et al.  Integration of Neural Networks with Fuzzy Reasoning for Measuring Operational Parameters in a Nuclear Reactor , 1993 .

[2]  Stephen Grossberg,et al.  Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system , 1991, Neural Networks.

[3]  Luis Rabelo,et al.  Nuclear reactor condition monitoring by adaptive resonance theory , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[4]  Shahla Keyvan,et al.  Application of artificial neural networks for the development of a signal monitoring system , 1997 .

[5]  Stephen Grossberg,et al.  ART 2-A: an adaptive resonance algorithm for rapid category learning and recognition , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[6]  Luis Rabelo,et al.  Sensor signal analysis by neural networks for surveillance in nuclear reactors , 1992 .

[7]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[8]  Marie-Christine Omnes-Chevalier,et al.  Autoregressive models with time-dependent log area ratios , 1988, IEEE Trans. Acoust. Speech Signal Process..

[9]  Kishan G. Mehrotra,et al.  Elements of artificial neural networks , 1996 .

[10]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[11]  Stephen Grossberg,et al.  Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps , 1992, IEEE Trans. Neural Networks.

[12]  James L. McClelland,et al.  Explorations in parallel distributed processing: a handbook of models, programs, and exercises , 1988 .

[13]  Mati Wax.  Order selection for AR models by predictive least-squares , 1986, 1986 25th IEEE Conference on Decision and Control.

[14]  R. N. Clark,et al.  Instrument Fault Detection in a Pressurized Water Reactor Pressurizer , 1982 .

[15]  Shien-Ming Wu,et al.  Time series and system analysis with applications , 1983 .

[16]  Stephen Grossberg,et al.  Art 2: Self-Organization Of Stable Category Recognition Codes For Analog Input Patterns , 1988, Other Conferences.

[17]  Eric B. Bartlett,et al.  Nuclear power plant status diagnostics using an artificial neural network , 1992 .