Accelerating learning of neural networks with conjugate gradients for nuclear power plant applications

Journal Article · Sun May 01 04:00:00 EDT 1994 · Nuclear Technology; (United States)

OSTI ID:7046473

Reifman, J ^[1]; Vitela, J E

---

1. Argonne National Lab, IL (United States). Reactor Analysis Div.

The method of conjugate gradients is used to expedite the learning process of feedforward multilayer artificial neural networks and to systematically update both the learning parameter and the momentum parameter at each training cycle. The mechanism for the occurrence of premature saturation of the network nodes observed with the back propagation algorithm is described, suggestions are made to eliminate this undesirable phenomenon, and the reason by which this phenomenon is precluded in the method of conjugate gradients is presented. The proposed method is compared with the standard back propagation algorithm in the training of neural networks to classify transient events in neural power plants simulated by the Midland Nuclear Power Plant Unit 2 simulator. The comparison results indicate that the rate of convergence of the proposed method is much greater than the standard back propagation, that it reduces both the number of training cycles and the CPU time, and that it is less sensitive to the choice of initial weights. The advantages of the method are more noticeable and important for problems where the network architecture consists of a large number of nodes, the training database is large, and a tight convergence criterion is desired.

• DOE Contract Number: W-31109-ENG-38
• OSTI ID: 7046473
• Journal Information: Nuclear Technology; (United States), Journal Name: Nuclear Technology; (United States) Vol. 106:2; ISSN 0029-5450; ISSN NUTYBB
• Country of Publication: United States
• Language: English

Related Subjects

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS
210200 -- Power Reactors
Nonbreeding
Light-Water Moderated
Nonboiling Water Cooled
22 GENERAL STUDIES OF NUCLEAR REACTORS
220400* -- Nuclear Reactor Technology-- Control Systems
ANALOG SYSTEMS
CLASSIFICATION
CONTROL SYSTEMS
ENRICHED URANIUM REACTORS
FUNCTIONAL MODELS
MIDLAND-2 REACTOR
NEURAL NETWORKS
NUCLEAR FACILITIES
NUCLEAR POWER PLANTS
POWER PLANTS
POWER REACTORS
PROCESS HEAT REACTORS
PWR TYPE REACTORS
REACTOR CONTROL SYSTEMS
REACTOR SIMULATORS
REACTORS
SIMULATORS
THERMAL POWER PLANTS
THERMAL REACTORS
TRANSIENTS
WATER COOLED REACTORS
WATER MODERATED REACTORS