Neural networks for control of nuclear reactors systems

A new architecture of artificial neural networks was developed with the development of new control systems for nuclear facilities and robotics. The new concepts introduced with this architecture were based in the design of task dedicated networks, in the use of multiple synaptic contacts with new transfer functions, and in the use of synaptic plasticity processes similar to that of biological organisms. These concepts take advantage of the evolutionary aspects of biological systems in their architecture, signal transmission, and memory and learning processes, given rise to a generalization capacity not obtained with classical feed-forward (F-F) neural networks. The new concepts were applied to the control of a planar two-link robotic manipulator and to the control of a natural circulation water loop. Its efficiency and generalization capacity were compared with a classic neural network in F-F, trained with the back propagation algorithm. The excellent performance obtained, mainly in the manipulator's problem, that characterizes a system of dynamic more complex, demonstrated that the use of the new task specialized network, produces much better results than the results obtained with use of generic F-F networks. The training task in the new proposed neural network was 150 times faster than the F-F neural network training with back-propagation. The results showed that the positioning errors with the new model were up to 60 times smaller than the errors found with the F-F network. (author)