An Exhaustive Employment of Neural Networks to Search the Better Configuration of Magnetic Signals in ITER Machine
Concerning the control of plasma column evolution in ITER machine, the reconstruction of the plasma shape in the vacuum vessel represents an important step. In this work, starting from magnetic measurements, a soft computing approach to estimate the distances of the plasma boundary from the first wall of the vacuum vessel is carried out by means of Neural Networks (NNs). In particular, Multi-Layer Perceptron (MLP) nets have been exploited for the purpose. Finally, to verify the robustness of the proposed approach, any different database and number of input parameters has been used.
KeywordsRoot Mean Square Error Magnetic Signal Vacuum Vessel Plasma Boundary Reconstruction Accuracy
Unable to display preview. Download preview PDF.
- 1.Wesson, J.: Tokamaks. Oxford Science Pub., Oxford (1987)Google Scholar
- 3.Bishop, C.M.: Neural Network for Pattern Recognition. Clarendon Press, Oxford (1995)Google Scholar
- 4.Morabito, F.C., et al.: Final report on EFDA Study Contract FU05 CT 2002-00162 (EFDA 02-1001)Google Scholar
- 5.Morabito, F.C., et al.: On Line Plasma Shape Identification in a Tokamak Reactor Via Neural Network. In: Proc. of V Italian Workshop on Neural Networks, Word Scientific Publishing, p. 349 (1992)Google Scholar
- 6.Morabito, F.C., Versaci, M.: A Fuzzy-Neural Approach to Real Time Plasma Bound- ary Reconstruction in Tokamak Reactors. In: IEEE ICNN International Conference on Neural Networks, Houston, Texas, pp. 43–47 (1997)Google Scholar