EFDA-JET-PR(05)04
Cellular Nonlinear Networks for Strike-Points Localization at JET
At JET the potential of fast image processing for real time purposes is actively investigated. Particular attention is devoted to smart sensors based on System on Chip Technology. In detail, to support and complement the magnetic diagnostics in the real time localization of the strike point position in the divertor, the data of the infrared cameras were processed with a new chip implementing a Cellular Nonlinear Network (CNN) structure. This circuit consists of two layers of CMOS components, the first being the sensor and the second implementing the actual CNN. With this innovative hardware, it has been possible to determine the position of maximum thermal load with time resolution of the order of 30ms. Good agreement is found with the resuls of the thermocouples in the divertor, proving the potential of the infrared data to locate the region of maximum thermal load. The results are also confirmed by JET magnetic codes, both those used for the equilibrium reconstructions and those devoted to the identification of the plasma boundary.