A technique using a single hidden layer backpropagation neural network is described to establish a nonlinear mapping between a set of magnetic flux measurements and some shaping parameters of a noncircular plasma. The technique has been applied for the identification of limiter and X point equilibria in the ASDEX Upgrade geometry; the dataset of equilibria required for training and testing the neural network has been generated by means of an integrated use of a fixed and a free boundary MHD code. The average accuracy of the identification procedure is quite good, with a further improvement if a linear connection between the input and output layers is introduced. A procedure is also proposed for the selection of the optimum location of a limited number of sensors. The relationship existing between the behaviour of the neural network and some statistical parameters of the dataset is analysed and discussed

A linearized non-rigid MHD consistent displacement model is shown to be adequate to the study of the vertical stability of a plasma in an air core or iron core tokamak. This simple but accurate approach, which can be extended to the study of shape and radial position control, can be used in determining the limits of validity of the linear approximation and simulating the behaviour of a detection system based on a set of flux measurements. The method provides a basis for the optimization of position measurements and feedback parameters. The features of the model are illustrated, with reference to the study of the vertical stability of a NET configuration, showing the significance of the choice of the input signal.

No abstract

No abstract