Speaker
Description
The CERN-SPS slow extraction has been recently equipped with a silicon bent crystal to reduce losses at the electrostatic septum (ES) wires. Such a concept exploits the coherent deflection that a thin crystal can give to part of the separatrix to avoid the ES wires.
In this contribution, we show how machine learning played a fundamental role in the design and operational deployment of the Si bent crystal for slow extraction loss reduction. First, we present how a multi-fidelity Gaussian Process (GP) based optimization was used to optimize the crystal design. Then, we detail how we exploited a neural network based surrogate model to design an efficient live controller. The final result shows a system that should be able to reduce extraction losses by one order of magnitude.
