Neural network technique for orbit correction in accelerators/storage rings

We are exploring the use of Neural Networks, using the SNNS simulator, for orbit control in accelerators (primarily circular accelerators) and storage rings. The orbit of the beam in those machines are measured by orbit monitors (input nodes) and controlled by orbit corrector magnets (output nodes). The physical behavior of an accelerator is changing slowly in time. Thus, an adoptive algorithm is necessary. The goal is to have a trained net which will predict the exact corrector strengths which will minimize a measured orbit. The relationship between ‘‘kick’’ from the correctors and ‘‘response’’ from the monitors is in general non‐linear and may slowly change during long‐term operation of the machine. In the study, several network architectures are examined as well as various training methods for each architecture.