Neural network structure optimization for Hefei Light Source II β function correction

Abstract

In this study, we address the design challenges related to hyperparameters, such as the number of layers and nodes in deep neural networks, by introducing an Improved Genetic Algorithm-based method for optimizing neural network structures (IGA-DNN). We apply this method to the practical problem of β function correction in particle accelerators and develop a storage ring β function correction scheme based on IGA-DNN. We compare our approach with traditional genetic algorithm-optimized neural networks to evaluate its performance. Our results reveal that the neural network optimized by the improved genetic algorithm reduces the number of layers by three and decreases training time by a factor of three, leading to a more efficient model. Moreover, the accuracy of β function simulation correction is enhanced using the IGA-DNN method. This approach can also be extended to optimize other optical parameters and tackle multi-parameter optimization problems, showcasing its versatility and potential for broader applications across various fields.

Ion beam stability prediction of ECR ion source based on TCN-DTW network

“…For instance, experts at the Hefei Light Source (HLS) developed an IGA-DNN method for beta function correction in a particle accelerator. This involved enhancing the genetic algorithm to optimize the deep neural network, resulting in improved accuracy in beta function correction and a simplified network structure [16]. In addressing image processing challenges, another group at HLS utilized full convolutional networks (FCN) to tackle high salt and pepper noise.…”