Modern synchrotron light source storage rings, such as the Swiss Light Source upgrade (SLS 2.0), use multibend achromats in their arc segments to achieve unprecedented brilliance. This performance comes at the cost of increased focusing requirements, which in turn require stronger sextupole and higher-order multipole fields for compensation of their effects on particles with energy deviation and lead to a considerable decrease in the dynamic aperture and/or energy acceptance. In this paper, to increase these two quantities, a multiobjective genetic algorithm (MOGA) is combined with a modified version of the well-known tracking code tracy. As a first approach, a massively parallel implementation of a MOGA is used. Compared to a manually obtained solution this approach yields very good results. However, it requires a long computation time. As a second approach, a surrogate model based on artificial neural networks is used in the optimization. This improves the computation time, but the quality of the results deteriorates beyond that of the manually obtained solution. As a third approach, the surrogate model is retrained during the optimization. This ensures a solution quality comparable to the one obtained with the first approach while also providing an order of magnitude speedup. Finally, good candidate solutions for SLS 2.0 are shown and further analyzed.

中文翻译：

---

基于人工神经网络的代理模型动态孔径的多目标优化

现代同步加速器光源存储环（例如Swiss Light Source升级（SLS 2.0））在其弧段中使用多弯消色差透镜，以实现前所未有的光彩。该性能是以增加聚焦要求为代价的，这又需要更强的六极和更高阶的多极场来补偿其对具有能量偏差的粒子的影响，并导致动态孔径和/或能量接受度的显着降低。在本文中，为了增加这两个数量，将多目标遗传算法（MOGA）与著名跟踪代码tracy的修改版本结合使用。作为第一种方法，使用了MOGA的大规模并行实现。与手动获得的解决方案相比，此方法可产生非常好的结果。但是，这需要很长的计算时间。第二种方法是在优化中使用基于人工神经网络的代理模型。这样可以改善计算时间，但是结果的质量会超出手动获得的解决方案的质量。第三种方法是在优化过程中重新训练代理模型。这确保了与第一种方法所获得的解决方案质量相当的解决方案质量，同时还提供了一个数量级的加速。最后，显示并进一步分析了SLS 2.0的良好候选解决方案。