The final optics recycling loop used on large laser facility is an effcient and necessary strategy to maintain the optics in intervals between long-term physical experiments, In order to avoid cross-use between optics of different quality levels, we put forward the A/B recycling loop strategy of optics refer to the strategy from NIF, which arranges optics of the same quality level working in the same beamline, and optics of large quality difference loop independently to protect high-quality optics. Additionally, in order to improve the efficiency of recycling task and the stability of classification standard, we have searched for a proper intelligence technology applying on the loop process. To solve the small sample problem under each label, we use data augmentation method to manually increase samples. Furthermore, transfer learning method based on VGG16 is also used to extract features of the target. As a result the accuracy of the learning model reaches over 90 %. From now on, the integration and data interaction with the computer centralized control system have been completed. The realization of online image automatic classification can estimate the quality grades of optics, so as to provide reference for optics maintaining and optimize the efficiency of the optics recycling loop.
Read full abstract