Residual network-based aberration correction in a sensor-less adaptive optics system

• Published in: Optics communications 2023-10, Vol.545, p.129707, Article 129707
• Main Authors: Liu, Wei, Ma, Xinyang, Jin, Dairan, Shi, Wenxiao, Gu, Haijun, Cao, Jingtai
• Format: Article
• Language: English
• Subjects: Bit error rate; Coupling efficiency; Free-space optical communication; Mixing efficiency; Residual network; Sensor-less adaptive optics
• ISSN: 0030-4018; 1873-0310
• DOI: 10.1016/j.optcom.2023.129707

The performance of free-space optical communication (FSOC) is often affected by atmospheric turbulence. The sensor-less adaptive optics (SLAO) system is an effective method for overcoming the effects of atmospheric turbulence. The performance of the control algorithm in the SLAO system directly determines whether the SLAO system can effectively correct wavefront aberrations. In this study, we introduce a residual network (ResNet) as a control algorithm to replace the traditional control algorithm. By lowering the number of iterations, this strategy enhances the real-time performance of the FSOC system. The final ResNet model can achieve an accuracy of 0.98 for training and 0.92 for testing. The simulation results show that stochastic parallel gradient descent (SPGD) algorithm takes 700 times longer and requires at least 500 iterations to achieve the same performance as ResNet. And we verify the feasibility of the ResNet model by setting up an experiment. •In the study, we improved the real-time performance of the FSOC by introducing the ResNet.•The final ResNet model can achieve an accuracy of 0.98 for training and 0.92 for testing.•We have verified the correction performance and real-time performance of the ResNet as a control algorithm for SLAO systems through simulation and experiment.