arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1904.11983eess.IVphysics.optics
收藏

深度学习实现了光纤光束的超快速和准确的M^2评估

Deep learning enabled superfast and accurate M^2 evaluation for fiber beams

Yi An, Jun Li, Liangjin Huang, Jinyong Leng, Lijia Yang, Pu Zhou

摘要:

据我们所知,我们首次引入深度学习技术来预测从少模光纤发射的激光束的光束传输因子M^2。深度卷积神经网络(CNN)使用模拟近场波束图案及其计算的M^2值的配对数据进行训练,旨在学习从前者到后者的快速准确的映射。然后,可以利用经训练的深度CNN来评估来自单个光束图案的光纤光束的M^2。模拟测试结果表明,即使在光纤中包含多达10个本征模的情况下,我们的方案也可以实现小于2%的平均预测误差。当输入波束图中加入强噪声时,误差略有增大,但仍小于2.5%,进一步证明了该方法的准确性和鲁棒性。此外,对于具有一次前向通过的准备好的光束图案,M^2估计仅需要约5ms,这可以用于仅用一个支持电荷耦合器件(CCD)的实时M^2确定。实验结果进一步证明了该方案的可行性。此外,我们提出的方法可以放心地扩展到其他类型的波束,提供足够的训练样本是可访问的。深度学习为超快速和准确的M^2评估铺平了道路,实验工作量非常小。

英文摘要:

We introduce deep learning technique to predict the beam propagation factor M^2 of the laser beams emitting from few-mode fiber for the first time, to the best of our knowledge. The deep convolutional neural network (CNN) is trained with paired data of simulated near-field beam patterns and their calculated M^2 value, aiming at learning a fast and accurate mapping from the former to the latter. The trained deep CNN can then be utilized to evaluate M^2 of the fiber beams from single beam patterns. The results of simulated testing samples have shown that our scheme can achieve an averaged prediction error smaller than 2% even when up to 10 eigenmodes are involved in the fiber. The error becomes slightly larger when heavy noises are added into the input beam patterns but still smaller than 2.5%, which further proves the accuracy and robustness of our method. Furthermore, the M^2 estimation takes only about 5 ms for a prepared beam pattern with one forward pass, which can be adopted for real-time M^2 determination with only one supporting Charge-Coupled Device (CCD). The experimental results further prove the feasibility of our scheme. Moreover, the method we proposed can be confidently extended to other kinds of beams provided that adequate training samples are accessible. Deep learning paves the way to superfast and accurate M^2 evaluation with very low experimental efforts.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑