Analyzing OAM mode purity in optical fibers with CNN-based deep learning

Tianying Lin; Ang Liu; Xiaopei Zhang; He Li; Liping Wang; Hailong Han; Ze Chen; Xiaoping Liu; Haibin Lü

doi:doi:10.3788/COL201917.100603

Chinese Optics Letters, 2019, 17 (10): 100603, Published Online: Sep. 25, 2019

Analyzing OAM mode purity in optical fibers with CNN-based deep learning Download： 903次

Tianying Lin ^1,2Ang Liu ^1,2Xiaopei Zhang ^1,2He Li ^1,2Liping Wang ^1,2Hailong Han ^1,2Ze Chen ^1,2Xiaoping Liu ^1,2,*Haibin Lü ^1,2,**

Author Affiliations

¹ National Laboratory of Solid State Microstructures and College of Engineering and Applied Sciences, Nanjing University, Nanjing 210093, China

² Collaborative Innovation Center of Advanced Microstructures, Nanjing University, Nanjing 210093, China

Figures & Tables

Fig. 1. (a) Schematic with a superimposed mode at the exit of the optical fiber and the corresponding far-field pattern that can be easily recorded by an imaging device (e.g., CCD) and analyzed by CNN. (b) Mode profiles including the electric intensity profiles and phase profiles of the $x$ -direction field component for the modes of interest in this work.

下载图片查看原文

Fig. 2. Diagram of our proposed CNN architecture to predict the OAM mode purity. The CNN architecture consists of eight layers with three convolutional layers ( $C o n v 1$ , convolutional layer 1; $P o o l 1$ , pool layer 1; etc.) and five fully connected layers ( $F C 1$ , fully connected layer 1; etc.).

下载图片查看原文

Fig. 3. (a) Training progress of our proposed CNN-based prediction model. (b) Histogram of AE distribution of 1000 testing samples. Inset: histogram with AE larger than 0.01.

下载图片查看原文

Fig. 4. Predicted OAM mode purities versus the labeled ones for both the training set and the testing set.

下载图片查看原文

Fig. 5. Prediction accuracy as a function of the size of the testing set with the tolerance of 0.02.

下载图片查看原文

Fig. 6. (a) Predicted OAM mode purities versus the labels for both the training set and the testing set when phase differences exist between different modes in the optical fiber. (b) Histogram of AE distribution of 10,000 testing samples. Inset: histogram with AE larger than 0.02.

下载图片查看原文

Fig. 7. Interferograms of the fundamental modes with the high-order modes.

下载图片查看原文

Fig. 8. Predicted OAM mode purities versus the labels for the testing set when no fundamental modes exist in the optical fiber.

下载图片查看原文

Tianying Lin, Ang Liu, Xiaopei Zhang, He Li, Liping Wang, Hailong Han, Ze Chen, Xiaoping Liu, Haibin Lü. Analyzing OAM mode purity in optical fibers with CNN-based deep learning[J]. Chinese Optics Letters, 2019, 17(10): 100603.

Analyzing OAM mode purity in optical fibers with CNN-based deep learning Download： 903次

Fig. 3. (a) Training progress of our proposed CNN-based prediction model. (b) Histogram of AE distribution of 1000 testing samples. Inset: histogram with AE larger than 0.01.

Fig. 4. Predicted OAM mode purities versus the labeled ones for both the training set and the testing set.

Fig. 5. Prediction accuracy as a function of the size of the testing set with the tolerance of 0.02.

Fig. 6. (a) Predicted OAM mode purities versus the labels for both the training set and the testing set when phase differences exist between different modes in the optical fiber. (b) Histogram of AE distribution of 10,000 testing samples. Inset: histogram with AE larger than 0.02.

Fig. 7. Interferograms of the fundamental modes with the high-order modes.

Fig. 8. Predicted OAM mode purities versus the labels for the testing set when no fundamental modes exist in the optical fiber.

关于本站 Cookie 的使用提示

全站搜索

Analyzing OAM mode purity in optical fibers with CNN-based deep learning Download： 903次

Fig. 2. Diagram of our proposed CNN architecture to predict the OAM mode purity. The CNN architecture consists of eight layers with three convolutional layers (Conv1, convolutional layer 1; Pool1, pool layer 1; etc.) and five fully connected layers (FC1, fully connected layer 1; etc.).

Fig. 3. (a) Training progress of our proposed CNN-based prediction model. (b) Histogram of AE distribution of 1000 testing samples. Inset: histogram with AE larger than 0.01.

Fig. 4. Predicted OAM mode purities versus the labeled ones for both the training set and the testing set.

Fig. 5. Prediction accuracy as a function of the size of the testing set with the tolerance of 0.02.

Fig. 6. (a) Predicted OAM mode purities versus the labels for both the training set and the testing set when phase differences exist between different modes in the optical fiber. (b) Histogram of AE distribution of 10,000 testing samples. Inset: histogram with AE larger than 0.02.

Fig. 7. Interferograms of the fundamental modes with the high-order modes.

Fig. 8. Predicted OAM mode purities versus the labels for the testing set when no fundamental modes exist in the optical fiber.

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索