Journal of Applied Optics, Volume. 43, Issue 6, 1037(2022)
Prediction model of K2CsSb photocathode reflectivity based on LSTM
Figures & Tables(13)
Fig. 7. Trend chart of sequence length, accuracy and training time
Fig. 8. Comparison of loss values under different layers of LSTM network
Fig. 9. Comparison of model prediction effects under different datasets
Table 1. Composition of network structure and the number of parameters
View tableView in ArticleTable 1. Composition of network structure and the number of parameters
网络层 输出维度 参数量 输入层 (None, 5, 5) 0 LSTM (None, 5, 10) 640 随机失活层 (None, 5, 10) 0 LSTM (None, 10) 840 随机失活层 (None, 10) 0 输出层 (None, 1) 11
Table 2. Parameters of experimental model
View tableView in ArticleTable 2. Parameters of experimental model
主要参数 参数值 损失函数 MSE 学习率 0.0003 优化器 Adam 序列长度 9 网络层数 2 迭代次数 100 批处理大小/条 32
Table 3. Effect of sequence length on accuracy and training time
View tableView in ArticleTable 3. Effect of sequence length on accuracy and training time
序列 长度 每轮训练 时间/s 准确率/% 序列 长度 每轮训练 时间/s 准确率/% 1 2.13 98.42 11 15.21 98.45 3 4.36 98.63 13 15.46 98.26 5 5.12 99.21 15 15.79 98.91 7 5.63 98.82 17 15.86 98.99 9 9.62 99.01 19 15.98 98.43
Table 4. Effect of network layers on accuracy and training time
View tableView in ArticleTable 4. Effect of network layers on accuracy and training time
BP神经网络 LSTM网络 网络 层数 每轮训练 时间/s 准确率/% 网络 层数 每轮训练 时间/s 准确率/% 1 2.12 90.89 1 3.26 98.79 2 4.52 94.45 2 5.12 99.21 3 5.89 95.69 3 6.65 98.93
Tools
Get Citation
Copy Citation Text
Jingwen WEI, Yunsheng QIAN, Yang CAO. Prediction model of K2CsSb photocathode reflectivity based on LSTM[J]. Journal of Applied Optics, 2022, 43(6): 1037
Paper Information
Category: Research Articles
Received: Aug. 8, 2022
Accepted: --
Published Online: Nov. 18, 2022
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20