Research on RF Intensity Temperature Sensing based on 1D-CNN
【Objective】In order to improve the accuracy and efficiency of temperature sensing, the application of Microwave Photonic Filter (MPF) based on One-Dimensional Convolutional Neural Network (1D-CNN) in Radio Frequency (RF) intensity temperature sensing is studied.【Methods】The MPF system based on Mach-...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
《光通信研究》编辑部
2025-04-01
|
| Series: | Guangtongxin yanjiu |
| Subjects: | |
| Online Access: | http://www.gtxyj.com.cn/zh/article/doi/10.13756/j.gtxyj.2025.240159/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850190800054386688 |
|---|---|
| author | DING Meiqi GUI Lin WANG Ziyi SHANG Disen QIAN Min LI Qiankun |
| author_facet | DING Meiqi GUI Lin WANG Ziyi SHANG Disen QIAN Min LI Qiankun |
| author_sort | DING Meiqi |
| collection | DOAJ |
| description | 【Objective】In order to improve the accuracy and efficiency of temperature sensing, the application of Microwave Photonic Filter (MPF) based on One-Dimensional Convolutional Neural Network (1D-CNN) in Radio Frequency (RF) intensity temperature sensing is studied.【Methods】The MPF system based on Mach-Zehnder Interferometer (MZI) structure is built experimentally, and the RF spectral data of 20~70 ℃ under the condition of notch depth of 8.1 dB are collected by changing the ambient temperature. 30 sets of data are collected under each temperature condition. Then the 1D-CNN structure is designed and optimized by greedy strategy to determine the number of network layers, the size of the convolutional kernel, the size of the pooled kernel and the type of activation function. The model is trained with the training set data and validated with the test set data to optimize the model parameters for optimal performance. Its nonlinear mapping capability is used to extract features from RF spectral data to achieve high-precision demodulation of RF intensity and temperature changes. Finally, the Root Mean Square Error (RMSE) is used as the evaluation index, and the performance of 1D-CNN is compared with the traditional algorithms (maximum-value method, centroid method and Gaussian fitting method) to analyze its performance under different temperature conditions.【Results】The experimental results show that the RMSE of the prediction model based on 1D-CNN reaches the order of 10<sup>-3</sup>, while the RMSE of the traditional algorithms is usually in the order of 10<sup>-1</sup>. Compared with the traditional Gaussian fitting algorithm, the demodulation speed of the 1D-CNN-based algorithm is improved by 2.72 times. 1D-CNN shows high stability and low error under different temperature conditions.【Conclusion】1D-CNN has significant advantages in dealing with complex nonlinear relationships and feature extraction, not only superior in computational efficiency and robustness, but also effective in dealing with noise and environmental interference. The research in this paper provides new ideas and methods for the application of MPF in the field of RF intensity temperature sensing. |
| format | Article |
| id | doaj-art-3943d960524c45f98df3131304d920dd |
| institution | OA Journals |
| issn | 1005-8788 |
| language | zho |
| publishDate | 2025-04-01 |
| publisher | 《光通信研究》编辑部 |
| record_format | Article |
| series | Guangtongxin yanjiu |
| spelling | doaj-art-3943d960524c45f98df3131304d920dd2025-08-20T02:15:11Zzho《光通信研究》编辑部Guangtongxin yanjiu1005-87882025-04-01240159-0690716570Research on RF Intensity Temperature Sensing based on 1D-CNNDING MeiqiGUI LinWANG ZiyiSHANG DisenQIAN MinLI Qiankun【Objective】In order to improve the accuracy and efficiency of temperature sensing, the application of Microwave Photonic Filter (MPF) based on One-Dimensional Convolutional Neural Network (1D-CNN) in Radio Frequency (RF) intensity temperature sensing is studied.【Methods】The MPF system based on Mach-Zehnder Interferometer (MZI) structure is built experimentally, and the RF spectral data of 20~70 ℃ under the condition of notch depth of 8.1 dB are collected by changing the ambient temperature. 30 sets of data are collected under each temperature condition. Then the 1D-CNN structure is designed and optimized by greedy strategy to determine the number of network layers, the size of the convolutional kernel, the size of the pooled kernel and the type of activation function. The model is trained with the training set data and validated with the test set data to optimize the model parameters for optimal performance. Its nonlinear mapping capability is used to extract features from RF spectral data to achieve high-precision demodulation of RF intensity and temperature changes. Finally, the Root Mean Square Error (RMSE) is used as the evaluation index, and the performance of 1D-CNN is compared with the traditional algorithms (maximum-value method, centroid method and Gaussian fitting method) to analyze its performance under different temperature conditions.【Results】The experimental results show that the RMSE of the prediction model based on 1D-CNN reaches the order of 10<sup>-3</sup>, while the RMSE of the traditional algorithms is usually in the order of 10<sup>-1</sup>. Compared with the traditional Gaussian fitting algorithm, the demodulation speed of the 1D-CNN-based algorithm is improved by 2.72 times. 1D-CNN shows high stability and low error under different temperature conditions.【Conclusion】1D-CNN has significant advantages in dealing with complex nonlinear relationships and feature extraction, not only superior in computational efficiency and robustness, but also effective in dealing with noise and environmental interference. The research in this paper provides new ideas and methods for the application of MPF in the field of RF intensity temperature sensing.http://www.gtxyj.com.cn/zh/article/doi/10.13756/j.gtxyj.2025.240159/1D-CNNMPFfiber optic sensingtemperature sensingRF intensity |
| spellingShingle | DING Meiqi GUI Lin WANG Ziyi SHANG Disen QIAN Min LI Qiankun Research on RF Intensity Temperature Sensing based on 1D-CNN Guangtongxin yanjiu 1D-CNN MPF fiber optic sensing temperature sensing RF intensity |
| title | Research on RF Intensity Temperature Sensing based on 1D-CNN |
| title_full | Research on RF Intensity Temperature Sensing based on 1D-CNN |
| title_fullStr | Research on RF Intensity Temperature Sensing based on 1D-CNN |
| title_full_unstemmed | Research on RF Intensity Temperature Sensing based on 1D-CNN |
| title_short | Research on RF Intensity Temperature Sensing based on 1D-CNN |
| title_sort | research on rf intensity temperature sensing based on 1d cnn |
| topic | 1D-CNN MPF fiber optic sensing temperature sensing RF intensity |
| url | http://www.gtxyj.com.cn/zh/article/doi/10.13756/j.gtxyj.2025.240159/ |
| work_keys_str_mv | AT dingmeiqi researchonrfintensitytemperaturesensingbasedon1dcnn AT guilin researchonrfintensitytemperaturesensingbasedon1dcnn AT wangziyi researchonrfintensitytemperaturesensingbasedon1dcnn AT shangdisen researchonrfintensitytemperaturesensingbasedon1dcnn AT qianmin researchonrfintensitytemperaturesensingbasedon1dcnn AT liqiankun researchonrfintensitytemperaturesensingbasedon1dcnn |