Fast and accurate Brillouin frequency shift extraction in Brillouin optical time domain reflectometry (BOTDR) distributed fiber sensor by using ensemble machine learning algorithm

Fast and accurate Brillouin frequency shift extraction in Brillouin optical time domain reflectometry (BOTDR) distributed fiber sensor by using ensemble machine learning algorithm
复制标题

使用集成机器学习算法快速准确地提取布里渊光时域反射计(BOTDR)分布式光纤传感器中的布里渊频移

DOI:
10.1088/1742-6596/2411/1/012012
复制
发表时间:
2022
期刊:
Journal of Physics: Conference Series
影响因子:
--
通讯作者:
Arsad N
Arsad N
中科院分区:
--
文献类型:
--
作者:
Almoosa A S K;Zan M S D;Ibrahim M F;Tanaka Y;Hamzah A E;Arsad N

文献摘要

参考文献

被引文献

相似文献

为了提高差分交叉谱布里渊光时域反射计(DCS-BOTDR)光纤传感器的布里渊频移(BFS)分辨率测量和处理时间,我们团队建议使用集成机器学习(EML)技术。由于与其他T-L情形相比,它给出了最好的边界层分辨率,因此我们使用脉冲宽度T-L=14 ns情形记录的边界层分布数据作为基本事实来训练EML模型。之后,我们对T L=4、60和90 ns的情况进行了EML模型检验。对于所有T L情况,我们将BFS分辨率提高了约2.85 MHz,与T L等于14 ns时的分辨率相当。这一结果表明,EML算法是可靠的、高效的、高精度的预测能力。此外,我们还记录了大约一秒的快速处理时间。此外,我们还成功地演示了T-L=60和90 ns的20厘米空间分辨率测量,这是用通常的DCSBOTDR信号处理方法所不能实现的。
To improve the Brillouin frequency shift (BFS) resolution measurement and processing time of the differential cross-spectrum Brillouin optical time domain reflectometry (DCS-BOTDR) fiber sensor, our team suggests employing the ensemble machine learning (EML) technique. Because it gave the best BFS resolution compared to the other T L cases, we used the BFS distribution data recorded by the pulse duration T L= 14 ns case as ground truth to train the EML model in this work. After that, we tested the EML model for T L= 4, 60, and 90 ns cases. We improved the BFS resolution for all T L situations by approximately 2.85 MHz, comparable to our resolution when T L was equal to 14 ns. This result demonstrates that the EML algorithm is reliable, efficient, and highly accurate in its predictive capabilities. Additionally, we have documented a rapid processing time of approximately one second. In addition, we have successfully demonstrated 20 cm spatial resolution measurement for T L= 60 and 90 ns, which was not previously possible with the usual DCS-BOTDR signal processing method.
DOI: 10.1109/icp.2018.8533208
发表时间: 2018
期刊: 2018 IEEE 7th International Conference on Photonics (ICP)
影响因子: --
作者:
M. Zan;Yuki Masui;T. Horiguchi
通讯作者: T. Horiguchi
DOI: 10.1007/3-540-45014-9
发表时间: 2000-06
期刊: --
影响因子: --
作者:
Thomas G. Dietterich
通讯作者: Thomas G. Dietterich
使用具有最少预测变量的机器学习算法检测慢性肾脏病
影响因子: 0.9
作者:
M. Almasoud;T. Ward
通讯作者: T. Ward
DOI: 10.1371/journal.pone.0228439
发表时间: 2020-02-06
期刊: PLOS ONE
影响因子: 3.7
作者:
Fang, Yong;Liu, Yongcheng;Liu, Liang
通讯作者: Liu, Liang