全波形反演下分布式光纤声波传感信号低信噪比自适应任务调度

doi:10.13229/j.cnki.jdxbgxb.20240335

摘要/Abstract

摘要：

针对分布式光纤声波传感信号在实际应用中受环境噪声干扰、光纤传输限制及多任务处理需求影响，导致低信噪比问题，提出了基于全波形反演的自适应任务调度方法，旨在提高信号信噪比，优化多任务调度，从而提升传感系统的整体性能。利用基于改进伴随状态源方程的全波形反演方法，对分布式光纤声波传感信号直接实施全波形反演。采用构建的神经网络，学习变量关系，根据变量关系给出当前迁移阶段选择主体任务各自子任务的解剩余数量，更新迁移任务被择选的概率，自适应地动态选择迁移任务，实现多任务调度。在基准测试函数上进行多任务调度效果检验，适应度与离散度评估结果的发展态势均相对积极，适应度超过8，离散度低于0.3。可见，该方法能够有效处理传感信号的低信噪比问题，提高分布式光纤声波传感系统的多任务调度质量，对于低信噪比信号的系统多任务调度具有强助力作用。

关键词: 分布式光纤声波传感系统, 低信噪比信号, 全波形反演, 变量关系学习, 迁移任务动态选择, 多任务调度

Abstract:

Distributed fiber optic acoustic sensing signals are affected by environmental noise interference， fiber optic transmission limitations， and multitasking processing requirements in practical applications. To solve this problem， an adaptive task scheduling method based on full waveform inversion is proposed， aiming to improve the signal-to-noise ratio， optimize multi task scheduling processing， and thus enhance the overall performance of the sensing system. Using a full waveform inversion method based on an improved adjoint state source equation， direct full waveform inversion is performed on distributed fiber optic acoustic sensing signals. Using a constructed neural network to learn variable relationships. Based on the variable relationship， provide the remaining number of solutions for each subtask of the selected main task in the current migration stage， update the probability of selecting the migration task， adaptively and dynamically select the migration task， and achieve multi task scheduling. The performance of multi task scheduling was tested on the benchmark test function， and the development trend of fitness and dispersion evaluation results was relatively positive， with fitness exceeding 8 and dispersion below 0.3. It can be seen that this method can effectively handle the problem of low signal-to-noise ratio of sensing signals， improve the quality of multi task scheduling in distributed fiber optic acoustic sensing systems， and have a strong assisting effect on multi task scheduling in systems with low signal-to-noise ratio signals.

Key words: distributed fiber optic acoustic sensing system, low signal-to-noise ratio signal, full waveform inversion, variable relationship learning, dynamic selection of migration tasks, multi task scheduling

中图分类号:

TP391

谭乐婷,邓慧. 全波形反演下分布式光纤声波传感信号低信噪比自适应任务调度[J]. 吉林大学学报(工学版), 2025, 55(4): 1412-1418.

Le-ting TAN,Hui DENG. Adaptive task scheduling for distributed fiber optic acoustic sensing signals with low signal-to-noise ratio under full waveform inversion[J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(4): 1412-1418.

图/表 6

图1

图2

表1

图3

图4

图5

参考文献 19

1	高莉宁, 丁思晴, 佘江江, 等. 压电技术在智能道路中应用研究现状[J]. 科学技术与工程, 2023, 23(27):11486-11495.
	Gao Li-ning, Ding Si-qing, She Jiang-jiang, et al. Research status of piezoelectric technology application in intelligent road[J]. Science Technology and Engineering, 2023, 23 (27): 11486-11495.
2	Farghal N S, Saunders J K, Parker G A. The potential of using fiber optic distributed acoustic sensing (DAS) in earthquake early warning applications[J].Bulletin of the Seismological Society of America, 2022, 112(3): 1416-1435.
3	李佳阳, 周哲海, 李子豪, 等. 基于Φ-OTDR的分布式光纤声波传感系统相位解调方法研究[J]. 激光杂志, 2022, 43(9): 14-19.
	Li Jia-yang, Zhou Zhe-hai, Li Zi-hao, et al. Research on phase demodulation method of distributed fiber optic acoustic wave sensing system based on Φ-OTDR[J]. Laser Journal, 2022, 43(9): 14-19.
4	唐枫, 冯翔, 虞慧群. 基于自适应知识迁移与资源分配的多任务协同优化算法[J]. 计算机科学, 2022, 49(7): 254-262.
	Tang Feng, Feng Xiang, Yu Hui-qun. Multi-task cooperative optimization algorithm based on adaptive knowledge transfer and resource allocation[J]. Computer Science, 2022, 49(7): 254-262.
5	史光伟, 王启任. 基于改进灰狼算法的多任务优化算法[J].天津工业大学学报, 2023, 42(5): 81-86.
	Shi Guang-wei, Wang Qi-ren. Improved grey wolf algorithm based multitask optimization algorithm[J]. Journal of Tianjin Polytechnic University, 2023, 42 (5): 81-86.
6	韩红桂, 徐子昂, 王晶晶. 基于Q学习的多任务多目标粒子群优化算法[J].控制与决策, 2023, 38(11):3039-3047.
	Han Hong-gui, Xu Zi-ang, Wang Jing-jing. A Q-learning-based multi-task multi-objective particle swarm optimization algorithm[J]. Control and Decision, 2023, 38 (11): 3039-3047.
7	Han H G, Bai X, Hou Y,et al.Adaptive multi-task optimization strategy for wastewater treatment process[J].Journal of Process Control, 2022, 119:44-54.
8	Ma X, Xu M, Yu Y,et al.Enhancing evolutionary multitasking optimization by leveraging inter-task knowledge transfers and improved evolutionary operators[J].Knowledge-based Systems, 2023,259(Sup.C): No. 110027.
9	孙倩, 王磊, 徐庆征, 等. 一种基于超粒子引导的自适应知识迁移多任务差分进化算法[J]. 控制与决策, 2024, 39(1): 26-38.
	Sun Qian, Wang Lei, Xu Qing-zheng, et al. A super-particle guided multifactorial differential evolution algorithm with adaptive knowledge transfer[J]. Control and Decision, 2024, 39(1): 26-38.
10	胡博涛, 黄超, 董良国, 等. 基于常分数阶拉普拉斯算子的黏声方程重建速度与衰减参数的全波形反演方法[J]. 地球物理学报, 2023, 66(5): 2123-2137.
	Hu Bo-tao, Huang Chao, Dong Liang-guo, et al. A constant fractional Laplacian operator based viscoacoustic full waveform inversion for velocity and attenuation estimation[J]. Chinese Journal of Geophysics, 2023, 66(5): 2123-2137.
11	马喆, 张明江, 江俊峰, 等. 基于线性调频脉冲的光纤分布式声波传感技术[J]. 激光与光电子学进展, 2023, 60(11): 24-43.
	Ma Zhe, Zhang Ming-jiang, Jiang Jun-feng, et al. Fiber-optic distributed acoustic sensing technology based on linear frequency modulation pulses[J]. Laser & Optoelectronics Progress, 2023, 60 (11): 24-43.
12	Yuan Y, Xu J, Liu L.Correlation-based maximal invariant statistic for spectrum sensing[J]. IEEE Communications Letters, 2023, 27(5): 1402-1406.
13	Matsuda T, Strawderman W E.Estimation under matrix quadratic loss and matrix superharmonicity[J].Biometrika, 2022, 109(2): 503-519.
14	彭更新, 刘威, 郭念民, 等.基于时空域交错网格有限差分法的应力速度声波方程数值模拟[J]. 石油物探, 2022, 61(1): 156-165, 173.
	Peng Geng-xin, Liu Wei, Guo Nian-min, et al. A time-space domain dispersion-relationship-based staggered-grid finite-difference scheme for modeling the stress-velocity acoustic wave equation[J]. Geophysical Prospecting for Petroleum, 2022, 61(1): 156-165, 173.
15	丁超, 马坚伟. 基于逆散射成像条件的转换波弹性波动方程自动偏移速度分析[J]. 石油物探, 2023, 62(4): 645-654, 668.
	Ding Chao, Ma Jian-wei. Converted phase elastic wave equation intelligent migration velocity analysis based on inverse-scattering imaging[J]. Geophysical Prospecting for Petroleum, 2023, 62(4): 645-654, 668.
16	周显春, 喻佳. 基于图神经网络的人工自然语言语义挖掘仿真[J]. 计算机仿真,2024, 41(1): 344-348.
	Zhou Xian-chun, Yu Jia. Artificial natural language semantic mining simulation based on graph neural network[J]. Computer Simulation, 2024, 41(1):344-348.
17	郭昊, 李岩, 侯冰冰, 等. 基于正交频分复用-多进制正交幅度调制的DC-DC变换器能量信息一体化技术[J].电工技术学报, 2023, 38(16): 4353-4365.
	Guo Hao, Li Yan, Hou Bing-bing, et al. Power information integration technology of DC-DC converters based on orthogonal frequency division multiplexing-multiple quadrature amplitude modulation[J]. Transactions of China Electrotechnical Society, 2023, 38 (16): 4353-4365.
18	潘乐, 李弼程, 万旺, 等. 基于关系强度理论与反馈机制的信息传播动态网络表示[J]. 计算机工程, 2023, 49(2): 246-253.
	Pan Le, Li Bi-cheng, Wan Wang, et al. Dynamic network representation of information diffusion based on relationship strength theory and feedback mechanism[J]. Computer Engineering, 2023, 49(2): 246-253.
19	马慧, 冯翔, 虞慧群. 基于两层知识迁移的多代理多任务优化方法[J]. 计算机科学, 2023, 50(10): 203-213.
	Ma Hui, Feng Xiang, Yu Hui-qun. Multi-surrogate multi-task optimization approach based on two-layer knowledge transfer[J]. Computer Science, 2023, 50 (10): 203-213.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

组件	指标	设定结果
声波传感器	传感距离	20 km
超低噪声掺铒光纤放大器	线宽	3 kHz
	中心波长	1 600 nm
	脉冲宽度	150 ns
	重复频率	20 kHz
	脉冲峰值激光功率	30 dB·m
声光调制器	输入阻抗	50 Ω
声光调制器	移频	80 MHz
平衡光电探测器	波长	1 550 nm
	增益	30 kV/A
	耦合方式	交流
	输出信号带宽	100 MHz
	探测路数	双路
	调制模式	外调制
尾纤	光纤种类	900 μm套管
	长度	（1 000±10） mm
	连接头种类	FC/APC

[1]	邱云飞,于鸿淼,王祥. 基于点对特征算法和SVD分解的三维激光点云识别[J]. 吉林大学学报(工学版), 2025, 55(5): 1735-1741.
[2]	金庆良,周鑫森,陈翼,吴承文. 基于群智能增强核极限学习机的创新人才预测模型[J]. 吉林大学学报(工学版), 2025, 55(5): 1763-1771.
[3]	程德强,王伟臣,韩成功,吕晨,寇旗旗. 基于改进密集网络和小波分解的自监督单目深度估计[J]. 吉林大学学报(工学版), 2025, 55(5): 1682-1691.
[4]	侯越,郭劲松,林伟,张迪,武月,张鑫. 分割可跨越车道分界线的多视角视频车速提取方法[J]. 吉林大学学报(工学版), 2025, 55(5): 1692-1704.
[5]	李燕飞,吴加宁. 基于改进RBF神经网络的人体姿态局部特征识别算法[J]. 吉林大学学报(工学版), 2025, 55(5): 1749-1755.
[6]	文斌,丁弈夫,杨超,沈艳军,李辉. 基于自选择架构网络的交通标志分类算法[J]. 吉林大学学报(工学版), 2025, 55(5): 1705-1713.
[7]	赵宏伟,周明珠,刘萍萍,周求湛. 基于置信学习和协同训练的医学图像分割方法[J]. 吉林大学学报(工学版), 2025, 55(5): 1675-1681.
[8]	肖红,刘显德. 考虑学习兴趣与微表情关联性的人脸细微特征识别算法[J]. 吉林大学学报(工学版), 2025, 55(5): 1728-1734.
[9]	薛雅丽,俞潼安,崔闪,周李尊. 基于级联嵌套U-Net的红外小目标检测[J]. 吉林大学学报(工学版), 2025, 55(5): 1714-1721.
[10]	王友卫,刘奥,凤丽洲. 基于知识蒸馏和评论时间的文本情感分类新方法[J]. 吉林大学学报(工学版), 2025, 55(5): 1664-1674.
[11]	才华,王玉瑶,付强,马智勇,王伟刚,张晨洁. 基于注意力机制和特征融合的语义分割网络[J]. 吉林大学学报(工学版), 2025, 55(4): 1384-1395.
[12]	刘广文,赵绮莹,王超,高连宇,才华,付强. 基于渐进递归的生成对抗单幅图像去雨算法[J]. 吉林大学学报(工学版), 2025, 55(4): 1363-1373.
[13]	张寒,黄炎焱,耿泽,陈天德. 海上被动无人搜救路线规划方法[J]. 吉林大学学报(工学版), 2025, 55(4): 1453-1466.
[14]	张彬桥,吴健. 基于跟踪-学习-检测算法的四旋翼无人机自主降落姿态控制方法[J]. 吉林大学学报(工学版), 2025, 55(4): 1419-1425.
[15]	刘广文,谢欣月,付强,才华,王伟刚,马智勇. 基于时空模板焦点注意的Transformer目标跟踪算法[J]. 吉林大学学报(工学版), 2025, 55(3): 1037-1049.