作者：刘喜凤1，朱鸿鹄*1,2，王家琛1,3,4，吴冰1，李杰1，曹鼎峰2,5，施斌1
1南京大学地球科学与工程学院，江苏 南京，200023
2广东省海洋土木工程重点实验室，广东 广州，510275
3中国长江三峡集团雄安分公司，河北 雄安新区，071700
4长江三峡集团雄安能源有限公司，河北 雄安新区，071700
5中山大学土木工程学院，广东 广州 ，510275
来源：岩土工程学报, 2022, 44(9): 1721-1729
视频报告链接：https://www.bilibili.com/video/BV1Dd4y1u7nN/
摘要：土壤水分时空分布的精准监测对于工程地质评估、地质灾害防治具有重要意义。当土壤含水率变化梯度较大时，准分布式主动加热光纤光栅（AH-FBG）法的测量误差相对较大。为分析该工况下的误差来源及其沿深度的分布状态，设计开展了3组室内土柱试验，并在试验基础上提出了基于人工神经网络（ANN）的联合分析法，以改进AH-FBG水分感测技术的分析方法。研究结果表明：将AH-FBG法应用在含水率变化梯度较大的土体中，加热时传感器和土体中会产生纵向传热，其中传感器纵向传热占主导地位；该效应会降低含水率监测精度，且相关误差不能通过减少加热时间进行消减；室内试验和现场监测数据均显示，相较于传统的最大升温值法，联合分析法考虑了升温跃迁和拖滞效应，因此得到的含水率监测精度明显提高，证明了该方法的优越性。
关键词：主动加热光纤（AHFO）法；神经网络；含水率；纵向传热；岩土工程监测
中图分类号：TU411 文献标识码：A 文章编号：1000–4548(2022)09–1721–09
作者简介：刘喜凤(1998— )，女，硕士研究生，主要从事地质与岩土工程监测方面的研究。E-mail: liuxf@smail.nju.edu.cn。
*通信作者：朱鸿鹄（E-mail: zhh@nju.edu.cn）
基金项目：国家重点研发计划课题（2018YFC1505104）；广东省海洋土木工程重点实验室开放基金项目（LMCE202006）；软弱土与环境土工教育部重点实验室开放基金项目（2019P05）
收稿日期：2021–09–13
Improved fiber optic sensing technology of soil moisture based on neural network
LIU Xi-feng1, ZHU Hong-hu*1,2, WANG Jia-chen1,3,4, WU Bing1, LI Jie1, CAO Ding-feng2,5, SHI Bin1
1 School of Earth Sciences and Engineering, Nanjing University, Nanjing 210023, China;
2 Guangdong Key Laboratory of Marine Civil Engineering, Guangzhou 510275, China;
3 Xiongan Branch, China Three Gorges Corporation, Xiongan 071700, China;
4 Yangtze Three Gorges Group Xiongan Energy Company Limited, Xiongan 071700, China;
5 School of Civil Engineering, Sun Yat-sen University, Guangzhou 510275, China)
Abstract: Accurate monitoring of temporal and spatial distribution of soil moisture is of great significance to engineering geological assessment and geo-hazard prevention. A large gradient of moisture content of soil has a relatively great influence on the measurement precision of the actively heated fiber Bragg grating (AH-FBG) method. To analyze the source of measurement errors and its distribution along the depth, three sets of laboratory soil column tests are designed and carried out. A joint analysis method based on the artificial neural network (ANN) algorithm is further proposed to improve the analysis method of AH-FBG moisture sensing technology. The results show that when the AH-FBG method is applied to the soil with a large gradient of moisture content, the longitudinal heat transfer of the sensor and soil will both occur during the heating process simultaneously, and the longitudinal heat transfer of the sensor is dominant. This effect reduces the monitoring accuracy of moisture content, and the related errors cannot be decreased by reducing heating time. The data from laboratory tests and field monitoring indicate that compared with the traditional maximum heating value method, the joint analysis method considers the heat transition and drag effect, and therefore the monitoring accuracy of moisture content is noticeably improved, which proves the superiority of the method.
Key words: actively heated fiber optic method; neural network; moisture content; longitudinal heat transfer; geotechnical engineering monitoring
参考文献：
[1] LU N, LIKOS W J. Unsaturated Soil Mechanics[M]. J. Wiley, 2004.
[2] 吴世余, 余金煌. 粉性土毛管水的力学和工程特性[J]. 岩土力学, 2013, 34(1): 80–84, 91. (WU Shi-yu, YU Jin-huang. Mechanical and engineering characteristics of capillary water of silty soils[J]. Rock and Soil Mechanics, 2013, 34(1): 80- 84, 91. (in Chinese))
[3] CHEN H, LEE C, LAW K. Causative mechanisms of rainfall-induced fill slope failures[J]. Journal of Geotechnical and Geo-environmental Engineering, 2004, 130(6): 593-602.
[4] TANG C S, CUI Y J, SHI B, et al. Desiccation and cracking behaviour of clay layer from slurry state under wetting-drying cycles[J]. Geoderma, 2011, 166(1): 111-118.
[5] CUOMO S, SALA M D. Rainfall-induced infiltration, runoff and failure in steep unsaturated shallow soil deposits[J]. Engineering Geology, 2013, 162: 118-127.
[6] CHAE B G, LEE J H, PARK H J, et al. A method for predicting the factor of safety of an infinite slope based on the depth ratio of the wetting front induced by rainfall infiltration[J]. Natural Hazards and Earth System Sciences, 2015, 15(8): 1835-1849.
[7] WEISS J D. Using fiber optics to detect moisture intrusion into a landfill cap consisting of a vegetative soil barrier[J]. Journal of the Air and Waste Management Association, 2003, 53(9): 1130-1148.
[8] SAYDE C, BUELGA J B, RODRIGUEZ-SINOBAS L, et al. Mapping variability of soil water content and flux across 1-1000 m scales using the actively heated fiber optic method[J]. Water Resources Research, 2014, 50(9): 7302-7317.
[9] 吴 冰, 朱鸿鹄, 曹鼎峰, 等. 黄土水分场光纤原位监测及非饱和渗透系数估算[J]. 防灾减灾工程学报, 2019, 39(5): 691–699. (WU Bing, ZHU Hong-hu, CAO Ding-feng, et al. In-situ monitoring of moisture field and estimation of unsaturated permeability coefficient of loess foundation[J]. Journal of Disaster Prevention and Mitigation Engineering, 2019, 39(5): 691-699. (in Chinese))
[10] SAYDE C, GREGORY C, GIL-RODRIGUEZ M, et al. Feasibility of soil moisture monitoring with heated fiber optics[J]. Water Resources Research, 2010, 46: W06201.
[11] STRIEGL A M, STEVEN I I. Heated distributed temperature sensing for field scale soil moisture monitoring[J]. Ground Water, 2012, 50(3): 340-347.
[12] LI M, SI B C, HU W, et al. Single-Probe heat pulse method for soil water content determination: comparison of methods[J]. Vadose Zone Journal, 2016, 15(7): 1-13.
[13] DUMINDA V G, ASIM B, IAN S, et al. Soil water measurement using actively heated fiber optics at field scale[J]. Sensors, 2018, 18(4): 1116-1131.
[14] 徐东升. 一种新型光纤光栅局部位移计在小应变测量中的应用[J]. 岩土工程学报, 2017, 39(7): 1330-1335. (XU Dong-sheng. New fiber Bragg grating sensor-based local displacement transducer for small strain measurements of soil specimens[J]. Chinese Journal of Geotechnical Engineering, 2017, 39(7): 1330-1335. (in Chinese))
[15] 郭君仪, 孙梦雅, 施 斌, 等. 不同环境温度下土体含水率主动加热光纤法监测试验研究[J]. 岩土力学, 2020, 41(12): 4137–4144. (GUO Jun-yi, SUN Meng-ya, SHI Bin, et al. Experimental study of water content in soils monitored with active heated fiber optic method at different ambient temperatures[J]. Rock and Soil Mechanics, 2020, 41(12): 4137-4144. (in Chinese))
[16] SUN M Y, SHI B, ZHANG D, et al. Study on calibration model of soil water content based on actively heated fiber-optic FBG method in the in-situ test[J]. Measurement, 2020, 165: 1-10.
[17] CAO D F, ZHU H H, WU B, et al. Investigating soil temperature and moisture profiles under different land covers using actively heated fiber Bragg grating sensors[J]. Engineering Geology, 2021, 290: 106197.
[18] 段超喆, 施 斌, 曹鼎峰, 等. 一种准分布式内加热刚玉管 FBG 渗流速率监测方法[J]. 防灾减灾工程学报, 2018, 38(3): 504–510. (DUAN Chao-zhe, SHI Bin, CAO Ding-feng, et al. A quasi-distributed velocity monitoring method using FBG embedded in internal heated alundum tube[J]. Journal of Disaster Prevention and Mitigation Engineering, 2018, 38(3): 504-510. (in Chinese))
[19] 王家琛, 朱鸿鹄, 王 静, 等. 基于主动加热光纤法的毛细阻滞入渗模型试验研究[J]. 岩土工程学报, 2020, 39(1): 62–70. (WANG Jia-chen, ZHU Hong-hu, WANG Jing, et al. Laboratory model of a capillary barrier infiltration test using active heated fiber optic method [J]. Chinese Journal of Geotechnical Engineering, 2020, 39(1): 62-70. (in Chinese))
[20] 曹鼎峰, 施 斌, 严珺凡, 等. 基于 C-DTS 的土壤含水率分布式测定方法研究[J]. 岩土工程学报, 2014, 36(5): 910–915. (CAO Ding-feng, SHI Bin, YAN Jun-fan, et al. Distributed method for measuring moisture content of soils based on C-DTS[J]. Chinese Journal of Geotechnical Engineering, 2014, 36(5): 910-915. (in Chinese))
[21] LIU I S. On Fourier’s law of heat conduction[J]. Continuum Mechanics and Thermodynamics, 1990, 2(4): 301-305.
[22] DUBI Y, VENTRA M D. Fourier’s Law: insight from a simple derivation[J]. Physical Review E, 2009, 79(4): 1-4.
[23] 甄作林，朱江鸿，张虎元，等. 砂土导热性能测试与预测研究[J]. 地下空间与工程学报, 2018, 14(6): 1577–1586. (ZHEN Zuo-lin, ZHU Jiang-hong, ZHANG Hu-yuan, et al. Study on the Measurement and Prediction of Thermal Properties for Sand [J]. Chinese Journal of Underground Space and Engineering, 2018, 14(6): 1577-1586. (in Chinese))
[24] 李双成, 郑 度. 人工神经网络模型在地学研究中的应用进展[J]. 地球科学进展, 2003, 18(1): 68–76. (LI Shuang-cheng, ZHENG Du. Laboratory model of a capillary barrier infiltration test using active heated fiber optic method [J]. Advance in Earth Sciences, 2003, 18(1): 68-76. (in Chinese))
[25] BASHEER I A, HAJMEER M. Artificial neural networks: fundamentals, computing, design, and application[J]. Journal of Microbiological Methods, 2000, 43(1): 3-31.
[26] 周振民, 刘 荻. 基于Matlab的人工神经网络用水量预测模型[J]. 中国农村水利水电, 2007, 0(4):45–47. (ZHOU Zhen-ming, LIU Di. A prediction model of water consumption based on artificial neural network based on MATLAB [J]. China Rural Water and Hydropower, 2007, 0(4): 45-47. (in Chinese))
[27] YU S, ZHU K, DIAO F. A dynamic all parameters adaptive BP neural networks model and its application on oil reservoir prediction[J]. Applied Mathematics and Computation, 2008, 195(1): 66-75.
[28] WU W, JIAN W, CHENG M, et al. Convergence analysis of online gradient method for BP neural networks[J]. Neural Networks Oxford, 2011, 24(1): 91-98.
[29] BORDOLOI S, GOPAL P, BODDU R, et al. Soil-biochar-water interactions: Role of biochar from Eichhornia crassipes in influencing crack propagation and suction in unsaturated soils[J]. Journal of Cleaner Production, 2019, 210: 847-859.
[30] 胡 优, 李 敏, 任姮烨, 等. 基于加热光纤分布式温度传感器的土壤含水率测定方法[J]. 农业工程学报, 2019, 35(10): 42–49. (HU You, LI Min, REN Heng-ye, et al. Measurement of soil water content using distributed temperature sensor with heated fiber optics[J]. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(10): 42-49. (in Chinese))
引用本文:
刘喜凤, 朱鸿鹄, 王家琛, 吴冰, 李杰, 曹鼎峰, 施斌. 基于神经网络的改进型土壤水分光纤感测技术研究[J]. 岩土工程学报, 2022, 44(9): 1721-1729.
LIU Xi-feng, ZHU Hong-hu, WANG Jia-chen, WU Bing, LI Jie, CAO Ding-feng, SHI Bin. Improved fiber optic sensing technology of soil moisture based on neural network. Chinese J. Geot. Eng., 2022, 44(9): 1721-1729.