基于VIM-OFE的盾构泥质渣土含水率智能快速识别方法

Intelligent and Rapid Recognition Method for Moisture Content in Clayey Shield Tunnel Muck Based on VIM-OFE

摘要

盾构泥质渣土含水率的快速、准确检测已成为提升渣土处理效率与降低环境污染的关键技术问题．本文提出一种基于VIM-OFE的智能识别方法,并选取3种不同地层来源的泥质渣土样品开展试验研究．通过对土样1应用动态调整分析窗口,提取出与水分含量高度相关的特征波段(1 438～1 455 nm和1 916～1 926 nm),在该波段下建立的预测模型表现出更高的预测准确性．研究进一步分析了吸收峰面积与深度特征对建模结果的影响,并将所提出方法与iPLS、SiPLS 及 CSMW 3 种特征提取方法在预测精度和计算效率方面进行对比．结果表明,VIM-OFE 方法在预测精度方面具有显著优势,且计算耗时与其他方法处于同一数量级．随后,分别构建了单一与混合样本的含水率预测模型,混合模型在土样1和土样3中仍保持较高预测精度(R²＞0.890),展现出良好的泛化能力．此外,研究还探讨了粒径和矿物成分对近红外光谱信号的影响,并提出优化极端值处理与建立区域性盾构渣土光谱数据库的建议,以进一步提升模型的准确性和适应性．本方法可为盾构泥质渣土含水率的现场快速检测提供可靠的技术支撑,具有广泛的工程应用前景．

Abstract

The rapid and accurate detection of moisture content in clayey shield tunnel muck is a key issue for improving the muck disposal efficiency and reducing environmental impact. In this paper,an intelligent identification method based on VIM-OFE was proposed,and experiments were conducted using three clayey muck samples from different geological strata. A dynamic analysis window was applied to Sample 1 to extract the spectral intervals highly correlated with the moisture content,specifically 1 438—1 455 nm and 1 916—1 926 nm. The resulting prediction models achieved high accuracy within these intervals. The study further examined the impact of absorption peak area and depth features on the model performance and compared the proposed method with iPLS,SiPLS and CSMW in terms of predictive accuracy and computational efficiency. Results show that VIM-OFE demonstrated superior prediction performance while maintaining a comparable computation time. Both the single-soil and mixed-soil moisture prediction models were developed,with the mixed model achieving high accuracy in Samples 1 and 3(R²＞0.890),indicating strong generalization capability. Additionally,the influence of particle size and mineral composition on near-infrared(NIR) spectral response was analyzed,and strategies such as outlier optimization and the development of a regional spectral database were proposed to enhance the model robustness and adaptability. The proposed method offers a reliable technical approach for on-site rapid detection of moisture content in clayey shield tunnel muck and shows promising application potential in engineering practice.

关键词

盾构渣土 / 含水率 / 近红外光谱 / 特征提取 / 智能感知

Key words

shield tunnel muck / moisture content / near-infrared(NIR) spectroscopy / feature extraction / intelligent sensing

参考文献

[1] 史杨. 基于可见光近红外光谱的土壤成分预测模型研究[D]. 合肥： 中国科学技术大学, 2018.

[2] Shi Yang. Research on Prediction Models of Soil Properties Using Visible/Near Infrared Spectroscopy[D]. Hefei： University of Science and Technology of China, 2018(in Chinese).

[3] 张书经, 阳栋, 谭立新, 等. 盾构渣土的含水率特征及脱水技术研究[J]. 中国水土保持, 2019(8): 37-42.

[4] Zhang Shujing, Yang Dong, Tan Lixin, et al. Characteristics of moisture content and dehydration technology of shield dregs[J]. Soil and Water Conservation in China, 2019(8): 37-42(in Chinese).

[5] 苏国君, 龚秋明, 周小雄, 等. 基于皮带出渣图像识别渣土含水率区间[J]. 隧道与地下工程灾害防治, 2024, 6(3): 73-81.

[6] Su Guojun, Gong Qiuming, Zhou Xiaoxiong, et al. Identifying the water content interval of muck based on the image fo belt slag[J]. Hazard Control in Tunnelling and Underground Engineering, 2024, 6(3): 73-81(in Chinese).

[7] 孟德伦, 孟繁佳, 段晓菲, 等. 基于频域法的便携式无线土壤水分测量装置设计与试验[J]. 农业工程学报, 2017, 33(增1): 114-119.

[8] Meng Delun, Meng Fanjia, Duan Xiaofei, et al. Design and experiment of a portable wireless soil moisture measuring device based on frequency—domain method[J]. Transactions of the Chinese Society of Agricultural Engineering, 2017, 33(Suppl 1): 114-119(in Chinese).

[9] Piuzzi E, Cataldo A, Cannazza G, et al. An improved reflectometric method for soil moisture measurement exploiting an innovative triple—short calibration[J]. IEEE Transactions on Instrumentation and Measurement, 2010, 59(10): 2747-2754.

[10] Feng L, Wang Y M, Yang W Z, et al. Comparison of standing wave ratio,time domain reflectometry and gravimetric method for soil moisture measurements[J]. Sensor Letters, 2011, 9(3): 1140-1143.

[11] Bobrov P P, Belyaeva T A, Kroshka E S, et al. Soil moisture measurement by the dielectric method[J]. Eurasian Soil Science, 2019, 52(7): 822-833.

[12] 常丹, 李旭, 刘建坤, 等. 土体含水率测量方法研究进展及比较[J]. 工程勘察, 2014, 42(9): 17-22,35.

[13] Chang Dan, Li Xu, Liu Jiankun, et al. Study progress and comparison of soil moisture content measurement methods[J]. Geotechnical Investigation & Suveying, 2014, 42(9): 17-22,35(in Chinese).

[14] 殷哲, 雷廷武, 董月群. 近红外土壤含水率传感器设计与试验[J]. 农业机械学报, 2013, 44(7): 73-77,72.

[15] Yin Zhe, Lei Tingwu, Dong Yuequn. Design and experiment of near infrared sensor for soil moisture measurement[J]. Transactions of the Chinese Society for Agricultural Machinery, 2013, 44(7): 73-77,72(in Chinese).

[16] 张东兴, 刘江, 杨丽, 等. 基于VIS—NIR的播种沟内土壤水分测量传感器研究[J]. 农业机械学报, 2021, 52(2): 218-226.

[17] Zhang Dongxing, Liu Jiang, Yang Li, et al. Soil moisture measurement sensor research in seeding ditch based on VIS—NIR[J]. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(2): 218-226(in Chinese).

[18] Murase S, Ma T, Ruan K L, et al. Estimation of water content of compacted Kunigel—V1 bentonite using near—infrared spectra[J]. Soils and Foundations, 2025, 65(1): 101545.

[19] Nawar S, Mouazen A M. Predictive performance of mobile vis—near infrared spectroscopy for key soil properties at different geographical scales by using spiking and data mining techniques[J]. Catena, 2017, 151: 118-129.

[20] 石文强, 许秀英, 张伟, 等. 近红外光谱的北方寒地土壤含水率预测模型研究[J]. 光谱学与光谱分析, 2022, 42(6): 1704-1710.

[21] Shi Wenqiang, Xu Xiuying, Zhang Wei, et al. Prediction model of soil moisture content in northern cold region based on near—infrared spectroscopy[J]. Spectroscopy and Spectral Analysis, 2022, 42(6): 1704-1710(in Chinese).

[22] Loshelder J I, Coffman R A. Soil moisture content from spectral reflectance using visible,near—infrared,and short—wave infrared light[J]. Journal of Irrigation and Drainage Engineering, 2023, 149(6): 04023010.

[23] de Santana F B, de Giuseppe L O, de Souza A M, et al. Removing the moisture effect in soil organic matter determination using NIR spectroscopy and PLSR with external parameter orthogonalization[J]. Microchemical Journal, 2019, 145: 1094-1101.

[24] Jiang T X, van der Werff H, van Ruitenbeek F, et al. The influence of changing moisture content on laboratory acquired spectral feature parameters and mineral classification[J]. International Journal of Applied Earth Observation and Geoinformation, 2024, 130: 103884.

[25] 杨柳, 徐榕, 雷廷武, 等. 近红外反射土壤含水率测量仪设计[J]. 农业工程学报, 2015, 31(20): 1-9.

[26] Yang Liu, Xu Rong, Lei Tingwu, et al. Design of near—infrared soil moisture measuring instrument[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(20): 1-9(in Chinese).

[27] 虞茉莉, 刘善军, 宋亮, 等. 不同含水量尾砂的光谱特征与遥感模型[J]. 光谱学与光谱分析, 2019, 39(10): 3096-3101.

[28] Yu Moli, Liu Shanjun, Song Liang, et al. Spectral characteristics and remote sensing model of tailings with different water contents[J]. Spectroscopy and Spectral Analysis, 2019, 39(10): 3096-3101(in Chinese).

[29] 刘广霖, 郭焱, 劳彩莲, 等. 基于田间原位土壤含水量估测的可见/近红外光谱建模方法[J]. 中国农业大学学报, 2016, 21(8): 125-131.

[30] Liu Guanglin, Guo Yan, Lao Cailian, et al. Estimation of soil water content in situ by using visible/near infrared spectrum modeling[J]. Journal of China Agricultural University, 2016, 21(8): 125-131(in Chinese).

[31] 孙建英, 李民赞, 郑立华, 等. 基于近红外光谱的北方潮土土壤参数实时分析[J]. 光谱学与光谱分析, 2006, 26(3): 426-429.

[32] Sun Jianying, Li Minzan, Zheng Lihua, et al. Real—time analysis of soil moisture,soil organic matter,and soil total nitrogen with NIR spectra[J]. Spectroscopy and Spectral Analysis, 2006, 26(3): 426-429(in Chinese).

[33] 金慧凝, 张新乐, 刘焕军, 等. 基于光谱吸收特征的土壤含水量预测模型研究[J]. 土壤学报, 2016, 53(3): 627-635.

[34] Jin Huining, Zhang Xinle, Liu Huanjun, et al. Soil moisture prediction model based on spectral absorption characteristics of the soil[J]. Acta Pedologica Sinica, 2016, 53(3): 627-635(in Chinese).

[35] 张乾, 王风, 温斯逊. 泥岩砂卵石复合地层盾构渣土含水特征分析[J]. 四川建筑, 2023, 43(5): 145-147.

[36] Zhang Qian, Wang Feng, Wen Sixun. Analysis of water content characteristics of shield muck in mudstone—sand cobble composite stratum[J]. Sichuan Architecture, 2023, 43(5): 145-147(in Chinese).

[37] 张智韬, 王海峰, 韩文霆, 等. 基于无人机多光谱遥感的土壤含水率反演研究[J]. 农业机械学报, 2018, 49(2): 173-181.

[38] Zhang Zhitao, Wang Haifeng, Han Wenting, et al. Inversion of soil moisture content based on multispectral remote sensing of UAVs[J]. Transactions of the Chinese Society for Agricultural Machinery, 2018, 49(2): 173-181(in Chinese).

[39] Du Y P, Liang Y Z, Jiang J H, et al. Spectral regions selection to improve prediction ability of PLS models by changeable size moving window partial least squares and searching combination moving window partial least squares[J]. Analytica Chimica Acta, 2004, 501(2): 183-191.

[40] Rinnan R, Rinnan Å. Application of near infrared reflectance(NIR)and fluorescence spectroscopy to analysis of microbiological and chemical properties of arctic soil[J]. Soil Biology and Biochemistry, 2007, 39(7): 1664-1673.

[41] 褚小立, 袁洪福, 陆婉珍. 近红外分析中光谱预处理及波长选择方法进展与应用[J]. 化学进展, 2004, 16(4): 528-542.

[42] Chu Xiaoli, Yuan Hongfu, Lu Wanzhen. Progress and application of spectral data pretreatment and wavelength selection methods in NIR analytical technique[J]. Progress in Chemistry, 2004, 16(4): 528-542 (in Chinese).

[43] Rinnan Å, van den Berg F, Engelsen S B. Review of the most common pre—processing techniques for near—infrared spectra[J]. TrAC Trends in Analytical Chemistry, 2009, 28(10): 1201-1222.

[44] Zhang Q B, Li C, Pan Y T, et al. Microstructure and mechanical properties of horns derived from three domestic bovines[J]. Materials Science and Engineering：C, 2013, 33(8): 5036-5043.

[45] 程介虹, 陈争光. 改进的联合区间随机蛙跳算法的近红外光谱波长选择[J]. 光谱学与光谱分析, 2020, 40(11): 3451-3456.

[46] Cheng Jiehong, Chen Zhengguang. Wavelength selection of near—infrared spectra based on improved SiPLS—random frog algorithm[J]. Spectroscopy and Spectral Analysis, 2020, 40(11): 3451-3456(in Chinese).

[47] Li M G, Feng Y Z, Yu Y, et al. Quantitative analysis of polycyclic aromatic hydrocarbons in soil by infrared spectroscopy combined with hybrid variable selection strategy and partial least squares[J]. Spectrochimica Acta Part A：Molecular and Biomolecular Spectroscopy, 2021, 257: 119771.

[48] 王平全, 谭敬明, 程地奎. 用红外光谱法确定黏土表面结合水界限[J]. 西南石油学院学报, 2001, 23(2): 53-55.

[49] Wang Pingquan, Tan Jingming, Cheng Dikui. The determination of bound water boundary on clay surface by infrared spectrum[J]. Journal of Southwest Petroleum Institute, 2001, 23(2): 53-55(in Chinese).

[50] 王平全. 黏土表面结合水定量分析及水合机制研究[D]. 南充： 西南石油学院, 2001.

[51] Wang Pingquan. The Study for Quantitative Analysis of Water on Clays and Their Hydration Mechanism[D]. Nanchong： Southwest Petroleum Institute, 2001(in Chinese).

[52] 彭润东, 李耀翔, 张哲宇, 等. 基于近红外的木屑含水率定量检测[J]. 中南林业科技大学学报, 2024, 44(2): 184-196.

[53] Peng Rundong, Li Yaoxiang, Zhang Zheyu, et al. Modeling moisture content of sawdust based on NIRS[J]. Journal of Central South University of Forestry & Technology, 2024, 44(2): 184-196(in Chinese).

[54] 周清. 土壤有机质含量高光谱预测模型及其差异性研究[D]. 杭州： 浙江大学, 2004.

[55] Zhou Qing. Study on the Hyperspectral Prediction Models of Soil Organic Matter and Its Differences Among Soil Types[D]. Hangzhou： Zhejiang University, 2004 (in Chinese).

[56] 韩小平, 王沛华, 崔传金, 等. 土样盒土表特征对近红外光谱测量土壤水分精度的影响[J]. 农业工程学报, 2010, 26(6): 47-51.

[57] Han Xiaoping, Wang Peihua, Cui Chuanjin, et al. Influence of soil surface disposal on precision of measuring soil water by near—infrared spectroscopy[J]. Transactions of the CSAE, 2010, 26(6): 47-51(in Chinese).

[58] 李民赞, 郑立华, 安晓飞, 等. 土壤成分与特性参数光谱快速检测方法及传感技术[J]. 农业机械学报, 2013, 44(3): 73-87.

[59] Li Minzan, Zheng Lihua, An Xiaofei, et al. Fast measurement and advanced sensors of soil parameters with NIR spectroscopy[J]. Transactions of the Chinese Society for Agricultural Machinery, 2013, 44(3): 73-87(in Chinese).

[60] 纪文君, 史舟, 周清, 等. 几种不同类型土壤的 VIS—NIR 光谱特性及有机质响应波段[J]. 红外与毫米波学报, 2012, 31(3): 277-282.

[61] Ji Wenjun, Shi Zhou, Zhou Qing, et al. VIS—NIR reflectance spectroscopy of the organic matter in several types of soils[J]. Journal of Infrared and Millimeter Waves, 2012, 31(3): 277-282(in Chinese).

基金资助

国家自然科学基金优秀青年基金资助项目(52422004)

国家自然科学基金资助项目(52179108)

深圳市可持续专项资助项目(KCXFZ20211020164013020)