基于深度学习的路基病害智能检测方法

doi:10.6040/j.issn.1672-3961.0.2024.309

摘要/Abstract

摘要： 针对目前路基病害隐匿性高、数据缺乏的问题,构建一种新型路基病害智能识别方法。该方法由基于注意力机制长短期记忆(iTransformer-long short-term memory, iTransformer-LSTM)神经网络的预测模块与弹性网络回归模块组成。通过模型试验对路面施加动荷载获取力学响应数据,以解决路基病害数据不足的问题;将力学响应数据输入模型预测路基结构的力学性能,识别病害类型。为验证这一方法,基于实际路基结构的材料配比构建路基缩尺模型,分别设计路基松散、不均匀沉降、路基裂缝和管线泄露等缺陷的路基试件,模拟实际场景下的路基病害,在模型试件中布设应变片式土压力计监测模型中不同层、不同位置的力学数据,继而对路基模型试件进行动荷载加载,采集、分析与验证试件的土压力。结果表明,构建的路基病害识别模型能根据荷载数据和位移数据预测路基结构中土压力的分布与发展趋势,继而快速、准确地识别路基中的病害类型。该研究成果为路基病害的无损检测提供新的思路。

关键词: 路基病害检测, 注意力机制, iTransformer-LSTM, 弹性神经网络, 模型试验

Abstract: A novel intelligent method for identifying subgrade distress was proposed to address the challenges associated with the concealed nature of subgrade defects and the scarcity of available data. The proposed framework consisted of a prediction module based on an attention-enhanced long short-term memory network(iTransformer-LSTM)and a regression module based on an elastic neural network. Mechanical response data were generated through dynamic loading tests on pavement model specimens, which effectively mitigated the problem of inadequate distress data. These data were subsequently used to predict the mechanical performance of the subgrade structure, and the distress types were identified accordingly. To verify the effectiveness of the proposed method, a scaled subgrade model was established using the material proportions of a real subgrade structure. Defective specimens representing looseness, differential settlement, cracks, and pipeline leakage were designed to reproduce realistic subgrade distress conditions. Strain-gauge earth pressure cells were embedded at different layers and positions within the model to monitor mechanical responses under dynamic loading. The measured earth pressure data were then collected, analyzed, and validated. The results demonstrated that the proposed model could accurately predict the distribution and evolution of earth pressure in the subgrade structure based on load and displacement data, thereby enabling rapid and accurate identification of distress types. The proposed method offered a new perspective for the nondestructive detection of subgrade distress.

Key words: subgrade disease detection, attention mechanism, iTransformer-LSTM, resilient neural network, model testing

中图分类号:

TN958.98

任红伟,孟菲,王继凯,田威杨,魏明召,程之恒,杜聪,吴建清. 基于深度学习的路基病害智能检测方法[J]. 山东大学学报 (工学版), 2026, 56(3): 93-105.

REN Hongwei, MENG Fei, WANG Jikai, TIAN Weiyang, WEI Mingzhao, CHENG Zhiheng, DU Cong, WU Jianqing. Intelligent detection method for subgrade disease based on deep learning[J]. Journal of Shandong University(Engineering Science), 2026, 56(3): 93-105.

参考文献

[1] WU J Q, ZHANG Z Y, TIAN Y, et al. Analysis of the evolution patterns for tunnel structures based on a data-driven method[J]. Structures, 2024, 65(1): 106646.
[2] LI Y, YANG X Z, HU X, et al. Mechanisms of rainfall-induced landslides and interception dynamic response: a case study of the Ni Changgou landslide in Shimian, China[J]. Scientific Reports, 2024, 14(1): 1567.
[3] GUO S L, XU Z W, LI X Z, et al. Detection and characterization of cracks in highway pavement with the amplitude variation of GPR diffracted waves: insights from forward modeling and field data[J]. Remote Sensing, 2022, 14(4): 976.
[4] WANG R, CHEN R Q, GUO X X, et al. Automatic recognition system for concrete cracks with support vector machine based on crack features[J]. Scientific Reports, 2024, 14(1): 20057.
[5] 马小平, 李松, 张瀚青, 等. 基于情景推演的铁路降雨灾害预测性防控方法[J]. 铁道科学与工程学报, 2024, 21(8):3382-3393. MA Xiaoping, LI Song, ZHANG Hanqing, et al. Predictive control method for railway rain-related disasters based on scenario deduction[J]. Journal of Railway Science and Engineering, 2024, 21(8): 3382-3393.
[6] 吴建清, 宋修广. 智慧公路关键技术发展综述[J]. 山东大学学报(工学版), 2020, 50(4): 52-69. WU Jianqing, SONG Xiuguang. Review on smart highways critical technology[J]. Journal of Shandong University(Engineering Science), 2020, 50(4): 52-69.
[7] LI J, DANG X T, ZHANG J W, et al. Mechanical properties of fly ash-slag based geopolymer for repair of road subgrade diseases[J]. Polymers, 2023, 15(2): 309.
[8] 宋修广, 张宏博. 粉喷桩复合地基摩阻力分布规律分析[J]. 岩土工程学报, 2006, 28(9): 1090-1094. SONG Xiuguang, ZHANG Hongbo. Analysis on distribution of frictional resistance in DJM pile composite foundation[J]. Chinese Journal of Geotechnical Engineering, 2006, 28(9): 1090-1094.
[9] 宋修广, 赵一民, 张宏博, 等. 加筋路堤下涵洞土压力分布规律及计算方法[J]. 山东大学学报(工学版), 2021, 51(4): 43-53. SONG Xiuguang, ZHAO Yimin, ZHANG Hongbo, et al. Distribution law and calculation method of earth pressure in culvert under reinforced embankment[J]. Journal of Shandong University(Engineering Science), 2021, 51(4): 43-53.
[10] HOU Z Z, ZHAO W G, YANG Y. Identification of railway subgrade defects based on ground penetrating radar[J]. Scientific Reports, 2023, 13(1): 6030.
[11] QI S S, LI G Y, CHEN D, et al. Damage properties of the block-stone embankment in the Qinghai-Tibet highway using ground-penetrating radar imagery[J]. Remote Sensing, 2022, 14(12): 2950.
[12] LIU Z, WU W X, GU X Y, et al. Application of combining YOLO models and 3D GPR images in road detection and maintenance[J]. Remote Sensing, 2021, 13(6):1081.
[13] 周黎明, 张杨, 付代光, 等. 道路地下空洞探地雷达波场和时频特性[J]. 同济大学学报(自然科学版), 2024, 52(1):77-85. ZHOU Liming, ZHANG Yang, FU Daiguang, et al. Wave field and time-frequency characteristics of ground penetrating radar for underground cavity of road[J]. Journal of Tongji University(Natural Science), 2024, 52(1): 77-85.
[14] 杜衍庆, 隋昕展, 师海, 等. 公路路基浅层疏松病害地质雷达正演模拟及复信号分析[J]. 北京交通大学学报, 2023, 47(6): 147-153. DU Yanqing, SUI Xinzhan, SHI Hai, et al. GPR forward simulation and complex signal analysis of shallow layer loosening defects in highway subgrade[J]. Journal of Beijing Jiaotong University, 2023, 47(6): 147-153.
[15] 何虎振, 刘国林, 王凤云, 等. 基于SBAS-InSAR和PSO-BP模型的鲁南高铁沿线地表沉降监测与预测[J]. 大地测量与地球动力学, 2024, 44(8): 820-826. HE Huzhen, LIU Guolin, WANG Fengyun, et al. Surface subsidence monitoring and prediction along Lunan high speed railway based on SBAS-InSAR and PSO-BP model[J]. Journal of Geodesy and Geodynamics, 2024, 44(8): 820-826.
[16] 董建军, 张莹, 李昕, 等. 采空区地表InSAR形变监测与安全稳定性评价[J]. 中国安全科学学报, 2024, 34(1): 140-149. DONG Jianjun, ZHANG Ying, LI Xin, et al. InSAR deformation monitoring and safety and stability evaluation on surface of coal mine goaf[J]. China Safety Science Journal, 2024, 34(1): 140-149.
[17] 李明佳, 孙建宝, 薛莲, 等. 广域InSAR时序分析技术对华北平原地表形变的监测[J]. 北京大学学报(自然科学版), 2023, 59(6): 934-944. LI Mingjia, SUN Jianbao, XUE Lian, et al. Wide-area InSAR time series analysis technique for monitoring of surface deformation in the North China Plain[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2023, 59(6): 934-944.
[18] 何毅, 姚圣, 陈毅, 等. ConvLSTM神经网络的时序InSAR地面沉降时空预测[J]. 武汉大学学报(信息科学版), 2025, 50(3): 488-502. HE Yi, YAO Sheng, CHEN Yi, et al. Spatio-temporal prediction of time-series InSAR land subsidence based on ConvLSTM neural network[J]. Geomatics and Information Science of Wuhan University, 2025, 50(3): 488-502.
[19] XING X M, ZHU L J, LIU B, et al. Measuring land surface deformation over soft clay area based on an FIPR SAR interferometry algorithm: a case study of Beijing Capital International Airport(China)[J]. Remote Sensing, 2022, 14(17):4253.
[20] 张旭苹, 张益昕, 王亮, 等. 分布式光纤传感技术研究和应用的现状及未来[J]. 光学学报, 2024, 44(1): 11-73. ZHANG Xuping, ZHANG Yixin, WANG Liang, et al. Current status and future of research and applications for distributed fiber optic sensing technology[J]. Acta Optica Sinica, 2024, 44(1): 11-73.
[21] 宋修广, 赵涛, 毕研美, 等. 光纤传感技术在道路交通中的应用[J]. 山东大学学报(工学版), 2024, 54(2): 13-26. SONG Xiuguang, ZHAO Tao, BI Yanmei, et al. Application of fiber optic sensing technology in road traffic[J]. Journal of Shandong University(Engineering Science), 2024, 54(2): 13-26.
[22] LI Z, YUAN K, ZHAO L G. Optical-fiber-embedded beam for subgrade distributed settlement monitoring: experiments and numerical modeling[J]. Applied Sciences, 2023, 13(16): 9047.
[23] 汪璋淳, 罗启迅, 孔洋, 等. 基于分布式光纤传感技术的二维变形监测试验研究[J]. 岩土工程学报, 2023, 45: 39-43. WANG Zhangchun, LUO Qixun, KONG Yang, et al. Experimental research on two-dimensional deformation monitoring based on distributed optical fiber sensing technology[J]. Chinese Journal of Geotechnical Engineering, 2023, 45: 39-43.
[24] 张敏捷, 李佳康, 张峰, 等. 基于OFDR技术的分布式光纤-砂土界面耦合性试验与评价模型研究[J]. 岩石力学与工程学报, 2024, 43(增刊1):3557-3567. ZHANG Minjie, LI Jiakang, ZHANG Feng, et al. Research on experiment and evaluation model of interface coupling between distributed optical fiber and sand based on OFDR[J]. Chinese Journal of Rock and Engineering, 2024, 43(Suppl.1): 3557-3567.
[25] 沙特, 罗勇, 雷坤超, 等. 基于分布式光纤传感技术的北京宋庄地面沉降和地裂缝综合监测[J]. 地质通报, 2024, 43(5): 859-867. SHA Te, LUO Yong, LEI Kunchao, et al. Comprehensive monitoring of land subsidence and ground fissures in Songzhuang, Beijing, based on distributed optical fiber sensing technology[J]. Geological Bulletin of China, 2024, 43(5): 859-867.
[26] 汪辛, 丁志凯, 刘胜春. 基于BOTDA的混凝土结构裂缝识别试验研究及工程应用[J]. 公路交通科技, 2023, 40(9): 151-157. WANG Xin, DING Zhikai, LIU Shengchun. Experimental study and engineering application of crack identification in concrete structures based on BOTDA[J]. Journal of Highway and Transportation Research and Development, 2023, 40(9): 151-157.
[27] 王大为, 吕浩天, 汤伏蛟, 等. 三维探地雷达道路隐性病害检测分析与数字化技术综述[J]. 中国公路学报, 2023, 36(3): 1-19. WANG Dawei, LYU Haotian, TANG Fujiao, et al. Road structural defects detection and digitalization based on 3D ground penetrating radar technology: a state-of-the-art review[J]. China Journal of Highway and Transport, 2023, 36(3): 1-19.
[28] 杜豫川, 岳光华, 刘成龙, 等. 探地雷达多特征融合的城市空洞自动识别方法[J]. 中国公路学报, 2023, 36(3): 108-119. DU Yuchuan, YUE Guanghua, LIU Chenglong, et al. Research on automatic detection of urban cavity based on multi-feature fusion of GPR[J]. China Journal of Highway and Transport, 2023, 36(3): 108-119.
[29] 张清河, 吴欣悦, 刘含, 等. 一种新颖的探地雷达快速正演模拟及埋地目标探测机器学习方法[J]. 地球物理学报, 2023, 66(8): 3482-3492. ZHANG Qinghe, WU Xinyue, LIU Han, et al. A novel method for fast forward simulation of ground penetrating radar and buried target detection based on machine learning[J]. Chinese Journal of Geophysics, 2023, 66(8): 3482-3492.
[30] 陈能辉,张伟超. 基于时序InSAR的地表形变监测与应用[J]. 北京测绘,2025, 39(8): 1233-1238. CHEN Nenghui, ZHANG Weichao. Ground surface deformation monitoring and application based on time-series InSAR[J]. Beijing Surveying & Mapping, 2025, 39(8): 1233-1238.
[31] 李鑫, 魏冠军, 张德龙. 联合PS-InSAR技术与多变量LSTM神经网络的高铁路基冻胀形变预测研究[J]. 测绘通报, 2024(1): 58-64. LI Xin, WEI Guanjun, ZHANG Delong. Research on frost heave deformation prediction of high railway foundation combined with PS-InSAR technology and multivariable LSTM neural network[J]. Bulletin of Surveying and Mapping, 2024(1): 58-64.
[32] 靳喜博, 刘琨, 江俊峰, 等. 基于卷积神经网络的多维度分布式光纤振动传感事件识别[J]. 光学学报, 2024, 44(1): 384-394. JIN Xibo, LIU Kun, JIANG Junfeng, et al. Multi-dimensional distributed optical fiber vibration sensing pattern recognition based on convolutional neural network[J]. Acta Optica Sinica, 2024, 44(1): 384-394.
[33] 罗阔, 王宇瑶, 朱柏蓉, 等. 基于生成对抗网络的布里渊分布式光纤传感器降噪[J]. 光学学报, 2024, 44(1): 395-405. LUO Kuo, WANG Yuyao, ZHU Bairong, et al. Noise reduction of Brillouin distributed optical fiber sensors based on generative adversarial network[J]. Acta Optica Sinica, 2024, 44(1): 395-405.
[34] 吐松江·卡日, 雷柯松, 马小晶, 等. 基于LSTM-Attention和CNN-BiGRU误差修正的光伏功率预测[J]. 太阳能学报, 2024, 45(12): 85-93. KARI·Tusongjiang, LEI Kesong, MA Xiaojing, et al. Photovoltaic power prediction based on LSTM-ATTENTION and CNN-BiGRU error correction[J]. Acta Energiae Solaris Sinica, 2024, 45(12): 85-93.
[35] 李璨, 伍黎艳, 赵威, 等. 基于Attention-LSTM的短期电力负荷预测[J]. 船电技术, 2025, 45(1): 5-8. LI Can, WU Liyan, ZHAO Wei, et al. Short-term power load forecasting based on Attention-LSTM[J]. Marine Electric & Electronic Engineering, 2025, 45(1):5-8.
[36] 叶彦汝. 基于RI-GRU的英语阅读兴趣分类预测[J]. 山西师范大学学报(自然科学版), 2024, 38(4): 154-160. YE Yanru. Based on the RI-GRU helped english reading interested in classification prediction[J]. Journal of Shanxi Normal University(Natural Science Edition), 2024, 38(4): 154-160.
[37] 王艳红, 赵亮, 王官军. 改进Transformer模型的语音识别轻量化设计[J]. 计算机工程与应用, 2025, 61(16): 196-204. WANG Yanhong, ZHAO Liang, WANG Guanjun. Improved speech recognition lightweight design for Transformer model[J]. Computer Engineering and Applications, 2025, 61(16): 196-204.
[38] 杨宝伟, 崇立国, 梁辉, 等. 基于SGWO-SVR的煤自燃温度预测研究[J]. 能源技术与管理, 2024, 49(6): 21-25. YANG Baowei, CHONG Liguo, LIANG Hui, et al. Research on coal Self-Ignition temperature prediction based on SGWO-SVR[J]. Energy Technology and Management, 2024, 49(6): 21-25.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed