Deep learning based wavelength prediction model for railway subgrade settlement detection
-
摘要:
针对铁路路基沉降探测波长预测精度不足、适应性差的问题,提出了基于深度学习的铁路路基沉降探测波长预测模型,旨在通过挖掘光纤传感器波长数据的时空特征,提升路基沉降风险的实时监测与预警能力。该模型通过位置编码模块捕捉时序关系,利用多头自注意力机制捕获全局空间依赖,结合时间卷积网络(TCN,Temporal Convolutional Network)的膨胀卷积提取多尺度时间模式,并引入双向长短期记忆(BLSTM,Bi-directional Long Short-Term Memory)网络增强对序列的记忆能力和上下文理解能力,实现对波长数据的时空特征提取与预测。基于潍烟(潍坊—烟台)高速铁路实测数据进行实验,实验结果表明,该模型在测试集上的预测误差较低,可准确识别异常数据,各项指标均优于通用模型,具有工程应用价值,为铁路路基沉降探测波长的高精度监测提供了技术支撑。
-
关键词:
- 铁路路基沉降 /
- 波长预测 /
- 自注意力机制 /
- 时间卷积网络(TCN) /
- 双向长短期记忆网络(BLSTM)
Abstract:This paper proposed a deep learning based wavelength prediction model for railway subgrade settlement detection to address the issues of insufficient accuracy and poor adaptability. The aim was to improve the real-time monitoring and early warning capabilities of subgrade settlement risks by mining the spatiotemporal characteristics of wavelength data from fiber optic sensors. This model captured temporal relationships through a position encoding module, captured global spatial dependencies using a multi head self-attention mechanism, extracts multi-scale temporal patterns using dilated convolutions of a Temporal Convolutional Network (TCN), and introduced a Bi-directional Long Short Term Memory (BLSTM) network to enhance the capacity of sequence memory and contextual understanding, implement spatiotemporal feature extraction and prediction of wavelength data. Based on the actual measurement data of the Weifang-Yantai high-speed railway, the experimental results show that the model has low prediction error on the test set, can accurately identify abnormal data, and all indicators are better than the general model. It has engineering application value and provides technical support for high-precision monitoring of railway subgrade settlement detection wavelength.
-
-
[1] 赖香铃. 高速铁路路基沉降预测分析与软件应用[J]. 路基工程,2023(5):149-153. [2] 翟婉明,赵春发,夏 禾,等. 高速铁路基础结构动态性能演变及服役安全的基础科学问题[J]. 中国科学:技术科学,2014,44(7):645-660. [3] 王子昂,王武斌,苏 谦,等. 新建铁路大临线临沧站站场路基沉降评估分析[J]. 铁道科学与工程学报,2020,17(7):1688-1698. [4] 高至飞. 海南东环客运专线路基沉降预测方法适用性研究[J]. 路基工程,2015(1):112-118. [5] 王志亮,黄景忠,李永池. 沉降预测中的Asaoka法应用研究[J]. 岩土力学,2006,27(11):2025-2028,2032. [6] 丁建文,魏 霞,高鹏举,等. 基于GA-BP神经网络的软土路基运营期沉降预测[J]. 东南大学学报(自然科学版),2023,53(4):585-591. [7] 王 恒,王佼佼. 基于改进BP神经网络的软土路基沉降预测研究[J]. 黑龙江科学,2024,15(16):72-76. [8] Xu W Q, Guo Y, You M X. Intelligent identification of differential subgrade settlement of ballastless track system based on vehicle dynamic responses and 1D-CNN approach[J]. Transportation Geotechnics, 2024, (48): 101302. DOI: 10.1016/j.trgeo.2024.101302
[9] Wang G K, Shan Y, Detmann B, et al. Physics-Informed Neural Network (PINN) model for predicting subgrade settlement induced by shield tunnelling beneath an existing railway subgrade[J]. Transportation Geotechnics, 2024, (49): 101409. DOI: 10.1016/j.trgeo.2024.101409
-
期刊类型引用(7)
1. 单杏花,翁湦元,朱建军,赵楠. 智能高铁R-MaaS平台构造及关键技术. 中国铁路. 2024(07): 145-155 . 百度学术
2. 翁湦元,阎志远,朱建军,张启蒙. 铁路客运延伸服务产品知识图谱构建与应用研究. 铁路计算机应用. 2022(06): 30-35 . 本站查看
3. 李甜. 推荐系统在档案知识服务中的应用研究. 档案管理. 2021(02): 40-41 . 百度学术
4. 张振海,张湘婷. 基于关联规则的高速铁路信息服务组合方法研究. 铁道学报. 2021(04): 85-94 . 百度学术
5. 张振海,张湘婷. 上下文感知的高铁信息服务推荐方法研究. 计算机工程与应用. 2021(12): 231-236 . 百度学术
6. 袁磊磊,王洪业,朱建生,徐东平,吕晓艳. 基于区块链技术的铁路餐饮积分链应用研究. 铁路计算机应用. 2020(01): 21-24 . 本站查看
7. 张志强,汪健雄,靳超. 铁路智能客服关键技术研究. 铁路计算机应用. 2019(09): 1-5 . 本站查看
其他类型引用(1)