[1]龚秋明,李顺文,黄流,等.基于 TBM 刀盘振动的 WSN-LSTM 围岩感知模型 [J].郑州大学学报(工学版),2026,47(4):18-25.[doi:10. 13705 / j. issn. 1671-6833. 2026. 04. 020]
　GONG Qiuming,LI Shunwen,HUANG Liu,et al.Surrounding Rock Mass Sensing Model Based on TBM Cutterhead Vibration Using WSN-LSTM [J].Journal of Zhengzhou University (Engineering Science),2026,47(4):18-25.[doi:10. 13705 / j. issn. 1671-6833. 2026. 04. 020]

点击复制

基于 TBM 刀盘振动的 WSN-LSTM 围岩感知模型
()

分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:

47

期数:

2026年4期

页码:

18-25

栏目:

出版日期:

2026-10-02

文章信息/Info

Title:

Surrounding Rock Mass Sensing Model Based on TBM Cutterhead Vibration Using WSN-LSTM

作者:

龚秋明¹，李顺文¹，黄流¹，王驹^2,3，曹子祥¹，马洪素^2,3

1. 北京工业大学 城市与工程安全减灾教育部重点实验室,北京 100124;2. 核工业北京地质研究院,北京 100029;3. 国家原子能机构高放废物地质处置创新中心,北京 100029

Author(s):

GONG Qiuming¹, LI Shunwen¹, HUANG Liu¹, WANG Ju^2,3, CAO Zixiang¹, MA Hongsu^2,3

1. Key Laboratory of Urban Security and Disaster Engineering of Ministry of Education, Beijing University of Technology, Beijing 100124, China; 2. Beijing Research Institute of Uranium Geology, Beijing 100029, China; 3. CAEA Innovation Center for Geological Disposal of High-Level Radioactive Waste, Beijing 100029, China

关键词:

TBM;  围岩感知;  振动监测系统;  小波散射网络;  深度学习

Keywords:

TBM;  surrounding rock mass sensing;  vibration monitoring system;  wavelet scattering network;  deep learning

分类号:

U45TP181

DOI:

10. 13705 / j. issn. 1671-6833. 2026. 04. 020

文献标志码:

A

摘要:

针对现有基于 TBM 振动信号的围岩识别方法在特征提取有效性和工程适应性方面的不足,提出了一种基于 TBM 刀盘振动的小波散射网络(WSN)和长短期记忆网络( LSTM)的围岩感知方法。 首先,依托北山地下实验室螺旋斜坡道工程,在 TBM 刀盘上安装振动监测系统,采集 TBM 掘进过程中的振动信号,通过稳定段提取、降噪、分割等数据预处理方法,并匹配隧道沿线地质信息,建立了基于刀盘振动的岩体感知数据库。 其次,利用 WSN 对振动信号进行多尺度时序特征提取,以增强特征的表达能力与抗噪能力,并利用 LSTM 捕捉时序依赖关系的优势,构建了 WSN-LSTM 围岩感知模型。 研究结果表明:WSN-LSTM 模型在测试集上的准确率达到 93. 7%,相较于基于小波散射网络的支持向量机( SVM)模型提高了 5. 6 百分点,且高于基于幅值域统计特征提取下的浅层机器学习模型(随机森林与 LightGBM) ,验证了 WSN 对刀盘振动信号特征提取的优势,以及捕捉刀盘振动特征时序依赖的必要性。

Abstract:

To address the limitations of existing surrounding rock mass identification methods based on TBM vibration signals in terms of feature extraction effectiveness and engineering adaptability,a novel surrounding rock mass perception method was proposed by integrating wavelet scattering network (WSN) and long short-term memory network ( LSTM) using TBM cutterhead vibration data. Firstly, relying on the spiral ramp project of the Beishan Underground Laboratory, a vibration monitoring system was mounted on the TBM cutterhead to acquire vibration signals during the TBM tunneling process. Then, a rock mass sensing database based on cutterhead vibration was established through a series of data preprocessing procedures, including stable tunneling segment extraction, noise reduction, and signal segmentation, combined with the matching of geological information along the tunnel alignment.

Secondly, the WSN was employed to perform multi-scale temporal feature extraction from the preprocessed vibration signals, so as to enhance the feature representation capability and noise robustness. On this basis, a WSN-LSTM surrounding rock mass perception model was constructed by leveraging the inherent superiority of the LSTM network in capturing the temporal dependencies. The results demonstrated that the proposed WSN-LSTM model achieved an accuracy of 93. 7% on the test set, which yielded a 5. 6 percentage points accuracy improvement compared with the wavelet scattering network-based support vector machine ( SVM) model, and outperformed shallow machine learning models ( random forest and LightGBM) based on amplitude-domain statistical feature extraction. These findings validated the superiority of WSN in feature extraction from TBM cutterhead vibration signals, as well as the necessity of capturing the temporal dependencies of cutterhead vibration features.

备注/Memo

备注/Memo:

收稿日期:2026-03-24;修订日期:2026-04-11

基金项目:国家自然科学基金资助项目(52438005) ;核设施退役治理专项资助科研项目(科工二司〔2020〕194 号)

作者简介:龚秋明(1969— ) ,男,湖南安化人,北京工业大学教授,博士,博士生导师,主要从事 TBM 智能化施工方面的研究,E-mail:gongqiuming@ bjut. edu. cn。

常用功能