• CSCD核心中文核心科技核心
  • RCCSE(A+)公路运输高质量期刊T1
  • Ei CompendexScopusWJCI
  • EBSCOPж(AJ)JST
二维码

隧道建设(中英文) ›› 2023, Vol. 43 ›› Issue (4): 592-601.DOI: 10.3973/j.issn.2096-4498.2023.04.005

• 研究与探索 • 上一篇    下一篇

基于Attention-ResNet-LSTM混合神经网络的盾构掘进速度预测新方法

高昆1, 于思淏2, 许维青1, 张子新2 *   

  1. (1. 中铁隧道集团二处有限公司, 河北 三河 065201 2. 同济大学地下建筑与工程系, 上海 200092
  • 出版日期:2023-04-20 发布日期:2023-05-23
  • 作者简介:高昆(1987—),男,河北省沧州人,2010年毕业于石家庄铁道学院,土木工程专业,本科,高级工程师,现从事铁路隧道施工及技术管理工作。Email: 490169302@qq.com。 *通信作者: 张子新, Email: zxzhang@tongji.edu.cn。

Novel Prediction Method for Shield Advancing Speed Based on AttentionResNetLong ShortTerm Memory Hybrid Neural Network

GAO Kun1, YU Sihao2, XU Weiqing1, ZHANG Zixin2, *   

  1. (1. The 2nd Engineering Co., Ltd. of China Railway Tunnel Group, Sanhe 065201, Hebei, China; 2. Department of Geotechnical Engineering, Tongji University, Shanghai 200092, China)
  • Online:2023-04-20 Published:2023-05-23

摘要: 针对传统方法存在的盾构性能精准预测阻碍盾构快速掘进技术发展的难题,提出一种基于Attention-ResNet-LSTM混合神经网络的盾构掘进速度预测方法。相比传统的LSTMGRU等网络预测模型,Attention-ResNet-LSTM模型引入了Attention机制。长距离盾构掘进过程中,针对地层条件存在很大的变异性情况,该模型可自适应更新权重矩阵,让模型面对不同的任务时具有一定的自调节能力,可有效提升预测精度。依托中俄东线天然气管道工程对盾构掘进速度进行了实时预测和验证,且结果表明该方法可分析盾构掘进过程中输入、输出参数之间的相关性,且具有较好的适应性。

关键词: 盾构隧道, 人工智能, 混合神经网络, 性能预测, 掘进速度

Abstract: People have always been concerned about the velocity and safety of shield tunneling, which have a close relationship with stratum conditions and operation parameters. However, it is difficult to predict the shield performance using traditional methods due to the complicated shieldground interaction, impeding the development of the rapid tunneling technology. In this paper, a new prediction method for shield advancing speed based on the AttentionResNetLong Shortterm Memory(LSTM) hybrid model is proposed to address this problem. Compared with traditional neural networks, such as LSTM and GRU, the proposed model has introduced the Attention mechanism, which can update the weight matrix adaptively according to various stratum conditions during longdistance shield tunneling. As a result, the model can modify the weight matrix itself when confronted with different tasks. This ability effectively increases the prediction accuracy, which has been validated through realtime prediction of shield advancing speed in the eastern route of the ChinaRussia gas pipeline project. The method can analyze the correlations between input and output parameters during shield tunneling. Moreover, it has good adaptability, which is of great significance in selecting the operation parameters for the velocity and safety of shield tunneling.

Key words: shield tunnel, artificial intelligence, hybrid neural network, property prediction, advance rate