| 60 | 0 | 6 |
| 下载次数 | 被引频次 | 阅读次数 |
合理准确预测隧道掘进机的推力和扭矩是实现TBM智能化控制的关键问题之一。对此，提出一种两阶段知识数据双驱动时空堆叠卷积网络(KD-NTS-GAT)预测方法。首先基于专家知识表达与NTS-NOTEARS方法提出一种新的信息融合技术，通过聚类方法将离散的专家经验与NTS-NOTEARS连续指标进行映射并平滑融合，量化提取TBM关键运行参数之间的因果关系，显著提高了因果关系的真实性。然后，将因果关系作为先验知识进一步与堆叠卷积网络深度学习模型结合，用于预测TBM推力和扭矩。结合新疆输水隧洞工程Ⅳ标段，将KD-NTS-GAT方法与纯数据驱动结果进行对比分析，结果表明两阶段知识数据双驱动时空堆叠卷积网络具有更好的推力与扭矩预测能力。研究结论可为TBM施工智能化控制提供参考。
Abstract：It is the key issues of reasonably and accurately predicting the thrust and torque of tunnel boring machines(TBM) to realize the intelligent control of TBMs. This paper proposes a two-stage prediction method of knowledge-data-driven spatio-temporal stacked convolutional network(KD-NTS-GAT). Firstly, based on expert knowledge and the NTS-NOTEARS method, a new information fusion technique is proposed. The discrete expert experience and the continuous NTS-NOTEARS indicators is mapped and smoothly fused through clustering. The causal relationships among the key operating parameters of the TBM is quantitatively extracted to improve the authenticity of the causal relationships significantly. Then, causality is further combined as a prior knowledge with stacked convolutional network deep learning model for predicting thrust and torque of TBM. Taking the bid Ⅳ of Xinjiang Water Conveyance Tunnel Project as an example, a comparative analysis of the KD-NTS-GAT method and the pure data-driven method shows that the KD-NTS-GAT has better prediction capability on thrust and torque. The conclusions can provide a reference for the intelligent control of TBM construction.
[1] JAKOBSEN P D,LANGMAACK L,DAHL F,et al.Development of the Soft Ground Abrasion Tester (SGAT) to predict TBM tool wear,torque and thrust[J].Tunnelling and underground space technology,2013,38:398-408.
[2] LI J B,CHEN Z Y,LI X,et al.Feedback on a shared big dataset for intelligent TBM Part I:Feature extraction and machine learning methods[J].Underground space,2023,11:1-25.
[3] LIU Z B,LI L,FANG X L,et al.Hard-rock tunnel lithology prediction with TBM construction big data using a global-attention-mechanism-based LSTM network[J].Automation in construction,2021,125:103647.
[4] 周小雄，龚秋明，殷丽君，等.基于BLSTM-AM模型的TBM稳定段掘进参数预测[J].岩石力学与工程学报，2020,39(增刊2):3505-3515.
[5] QIN C J,SHI G,TAO J F,et al.Precise cutterhead torque prediction for shield tunneling machines using a novel hybrid deep neural network[J].Mechanical systems and signal processing,2021,151:107386.
[6] LI J B,CHEN Z Y,LI X,et al.Feedback on a shared big dataset for intelligent TBM Part II:Application and forward look[J].Underground space,2023,11:26-45.
[7] WANG K Y,ZHANG L M,FU X L.Time series prediction of tunnel boring machine (TBM) performance during excavation using causal explainable artificial intelligence (CX-AI)[J].Automation in construction,2023,147:104730.
[8] WANG H R,LI J M,ZHU G F.A data feature extraction method based on the NOTEARS causal inference algorithm[J].Applied sciences,2023,13(14):8438.
[9] 苗海宾，向朝建，刘胜楠，等.专家知识增强的机器学习建模在高强高导铜合金开发中的应用[J].工程科学学报，2023,45(11):1908-1917.
[10] FU X L,PAN Y,ZHANG L M.A causal-temporal graphic convolutional network (CT-GCN) approach for TBM load prediction in tunnel excavation[J].Expert systems with applications,2024,238:121977.
[11] HOU S K,LIU Y R.Early warning of tunnel collapse based on Adam-optimised long short-term memory network and TBM operation parameters[J].Engineering applications of artificial intelligence,2022,112:104842.
[12] WANG L T,ZHU F Z,LI J,et al.A data-driven approach for modeling and predicting the thrust force of a tunnel boring machine[J].Journal of Zhejiang university-SCIENCE A,2023,24(9):801-816.
[13] ZHAO D K,HE Y J,CHEN X,et al.Data-driven intelligent prediction of TBM surrounding rock and personalized evaluation of disaster-inducing factors[J].Tunnelling and underground space technology,2024,148:105768.
基本信息:
DOI：10.20040/j.cnki.1000-7709.2025.20241868
中图分类号:U455.31
引用信息:
[1]杨耀红,张哲,陈建国等.基于信息融合与堆叠卷积网络的TBM推力和扭矩预测[J].水电能源科学,2025,43(09):92-96.DOI:10.20040/j.cnki.1000-7709.2025.20241868.
基金信息:
国家自然科学基金项目(51679089); 河南省学科创新引智基地项目“智慧水利”(GXJD004); 河南省水利厅科技攻关项目(GG202358)