| 63 | 0 | 55 |
| 下载次数 | 被引频次 | 阅读次数 |
【目的】针对隧道掘进机(TBM)净掘进速率(PR)预测中影响因素识别困难、预测模型精度受样本容量和影响因素输入的影响，提出了兼顾预测精度与工程适用性的PR预测方法。【方法】基于机器学习建模框架，提出了融合相关性分析、模型封装训练与工程应用约束的影响因素筛选方法，实现了对TBM净掘进速率关键控制因素的系统识别。在此基础上，构建了融合非洲秃鹫优化算法与随机森林的AVOA-RF预测模型，并基于马来西亚PSRWT隧道工程数据对模型性能进行了验证。通过参数敏感性分析、数据稀疏性分析及影响因素消融试验，系统验证了所提出AVOA-RF预测模型的鲁棒性与稳定性。【结果】结果显示：AVOA-RF模型表现出优异预测性能，R2高达0.943，整体性能优于其他经验公式和机器学习模型。参数敏感性分析表明，单轴抗压强度是影响PR预测的关键因素(SHAP值为0.616)。为保证PR预测的准确性，所需训练样本最小容量为62组。相比预测精度最高的经验公式，AVOA-RF模型的R提升了3.63%，验证了AVOA-RF模型的有效性与工程适应性。【结论】结果表明：AVOA-RF能够准确预测TBM净掘进速率，具有较强泛化能力和鲁棒性，预测结果对TBM工程进度与成本控制具有借鉴意义。
Abstract：[Objective] To address the difficulties in identifying influential factors for predicting the net penetration rate (PR) of tunnel boring machines (TBMs)， as well as the sensitivity of prediction accuracy to sample size and input variables， this study proposes a PR prediction method that balances high accuracy with engineering applicability. [Methods] Within a machine-learning-based modeling framework， an integrated influential-factor selection strategy combining correlation analysis， model-encapsulated training， and engineering constraints is developed to systematically identify the key controlling factors of TBM net penetration rate. On this basis， a hybrid prediction model coupling the African Vulture Optimization Algorithm with Random Forest (AVOA–RF) is established and validated using data from the PSRWT tunnel project in Malaysia. The robustness and stability of the proposed model are further examined through parameter sensitivity analysis， data sparsity analysis， and influential-factor ablation experiments. [Results] The results demonstrate that the AVOA–RF model exhibits superior predictive performance， achieving a coefficient of determination (R2) of 0.943 and outperforming existing empirical formulas and other machine learning models. Sensitivity analysis indicates that uniaxial compressive strength is the dominant factor influencing PR prediction， with a SHAP value of 0.616. In addition， the minimum training sample size required to ensure reliable prediction accuracy is identified as 62 samples. Compared with the most accurate empirical formula， the proposed AVOA–RF model improves the R2 value by 3.63%， confirming its effectiveness and engineering applicability. [Conclusion] The proposed AVOA–RF model can accurately predict TBM net penetration rate with strong generalization capability and robustness. The prediction results provide valuable support for TBM construction scheduling and cost control in practical engineering applications.
[1] 陶志刚， 赵军政， 胡杰， 等. 引汉济渭工程秦岭引水隧洞岩爆三维NPR支护技术[J]. 南水北调与水利科技（中英文）， 2023， 21(6): 11651173.
[2] 马永涛，高发勇，段进睿，等. 深埋输水隧洞TBM穿越高瓦斯地层双出风口通风特性研究 [J]. 现代隧道技术， 2026， 63 (3): 183-191.
[3] 陈亮， 孙晨， 王雷雨， 等. 引水隧洞超前预处理灌浆材料研究与应用进展[J]. 南水北调与水利科技（中英文）， 2024， 22(6): 1181-1188.
[4] 韩佳霖，刘学，王贤钧，等. 全球全断面隧道掘进机典型应用工程案例统计与发展分析 [J]. 隧道建设(中英文)， 2026， 46 (6): 1359-1382.
[5] 闫长斌， 汪鹤健， 杨继华， 等. 利用PLSR-DNN耦合模型预测TBM净掘进速率[J]. 岩土力学， 2021， 42(2): 519-528.
[6] GHASEMI E， YAGIZ S， ATAEI M. Predicting penetration rate of hard rock tunnel boring machine using fuzzy logic [J]. Bulletin of Engineering Geology and the Environment， 2014， 73(1): 23-35.
[7] MIKAEIL R， NAGHADEHI M Z， SERESHKI F. Multifactorial fuzzy approach to the penetrability classification of TBM in hard rock conditions [J]. Tunnelling and Underground Space Technology， 2009， 24(5): 500-505.
[8] BENARDOS A G， KALIAMPAKOS D C. Modelling TBM performance with artificial neural networks[J]. Tunnelling and Underground Space Technology， 2004， 19(6): 597-605.
[9] ALVAREZ GRIMA M， BRUINES P A， VERHOEF P N W. Modeling tunnel boring machine performance by neuro-fuzzy methods [J]. Tunnelling and Underground Space Technology， 2000， 15(3): 259-269.
[10] YAGIZ S， KARAHAN H. Application of various optimization techniques and comparison of their performances for predicting TBM penetration rate in rock mass[J]. International Journal of Rock Mechanics and Mining Sciences， 2015， 80: 308-315.
[11] MAHDEVARI S， SHAHRIAR K， YAGIZ S， et al. A support vector regression model for predicting tunnel boring machine penetration rates[J]. International Journal of Rock Mechanics and Mining Sciences， 2014， 72: 214-229.
[12] 仉文岗， 唐理斌， 陈福勇， 等. 基于4种超参数优化算法及随机森林模型预测TBM掘进速度[J]. 应用基础与工程科学学报， 2021， 29(5): 1186-1200.
[13] JAHED ARMAGHANI D， FARADONBEH R S， MOMENI E， et al. Performance prediction of tunnel boring machine through developing a gene expression programming equation[J]. Engineering with Computers， 2018， 34(1): 129-141.
[14] 丁自伟， 高成登， 张玲， 等. 基于数据驱动的TBM掘进地层岩性识别预测方法[J]. 采矿与安全工程学报， 2025， 42(1): 147-160.
[15] 马世伟， 李守定， 李晓， 等. 隧道岩体质量智能动态分级KNN方法[J]. 工程地质学报， 2020， 28(6): 1415-1424.
[16] 张庆龙， 朱燕文， 马睿， 等. 基于注意力加强Bi-LSTM模型的TBM掘进参数预测研究[J]. 现代隧道技术， 2022， 59(4): 69-80.
[17] 李晓静， 张永华， 魏小兵， 等. 基于深度学习的TBM运行参数预测及小样本扩充研究[J]. 应用基础与工程科学学报， 2025， 33(3): 727-742.
[18] 刘建琴， 吴迪， 徐攀， 等. 基于改进CSM模型的硬岩掘进机刀盘危险点应力分析方法[J]. 天津大学学报（自然科学与工程技术版）， 2024， 57(3): 283-290.
[19] PAN Y， FU X L， ZHANG L M. Data-driven multi-output prediction for TBM performance during tunnel excavation: An attention-based graph convolutional network approach[J]. Automation in Construction， 2022， 140: 104386.
[20] SAPIGNI M， BERTI M， BETHAZ E， et al. TBM performance estimation using rock mass classifications[J]. International Journal of Rock Mechanics and Mining Sciences， 2002， 39(6): 771-788.
[21] YAGIZ S. Utilizing rock mass properties for predicting TBM performance in hard rock condition[J]. Tunnelling and Underground Space Technology， 2008， 23(3): 326-339.
[22] SALIMI A， ESMAEILI M. Utilising of linear and non-linear prediction tools for evaluation of penetration rate of Tunnel Boring Machine in hard rock condition[J]. International Journal of Mining and Mineral Engineering， 2013， 4(3): 249-264.
[23] DELISIO A， ZHAO J. A new model for TBM performance prediction in blocky rock conditions[J]. Tunnelling and Underground Space Technology， 2014， 43: 440-452.
[24] GOODARZI S， HASSANPOUR J， YAGIZ S， et al. Predicting TBM performance in soft sedimentary rocks， case study of Zagros mountains water tunnel projects[J]. Tunnelling and Underground Space Technology， 2021， 109: 103705.
[25] ARMAGHANI D J， YAGIZ S， MOHAMAD E T， et al. Prediction of TBM performance in fresh through weathered granite using empirical and statistical approaches[J]. Tunnelling and Underground Space Technology， 2021， 118: 104183.
[26] SHE L， HU C， LI Y， et al. An empirical method for estimating TBM penetration rate using tunnelling specific energy[J]. Tunnelling and Underground Space Technology， 2024， 144: 105525.
[27] 闫长斌， 姜晓迪. 基于岩体指标和掘进参数的TBM净掘进速率预测模型[J]. 现代隧道技术， 2020， 57(2): 26-33.
[28] 杜立杰， 齐志冲， 韩小亮， 等. 基于现场数据的TBM可掘性和掘进性能预测方法[J]. 煤炭学报， 2015， 40(6): 1284-1289.
[29] ARMAGHANI D J， MOHAMAD E T， NARAYANASAMY M S， et al. Development of hybrid intelligent models for predicting TBM penetration rate in hard rock condition[J]. Tunnelling and Underground Space Technology， 2017， 63: 29-43.
[30] YAGIZ S， KARAHAN H. Prediction of hard rock TBM penetration rate using particle swarm optimization[J]. International Journal of Rock Mechanics and Mining Sciences， 2011， 48(3): 427-433.
[31] KOOPIALIPOOR M， NIKOUEI S S， MARTO A， et al. Predicting tunnel boring machine performance through a new model based on the group method of data handling[J]. Bulletin of Engineering Geology and the Environment， 2019， 78(5): 3799-3813.
[32] KOOPIALIPOOR M， TOOTOONCHI H， JAHED ARMAGHANI D， et al. Application of deep neural networks in predicting the penetration rate of tunnel boring machines[J]. Bulletin of Engineering Geology and the Environment， 2019， 78(8): 6347-6360.
[33] DU C L， PAN Y C， LIU Q S， et al. Rockburst inoculation process at different structural planes and microseismic warning technology: A case study[J]. Bulletin of Engineering Geology and the Environment， 2022， 81(12): 499.
[34] HASSANPOUR J， GHAEDI VANANI A A， ROSTAMI J， et al. Evaluation of common TBM performance prediction models based on field data from the second lot of Zagros water conveyance tunnel (ZWCT2)[J]. Tunnelling and Underground Space Technology， 2016， 52: 147-156.
[35] MAHMOODZADEH A， MOHAMMADI M， HASHIM IBRAHIM H， et al. Machine learning forecasting models of disc cutters life of tunnel boring machine[J]. Automation in Construction， 2021， 128: 103779.
[36] FARROKH E， ROSTAMI J， LAUGHTON C. Study of various models for estimation of penetration rate of hard rock TBMs[J]. Tunnelling and Underground Space Technology， 2012， 30: 110-123
[37] 张建明， 侍克斌， 贾运甫， 等. 基于VMD与加权RF的TBM掘进速度预测SHAP解释模型[J]. 隧道建设（中英文）， 2024， 44(5): 1012-1028.
[38] XU H， ZHOU J G. ASTERIS P， et al. Supervised machine learning techniques to the prediction of tunnel boring machine penetration rate[J]. Applied Sciences， 2019， 9(18): 3715.
[39] MA H， SIMON D. Blended biogeography-based optimization for constrained optimization[J]. Engineering Applications of Artificial Intelligence， 2011， 24(3): 517-525.
[40] MIAO K， MAO XL， LI C. Individualism of particles in particle swarm optimization[J]. Applied Soft Computing， 2019， 83: 105619.
[41] ABBASI B， MAJIDNEZHAD V， MIRJALILI S. ADE: Advanced differential evolution[J]. Neural Computing and Applications， 2024， 36(25): 15407-15438.
[42] LEI Z Y， GAO S C， GUPTA S， et al. An aggregative learning gravitational search algorithm with self-adaptive gravitational constants[J]. Expert Systems with Applications， 2020， 152: 113396.
[43] ZOU F， CHEN D， XU Q Z. A Survey of teaching–learning-based optimization[J]. Neurocomputing， 2019， 335: 366-383.
[44] TSAI H C， SHI J Y. Potential corrections to grey wolf optimizer[J]. Applied Soft Computing， 2024， 161: 111776.
[45] SHEHAB M， ABUALIGAH L， AL HAMAD H， et al. Moth–flame optimization algorithm: variants and applications[J]. Neural Computing and Applications， 2020， 32(14): 9859-9884.
[46] LI J， WEI X Y， LI B， et al. A survey on firefly algorithms[J]. Neurocomputing， 2022， 500: 662-678.
基本信息:
中图分类号:TV554
引用信息:
[1]韩守杰,王玉雅,卜鹏,等.基于AVOA-RF算法的TBM净掘进速率智能预测方法及应用[J].水利水电技术(中英文)().
基金信息:
国家自然科学基金项目(52409175); 河南省高等学校重点科研项目(24B560019); 商丘工学院2023年度校级科研项目(24B560019)
2026-08-28
2026-08-28
2026-08-28