The study optimized the ventilation strategy in high-altitude tunnel construction through big data analysis and machine learning techniques, and developed a high-precision prediction model. Using a combination of random forest and long short-term memory network (LSTM), the environmental data collected during the initial excavation stage is used to predict the ventilation demand and environmental changes during long-distance excavation. When the tunnel is excavated to 100 m, high-precision sensors are installed to collect real-time data such as temperature, humidity, wind speed, dust, and CO concentration, which are transmitted to the central database for preprocessing through wireless networks. The model optimizes hyperparameters through grid search and random search, and evaluates performance using 10-fold cross-validation. The results show that: The RF and LSTM models achieved prediction accuracies of 89% and 93%, respectively. It has demonstrated outstanding predictive capabilities and practicality in actual construction. When the tunnel was excavated to a depth of 1 km to 2 km, the predicted values of the model were highly consistent with the measured data, with an error rate of less than 7%.It effectively responded to large-scale blasting operations, ensuring air quality and worker safety. Compared to traditional methods, the RF and LSTM fusion model better handles complex nonlinear relationships and time-series data, improving ventilation system design and operational efficiency. This integrated approach offers a significant advancement in managing tunnel construction in challenging high-altitude environments, providing reliable predictions to maintain safe and efficient working conditions.
Sun Sanxiang
,
Zheng Xuting
,
Tian Weihai
. Optimization of Tunnel Construction Ventilation Based on the Fusion Model of Random Forest and LSTM[J]. Chinese Journal of Underground Space and Engineering, 2025
, 21(S1)
: 470
-479
.
DOI: 10.20174/j.JUSE.2025.S1.56
[1] 陈星宇,吴剑,任松,等. 高海拔隧道施工期污染物扩散规律[J]. 浙江大学学报(工学版), 2024,58(1):176-187.
[2] 刘庆宽,郑肖楠,崔会敏,等. 高海拔高地温铁路隧道施工通风CO扩散特性分析[J]. 地下空间与工程学报,2022,18(增2): 1015-1022, 1029.
[3] 邹宗良,胡学兵,袁野,等. 爆破作业对高海拔隧道CO及粉尘扩散的影响规律探究[J]. 中国公路,2022(11):150-152.
[4] 张云霞.高海拔内燃牵引隧道自然通风界限及活塞风特性研究[J]. 岩石力学与工程学报,2014,33(12):2592.
[5] MishalaniI R G. The control of highway tunnel ventilation using fuzzy logic[J]. Engineering Applications of Artificial Intelligence, 2003,16(7-8):717-721.
[6] Li F Y, Lai Y J, Chen X Q. Towards big data driven construction industry[J]. Journal of Industrial Information Integration, 2023,35:100483.
[7] Zhang Y, Chen J Q, Han S, et al. Big data-based performance analysis of tunnel boring machine tunneling using deep learning[J]. Buildings,2022,12(10):1567.
[8] 谭忠盛,邓铭江. 超特长隧洞TBM智能辅助掘进技术研究及应用[J]. 隧道建设(中英文), 2024,44(3):442-463.
[9] 闵世平,林国庆. BIM及空间大数据技术支持下的铁路隧道施工数据管理[J]. 测绘通报, 2021(8):144-149, 153.
[10] 林国庆. 基于空间大数据技术的隧道施工信息化管理系统研究[J]. 铁路工程技术与经济, 2023, 38 (6): 62-67.
[11] Afan Galih S, Bayu K. Visibility forecasting using autoregressive integrated moving average (ARIMA) models[J]. Procedia Computer Science, 2021, 179: 252-259.
[12] Liu R, He Y, Zhao Y F, et al. Tunnel construction ventilation frequency-control based on radial basis function neural network[J]. Automation in Construction, 2020,118:103293.
[13] 霍宗文,王岩.内燃牵引单线铁路长大隧道通风系统的自动控制设计[J]. 铁道建筑,2010(10):38-40.
[14] 魏泰,贺少雄,胡子武,等. 基于改进孤立森林算法的风电机组异常数据清洗[J]. 科学技术与工程, 2024, 24 (9): 3691-3699.
[15] 牛聪,王建花,邬蒙蒙,等. 基于改进的随机森林算法的井曲线填补研究及应用[J]. 中国海上油气, 2023, 35 (6): 43-50.
[16] Nugroho H, Utama N P,Surendro K. Normalization and outlier removal in class center-based firefly algorithm for missing value imputation[J]. Journal of Big Data, 2021, 8: 129.
[17] Lin Z, Sekar V, Fanti G. Why spectral normalization stabilizes gans: Analysis and improvements[J]. Advances in Neural Information Processing Systems, 2021, 34: 9625-9638.
[18] Xu H, Liu Y L. Research and design of intelligent mine ventilation construction architecture[J]. International Journal of Low-Carbon Technologies, 2022, 17: 1232-1238.
[19] 顾清华,王晨曦,王倩,等. 考虑卡车尾气排放因素的露天矿粉尘质量浓度预测[J]. 矿业研究与开发, 2024, 44 (4): 161-167.
[20] He Y, Chen Q. Construction and application of LSTM-based prediction model for tunnel surrounding rockdeformation[J]. Sustainability,2023,15: 6877.
[21] 陈治亚,王小军.基于多维度LSTM模型的短时交通流预测[J]. 铁道科学与工程学报, 2020, 17 (11): 2946-2952.
