Scholarlink

<p>The real-time prediction of surrounding rock grade is of great significance to the safety and efficiency of TBM tunnel construction. Based on a water diversion project in China, the distribution patterns of nine tunneling parameters in different surrounding rock grades were studied using Boxplot. Then, Principal Component Regression (PCR) and Partial Least Squares Regression (PLSR) were used to reduce the dimension of the model input variables, and compared with the dimensionality reduction results of Boxplot to obtain the optimal model input variables. On this basis, five machine learning models for real-time identification of surrounding rock grade were constructed: Random Forest (RF) model, Error Back Propagation Neural Network (BPNN) model, Bayesian Network (BN) model, Support Vector Machine (SVM) model and K-Nearest Neighbor (KNN) model. Through the statistics of the prediction accuracy and running time of the five models, it was found that the prediction accuracy of RF model was the highest (85%), and the prediction accuracy of BPNN, BN, SVM and KNN models were 75%, 72.5%, 77.5% and 52.5% respectively; the running time of BN model was the shortest (0.1406s), and that of RF, BPNN, SVM and KNN models were 0.8832s, 0.9338s, 1.3335s and 0.3095s respectively. Based on a comprehensive comparison of prediction accuracy and running time, the RF model was the best method for real-time identification of TBM tunnel surrounding rock grade, which can meet the requirements for guiding TBM on-site construction.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Research on TBM tunnel stratum variation perception with tunneling based on multiple machine learning algorithms

  • 期刊论文

  • 发表日期：

    2025年6月23日

查看全文
  • Kang Fu,
  • Daohong Qiu,
  • Yiguo Xue,
  • Fanmeng Kong

摘要

The real-time prediction of surrounding rock grade is of great significance to the safety and efficiency of TBM tunnel construction. Based on a water diversion project in China, the distribution patterns of nine tunneling parameters in different surrounding rock grades were studied using Boxplot. Then, Principal Component Regression (PCR) and Partial Least Squares Regression (PLSR) were used to reduce the dimension of the model input variables, and compared with the dimensionality reduction results of Boxplot to obtain the optimal model input variables. On this basis, five machine learning models for real-time identification of surrounding rock grade were constructed: Random Forest (RF) model, Error Back Propagation Neural Network (BPNN) model, Bayesian Network (BN) model, Support Vector Machine (SVM) model and K-Nearest Neighbor (KNN) model. Through the statistics of the prediction accuracy and running time of the five models, it was found that the prediction accuracy of RF model was the highest (85%), and the prediction accuracy of BPNN, BN, SVM and KNN models were 75%, 72.5%, 77.5% and 52.5% respectively; the running time of BN model was the shortest (0.1406s), and that of RF, BPNN, SVM and KNN models were 0.8832s, 0.9338s, 1.3335s and 0.3095s respectively. Based on a comprehensive comparison of prediction accuracy and running time, the RF model was the best method for real-time identification of TBM tunnel surrounding rock grade, which can meet the requirements for guiding TBM on-site construction.