During tunnel boring machine(TBM)excavation,lithology identification is an important issue to understand tunnelling performance and avoid time-consuming excavation.However,site investigation generally lacks ground sam...During tunnel boring machine(TBM)excavation,lithology identification is an important issue to understand tunnelling performance and avoid time-consuming excavation.However,site investigation generally lacks ground samples and the information is subjective,heterogeneous,and imbalanced due to mixed ground conditions.In this study,an unsupervised(K-means)and synthetic minority oversampling technique(SMOTE)-guided light-gradient boosting machine(LightGBM)classifier is proposed to identify the soft ground tunnel classification and determine the imbalanced issue of tunnelling data.During the tunnel excavation,an earth pressure balance(EPB)TBM recorded 18 different operational parameters along with the three main tunnel lithologies.The proposed model is applied using Python low-code PyCaret library.Next,four decision tree-based classifiers were obtained in a short time period with automatic hyperparameter tuning to determine the best model for clustering-guided SMOTE application.In addition,the Shapley additive explanation(SHAP)was implemented to avoid the model black box problem.The proposed model was evaluated using different metrics such as accuracy,F1 score,precision,recall,and receiver operating characteristics(ROC)curve to obtain a reasonable outcome for the minority class.It shows that the proposed model can provide significant tunnel lithology identification based on the operational parameters of EPB-TBM.The proposed method can be applied to heterogeneous tunnel formations with several TBM operational parameters to describe the tunnel lithologies for efficient tunnelling.展开更多
Effective control of blasting outcomes depends on a thorough understanding of rock geology and the integration of geological characteristics with blast design parameters.This study underscores the importance of adapti...Effective control of blasting outcomes depends on a thorough understanding of rock geology and the integration of geological characteristics with blast design parameters.This study underscores the importance of adapting blast design parameters to geological conditions to optimize the utilization of explosive energy for rock fragmentation.To achieve this,data on fifty geo-blast design parameters were collected and used to train machine learning algorithms.The objective was to develop predictive models for estimating the blast oversize percentage,incorporating seven controlled components and one uncontrollable index.The study employed a combination of hybrid long-short-term memory(LSTM),support vector regression,and random forest algorithms.Among these,the LSTM model enhanced with the tree seed algorithm(LSTM-TSA)demonstrated the highest prediction accuracy when handling large datasets.The LSTM-TSA soft computing model was specifically leveraged to optimize various blast parameters such as burden,spacing,stemming length,drill hole length,charge length,powder factor,and joint set number.The estimated percentage oversize values for these parameters were determined as 0.7 m,0.9 m,0.65 m,1.4 m,0.7 m,1.03 kg/m^(3),35%,and 2,respectively.Application of the LSTM-TSA model resulted in a significant 28.1%increase in the crusher's production rate,showcasing its effectiveness in improving blasting operations.展开更多
基金supported by Japan Society for the Promotion of Science KAKENHI(Grant No.JP22H01580).
文摘During tunnel boring machine(TBM)excavation,lithology identification is an important issue to understand tunnelling performance and avoid time-consuming excavation.However,site investigation generally lacks ground samples and the information is subjective,heterogeneous,and imbalanced due to mixed ground conditions.In this study,an unsupervised(K-means)and synthetic minority oversampling technique(SMOTE)-guided light-gradient boosting machine(LightGBM)classifier is proposed to identify the soft ground tunnel classification and determine the imbalanced issue of tunnelling data.During the tunnel excavation,an earth pressure balance(EPB)TBM recorded 18 different operational parameters along with the three main tunnel lithologies.The proposed model is applied using Python low-code PyCaret library.Next,four decision tree-based classifiers were obtained in a short time period with automatic hyperparameter tuning to determine the best model for clustering-guided SMOTE application.In addition,the Shapley additive explanation(SHAP)was implemented to avoid the model black box problem.The proposed model was evaluated using different metrics such as accuracy,F1 score,precision,recall,and receiver operating characteristics(ROC)curve to obtain a reasonable outcome for the minority class.It shows that the proposed model can provide significant tunnel lithology identification based on the operational parameters of EPB-TBM.The proposed method can be applied to heterogeneous tunnel formations with several TBM operational parameters to describe the tunnel lithologies for efficient tunnelling.
基金funded by China Scholarship Council (No.202006370006).
文摘Effective control of blasting outcomes depends on a thorough understanding of rock geology and the integration of geological characteristics with blast design parameters.This study underscores the importance of adapting blast design parameters to geological conditions to optimize the utilization of explosive energy for rock fragmentation.To achieve this,data on fifty geo-blast design parameters were collected and used to train machine learning algorithms.The objective was to develop predictive models for estimating the blast oversize percentage,incorporating seven controlled components and one uncontrollable index.The study employed a combination of hybrid long-short-term memory(LSTM),support vector regression,and random forest algorithms.Among these,the LSTM model enhanced with the tree seed algorithm(LSTM-TSA)demonstrated the highest prediction accuracy when handling large datasets.The LSTM-TSA soft computing model was specifically leveraged to optimize various blast parameters such as burden,spacing,stemming length,drill hole length,charge length,powder factor,and joint set number.The estimated percentage oversize values for these parameters were determined as 0.7 m,0.9 m,0.65 m,1.4 m,0.7 m,1.03 kg/m^(3),35%,and 2,respectively.Application of the LSTM-TSA model resulted in a significant 28.1%increase in the crusher's production rate,showcasing its effectiveness in improving blasting operations.
