Developing a hybrid model of Jaya algorithm-based extreme gradient boosting machine to estimate blast-induced ground vibrations
- Zhou, Jian, Qiu, Yingui, Khandelwal, Manoj, Zhu, Shuangli, Zhang, Xiliang
- Authors: Zhou, Jian , Qiu, Yingui , Khandelwal, Manoj , Zhu, Shuangli , Zhang, Xiliang
- Date: 2021
- Type: Text , Journal article
- Relation: International Journal of Rock Mechanics and Mining Sciences Vol. 145, no. (2021), p.
- Full Text:
- Reviewed:
- Description: Blasting is still being considered to be one the most important applicable alternatives for conventional excavations. Ground vibration generated due to blasting is an undesirable phenomenon which is harmful for the nearby structures and should be prevented. In this regard, a novel intelligent approach for predicting blast-induced PPV was developed. The distinctive Jaya algorithm and high efficient extreme gradient boosting machine (XGBoost) were applied to obtain the goal, called the Jaya-XGBoost model. Accordingly, 150 sets of data composed of 13 controllable and uncontrollable parameters are chosen as input independent variables and the measured peak particle velocity (PPV) is chosen as an output dependent variable. Also, the Jaya algorithm was used for optimization of hyper-parameters of XGBoost. Additionally, six empirical models and several machine learning models such as XGBoost, random forest, AdaBoost, artificial neural network and Bagging were also considered and applied for comparison of the proposed Jaya-XGBoost model. Accuracy criteria including determination coefficient (R2), root-mean-square error (RMSE), mean absolute error (MAE), and the variance accounted for (VAF) were used for the assessment of models. For this study, 150 blasting operations were analyzed. Also, the Shapley Additive Explanations (SHAP) method is used to interpret the importance of features and their contribution to PPV prediction. Findings reveal that the proposed Jaya-XGBoost emerged as the most reliable model in contrast to other machine learning models and traditional empirical models. This study may be helpful to mining researchers and engineers who use intelligent machine learning algorithms to predict blast-induced ground vibration. © 2021 Elsevier Ltd
- Authors: Zhou, Jian , Qiu, Yingui , Khandelwal, Manoj , Zhu, Shuangli , Zhang, Xiliang
- Date: 2021
- Type: Text , Journal article
- Relation: International Journal of Rock Mechanics and Mining Sciences Vol. 145, no. (2021), p.
- Full Text:
- Reviewed:
- Description: Blasting is still being considered to be one the most important applicable alternatives for conventional excavations. Ground vibration generated due to blasting is an undesirable phenomenon which is harmful for the nearby structures and should be prevented. In this regard, a novel intelligent approach for predicting blast-induced PPV was developed. The distinctive Jaya algorithm and high efficient extreme gradient boosting machine (XGBoost) were applied to obtain the goal, called the Jaya-XGBoost model. Accordingly, 150 sets of data composed of 13 controllable and uncontrollable parameters are chosen as input independent variables and the measured peak particle velocity (PPV) is chosen as an output dependent variable. Also, the Jaya algorithm was used for optimization of hyper-parameters of XGBoost. Additionally, six empirical models and several machine learning models such as XGBoost, random forest, AdaBoost, artificial neural network and Bagging were also considered and applied for comparison of the proposed Jaya-XGBoost model. Accuracy criteria including determination coefficient (R2), root-mean-square error (RMSE), mean absolute error (MAE), and the variance accounted for (VAF) were used for the assessment of models. For this study, 150 blasting operations were analyzed. Also, the Shapley Additive Explanations (SHAP) method is used to interpret the importance of features and their contribution to PPV prediction. Findings reveal that the proposed Jaya-XGBoost emerged as the most reliable model in contrast to other machine learning models and traditional empirical models. This study may be helpful to mining researchers and engineers who use intelligent machine learning algorithms to predict blast-induced ground vibration. © 2021 Elsevier Ltd
Estimation of the TBM advance rate under hard rock conditions using XGBoost and Bayesian optimization
- Zhou, Jian, Qiu, Yingui, Zhu, Shuangli, Armaghani, Danial, Khandelwal, Manoj, Mohamad, Edy
- Authors: Zhou, Jian , Qiu, Yingui , Zhu, Shuangli , Armaghani, Danial , Khandelwal, Manoj , Mohamad, Edy
- Date: 2021
- Type: Text , Journal article
- Relation: Underground Space Vol. 6, no. 5 (Oct 2021), p. 506-515
- Full Text:
- Reviewed:
- Description: The advance rate (AR) of a tunnel boring machine (TBM) under hard rock conditions is a key parameter in the successful implementation of tunneling engineering. In this study, we improved the accuracy of prediction models by employing a hybrid model of extreme gradient boosting (XGBoost) with Bayesian optimization (BO) to model the TBM AR. To develop the proposed models, 1286 sets of data were collected from the Peng Selangor Raw Water Transfer tunnel project in Malaysia. The database consists of rock mass and intact rock features, including rock mass rating, rock quality designation, weathered zone, uniaxial compressive strength, and Brazilian tensile strength. Machine specifications, including revolution per minute and thrust force, were considered to predict the TBM AR. The accuracies of the predictive models were examined using the root mean squares error (RMSE) and the coefficient of determination (R-2) between the observed and predicted yield by employing a five-fold cross-validation procedure. Results showed that the BO algorithm can capture better hyper-parameters for the XGBoost prediction model than can the default XGBoost model. The robustness and generalization of the BO-XGBoost model yielded prominent results with RMSE and R-2 values of 0.0967 and 0.9806 (for the testing phase), respectively. The results demonstrated the merits of the proposed BO-XGBoost model. In addition, variable importance through mutual information tests was applied to interpret the XGBoost model and demonstrated that machine parameters have the greatest impact as compared to rock mass and material properties.
- Authors: Zhou, Jian , Qiu, Yingui , Zhu, Shuangli , Armaghani, Danial , Khandelwal, Manoj , Mohamad, Edy
- Date: 2021
- Type: Text , Journal article
- Relation: Underground Space Vol. 6, no. 5 (Oct 2021), p. 506-515
- Full Text:
- Reviewed:
- Description: The advance rate (AR) of a tunnel boring machine (TBM) under hard rock conditions is a key parameter in the successful implementation of tunneling engineering. In this study, we improved the accuracy of prediction models by employing a hybrid model of extreme gradient boosting (XGBoost) with Bayesian optimization (BO) to model the TBM AR. To develop the proposed models, 1286 sets of data were collected from the Peng Selangor Raw Water Transfer tunnel project in Malaysia. The database consists of rock mass and intact rock features, including rock mass rating, rock quality designation, weathered zone, uniaxial compressive strength, and Brazilian tensile strength. Machine specifications, including revolution per minute and thrust force, were considered to predict the TBM AR. The accuracies of the predictive models were examined using the root mean squares error (RMSE) and the coefficient of determination (R-2) between the observed and predicted yield by employing a five-fold cross-validation procedure. Results showed that the BO algorithm can capture better hyper-parameters for the XGBoost prediction model than can the default XGBoost model. The robustness and generalization of the BO-XGBoost model yielded prominent results with RMSE and R-2 values of 0.0967 and 0.9806 (for the testing phase), respectively. The results demonstrated the merits of the proposed BO-XGBoost model. In addition, variable importance through mutual information tests was applied to interpret the XGBoost model and demonstrated that machine parameters have the greatest impact as compared to rock mass and material properties.
Performance of hybrid SCA-RF and HHO-RF models for predicting backbreak in open-pit mine blasting operations
- Zhou, Jian, Dai, Yong, Khandelwal, Manoj, Monjezi, Masoud, Yu, Zhi, Qiu, Yingui
- Authors: Zhou, Jian , Dai, Yong , Khandelwal, Manoj , Monjezi, Masoud , Yu, Zhi , Qiu, Yingui
- Date: 2021
- Type: Text , Journal article
- Relation: Natural Resources Research Vol. 30, no. 6 (2021), p. 4753-4771
- Full Text:
- Reviewed:
- Description: Backbreak is an adverse phenomenon in blasting operation, which can cause, among others, mine walls instability, falling down of machinery, drilling efficiency reduction and stripping ratio enhancement. Therefore, this research aimed to develop two-hybrid RF (Random Forest) prediction models of random forest, which are optimized by Harris hawks optimizer (HHO) and sine cosine algorithm (SCA), for estimation of the backbreak distance. The HHO and SCA algorithms were adopted to determine two hyper-parameters (mtry and ntree) in the RF models, in which root mean square error (RMSE) was utilized as a fitness function. A database with 234 samples was established, in which six variables [i.e., hole length (L), burden (B), spacing (S), stemming (T), special drilling (SD) and powder factor (PF)] were used as input variables, and backbreak was defined as output variable. Additionally, three classical regression models (i.e., extreme learning machine, radial basis function network and general regression neural network) were adopted to verify the superiority of the hybrid RF prediction models. The predictive reliability of the proposed models was assessed by the combination of mean absolute error (MAE), RMSE, variance accounted for (VAF) and Pearson correlation coefficient (R2). The results revealed that the SCA-RF model outperformed all the other prediction models with MAE of (0.0444 and 0.0470), RMSE of (0.0816 and 0.0996), VAF of (96.82 and 95.88) and R2 of (0.9876 and 0.9829) in training and testing stages, respectively. A Gini index generated internally in the RF model showed that backbreak was significantly more sensitive to L and T than to SD. © 2021, International Association for Mathematical Geosciences.
- Authors: Zhou, Jian , Dai, Yong , Khandelwal, Manoj , Monjezi, Masoud , Yu, Zhi , Qiu, Yingui
- Date: 2021
- Type: Text , Journal article
- Relation: Natural Resources Research Vol. 30, no. 6 (2021), p. 4753-4771
- Full Text:
- Reviewed:
- Description: Backbreak is an adverse phenomenon in blasting operation, which can cause, among others, mine walls instability, falling down of machinery, drilling efficiency reduction and stripping ratio enhancement. Therefore, this research aimed to develop two-hybrid RF (Random Forest) prediction models of random forest, which are optimized by Harris hawks optimizer (HHO) and sine cosine algorithm (SCA), for estimation of the backbreak distance. The HHO and SCA algorithms were adopted to determine two hyper-parameters (mtry and ntree) in the RF models, in which root mean square error (RMSE) was utilized as a fitness function. A database with 234 samples was established, in which six variables [i.e., hole length (L), burden (B), spacing (S), stemming (T), special drilling (SD) and powder factor (PF)] were used as input variables, and backbreak was defined as output variable. Additionally, three classical regression models (i.e., extreme learning machine, radial basis function network and general regression neural network) were adopted to verify the superiority of the hybrid RF prediction models. The predictive reliability of the proposed models was assessed by the combination of mean absolute error (MAE), RMSE, variance accounted for (VAF) and Pearson correlation coefficient (R2). The results revealed that the SCA-RF model outperformed all the other prediction models with MAE of (0.0444 and 0.0470), RMSE of (0.0816 and 0.0996), VAF of (96.82 and 95.88) and R2 of (0.9876 and 0.9829) in training and testing stages, respectively. A Gini index generated internally in the RF model showed that backbreak was significantly more sensitive to L and T than to SD. © 2021, International Association for Mathematical Geosciences.
- «
- ‹
- 1
- ›
- »