A combination of expert-based system and advanced decision-tree algorithms to predict air-overpressure resulting from quarry blasting
- He, Ziguang, Armaghani, Danial, Masoumnezhad, Mojtaba, Khandelwal, Manoj, Zhou, Jian, Murlidhar, Bhatawdekar
- Authors: He, Ziguang , Armaghani, Danial , Masoumnezhad, Mojtaba , Khandelwal, Manoj , Zhou, Jian , Murlidhar, Bhatawdekar
- Date: 2021
- Type: Text , Journal article
- Relation: Natural Resources Research Vol. 30, no. 2 (2021), p. 1889-1903
- Full Text:
- Reviewed:
- Description: This study combined a fuzzy Delphi method (FDM) and two advanced decision-tree algorithms to predict air-overpressure (AOp) caused by mine blasting. The FDM was used for input selection. Thus, the panel of experts selected four inputs, including powder factor, max charge per delay, stemming length, and distance from the blast face. Once the input selection was completed, two decision-tree algorithms, namely extreme gradient boosting tree (XGBoost-tree) and random forest (RF), were applied using the inputs selected by the experts. The models are evaluated with the following criteria: correlation coefficient, mean absolute error, gains chart, and Taylor diagram. The applied models were compared with the XGBoost-tree and RF models using the full set of data without input selection results. The results of hybridization showed that the XGBoost-tree model outperformed the RF model. Concerning the gains, the XGBoost-tree again outperformed the RF model. In comparison with the single decision-tree models, the single models had slightly better correlation coefficients; however, the hybridized models were simpler and easier to understand, analyze and implement. In addition, the Taylor diagram showed that the models applied outperformed some other conventional machine learning models, including support vector machine, k-nearest neighbors, and artificial neural network. Overall, the findings of this study suggest that combining expert opinion and advanced decision-tree algorithms can result in accurate and easy to understand predictions of AOp resulting from blasting in quarry sites. © 2020, International Association for Mathematical Geosciences.
- Authors: He, Ziguang , Armaghani, Danial , Masoumnezhad, Mojtaba , Khandelwal, Manoj , Zhou, Jian , Murlidhar, Bhatawdekar
- Date: 2021
- Type: Text , Journal article
- Relation: Natural Resources Research Vol. 30, no. 2 (2021), p. 1889-1903
- Full Text:
- Reviewed:
- Description: This study combined a fuzzy Delphi method (FDM) and two advanced decision-tree algorithms to predict air-overpressure (AOp) caused by mine blasting. The FDM was used for input selection. Thus, the panel of experts selected four inputs, including powder factor, max charge per delay, stemming length, and distance from the blast face. Once the input selection was completed, two decision-tree algorithms, namely extreme gradient boosting tree (XGBoost-tree) and random forest (RF), were applied using the inputs selected by the experts. The models are evaluated with the following criteria: correlation coefficient, mean absolute error, gains chart, and Taylor diagram. The applied models were compared with the XGBoost-tree and RF models using the full set of data without input selection results. The results of hybridization showed that the XGBoost-tree model outperformed the RF model. Concerning the gains, the XGBoost-tree again outperformed the RF model. In comparison with the single decision-tree models, the single models had slightly better correlation coefficients; however, the hybridized models were simpler and easier to understand, analyze and implement. In addition, the Taylor diagram showed that the models applied outperformed some other conventional machine learning models, including support vector machine, k-nearest neighbors, and artificial neural network. Overall, the findings of this study suggest that combining expert opinion and advanced decision-tree algorithms can result in accurate and easy to understand predictions of AOp resulting from blasting in quarry sites. © 2020, International Association for Mathematical Geosciences.
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
- ›
- »