Adaptive Weighted Multi-kernel Learning for Blast-Induced Flyrock Distance Prediction DOI Creative Commons
Ruixuan Zhang, Yuefeng Li,

Yilin Gui

и другие.

Rock Mechanics and Rock Engineering, Год журнала: 2024, Номер unknown

Опубликована: Сен. 25, 2024

Abstract In the field of civil and mining engineering, blasting operations are widely frequently used for rock excavation, However, some undesirable environmental problems induced by cannot be ignored. Blast-induced flyrock is one important issue operation, which needs to well predicted identify zone’s safety zone. This study introduces an adaptive weighted multi-kernel learning model (AW-MKL) provide accurate prediction blast-induced distance in Sungun Copper Mine site. The proposed uses a combination (MKL) approach weighting strategy based on Euclidean modified local outlier factor (MLOF) maximally improve predictive ability kernel ridge regression (KRR). To demonstrate superiority approach, six machine models were developed as comparisons, i.e., KRR, RF, GBDT, SVM, M5 Tree, MARS AdaBoost. outcomes method achieved highest accuracy testing phase, with RMSE 2.05, MAE 0.98 VAF 99.92, confirmed strong capability AW-MKL predicting distance.

Язык: Английский

Optimizing Demand Forecasting Method with Support Vector Regression for Improved Inventory Planning DOI Creative Commons

Tryantomo Lokhilmahful Palgunadi,

Rina Fitriana, Anik Nur Habyba

и другие.

Jurnal Optimasi Sistem Industri, Год журнала: 2025, Номер 23(2), С. 149 - 166

Опубликована: Янв. 31, 2025

Problems arising from suboptimal production planning can cause inventory management to be less effective and efficient in the company. The lack of integrated presentation information also causes efficiency making decisions. This study aims obtain best kernel function forecasting model by predicting ground rod sales using Support Vector Regression (SVR) method order determine level accuracy results future which are presented an optimal data visualization. problem-solving is done with method, consists linear functions, polynomial radial basis (RBF) functions Grid Search Algorithm. Based on parameter search that has been grid algorithm, it concluded a value C = 100 ε 10-3. this MAPE training testing 2.048% 1.569%, where smallest compared other two functions. After getting model, was carried out within five months, obtaining average 6,647 monthly pieces. historical reviewed visualization Business Intelligence so well exposed, shows increase every month.

Язык: Английский

Процитировано

0
TBM performance prediction based on XGBoost models: a case study of the ghomrud water conveyance tunnel (Lots 3 and 4) DOI
Mohammad Rouhani, Ebrahim Farrokh

Bulletin of Engineering Geology and the Environment, Год журнала: 2025, Номер 84(6)

Опубликована: Май 14, 2025

Язык: Английский

Процитировано

0
Experimental and theoretical analysis of charge length on single-hole vibration amplitude from underground deep-hole blasting DOI
Yonggang Gou,

M. Ye,

Zhi Yu

и другие.

International Journal of Rock Mechanics and Mining Sciences, Год журнала: 2024, Номер 182, С. 105876 - 105876

Опубликована: Авг. 28, 2024

Язык: Английский

Процитировано

2
Measurement and Prediction of Blast-Induced Flyrock Distance Using Unmanned Aerial Vehicles and Metaheuristic-Optimized ANFIS Neural Networks DOI
Hoang Nguyen,

Nguyen Van Thieu

Natural Resources Research, Год журнала: 2024, Номер unknown

Опубликована: Дек. 21, 2024

Язык: Английский

Процитировано

1
Adaptive Weighted Multi-kernel Learning for Blast-Induced Flyrock Distance Prediction DOI Creative Commons
Ruixuan Zhang, Yuefeng Li,

Yilin Gui

и другие.

Rock Mechanics and Rock Engineering, Год журнала: 2024, Номер unknown

Опубликована: Сен. 25, 2024

Abstract In the field of civil and mining engineering, blasting operations are widely frequently used for rock excavation, However, some undesirable environmental problems induced by cannot be ignored. Blast-induced flyrock is one important issue operation, which needs to well predicted identify zone’s safety zone. This study introduces an adaptive weighted multi-kernel learning model (AW-MKL) provide accurate prediction blast-induced distance in Sungun Copper Mine site. The proposed uses a combination (MKL) approach weighting strategy based on Euclidean modified local outlier factor (MLOF) maximally improve predictive ability kernel ridge regression (KRR). To demonstrate superiority approach, six machine models were developed as comparisons, i.e., KRR, RF, GBDT, SVM, M5 Tree, MARS AdaBoost. outcomes method achieved highest accuracy testing phase, with RMSE 2.05, MAE 0.98 VAF 99.92, confirmed strong capability AW-MKL predicting distance.

Язык: Английский

Процитировано

0