Optimizing Mean Fragment Size Prediction in Rock Blasting: A Synergistic Approach Combining Clustering, Hyperparameter Tuning, and Data Augmentation

IR (HANDLE) Open Access
  • Krop, Ian
    Department of Earth Resources Engineering, Kyushu University Department of Mining, Materials and Petroleum Engineering, Jomo Kenyatta University of Agriculture and Technology
  • Sasaoka, Takashi
    Department of Earth Resources Engineering, Kyushu University
  • Shimada, Hideki
    Department of Earth Resources Engineering, Kyushu University
  • Hamanaka, Akihiro
    Department of Earth Resources Engineering, Kyushu University

Description

Accurate estimation of the mean fragment size is crucial for optimizing open-pit mining operations. This study presents an approach that combines clustering, hyperparameter optimization, and data augmentation to enhance prediction accuracy using the Xtreme Gradient Boosting (XGBoost) regression model. A dataset of 110 blasts was divided into 97 blasts for training and testing, whereas a separate set of 13 new, unseen blasts was used to evaluate the robustness and generalization of the model. Hierarchical Agglomerative (HA) and K-means clustering algorithms were used, with HA clustering providing a higher cluster quality. To address class imbalance and improve model generalization, a synthetic minority oversampling technique for regression with Gaussian noise (SMOGN) was employed. Hyperparameter tuning was conducted using HyperOpt by comparing Random Search (RS) with the Advanced Tree-structured Parzen Estimator (ATPE). The combination of ATPE with HA clustering and SMOGN in an expanded search space produced the best results, achieving superior prediction accuracy and reliability. The proposed HAC1-SMOGN model, which integrates HA clustering, ATPE tuning, and SMOGN augmentation, achieved a mean squared error (MSE) of 0.0002 and an R^2 of 0.98 on the test set. This study highlights the synergistic benefits of clustering, hyperparameter optimization, and data augmentation in enhancing machine learning models for regression tasks, particularly in scenarios with class imbalance or limited data.

Journal

  • Eng

    Eng 5 (3), 1905-1936, 2024-08-15

    Multidisciplinary Digital Publishing Institute : MDPI

Details 詳細情報について

  • CRID
    1050020054806534528
  • ISSN
    26734117
  • HANDLE
    2324/7234042
  • Text Lang
    en
  • Article Type
    journal article
  • Data Source
    • IRDB

Report a problem

Back to top