A Comparative Study of Machine Learning Methods for Prediction of Blast-Induced Ground Vibration
Publish place: Journal of Mining and Environment، Vol: 12، Issue: 3
Publish Year: 1400
نوع سند: مقاله ژورنالی
زبان: English
View: 458
This Paper With 11 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
این Paper در بخشهای موضوعی زیر دسته بندی شده است:
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
JR_JMAE-12-3_005
تاریخ نمایه سازی: 18 مهر 1400
Abstract:
Blast-induced ground vibration (PPV) evaluation for a safe blasting is a long-established criterion used mainly by the empirical equations. However, the empirical equations are again considering a limited information. Therefore, using Machine Learning (ML) tools [Support Vector Machine (SVM) and Random Forest (RF)] can help in this context, and the same is applied in this work. A total of ۷۳ blasts are monitored and recorded in this work. For the ML tools, the dataset is divided into the ۸۰-۲۰ ratio for the training and testing purposes in order to evaluate the performance capacity of the models. The prediction accuracies by the SVM and RF models in predicting the PPV values are satisfactory (up to ۹% accuracy). The results obtained show that the coefficient of determination (R۲) for RF and SVM is ۰.۸۱ and ۰.۷۵, respectively. Compared to the existing linear regressions, this work recommends using a machine learning regression model for the PPV prediction.
Keywords:
Authors
A. Srivastava
Department of Mining Engineering, Indian Institute of Technology (ISM), Dhanbad, India
B. Choudhary
Department of Mining Engineering, Indian Institute of Technology (ISM), Dhanbad, India
M. Sharma
Department of Mining Engineering, Indian Institute of Technology (ISM), Dhanbad, India
مراجع و منابع این Paper:
لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :