A State of the art Catboost-Based T-Distributed Stochastic Neighbor Embedding Technique to Predict Back-break at Dewan Cement Limestone Quarry
Publish place: Journal of Mining and Environment، Vol: 12، Issue: 3
Publish Year: 1400
نوع سند: مقاله ژورنالی
زبان: English
View: 133
This Paper With 13 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
JR_JMAE-12-3_006
تاریخ نمایه سازی: 18 مهر 1400
Abstract:
The blasting operation is an important rock fragmentation technique employed in several foundation engineering disciplines such as mining, civil, tunneling, and road planning. Back-break (BB) is one of the adverse effects caused by the blasting operations that produces several effects including vulnerability of mining machinery, bench slope design, and risks to the next blast-patterns due to the eruption of gases from several discontinuities in jointed rock masses. Several techniques have been executed by the researchers in order to predict BB in the blasting operations. However, this is the first work to implement a-state-of-the-art Catboost-based t-distributed stochastic neighbor embedding (t-SNE) approach to predict BB. A total of ۶۲ datasets having ۱۲ influential BB-generating features are collected from genuine blasting patterns. A novel dimensionality depletion technique t-SNE that operates the Kullback-Leibler divergence interpretation is employed to tailor the pioneer exaggeration of the blasting dataset. Then the t-SNE dataset obtained is split into a ۷۰:۳۰ ratio of the training and testing datasets. Finally, the Catboost method is implemented on a low-dimensionality blasting database. The performance evaluation criterion confirms that the BB predictive model is more stable with a goodness of fit = ۹۹.۰۴ in the training dataset, ۹۷.۲۶ in the testing datasets, and could anticipate a more accurate prediction. Moreover, the model presented in this work performs superior to the existing publicly available execution of BB. In summary, this model can be practiced in order to predict BB in several rock engineering practices and mining industry scenarios.
Keywords:
Authors
M. Kamran
Department of Mining Engineering, Institute Technology of Bandung, Indonesia
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 :