Investigation of Micro-Scale Damage and Weakening Mechanisms in Rocks Induced by Microwave Radiation and Their Associated Strength Reduction Patterns: Employing Meta-Heuristic Optimization Algorithms and Extreme Gradient Boosting Models

Zhongyuan Gu, Xin Xiong, Chengye Yang () and Miaocong Cao
Additional contact information
Zhongyuan Gu: College of Jilin Emergency Management, Changchun Institute of Technology, Changchun 130021, China
Xin Xiong: School of Resources and Safety Engineering, Central South University, Changsha 410083, China
Chengye Yang: School of Resources and Safety Engineering, Central South University, Changsha 410083, China
Miaocong Cao: School of Investigation and Surveying Engineering, Changchun Institute of Technology, Changchun 130021, China

Mathematics, 2024, vol. 12, issue 18, 1-23

Abstract: Microwave-assisted mechanical rock breaking represents an innovative technology in the realm of mining excavation. The intricate and variable characteristics of geological formations necessitate a comprehensive understanding of the interplay between microwave-induced rock damage and the subsequent deterioration in rock strength. This study conducted microwave irradiation damage assessments on 78 distinct rock samples, encompassing granite, sandstone, and marble. A total of ten critical parameters were identified: Microwave Irradiation Time (MIT), Microwave Irradiation Power (MIP), Longitudinal Wave Velocity prior to Microwave Treatment (LWVB), Longitudinal Wave Velocity post-Microwave Treatment (LWVA), Percentage Decrease in Longitudinal Wave Velocity (LWVP), Porosity before Microwave Treatment (PB), Porosity after Microwave Treatment (PA), Percentage Increase in Porosity (PP), and Uniaxial Compressive Strength following Microwave Treatment (UCSA). Utilizing the Pied Kingfisher Optimizer (PKO) alongside Extreme Gradient Boosting (XGBoost), we developed a PKO-XGBoost machine learning model to elucidate the relationship between UCSA and the nine additional parameters. This model was benchmarked against other prevalent machine learning frameworks, with Shapley additive explanatory methods employed to assess each parameter’s influence on UCSA. The findings reveal that the PKO-XGBoost model provides superior accuracy in delineating relationships among rock physical properties, microwave irradiation variables, microscopic attributes of rocks, and UCSA. Notably, PA emerged as having the most significant effect on UCSA, indicating that microwave-induced microscopic damage is a primary contributor to reductions in rock strength. Additionally, MR exhibited substantial influence; under identical microwave irradiation conditions, rocks with lower density demonstrated greater susceptibility to strength degradation. Furthermore, during microwave-assisted rock breaking operations, it is imperative to establish optimal MIT and MIP values to effectively diminish UCSA while facilitating mechanical cutting processes. The insights derived from this research offer a more rapid, cost-efficient approach for accurately assessing correlations between microwave irradiation parameters and resultant rock damage—providing essential data support for enhancing mechanical rock-breaking efficiency.

Keywords: microwave irradiation; machine learning; microwave-assisted mechanical rock breaking; Shapley additive explanatory (SHAP); rock damage; meta-heuristic optimization algorithms (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/18/2954/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/18/2954/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:18:p:2954-:d:1483597

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().