Reliability and availability artificial intelligence models for predicting blast-induced ground vibration intensity in open-pit mines to ensure the safety of the surroundings

Hoang Nguyen, Xuan-Nam Bui and Erkan Topal

Reliability Engineering and System Safety, 2023, vol. 231, issue C

Abstract: This study aims to predict ground vibration intensity in mine blasting, which is measured by peak particle velocity (PPV), using three novel intelligent models based on metaheuristic algorithms and extreme learning machine (ELM) model, including salp swarm optimization (SalSO), sparrow search optimization (SpaSO), and moth-flame optimization (MFO), named as SpaSO-ELM, SalSO-ELM, and MFO-ELM models. In this study, the SpaSO, SalSO and MFO algorithms were utilized to optimize the weights of the ELM for predicting PPV based on their different optimization mechanisms. In order to assess the performance of these models, 216 blasting records were considered and the corresponding PPV values were measured at the Coc Sau open-pit coal mine (located in the North of Vietnam). The algorithms’ parameters were structured with different activation functions of the ELM model. Furthermore, in order to diagnose the improvement of the SpaSO-ELM, SalSO-ELM, and MFO-ELM models, the standalone ELM and two empirical models (linear and nonlinear models) were also investigated and evaluated. The results revealed that nonlinear models are potential candidates for predicting PPV, and the ELM-based models are robust solutions to model the nonlinear relationships of the dataset. The developed models were then also validated in practical engineering, and the findings indicated that the SpaSO-ELM model is the best intelligent model for predicting PPV in this study with an accuracy of 91.4%. The remaining hybrid models provided slightly lower performances with the accuracies in the range of 89.8%—90.5%. Although the nonlinear empirical model predicted PPV much better than the linear model; its performance is still significantly lower than the proposed hybrid intelligent models. Thus, the optimized metaheuristic-based ELM models proposed in this study are considered as the high reliability models for predicting blast-induced ground vibration intensity in open-pit mines to ensure the safety of the surroundings.

Keywords: Reliability model; Mine blasting; Ground vibration; Risk assessment; Optimization; Man-made hazards (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (7)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0951832022006470
Full text for ScienceDirect subscribers only

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:eee:reensy:v:231:y:2023:i:c:s0951832022006470

DOI: 10.1016/j.ress.2022.109032

Access Statistics for this article

Reliability Engineering and System Safety is currently edited by Carlos Guedes Soares

More articles in Reliability Engineering and System Safety from Elsevier
Bibliographic data for series maintained by Catherine Liu ().