Impact of velocity of detonation and charge per bank cubic meter on flyrock throw prediction using support vector machine

This study emphasizes the importance of understanding the factors that influence the throwing of flyrock in mining operations, a significant hazard to both workers and nearby structures. Moreover, it highlights how blasting engineers, when estimating flyrock occurrences and their travel distance, typically rely on input parameters such as powder factor (PF), hole length (HL), subdrill (SD), spacing (S), hole diameter (D), burden (B) and stemming length (ST), while overlooking crucial factors like velocity of detonation (VOD) and charge per bank cubic meter (CPBCM). Through analysis using support vector machine (SVM) modeling in MATLAB, the study underscores the impact of including or excluding VOD and CPBCM on flyrock throw distance. Background The use of explosives in mining operations has associated hazards, including flyrock throw, which poses a substantial risk to workers and neighboring structures. Understanding the elements that influence flyrock throw is critical to assuring blasting safety. Through support vector machine (SVM) modeling, this research investigates the impact of two key parameters on flyrock throw: VOD and CPBCM. Methods The research used data from controlled blasting experiments conducted at Damang, Ghana, a mining site located in West Africa. Both the VOD and CPBCM were systematically included and excluded, and the resultant distances of flyrock throw were measured. The input parameters used for the analysis are outlined in Table 1. Various SVM algorithms — medium Gaussian support vector machine (MGSVM), coarse Gaussian support vector machine (CGSVM), quadratic Gaussian support vector machine (QGSVM), linear support vector machine (LSVM), and fine Gaussian support vector machine (FGSVM) — were assessed using the modeling shown in the flowchart (Fig. 1). Fig. 1 Flowchart of SVM modeling. Results and discussions The research revealed significant correlations between the VOD, CPBCM and flyrock throw distance. Elevated levels of VOD and CPBCM were associated with greater distances of flyrock throw. The SVM model effectively captured these relationships, illustrating the nonlinear nature of the connections between the input parameters and flyrock throw distance. These findings underscore the criticality of regulating the VOD and CPBCM to mitigate the risk of flyrock throw during blasting operations. By comprehending the influence of these factors, blasting engineers can optimize blast designs to bolster safety measures and reduce the potential for flyrock incidents. Additionally, the utilization of SVM modeling showcases the robust effectiveness of machine learning techniques in forecasting and dissecting intricate phenomena within mining and blasting engineering. Understanding the correlations among VOD, CPBCM and flyrock throw facilitates more precise risk evaluations. Mining firms can leverage this insight to pinpoint high-risk scenarios and implement tailored mitigation strategies to diminish the occurrence of flyrock incidents. These findings can be incorporated into training initiatives for blasting engineers and personnel. By educating staff on the factors affecting flyrock behavior and the significance of adept management of blasting parameters, mining enterprises can heighten safety consciousness and practices at the operational level. Regulatory bodies tasked with overseeing mining activities can leverage the findings of this study to inform regulations and standards pertaining to blasting procedures. By integrating evidence-based best practices into regulatory frameworks, governing bodies can foster safer and more sustainable mining endeavors. Mining enterprises can use the insights gleaned from the study as part of an ongoing enhancement process. Through real-time monitoring and analysis of blasting performance data, operators can refine blasting parameters and protocols to continually optimize safety and operational efficiency. Conclusions The predictive performances of the LSVM, QGSVM, FGSVM, MGSVM and CGSVM models were assessed. Among these models, the LSVM exhibited the most accurate prediction for flyrock throw distance, achieving a coefficient of determination and root-mean-squared error values of 1.00 and 0.05, respectively. This performance surpassed that of empirical predictions. The study also highlighted the significant improvement gained from incorporating VOD and CPBCM into the models. The enhancements in coefficient of determination and root-mean-squared error values for each model, attributable to the inclusions of VOD and CPBCM, respectively, are as follows: LSVM, 0.00 percent and 80.00 percent; FGSVM, 39.5.00 percent and 94.00 percent; MGSVM, 14.00 percent and 75.00 percent; CGSVM, 3.00 percent and 65.00 percent; and QGSVM, 1.00 percent and 98.00 percent. While this study was conducted specifically in the context of Ghanaian mining operations, its methodology could be replicated elsewhere provided that relevant data have been adequately trained and evaluated within the utilized model. References A list of all references is available in the full paper.

Impact of velocity of detonation and charge per bank cubic meter on flyrock throw prediction using support vector machine

Authored by:
Newton Amegbey, Manoj Khandelwal, Daniel Mireku-Gyimah, Bright Akuinor Tsidi

To view this article you must be a member of SME/UCA.

Fall is just around the corner, bringing back hazards of rain and reduced visibility

A big thank you to all of our Industrial Minerals Review authors

Submit to MINEXCHANGE 2027 proceedings and Environmental Division Student Poster Contest

Fall is just around the corner, bringing back hazards of rain and reduced visibility

A big thank you to all of our Industrial Minerals Review authors

Submit to MINEXCHANGE 2027 proceedings and Environmental Division Student Poster Contest

To view this article you must be a member of SME/UCA.

Environmental, social and governance considerations in production scheduling optimization for sublevel stoping mining operations: A review of relevant works and future directions

Ore types: What they are, how they’re made, and their uses and abuses

Related Articles

Rare earth elements in the global economy: Usage, recovery and the quest for supply security — A review

A systematic evaluation of localization signals in the advancing openpit mine Aitik

From foundation to future: Revisiting AI integration in mining engineering education through current perspectives of students, educators and industry

Iron ore tailings reprocessing by electrostatic separation plus two-stage froth flotation

Fall is just around the corner, bringing back hazards of rain and reduced visibility

A big thank you to all of our Industrial Minerals Review authors

Submit to MINEXCHANGE 2027 proceedings and Environmental Division Student Poster Contest

Fall is just around the corner, bringing back hazards of rain and reduced visibility

A big thank you to all of our Industrial Minerals Review authors

Submit to MINEXCHANGE 2027 proceedings and Environmental Division Student Poster Contest

Use Single Sign On