Comparing blast-induced ground vibration models using ANN and empirical geomechanical relationships

Abstract

Blasting remains as an economical and reliable excavation technique, but there are some environmental shortcomings such as the control of blast-induced vibration. The impacts of vibration over surrounding communities in a blast area have been investigated for decades and researchers have been using a myriad of empirical predictive attenuation equations. These models, however, may not have satisfactory accuracy, since parameters associated to geomechanical properties and geology affect the propagation of seismic waves, making vibration modeling a complex process. This study aims for application of an Artificial Neural Network (ANN) method and Geomechanical parameter relationships to simulate the blast-induced vibration for a Brazilian mining site and then compare them to the traditional approach. ANN had the best performance for this mine despite having demanded large datasets (as much as for the traditional approach), while geomechanical parameters like RQD and GSI may be used to deliver a fair approach even without seismic data. Also, ANN methods may be useful in dealing with a large amount of information to facilitate the simulation process when combined with other methods. Therefore, alternative prediction methods may be helpful for small budget mining operations in planning and controlling blast-induced vibration and helping mining in urban areas becoming a more sustainable activity.

A Re-Look Into Modified Scaled Distance Regression for Prediction of Blast-Induced Ground Vibration

“…The underestimation aspect had been addressed in some blasting studies (Dauji 2020), whereas it had been missed by many studies till recent times (Khandelwal & Singh, 2009;Longjun et al, 2011;Singh et al, 2015;Tripathy et al 2016;Kalayki & Ozer, 2016;Iramina et al, 2018;Ray & Dauji, 2019;Jayasinghe et al, 2019;Rajabi & Vafaee, 2019;Matidza et al, 2020;Rana et al, 2020;Yu et al, 2020). In this article, this aspect will be highlighted using the data from literature (Agarwal & Mishra, 2019).…”

“…The various performance measures reported in literature include correlation coefficient / coefficient of determination (Nguyen et al, 2018;Dauji, 2018;Huang et al, 2019;Jayasinghe et al, 2019;Ray & Dauji, 2019;Rajabi & Vafaee, 2019;Agarwal & Mishra, 2019;Yu et al, 2020;Matidza et al, 2020;Rana et al, 2020;Dauji, 2020), root mean square error (Iramina et al, 2018;Nguyen et al, 2018;Yu et al, 2020;Matidza et al, 2020;Rana et al, 2020;Dauji, 2020), mean absolute error (Yu et al, 2020;Matidza et al, 2020;Dauji, 2020), mean absolute percentage error (Matidza et al, 2020), median absolute error (Matidza et al, 2020), error (Agarwal andMishra, 2019), mean square error (Dauji, 2018;Ray & Dauji, 2019), overestimation (Dauji, 2020), underestimation (Dauji, 2020), mean absolute relative error (Dauji, 2020), and AIC (Dauji, 2018;Ray & Dauji, 2019). It can be observed that some of the studies relied on one or two performance measures (mostly correlation coefficient or the error) for evaluation of the developed models, and only a few employed multiple performance measures for comprehensive evaluation.…”

Performance Evaluation of Training Algorithms in Backpropagation Neural Network Approach to Blast-Induced Ground Vibration Prediction

“…The blast data comprised of the following parameters: number of blast holes, maximum instantaneous charge (kg), distance between blasting point and monitoring station (m), hole depth (m), powder factor (kg/m 3 ) and Peak Particle Velocity (PPV) (mm/s). These recorded parameters are deemed significant in affecting the levels of blast-induced vibrations in literature It is noteworthy that PPV is the most preferred parameter for evaluating blast-induced ground vibration (Iramina et al, 2018;Arthur et al, 2020b). However, for the development of the various models as presented in this study, number of blast holes, maximum instantaneous charge (kg), distance between blasting point and monitoring station (m), hole depth (m), powder factor (kg/m 3 ) were used as the input parameters while the PPV (mm/s) values served as the output parameter.…”

Implications of machine learning on geomechanical characterization and sand management: a case study from Hilal field, Gulf of Suez, Egypt

“…Well logs are commonly used to derive the in situ stress state at the reservoir level; however, they do not provide the most accurate parameters, which affect the results of the estimated geomechanical elements and may lead to incorrect interpretation (Zoback 2010;Radwan et al 2021). Geomechanical studies in many areas worldwide are dependent on empirical equations for geomechanical parameter estimation, which may work in some places but not always (Sarkar et al 2012;Suorineni 2014a, b;Najibi et al 2015;Iramina 2018). Machine learning techniques have been widely used in the oil and gas industry as a powerful tool for prediction of several vital parameters in the energy industry (e.g., Vo Thanh et al 2020;Ashraf et al 2020Ashraf et al , 2021Rajabi et al 2021;Mustafa et al 2022;Safaei-Farouji et al 2022;Radwan et al 2022).…”