Forecasting the Collapse-Induced Ground Vibration Using a GWO-ELM Model

Ground vibration is one of the effects of the blasting process; when the ground vibration reaches the highest level, it will disturb comfort and even cause damage to the surrounding building structure. This research aims to determine the magnitude of ground vibrations in Pit A and Pit C, as well as determine the relationship between Peak Particle Velocity (PPV) and scaled Distance, and determine the maximum explosive charge weight per delay based on the SNI 7571: 2010 reference. Actual ground vibration measurement data during research based on PPV theory and the actual PPV power regression relationship with scaled distance was used to obtain a ground vibration prediction formula to be a reference for determining the amount of explosive filling per delay. The ground vibration produced in the blasting process is hoped not to exceed the safe threshold. Prediction of the ground vibration formula at 100 m to 1500 m according to the US Bureau of Mines where the Mean Squared Error (MSE) value is 0.54, the MSE value from the Langefors-Kihlstrom equation is 1.85 while the MSE value from the Ambersays-Hendorn equation is 0.31 with the slightest deviation is very good to use as a reference for predicting ground vibrations with the predicted PPV formula. Hence, the maximum explosive charge with a PPV limit of 2 mm/s is 2.452 kg, a PPV limit of 3 mm/s is 11.332 kg, and a PPV limit of 5 mm/s is 23.040 kg. The factors that influence ground vibration are the Distance from the blasting location to the measurement location and the maximum number of explosives per delay, so the results taken from this research are that blasting in Pit A and Pit C is still categorized as safe for infrastructure and community housing.

This research was conducted in Nyapa West P2 PIT in PT Dahana CK GOC Job Site, Berau, East Kalimantan. One of the excavation activities in the area of research is the stripping of the overburden. This activity was preceded by dispersing process using drilling and blasting method. One of the effect of the blasting activity is the ground vibration. Under the standard vibration levels refer to the criteria of SNI 7571: 2010 classified as class 2, with the blasting vibration frequency is in the range between 5.2 Hz to 12 Hz, then the Threshold Limit Value (TLV) of 5 mm/s. With the PPV value of 5.26 mm/s - 14.87 mm/s at a distance of 200 m - 300 m declared unsafe to the building nearby. While the value of PPV of 0.46 mm / s - 1.12 with a distance of 400 m - 750 m declared safe to the building nearby. Calculation of PPV value approaching the actual PPV value using the USBM equation, so it can be used to predict the future ground vibrations. The results of the PPV according to the USBM equation that has a large enough range of values is 4.90 mm/s using USBM equation and 0.46 mm/s for the actual data, it caused by several factors that lead to that labour, ground vibration measurement error and the distance measurement error. Equation formula of the Peak Particle Velocity (PPV) relations with the Scale Distance (SD) obtained from the ground vibration analysis measurement data is PPV = 1331.9 (SD)-1.972 with R2 = 0.4931 and R = -0.702. R = -0.702 expressed correlation of the equation that are negative and strong. Ground vibration measurement results using Blastware application established the constant disintegration value with the conviction level of 50 % that is disintegration coefficient is -1.941 and rock factor 2.200,4, while the 90% confidence level that the disintegration coefficient is -1.941 and rock factor 5.018, 4. The tie-up plan evaluation with controlling the vibration level is at the optimum level. Because of the tie-up resulted only few holes exploded simultaneously. Optimization of explosives according to a threshold limit value that has been determined with the value of 3 mm/s, using the VS, SD, and PPV graph from the Blastware application. With a distance of 300 m for explosives / delay that used 100 kg, while at a distance of 200 m used 44.44 Kg.

Prediction of blast-induced ground vibration using artificial neural networks

Peak Particle Velocity (PPV) of ground vibration induced by blasting have been used for long time as a standard for evaluating damage of structures. However, in recent years, it is often discussed whether the PPV standard is adequate or not for evaluating public environmental disturbances. In such case, Vibration Level (VL) is used, which is established and defined to allow for the feeling of human body against the acceleration of vibration. Hence the necessity of measurement by both PPV and VL is increasing. If the relation between PPV and VL can be quantitatively clarified, then it is possible to estimate PPV from VL and vice versa. The relation, however, is complicated in case of ground vibration induced by practical delayed blastings because of some factors, namely such as the frequency components and the shape of wave form.In this paper, firstly, a new method to calculate VL from the velocity wave form was discussed. Through the discussion, many factors were investigated which have to be considered when the vibration wave form is converted into VL. Then such method was applied to measured waves caused by tunnelling blasting in order to evaluate a variation due to each primary factor. As a result, a new relationship equation between PPV and VL for ground vibration due to blasting was proposed.

Blasting is a widely used technique for rock fragmentation in surface mines and tunneling projects. The ground vibrations produced by blasting operations are the main concern for the industries undertaking blasting operations, which can damage the surrounding structures, adjacent rock masses, roads and slopes in the vicinity. Therefore, proper prediction of blast-induced ground vibrations is essential to demarcate the safety area of blasting. In this research, classification and regression tree (CART) as a rule-based method was used to predict the peak particle velocity through a database comprising of 51 datasets with results of maximum charge per delay and distance from the blast face were fixed as model inputs. For comparison, the empirical and multiple regression (MR) models were also applied and proposed for peak particle velocity prediction. Performance of the proposed models were compared and evaluated using three statistical criteria, namely coefficient of correlation (R2), root mean square error (RMSE) and variance account for (VAF). Comparison of the obtained results demonstrated that the CART technique is more reliable for predicting the peak particle velocity than the MR and empirical models and it can be introduced as a new technique in this field.

Prediction of ground vibration induced by blasting operations is a crucial challenge to engineers working in surface mines. This study aims to assess the efficiency of two advanced machine learning models in predicting ground vibrations in a granite quarry located in Malaysia. To this end, two intelligent models were proposed by hybridizing the relevance vector regression (RVR) with the grey wolf optimization (GWO) (which formed the RVR-GWO model) and with the bat-inspired algorithm (BA) (which formed the RVR-BA model). To the best of our knowledge, this is the first attempt to predict ground vibration using the RVR-GWO and RVR-BA models. The afore-mentioned models were developed and tested using 95 datasets. Then, the performance of the developed models was statistically checked through four comparative experiments using, among others, mean square error (MSE) and correlation coefficient (R). The results indicated the superiority of the RVR-GWO model over the RVR-BA model in terms of prediction precision. The RVR-GWO model with R of 0.915 and MSE = 7.920 predicted the ground vibration better than the RVR-BA model with R of 0.867 and MSE = 8.551. Accordingly, it was concluded that applying the GWO algorithm to RVR can result in high accuracy in the prediction of blast-induced ground vibration.

To effectively predict and control the peak particle velocity (PPV) induced by tunnel blasting, this study investigates the Qinhuangdao Jiaoshan Tunnel as a case study. This study first proposes an Improved Particle Swarm Optimization (IPSO) algorithm through theoretical derivation. Building upon IPSO, a further enhanced algorithm, termed CIPSO, is developed by integrating a dependency model derived from Copula theory. The CIPSO algorithm is then employed to optimize a Support Vector Regression (SVR) model, establishing the final CIPSO-SVR prediction framework. Copula theory was employed to quantify the correlation between PPV and surface cumulative settlement (S). A regularization term incorporating Kullback-Leibler (KL) divergence was then embedded into the SVR objective function. The Hyperparameters of the CIPSO-SVR model were optimized using fixed-step rolling cross-validation. The model’s predictive performance was rigorously compared against CIPSO-optimized Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) models, as well as against SVR, CNN, and LSTM models optimized by the Grey Wolf Optimizer (GWO) and Moth-Flame Optimization (MFO) algorithms. The results show that the CIPSO-SVR model achieves superior accuracy and robustness on the test set (R2= 0.9569) in predicting PPV compared to the alternative models. Crucially, the model effectively captures the inherent nonlinear relationships of complex engineering problems, even with small-sample data.OPEN ACCESS Received: 18/08/2025 Accepted: 17/10/2025 Published: 23/01/2026

Accidental and intended blast-related activities might be detrimental to structures and their personnel. The detonation of explosives for various blast scenarios induces ground shocks that cause a ground vibration, known as a blast-induced ground motion (BIGM). These vibrations can affect the facilities or structures in the vicinity; therefore, it is essential to predict the intensity of the vibrations due to BIGMs to safeguard personnel and structures. The BIGM is measured as the peak particle velocity (PPV), peak ground acceleration (PGA), peak ground displacement (PGD), and principal frequency (PF) content. These parameters depend on the charge intensity, arrival time, and wave duration, which are usually expressed as the PPV and PGA. In this study, finite-element (FE)-based numerical simulations are carried out to investigate the influence of various geomedia, such as granite, limestone, and sandstone, on the prediction of the BIGM parameters. In addition, the numerical simulation-based estimation of the PPV for different geomedia is compared with the existing code-based and empirical approaches. Therefore, a new PPV predictor equation has been proposed that is based on numerical simulations for three rock types of granite, limestone, and sandstone. This study shows the significance of the effect of the depth of burst (DOB) and charge shape on the PPV estimation. In addition, the spatial and temporal variations in the PGA are estimated for various geomedia, and the correlation equations are proposed from the numerical study, which confirms the geomedia’s significance in the PGA prediction. The geological site constants are estimated from the numerical simulations and the investigations revealed that the prediction of the geological site constant that is based on the findings is in good agreement for sandstone and limestone for lower scaled distances; however, limestone matches well with those specified in the Indian Standard (IS) guidelines for hard rock. Therefore, comparisons between various prediction models that are presented in this study could contribute to the selection of suitable PPV and PGA predictor equations for different blast scenarios and site conditions.

In this study, ground vibrations caused by blasting applications in a quarry were recorded and these values were evaluated and estimated by using an artificial neural network (ANN) model. Of the 28 vibration data measured, 20 were used for ANN training, 4 for validation and the remaining 4 for testing. In the model, peak particle velocity (PPV) was used as the output parameter, and the maximum explosive amount per delay and scaled distance were used as input parameters. In addition, MAPE, RMSE and R2 performance criteria were calculated from the realized, predicted by ANN and PPV values obtained from the field equation. The maximum amount of explosives used per delay and the sensitivity analysis of the scaled distance on the highest particle velocity were also determined. As a result, when the vibration data calculated from the field equation and estimated from the ANN model were compared with the realized vibration data, it was seen that the values obtained by the ANN model had a higher correlation.

Train-induced ground vibration problems have become an important subject, as the number of the high speed railroad construction projects rapidly increases worldwide. Various numerical approaches have been proposed and used for the prediction of the train-induced ground vibration. However, the estimation performance has not been satisfactory due to the difficulty in modeling the train-transit loads on railroad structures and the structure-soil interaction system, which are essential for the accurate prediction of ground vibration. In this study, a new semi-analytical method was proposed for the prediction of ground vibration and the evaluation of environmental vibration levels with simple measurements of the ground vibration on the surface. The proposed method does not need any analytical model for inputting the train load. Instead, it identifies the effective train loads acting on the railroad track structure based on the measured ground responses at several locations and the numerical model of the structure-soil interaction system through the identification of the properties of the soil layers. Then, the effective train load is utilized as an input to the structure-soil interaction problem to predict the ground vibrations and the environmental vibration levels of the structures. A finite and infinite element model was utilized to solve the wave propagation problem in the soil medium in the frequency domain. Field validations were carried out at a site where Korea high-speed trains run over an elevated bridge structure. The predicted ground accelerations were found to be in good agreement with the measured data.

Abstract. At PT. Hutama Karya Basuki BRP KSO carries out chemical rock breaking activities by blasting. The breaking location is in the Gunung Siki Public Facilities on the Tiga Dihaji Dam project. The blasting location is close to the Dam body construction. One of the negative impacts of blasting activities is seismic waves that move in the ground originating from energy generated from nature and blasting activities. Ground vibrations will have a negative impact on the Dam construction. Therefore, research is needed to determine the effect of blasting vibrations on the Dam construction. The research method used is to conduct a comparative analysis between scaled distance (SD) and peak particle velocity (PPV). Determination of the influence of waves on the peak particle velocity value depends on the decay constant (k) and site exponent (e). The predictors used to predict the ground vibration value are USBM, Ambersay and Hendriom, and Langefors and Kihlstrom. Determination of the influence of waves on the peak particle velocity value depends on the decay constant (k) and site exponent (e). The results obtained will provide recommendations for optimal explosives that do not exceed the threshold value based on SNI 7571:2023, which is 40 mm/s. From the research results, the actual value of the peak vector sum (PVS) ranges from 0.652 mm/s - 3.479 mm/s. Based on the area of the blasting front, the optimization of explosives is planned for 60 holes that explode. Together with 5 holes with the closest distance of 118 m, the predicted PPV is 5.248 mm/s. Abstrak. PT. Hutama Karya Basuki BRP KSO melakukan kegiatan pemberaian batuan secara kimiawi dengan peledakan. Lokasi pemberaian berada di Fasum Gunung Siki pada proyek Bendungan Tiga Dihaji. Lokasi peledakan dekat dengan kontruksi badan Bendungan. Salah satu dampak negatif dari kegiatan peledakan yaitu gelombang seismik yang bergerak di dalam tanah bersumber dari energi yang dihasilkan dari alam maupun kegiatan peledakan. Getaran tanah akan berdampak negatif pada kontruksi Bendungan Oleh karena itu perlu dilakukan penelitian untuk mengetahui pengaruh dari getaran peledakan terhadap kontruksi Bendungan. Metoda penelitian yang digunakan dengan melakukan analisis komparatif antara scaled distance (SD) dengan peak particle velocity (PPV). Penentuan pengaruh gelombang pada nilai peak particle velocity tergantung pada nilai konstanta peluruh (k) dan site exponent (e). Prediktor yang digunakan untuk memprediksi nilai getaran tanah yaitu USBM, Ambersay and Hendriom, dan Langefors and Kihlstrom. Penentuan pengaruh gelombang pada nilai peak particle velocity tergantung pada nilai konstanta peluruh (k) dan site exponent (e). Hasil yang didapatkan akan memberikan rekomendasi bahan peledak optimal yang tidak melebihi nilai ambang batas berdasarkan SNI 7571:2023 yaitu 40 mm/s. Dari hasil penelitian didapatkan nilai aktual dari peak vector sum (PVS) berkisar dari 0.652 mm/s - 3.479 mm/s. Berdasarkan luas front peledakan maka optimalisasi bahan peledak direncanakan untuk 60 lubang yang meledak Bersama 5 lubang dengan jarak terdekat 118 m didapatkanlah PPV prediksi sebesar 5.248 mm/s.

Ground vibration is an integral part of the rock blasting process in surface mines, which may cause severe damages to structures and plants in the nearby environment. Therefore, its prediction plays an important role in the minimization of environmental impacts. The peak particle velocity (PPV) is an important predictor for ground vibration. In this paper, first a fuzzy logic model was developed to predict PPV based on collected data from blasting events in Sarcheshmeh copper mine, located in the southwest of Iran. The predictive fuzzy model was implemented on the fuzzy logic toolbox of MATLAB using the Mamdani algorithm. Then, the PPV was predicted by conventional empirical predictors used in blasting practice and also by multiple regression analysis. Finally, a comparative analysis between the results obtained by the fuzzy model and common vibration predictors was carried out. The results indicated the high predictive capacity of fuzzy model, which can be used as a reliable predictor of ground vibration for the studied mine.

Ground vibrations due to blasting can cause damage to nearby structures. In this context, a damage prevention criterion was developed to avoid this potential risk, establishing a limit value for the Peak Particle Velocity (PPV) as a function of ground natural frequency and type of structure to protect. In addition, several empirical attenuation laws to estimate the PPV and frequency as a function of the distance and amount of explosive were also developed. These models can be used to separately predict PPV and frequency, obtaining the representative point of the designed blast and decide if a potential damage could exist or not. The proposed approach allows one to simultaneously work with an attenuation law for the PPV and another one for the frequency, defining an area in the damage criterion abacus instead of a single representative point. The system was applied using data from 75 blasts in different limestone quarries in the north of Spain.

Blasting excavation is extensively used in tunnel construction, and the adverse effect of ground vibration induced by blasting on surrounding structures and inhabitants is a critical problem. This study aims to investigate the tunnel hollow effect on triaxial peak particle velocities (PPV) and dominant frequencies induced by electronic detonator. Field experiments were conducted in a shallow tunnel construction site and the ground vibration waveforms were recorded. Variational mode decomposition (VMD) was applied to denoise and correct the zero‐drift phenomenon, and the proposed method of selecting the optimal parameter was verified. A series of statistical analyses and tests were performed to evaluate the differences of peak particle velocity and dominant frequency among various monitoring points. The results showed that the hollow effect on Z‐axis PPV is significant, and triaxial PPV is also affected when the horizontal distance exceeds 30 m. The hollow effect on dominant frequency could not be identified since the hollow of tunnel is a free face, and the dominant frequency of reflected wave remains unchanged. An augmented factor of 1.229 is determined carefully as the hollow effect factor on PPV. Therefore, blasting vibration induced by electronic detonator of the excavated zone should be attached with greater importance, and hollow effect on PPV should be considered in the blasting design of tunnel excavation.

Study on influencing factors and prediction of peak particle velocity induced by roof pre-split blasting in underground