Reliable estimates of peak particle velocity (PPV) from blasting-induced vibrations at a construction site play a crucial role in minimizing damage to nearby structures and maximizing blasting efficiency. However, reliably estimating PPV can be challenging due to complex connections between PPV and influential factors such as ground conditions. While many efforts have been made to estimate PPV reliably, discrepancies remain between measured and predicted PPVs. Here, we analyzed various methods for assessing PPV with several key relevant factors and 1191 monitored field blasting records at 50 different open-pit sites across South Korea to minimize the discrepancies. Eight prediction models are used based on artificial neural network, conventional empirical formulas, and multivariable regression analyses. Seven influential factors were selected to develop the prediction models, including three newly included and four already formulated in empirical formulas. The three newly included factors were identified to have a significant influence on PPV, as well as the four existing factors, through a sensitivity analysis. The measured and predicted PPVs were compared to evaluate the performances of prediction models. The assessment of PPVs by an artificial neural network yielded the lowest errors, and site factors, K and m were proposed for preliminary open-pit blasting designs.

During tunnel construction, the ground properties, initially evaluated, are continuously assessed and verified through back analysis. This procedure generally requires many numerical analyses, so a metamodel based on artificial neural networks has been used to reduce the number of analyses. More datasets can be used to create more reliable metamodels. However, there are no established rules regarding the optimum number of datasets for a reliable metamodel. Metamodels predicting the vertical displacement of the tunnel crown using five ground parameters (unit weight (γ), uniaxial compressive strength (UCS), material constant m_i, geological strength index (GSI), and coefficient of lateral pressure (K)), with 3, 4, 6, 8, and 10 values per property, were created to confirm the reliability of the metamodel based on the number of datasets in this study. Metamodels using 6 and 8 values for each property showed 5% and 1% mean absolute percent errors, respectively. These numbers of each of the properties would be appropriate for developing the metamodel. Among the five parameters, only the results of the global sensitivity analyses of GSI and K are higher than 0.9. According to these results, it is verified that assessments based only on these parameters are sufficient in the back analysis.

The multi-setting smart-investigation of the ground and pre-large hole boring method (MSP) has been widely used to secure a free face to effectively reduce the peak particle velocity (PPV) at tunnel construction. MSP generally involves drilling a 50-m borehole in the sub-horizontal direction using a 0.9-ton hammer bit at the end of MSP rod. As the borehole length increases, the hammer bit begins to vertically sag as a result of its heavy weight. If the alignment of the borehole diverges from its intended target, borehole reconstruction is inevitable, which leads to extensive time delays and extra costs. Though the borehole height is a crucial factor in determining whether reconstruction is required, there is currently no quantitative method to predict the vertical alignment of the borehole. We gathered 2,630 datasets from 13 tunnel construction sites where MSP had been applied, and developed a prediction model about the borehole height using artificial neural networks. In testing with 25% of those datasets, the mean absolute error was 0.008 m and the coefficient of determination between the measured and predicted values was 0.9998. The prediction model demonstrated good agreement with the actual measurements and can contribute to preventing unnecessary reconstruction events.