A Field-Calibrated Physics-Informed Digital Twin Framework for Production Blasting Using Dynamic Finite Element Modeling and Seismic Source Reconstruction

Blast-induced ground vibration is traditionally predicted using empirical scaled-distance equations or numerical simulations driven by simplified analytical loading functions. Although dynamic finite element modeling has significantly advanced the understanding of stress-wave propagation, existing approaches remain unable to reproduce the complete seismic response of actual production blasting because the true blast source is generally unknown and is therefore replaced by simplified pressure–time functions. Consequently, a field-calibrated physics-informed Digital Twin framework for production blasting remains insufficiently established. This study presents a PI-DDT framework for production blasting based on field-derived seismic source reconstruction. The proposed methodology consists of two complementary innovations. First, the three-component near-field pilot-blast record was analyzed through deconvolution-based inverse wave propagation, and the transverse, longitudinal, and vertical components were independently deconvolved to reconstruct three orthogonal equivalent single-hole seismic source histories at the pilot blast hole. Second, the three reconstructed source histories were incorporated into the PLAXIS 3D dynamic finite element model through component-specific dynamic multiplier functions together with the actual production-blast geometry, blast-hole coordinates, electronic initiation sequence, site-specific rock-mass properties, and attenuation characteristics to establish a field-calibrated PI-DDT framework for a full-scale production blast. The proposed framework was applied to a full-scale production blast comprising 83 blast holes in an operating open-pit mine. Model performance was evaluated through a multi-domain performance assessment including PPV, amplitude-envelope development, frequency-spectrum agreement, and cumulative-energy evolution. The simulated responses showed practically meaningful agreement with field measurements across multiple monitoring locations, with a median component PPV error of 11.8%, a mean three-dimensional resultant PPV error of 14.2%, a mean resultant spectral similarity of 84.0%, and a mean three-dimensional cumulative-energy MAE of 4.7%. Unlike conventional blasting simulations that rely on simplified analytical loading functions, the proposed methodology reconstructs a field-derived equivalent seismic source signature and integrates it directly into a physics-based numerical model. The principal scientific contribution of the study lies in the field-calibrated integration of equivalent seismic source reconstruction, actual production-blast geometry and initiation timing, three-dimensional dynamic FEM, and multi-domain model-performance evaluation within a unified physics-informed framework. The developed framework provides a physics-based computational foundation for blast-design evaluation, vibration-control planning, digital mining applications, and future AI-assisted blast-design optimization and adaptive vibration-control workflows.