In order to improve the blasting contour accuracy and surrounding rockprotection under complex geological conditions, comparative experiments of protective blasting and protective notched-coupling blasting were conducted using a digital laser dynamic caustic experimental system and polymethyl methacrylate specimens. The crack propagation mechanisms and mechanical response characteristics of the two blasting modes were systematically investigated. The results show that in the protective notched-coupling blasting, the main crack propagates stably along the preset notched direction, demonstrating effective directional control. Meanwhile, the secondary peak value of the crack-tip stress intensity factor is significantly higher than that of the single protective blasting, indicating a stronger dynamic stress concentration effect. The notched-coupling blasting not only achieves a higher overall crack propagation velocity with slower attenuation at later stages, but also exhibits greater persistence and stability. In addition, this blasting mode effectively reduces the length and number of cracks on the protected wall side, thereby providing better rock-mass protection. The study reveals that the protective notched-coupling blasting optimizes crack propagation behavior and improves the directionality and energy utilization efficiency of blasting through the combined mechanisms of notch guidance and energy re-concentration. These findings provide theoretical support and technical guidance for precision blasting design and engineering applications in deep rock masses.

Blasting crater prediction is critical for optimizing charge design and ensuring safety in engineering practice; however, traditional theoretical models suffer from idealized assumptions, numerical simulations are hindered by empirical parameter calibration and high computational cost, and physical experiments are constrained by scalability and repeatability. To address these challenges, a novel Wavelet-Augmented Physics-Informed Neural Networks (WA-PINNs) framework for accurately and efficiently predicting the diameter and volume of blasting craters induced by cylindrical charges is proposed. By leveraging Starfield's superposition method to equivalently model cylindrical charges as a series of spherical sources, a partial differential equation (PDE) system governing the tensile stress field responsible for crater formation was established. Comprehensive validation against high-fidelity numerical simulations and field experiments at Baima Iron Mine demonstrated that the WA-PINNs (Dog) achieves superior accuracy in predicting crater diameter and volume compared to conventional PINNs, with relative errors as low as 0.01 and markedly reduced training time. The results confirmed that the proposed WA-PINNs (Dog) is a robust, efficient, and physics-consistent intelligent solution for complex blasting problems, offering significant potential for real-world blasting design optimization.