Full Waveform Prediction of Blasting Vibration Using Deep Learning

Blasting vibration could cause dynamic instability of rock masses within a critical steady state. To control the blasting vibration, it is necessary to understand complete response process under vibration. The Long Short-Term Memory (LSTM) technique uses blast monitoring data predict full waveform Based on LSTM, new prediction model proposed in this study. verify feasibility model, sample were constructed using well-known linear wave superposition formula. trained and predicted actual are then evaluated compared. loss function calculated discussed, which verifies method. In addition numerical research, also used for verification. parameters, such as sequence size, training algorithm, some hidden layer nodes, discussed optimized. results show that based LSTM can waveform. This study provides idea