Rockburst Intensity Level Prediction Method Based on FA-SSA-PNN Model

To accurately and reliably predict the occurrence of rockburst disasters, a intensity level prediction model based on FA-SSA-PNN is proposed. Crding to internal external factors occurrence, six influencing (σθ, σt, σc, σc/σt, σθ/σc, Wet) were selected build index system. Seventy-five sets typical case data at home abroad collected, original preprocessed factor analysis (FA), comprehensive indexes, CPI1, CPI2, CPI3, obtained after dimensionality reduction, used as input features SSA-PNN model. Sixty extracted training set, remaining 15 test set. After was completed, results analysed evaluated. The research show that proposed method has advantages high accuracy fast convergence, which can in short period time be new for prediction, providing better guidance problems deep rock projects.