Trend of time sequence b value of rock burst mine based on phase space reconstruction and deep learning

Abstract

Rock burst is one of serious disasters that inhibit safe and high efficient coal mining. The realization of intelligent pre-warning of rock burst is the critical path to ensure coal mine intelligent and safe mining. As the b value is an effective monitoring indicator of rock burst, it is of great significance for a timely pre-warning of rock burst to grasp the evolution trend of b value in the process of mining. Therefore, based on the phase space reconstruction (PSR) and deep learning, a short-term forecast method for the b value of time sequence in mine exploitation is proposed. The b value of time sequence identified by CNN and denoised is extended to a high-dimensional space through phase space reconstruction technique, and then the long short-term memory (LSTM) network optimized by the genetic algorithm (GA) learns the high-dimensional data feature, which constructs the b value prediction Model (PSR−GA−LSTM). Combined with the W1123 fully mechanized mining face of the Kuangou coal mine identified rock burst mine, the b value of time sequence denoised is reconstructed using the optimized parameters of PSR. The prediction performance of different models is evaluated and the case research of the optimal prediction model is carried out. The research results show that after the b value of time sequence is processed by noise reduction technology, the learning ability of the model for the b value trend feature can be enhanced and the interference of noise to the precursory information of rock burst can be reduced. After the b value of time sequence is reconstructed in phase space and the hyperparameters of the LSTM are optimized, the prediction accuracy of the model can be significantly improved. Compared with other models, the residual fluctuation range of the PSR−GA−LSTM model is the smallest and stable within 0.005, and its root mean square error (RMSE), mean absolute error (MAE) and the mean absolute percentage error (MAPE) is 0.001 51, 0.001 33, 0.29%, which are lower than other models. After the PSR−GA−LSTM model is trained on the b value of time sequence, the predicted b value trend contains the precursory information of rock burst, which can provide b value pre-warning indicators for the occurrence of rock burst events in advance. The model has a better ability to predict the trend development of the b value of rock burst mine with uniform advance, and the method used in this paper can provide a reference for the prediction and pre-warning research on the evolution of rock burst in time.

Keywords

• rock burst
• b value
• lstm
• phase space reconstruction
• pre-warning
• deep learning