Frontiers in Earth Science (Jan 2023)
Study on critical slowdown characteristics and early warning model of damage evolution of sandstone under freeze–thaw cycles
Abstract
Freeze–thaw damage of rock mass poses a great threat to the safety of rock engineering, ground buildings, and low-temperature storage of liquefied natural gas (LNG) in cold regions. By collecting acoustic emission (AE) signals of sandstone during uniaxial compression failures, this paper analyzed the critical slowdown phenomenon of different types of sandstone during the freeze–thaw failure. According to the auto-correlation coefficients and the variance of AE signals under different windows and steps, the precursors were determined and a warning model of rock engineering failure precursors based on the critical slowdown principle was proposed. Then the Grey Wolf Optimizer (GWO) algorithm was used to optimize the initial weights and thresholds of the back propagation (BP) neural network, and the influence factors of rock engineering failure under different working conditions were input as training sets to train the network. The results showed that the correlation coefficients between the predicted value and real value of the GWO-BP neural network reached 99.90% and 98.81% respectively, indicating that the accuracy of the BP neural network prediction was improved. This study provides a new method for rock engineering failure early warning, and has great theoretical and guiding significance for enriching and improving the rock mass AE monitoring technology.
Keywords
