Experimental study on rapid prediction of rock mechanical parameters based on vibration signals of raw rock with drilling

In order to reveal the response relationship between the vibration signal with drilling and the uniaxial compressive strength（UCS） of rock, and to realize the rapid sensory prediction of UCS, a hybrid genetic algorithm optimization (GA-BP) artificial neural network rapid prediction method of UCS is proposed based on the vibration signal with drilling. Fourier transform and mathematical operations are used to extract the eigenvalues of the vibration signals of granite, limestone, shale, sandstone and coal in the time and frequency domains, to construct different neural network prediction models and to analyze and compare the prediction performance of each model. The results of the study show that the coefficient of determination R2 of the GA-BP neural network model optimized by the genetic algorithm for the training set is 0.778, which is improved by 9.4% compared with the BP neural network model. The model constructed in this paper has a good prediction ability for UCS, and the method used provides a new technological path for the development of intelligent and automated techniques for rapid acquisition of rock mechanical parameters.