AUTHOR=Guo Ying , Gu Shitan , Du Ruimin , Shen Jianbo 

TITLE=Multi-parameter comprehensive early warning of coal pillar rockburst risk based on DNN

JOURNAL=Frontiers in Earth Science

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/earth-science/articles/10.3389/feart.2023.1201946

DOI=10.3389/feart.2023.1201946

ISSN=2296-6463

ABSTRACT=This study proposes a multiparameter comprehensive early warning method for coal pillar-type rockburst risk based on the deep neural network. By utilizing preprocessed data from the surveillance of coal pillar impact hazards in the Yangcheng coal mine, this study incorporates training samples derived from three distinct coal pillar type impact hazard monitoring methodologies: microseismic monitoring, borehole cuttings analysis, and real-time stress monitoring. The data characteristics of the monitoring data are extracted, evaluated and classified, and verified by monitoring data of different working faces. The application of this method to develop the depth of a multiparameter neural network comprehensive early warning software in engineering practice shows that the depth for burst monitoring data processing can effectively improve the accuracy of early warning, compared with the traditional monitoring and early warning method, the accuracy of this method is improved by 7%~17%,and the coal pillar relieving effect to avoid the occurrence rockburst hazard of coal pillar.