Intelligent Decision Supporting System for Precursors of Rock Instability: The Application of Early Warning of Rock Shear-Slip Instability

Abstract

Underground mining is developing towards deep and large scales; the safety production situation of mining becomes more and more severe. The difficulty of early warning of rock mass instability has increased sharply. The rock shear-slip test is carried out first, crack propagation features are investigated. Based on the idea of “the integrated development of deep learning technology and mine rock mass monitoring,” an intelligent decision-making platform (IDMP) for the precursors of rock instability is proposed. The results show that the crack network of marble specimens under the shear-slip test is composed of dominant and secondary cracks. The intelligent identification model (IIM) of rock shear slip instability is constructed by the long short-term memory network (LSTM), with 16 kinds of acoustic emission (AE) timing parameters as the input vectors and three states of no warning [0, 0], first-level warning [1, 0], and second-level warning [1, 1] as the output ends. The instability IIM can effectively identify rock shear-slip instability and determine the early warning level, and the recognition effect is good. Finally, based on the IIM, an IDMP for rock instability precursors is constructed. IDMP consists of an early warning identification layer, an early warning analysis layer, and an early warning decision-making layer, which can make intelligent decisions on whether to give early warning and determine the level of early warning. The research results provide a new idea and method for the intelligent identification and early warning release of rock mass instability early warning information.