Research On The System Design For Advance Geological Prediction In TBM Construction Tunnel Based On Drilling Machine

The accidents of collapse, roof fall, rock burst, or gush, often occur because the geological engineering conditions in front of the face aren't clear during tunneling. Especially, to the tunnels constructed by TBM(Tunnel Boring Machine), the work for advance geological prediction is crucial to the successful construction of a project.On the basis of elaborating the characteristics of TBM construction and the methods for advance geological prediction in common use abroad and at home, integrating the geological survey, TSP(Tunnel Seismic Prediction)method, forward drilling and probing(including percussive drilling and core drilling)and acoustic sounding are brought forward to applying to practical engineering. Taking the integration of percussive drilling and core drilling as core geological prediction method, the thesis discusses detailedly the geological prediction principles of the percussive drilling and core drilling, analyzes and confirms the sensitive parameters during drilling, designs the overall structure of the advance geological prediction system in TBM construction tunnel, constructs real-time data acquisition and analyzing system of sensitive parameters during drilling, including software design and hardware design of the measurement and control system, and presents the judgement standard for switching the drilling machine.In this dissertation, the artificial neural network module of advance geological prediction system in TBM construction tunnel is also emphasized on. On the basis of fully realizing the importance of predicting the rock masses classification in front of the tunnel face, artificial neural network is used to predict the rock masses classification, and mainly discusses the preferences, stylebook collection and disposal, and how to structure BP neural network module and its optimization, and compares the effects of adding drilling speed eigenvector with not adding, thanks to BP neural network's superioriry in dealing with non-linear complicated relation. By training and check up of the stylebook, it's satisfying to predict the rock masses classification in front of the tunnel face.