Prediction of the geological indicators in TBM tunnel based on optimized proportion of surrounding rock grades

With tunnel boring machine being used in underground engineering,accurate geological indicators have been the important basis for tunnel boring machine(TBM)construction.Back propagation neural network(BPNN)has been used to predict the geological indicators of tunnels in previous studies.Nevertheless,these studies ignored the imbalance proportion of surrounding rock grades,leading to the indiscriminate use of data,thus affecting the predictive effect of BPNN.In order to prove the importance of the proportion of surround-ing rock grade in geological prediction,we mainly attempt to utilize particle swarm optimization(PSO)to optimize the proportion of sample data,and integrate with BPNN to establish a PSO-BPNN theoretical model to predict geological indicators.At the same time,combined with the actual engineering data,5 tunneling indicators were selected as input and 4 geological indicators were selected as out-put by a variety of dimensionality reduction methods.The geological indicators are density,uniaxial compressive strength,internal fric-tion angle(u)and Poisson’s ratio(e).On this basis,the PSO-BPNN prediction model was established in detail.By comparing the prediction of traditional BPNN,PSO-BPNN and other optimization-integrated models,the result shows that optimized proportion of surrounding rock grades reduces the prediction error and improves the interpretability of the prediction model.Meanwhile,we com-bined the theory of surrounding rock partition to illustrate the rationality of surrounding rock proportion in PSO result,that is,the proportion of complex surrounding rock should be increased appropriately to improve the prediction result.Ultimately,based on the optimization-integrated models with engineering data and the surrounding rock classification theory,the importance of proportion of surrounding rock grades for tunnel geological prediction is confirmed.

The Characteristics of the Hydrothermal Exhalative Dolostone of Lucaogou Formation in Santanghu basin and its Geology Setting Indication

The NW-SE trending Santanghu basin is located in Xinjiang,NW China,between Tianshan Mountains and Altai Mountains.The tectonic evolution history of north Xinjiang has long been debated,especially the question when did that area began its intraplate rift evolution stage.This abstract discusses the features and possible origin of the hydrothermal exhalative dolostone of Lucaogou Formation in Santanghu basin,aiming to provide relevant information about this question.The target dolostone are characterized by extreme thin lamina of 0.3cm–1 cm thick.Dolomite,ankerite,potassium feldspar and analcite are dominant composition.Most dolomite is poor crystallized and is in anhedral or subhedral shapes.Ankerite is generally porphyritic,few is in irregular shapes.It has to be noted that the porphyritic ankerite commonly develop zonal textures characterized by rings with various Fe O content.Potassium feldspar and analcite（<50%）are commonly observed in dolostones.Thin sections show some analcite is tetragonal trisoctahedron with harbour–like corrosion rims.Besides,few fragments of carbonatite rocks are observed in Lucaogou Formation and they perform intermittent or scattered distribution in rock layers.Previous work done by our study team showsδ13C PDB values are 4.8‰;1.4‰,6.93‰on average.Theδ18 O PDB values are between-5‰;21.1‰,-10.94‰on average.Paleosalinity calculated byδ13C andδ18 O is between 128.35 and 136.81,134.42 on average.Sr content of dolostones in study area reaches to164×10-6;37×10-6（379.1×10-6 on average）,most dolostone in target area are between 0.70457;.706194, average at 0.705360.Considering either accompanying residual tuff or residual leucite is found via electron probe,this indicates the analcite may derive form analcime phonolite.Furthermore,fragments of carbonatite rocks proves mantle-derived magmatism exist.The rapid variation ofδ18 O indicates multiple interactions of hydrothermal fluids with lake water during Lucaogou sedimentary period.87Sr/86Sr values are much lower than that of crustal silica rocks while are more close to mantle derived rocks,which indicates diagenetic hydrothermal fluid is mantle-origin.It has been reported that dolostone does not intergrow with iron-rich dolostone in study area.According to the latest X diffraction results of cores,iron-rich dolostone distributes rather locally.Given that ankerite commonly develop zonal textures characterized by various Fe O content,we confirm it is due to multiple hydrothermal fluids activities in different hydrothermal vents.There should be abundant hydrothermal vents during Lucaogou period.Deep faults and its relevant fractures built plenty paths for mantle-origin hydrothermal fluids to run up.Different vents owned various fluid properties,so did relevant sedimentation products.Hence we inclined to believe Santanghu basin was at intraplate rift evolution stage,under regional extension condition in late Carboniferous.During early-mid Permian the basin was a starved,deep lacustrine intracontinental rift basin.Accordingly,in northern Xinjiang,ocean basin may close in late Carboniferous and started continental sedimentary development in early Permian.