Study On Collapse Risk And Stability Evaluation In Mining Construction Of Mountain Tunnel

The identification of risk factors and risk evaluation in the risk management of underground engineering,such as tunnels,is more focused on the use of expert experience to carry out the overall and static risk classification,which can play a reference role in the experience of the project.But for less experienced engineering,this method may lead to misjudgment.Therefore,a more objective and practical approach needs to be proposed.In China,tunnel and other underground engineering construction has accumulated a large number of engineering construction cases.These cases are important resources in the current and future risk management,technical improvement.It should be studied that how to fully using these data in more practical risk identification and risk assessment.Secondly,with the progress of big data theory and technology,data mining methods have been widely used in all walks of life.The used data accumulated by tunnel construction can not only provide an effective method for more reasonable construction period forecast and investment cost estimation,but also be a risk identification,risk prediction and provide new ideas on issues such as risk evaluation.In this paper,the relevant data of existing tunnel engineering and the data of collapse accidents are collected,and the risk factors in the process of mountain tunnel construction are identified by using data mining method.Monitoring data during tunnel construction collected,the variation law and influence relationship of monitoring data are analyzed and studied.A dynamic evaluation method based on the change and correlation of measured data is proposed.Mainly complete the following related content research:(1)Using the case data of a large number of established tunnels,through data mining,identify the risk factors in the construction process of tunnels,reveal the relationship between the factors,change the identification of risk factors in the past mainly relying on the experience of experts to reduce the influence of subjective factors and improve the accuracy of risk prediction.(2)A new expert investigation is proposed with small probability intervals,expert weights,confidence index,etc.After gaining expert judgment by expert investigation,Chauvenet's criterion is first introduced in a discrepancy analysis to eliminate outlier data from the expert judgment and obtain a more reliable value.The t distribution and its confidence interval are also adopted to determine the characteristic value of the survey data as a triangular fuzzy number.A conditional probability table of the model is integrated with historical data and prior knowledge through the weight index.Sensitivity analysis is used to identify the critical factors by changing the probability distribution of each factor and observing the related changes in the risk event.The proposed method ensures the accuracy and scientific rigor of the assessment and the diagnosis of a tunnel accident.(3)Based on the optimization of the background value of the Verhulst model.combined with the Markov chain,the optimization Verhulst-MC Prediction model is proposed.The Verhulst model and Markov chain of the shift of trend item displacement and stochastic terms in the displacement are extracted and predicted respectively.More accurate predictions can be obtained by predicting their trend and randomness,respectively.Tunnel displacement monitoring,with the new monitoring data is constantly supplemented into the original data column,a variety of factors will produce new interference.So the construction of the model accuracy will be reduced to reduce the resulting error,in the model construction of the use of metabolic method.(4)Quantifying tunnel stability using the proposed combination of back analysis and the strength reduction method(SRM)is useful during construction.To feasibly and reliably obtain geotechnical parameters for the surrounding rock(which vary in different places),a real-coded genetic algorithm is used in setting the initial parameters of the neural network to improve the prediction accuracy of the parameters via back analysis by reasonably selecting the selection operator,crossover operator,and mutation operator.After obtaining the parameters,the proposed SRM,i.e.,the optimization double-strength reduction method(ODSRM),which is based on the optimization method,is used to evaluate stability.By using this method,the cohesion and friction angle have different reduction factors that are more reasonable and accurate.The combined method is verified in an application to the Yu Liao Tunnel,where it is demonstrated that the combined method can use the measured displacements to obtain the safety factor.Compared with the traditional method,the proposed back analysis method can reduce errors in the predicted performance,and unlike the SRM,the ODSRM can avoid overestimating the safety factor with the same reduction factor.(5)Combining the related functions in R language packets such as shiny,bnlean,RJava and grain,using Excel as the main data input method,the risk evaluation software of tunnel collapse is constructed.The system has four models built in,namely discrete distributed data network,Gaussian distributed data network,tunnel collapse data network and data upload network.The third model is the tunnel collapse risk evaluation model,which is based on the nodes and network structure determined by the previous related research,and the conditional probability of each node is assigned according to the existing research results,and the conditional probability calculation of Bayesian model and its nodes can be constructed directly according to the relevant data when there is enough data.