Research On Safety Knowledge Dynamics-integrated Map And Visualization For Metro Construction

Statistical data on accident rates associated with metro construction projects indicated the high risks involved,which caused a huge loss of life and property.The circumstance,that project safety knowledge cannot be made full reuse,has restricted the improvement of metro construction safety management.How to identify the reasons why the safety knowledge cannot be made full reuse in metro construction,and how to solve the problems based on generated safety data,has become important issues in metro construction safety management.This dissertation put forward the study on safety knowledge-dynamics integrated map and visualization for metro construction,which facilitated the visualization of safety knowledge flow in the metro construction safety management;and the Non-parametric Bayesian network,position probability grid,and Copula have been adopted in this dissertation,to visualize the safety knowledge based on different types of data sources,which facilitated eliminating safety knowledge flow barriers in metro construction.First,this dissertation took the Wuhan Metro Project as the research object and constructed the safety knowledge-dynamics integrated map for metro construction,which visualized the safety knowledge flow in metro construction.Then,the knowledge flow barriers have been identified,which were knowledge characteristics barrier,the knowledge receiver barrier,the context barrier and the mechanism barrier.Second,this dissertation constructed the safety risk assessment model for metro shield tunnel construction based on expert experience,which was to eliminate the knowledge characteristics barrier.Structutered expert judement was adopted to extract the uncertainty distribution of risk factors and the product correlation coefficient between risk factors.The validity of the model has been verified by the survey data of Fuxing Road Station incident of Wuhan Metro Line 4.Finally,the safety knowledge visualization based on expert experience has been completed by the safety risk map.Third,this dissertation constructed the workers' proactive risk detection model based on the position probability grid,which was to eliminate the knowledge receiver barrier and context barrier.The knowledge receiver barrier and context barrier affected the workers' absorption of safety knowledge,which made it impossible for workers to identify their safety situations timely and effectively.This dissertation modeled the workers' movement by the position probability grid,realized the proactive risk assessment and intelligent early warning based on the workers' next location prediction.The safety knowledge visualization based on spatial data was completed by the gray-scale risk map.Finally,this dissertation constructed the D-vine Copula model based on the near-miss time series,which revealed the time autocorrelation behind the safety data.It eliminated the safety knowledge flow mechanism barrier caused by the non-disclosure of safety data,and completed the safety knowledge visualization based on time data with the safety risk map along the number of near-misses each month.This dissertation constructed the safety knowledge-dynamics integrated map of metro construction,the safety risk assesstment model for metro shield construction,the proactive risk detection model for metro construction workers and the D-vine Copula model of near-miss time series.The visualization of safety knowledge flow and safety knowledge based on different types of data sources has been realized,which promoted the reuse of safety knowledge in metro construction.The validity of the models has been verified by practical engineering cases,which is of great significance for improving the metro construction safety management.