Reliability Analysis Of Existing Maronry Structural Buildings Above Goafs

With the inconsistent layout between rapid development of coal production and the expanding of many mining area cities, coal mining under buildings has been caused. Considerable exploitation of mineral resource has engendered massive mining subsidence areas. And lots of buildings above mining subsidence areas have been impacted negatively. It is necessary for engineering construction and sustainable development of coal industry to evaluate the reliability of existing buildings above goafs.A high amount of time is spent on the reliability evaluation of buildings above goafs for its complex and multidisciplinary influencing factors. Consequently how to evaluate the required buildings rapidly and exactly is an important theme. Reliability evaluation of existing structures is shown from the angle of artificial neural network. The influencing factors and deformation characteristics of buildings above goafs are summarized based on the code of coal pillar design and pressed coal mining for buildings, water-bodies, railroads and main mine roadway. The model of neural network is build to solve the problems about complex influencing factors and long evaluating time of building evaluation. BP network model compared with traditional way has strong practicability and extension value.The basic theory of artificial neural network and a summary about its application in civil engineering are given. And the application of neural network on some actual problems in civil engineering is shown. It is detailed to analyze the factors affecting district building reliability. The deformation characteristics are summarized according to the influences of ground deformation on buildings.For the complex influencing factors and long evaluating time of building evaluation, BP neural network model is founded which has better nonlinear mapping capability with matlab and existent evaluating cases of buildings.At last, neural network evaluating model is demonstrated in a case study. And the evaluation results are in accord with ones by traditional method. A comparative result indicates that the BP network model has strong practicability and comprehensive extension value.