Safety Evaluation System Of Yinluan Tunnel

Safety monitoring of the engineering structure is one of the most important methods for finding the abnormality or potential failure during the service of the structure, so that repair work or emergence action can be carried out in time to ensure the safety of the structure. It is also a way to let us know what happens in the structure, under the different load case, so we can have a better understanding of the structure thus improve the design method and operation of the structure. With the development of sensor, computer, network, and communication, it's possible now to build up an on-line monitoring system to obtain the information such as the loads and deformation reliably. That information are relate with the health of the structure, if the monitoring instruments are installed in the right place. However, the safety of the structure cannot be evaluated currently in the forms of the on-line, due to the way of using the information obtained by the monitoring system. Thus the evaluation of the safety of the structure, based on the monitoring information, is a bottleneck of the development of the monitoring system. In this thesis, an on-line safety evaluation system for the Yinluan Tunnel, a water divert tunnel with 19 years in service, is studied based on a new on-line monitoring system which is now in construction. Existing monitoring data obtained before 1990 are investigated first. Results shows that reinforced concrete liner of the tunnel is mainly affected by the temperature and the permeate water pressure between the liner and surrounding rock, and the effect of rock pressure is much smaller. Analysis of tunnel in different permeate water pressure shows that the concretive rock surrounded the reinforced concrete liner has a great contribution the permeate water pressure. Thus, the surrounding rock, together with the concrete liner, should be considered in safety evaluation of the tunnel.Neural network has good nonlinear mapping ability and can be used to simulate the nonlinear relationship of tunnel load and effect, the reaction of the liner to the load. In this thesis, a neural network model is built to evaluate tunnel safety and isvalidated by existing monitoring data. The error of neural network model is equivalent the error of monitoring instrument, the result shows that it's reasonable to build tunnel monitoring model with neural network.Deformation is the most direct reaction of the tunnel, when mechanical state of tunnel is changed. It can be used as a major parameter in tunnel safety evaluation. In this thesis, according to the mechanical characteristic of tunnel, monitoring indices of Yinluan tunnel deformation are determined via FEM analysis in order to carry out the on-line safety evaluation.