Water leakage risk monitoring method based on SVM and DS theories

Abstract

The invention discloses a water leakage risk monitoring method based on SVM and DS theories. The method comprises the steps: constructing a shield tunnel water leakage three-level risk monitoring parameter system, and obtaining real-time monitoring data; constructing and training an SVM classification model, and based on the real-time monitoring data, obtaining basic probability assignment of secondary risk monitoring parameters through the SVM classification model; performing evidence fusion on the BPA of the second-level risk monitoring parameter based on a D-S evidence theory to obtain a risk level partship degree of the second-level risk monitoring parameter; and according to the risk grade partship degree of the secondary risk monitoring parameter, obtaining a shield tunnel water leakage risk grade, and reversely calculating the corresponding risk monitoring parameter to complete shield tunnel water leakage risk monitoring. The objectivity and accuracy of tunnel water leakage riskmonitoring are effectively improved, risk control can be carried out in a targeted mode, the leakage risk is reduced, and safe operation of a subway tunnel is guaranteed.

Description

technical field [0001] The invention relates to the technical field of water leakage monitoring, in particular to a water leakage risk monitoring method based on SVM and DS theory. Background technique [0002] Due to the special structure of the shield tunnel, during the operation of the tunnel, under the influence of the tunnel itself and external use, various diseases will appear in its structure, which will lead to the risk of function reduction and threat to operational safety. The main diseases of the shield tunnel during its service include water leakage, cracks, uneven settlement, concrete cracking, misalignment, bolt failure, etc. Under the interaction of these diseases, various diseases will continue to develop, and further affect the tunnel It has a significant impact on operational safety and service life. Among these common diseases during the operation period of shield tunnels, water leakage is one of the diseases with the highest probability of occurrence and...

AI Technical Summary

Problems solved by technology

[0003] At present, the water leakage risks of tunnels in my country are mostly concentrated in highway and railway tunnels, and the existing risk monitoring methods have more qualitative components, rely more on expert experience, are highly subjective, and have inaccurate monitoring data. The evidence obtained by the sensor is used for risk monitoring, resulting in low accuracy and large errors in actual risk monitoring

Images