Open Access Open Access  Restricted Access Subscription or Fee Access

An Abnormal Detection Analysis for Shield Tunnel SHM Based on Fuzzy Cluster Method

F. ZHOU, W. ZHANG, K. SUN, B. SHI

Abstract


Shield tunnel SHM is in the path of rapid development currently while massive monitoring data processing and quantitative health grading remain a real challenge, since multiple sensors belonging to different types are employed in SHM system. This paper addressed the fuzzy cluster method based on fuzzy equivalence relationship for the health evaluation of shield tunnel SHM. The method was optimized by exporting the FSV map to automatically generate the threshold value. Two abnormal monitoring data conditions were defined and a pilot test was studied to demonstrate the effectiveness of the definition. A case study on Nanjing Yangtze River Tunnel was presented to apply this method. Three types of indicators, namely soil pressure, pore pressure and steel strain, were used to develop the evaluation set U. The clustering results were verified by analyzing the engineering geological conditions; the applicability and validity of the proposed method was also demonstrated. This investigation indicated the fuzzy cluster method and HHS is capable of characterizing the fuzziness of tunnel health, and it is beneficial to clarify the tunnel health evaluation uncertainties.

doi: 10.12783/SHM2015/70


Full Text:

PDF