<<
[an error occurred while processing this directive] | [an error occurred while processing this directive] >>
基于属性识别理论的隧道施工超前地质预报可靠性分析
（1海军工程设计研究院，北京100070；2解放军理工大学国防工程学院，南京210007）
Analysis of the Reliability of Advanced Geological Prediction during TunnelConstruction Based on the Attribute Recognition Theory
(1 The Navy Engineering Design and Research Academy, Beijing 100070; 2 College of Defense Engineering, PLA University of Science & Technology, Nanjing 210007)
Abstract：
Advanced geological prediction is an important technical measure that foresees unfavorable geological conditions in front of the working face and reduces the risk associated with construction. In order to ensure the accuracy and reliability of predicted geological information, an assessment model based on attribute recognition theory is developed for assessing the reliability of advanced geological prediction in tunnels. Considering the influential factors for prediction reliability, and with respect to the scheme, technician, equipment, environment and management,etc., the number of prediction methods, the career time of technicians, the maintenance frequency of the equipment,the number of people and equipment that have nothing to do with prediction, and the rationality of prediction management is selected as the assessment index, a qualitative and quantitative analysis of the indexes are conducted,and the classification criteria for the indexes is determined. The index weight is calculated by integrating a simple correlation function. The assessment indexes acquired by site investigation and the attribute measure function are used to calculate a single index attribute measure and comprehensive attribute measure of the predicted tunnel section, and the reliability of the advanced geological prediction results is assessed by the confidence criterion. The practical case shows the attribute assessment results are consistent with the actual situation.
.Analysis of the Reliability of Advanced Geological Prediction during TunnelConstruction Based on the Attribute Recognition Theory[J] MODERN TUNNELLING TECHNOLOGY, 2017,V54(4): 48-55
2017, Vol. 54 