Abstract: The shield tunneling parameters is mainly set according to the experience of shield drivers, but the effective correlation of tunneling parameters and geological parameters is difficult to be achieved due to various factors affecting tunneling process. Hence, related tunneling and geology parameters are selected and classified through construction experience based on the massive data of TBM big data platform, and the range of related parameters is determined. The primary data cleaning is carried out by means of parameter range definition, data continuity analysis and data frequency statistics; by extracting the digital characteristics of variables to establish the distribution statistical algorithm model database, the data in the database are processed in real time, the abnormal data is removed and the frequency distribution of the experience interval is determined; through the combination retrieval of related parameters and the visual analysis of the related parameters, the empirical interval and the related relationship of the main driving parameters (i.e. cutter speed, cutter torque, driving speed, cylinder thrust, etc.) of different shield machines in various geological conditions are obtained. The association analysis method is deployed in the big data platform of shield TBM. After a long time of application and onsite feedback, the applicability and effectiveness of the method are verified, which has a positive guiding effect for shield construction and shield machine selection.

Key words: shield machine, shield tunneling parameters, geology, association analysis, big data