摘要
针对全断面隧道掘进机(TBM)施工过程中刀具过度磨损或异常磨损的识别问题,在分析TBM掘进效率影响因素和进行掘进状况无监督模式识别的基础上,利用现场掘进数据,得到场切深指数fFPI和切割系数C在不同掘进状况下的相互影响规律,据此提出以两者作为TBM刀具异常磨损的二维特征识别参量,确定了此空间中的刀具异常磨损决策阈值。TBM刀具磨损的预测和异常磨损识别方法的确定,对于保障TBM的安全掘进以及提高其利用率和经济性具有重要意义。
In order to decrease the cutter consume and the time loss of machine standing, to enhance the utilization of TBM, the abnormal cutter wear of TBM needs to be recognized in time. The factors which affect the boring efficiency had been analyzed based on the results of boring performance unsupervised pattern recognition(the data are from Qingling tunnel boring on site), and then the interactive rules between field penetration index fFPI and cutting coefficient C with different boring performances has been obtained, consequently the fFPI and cutting coefficient C were selected as the recognizing features. Finally,the criterion of abnormal cutter wear in the fFPI-C space is gained. The results show this way can solve the problem effectively .
出处
《中国机械工程》
EI
CAS
CSCD
北大核心
2007年第2期150-153,共4页
China Mechanical Engineering