上软下硬砂-岩复合地层盾构镶齿滚刀磨损规律及预测研究  

Research on Wear Law and Prediction of Inserted-tooth Hob of Slurry Shield in Upper-soft and Lower-hard and Rock-sandstone Composite Stratum

作　　者：徐文礼 杨志超 张炎 张建峰[4] 张雷 闵凡路[2] XU Wenli;YANG Zhichao;ZHANG Yan;ZHANG Jianfeng;ZHANG Lei;MIN Fanlu(CCCC Tunnel Engineering Co.,Ltd.,Beijing 100102,China;School of Civil Engineering and Transportation,Hohai University,Nanjing,Jiangsu 210024,China;Zaozhuang Urban and Rural Water Bureau,Zaozhuang,Shandong 277800,China;School of Mechanics and Materials,Hohai University,Nanjing,Jiangsu 211100,China)

机构地区：[1]中交隧道工程局有限公司,北京100102 [2]河海大学土木与交通学院,江苏南京210024 [3]枣庄市城乡水务局,山东枣庄277800 [4]河海大学力学与材料学院,江苏南京211100

出　　处：《施工技术(中英文)》2025年第7期129-136,共8页Construction Technology

基　　金：国家自然科学基金(52378394);中交集团重大科技项目(2022-ZJKJ-10)。

摘　　要：针对盾构机穿越岩层时滚刀磨损严重的问题,依托南京和燕路过江通道右线盾构隧道工程中砂-岩复合地层与中硬岩地层掘进实例,对镶齿滚刀磨损进行实测,分析其磨损规律,并使用BP神经网络对实测滚刀刀齿崩落情况进行拟合和预测。结果表明:砂-岩复合地层中对镶齿滚刀磨损影响最大的因素为贯入度与推进速度,而中硬岩地层中为刀盘扭矩;盾构机从砂-岩复合地层逐渐掘进至中硬岩地层过程中,镶齿滚刀刀齿崩落数量逐渐增加,刀齿缺损占比由28%增长至86%,同时滚刀偏磨现象逐渐严重。BP神经网络经过训练,可以得到均方误差较小的神经网络预测模型;模型训练数据量直接关系到BP神经网络模型预测刀齿崩落的精度,在训练数据(56组)较少的情况下,砂-岩复合地层镶齿滚刀刀齿崩落量预测误差率为45%;而训练数据(135组)较多的中硬岩地层刀齿崩落量平均预测误差率8.03%。建议在硬岩地层中掘进时,控制较小的刀盘转速以减小磨损,同时在实际预测刀具磨损时实测更多的样本训练数据,从而提高预测精度。Aiming at the problem of serious cutter wear when the shield machine passes through the rock stratum,based on the excavation examples of sand-rock composite stratum and medium-hard rock stratum in the shield tunnel project of the right line of Nanjing Heyan Road Cross-River Channel,the wear of the inserted-tooth hob is measured,its wear law is analyzed,and the BP neural network is used to fit and predict the measured cutter tooth collapse.The results indicate that the most influential factors on the wear of the inserted-tooth hob in the sand-rock composite stratum are penetration and propulsion speed,while in the medium-hard rock stratum,it is the cutterhead torque.In the process of shield machine tunneling from sand-rock composite stratum to medium-hard rock stratum,the number of cutter teeth of the inserted-tooth roller cutter gradually increases,and the proportion of cutter teeth defect increases from 28%to 86%.At the same time,the eccentric wear of the roller cutter is becoming increasingly serious.After BP neural network training,a neural network prediction model with a smaller mean square error can be obtained.The amount of model training data is directly related to the accuracy of the BP neural network model in predicting cutter tooth collapse.In the case of smaller training data(56 groups),the prediction error rate of cutter tooth collapse in sand-rock composite strata is 45%.The average prediction gap of cutter tooth collapse in medium-hard rock strata with more training data(135 groups)is 8.03%.It is recommended to control a smaller cutterhead speed to reduce wear when tunneling in hard rock formations.Meanwhile,more sample training data should be measured when the tool wear is actually predicted,thereby improving the prediction accuracy.

关 键 词：隧道 盾构 镶齿滚刀 磨损 预测 BP神经网络 

分 类 号：U459[建筑科学—桥梁与隧道工程]