[1]丁小彬,谢宇轩,薛皓文,等.基于神经网络算法的滚刀磨损量预测方法[J].郑州大学学报(工学版),2023,44(01):83-88.[doi:10.13705/j.issn.1671-6833.2022.04.009]
　Ding Xiaobin,Xie Yuxuan,Xue Haowen,et al.A method for disc cutter wear ba＜x＞sed on artificial neural network[J].Journal of Zhengzhou University (Engineering Science),2023,44(01):83-88.[doi:10.13705/j.issn.1671-6833.2022.04.009]
点击复制

基于神经网络算法的滚刀磨损量预测方法()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
44卷
期数:
2023年01期
页码:
83-88
栏目:
出版日期:
2022-12-06

文章信息/Info

Title:
A method for disc cutter wear ba＜x＞sed on artificial neural network
作者:
丁小彬1; 2;  谢宇轩1;  薛皓文1;  李世佳3
1. 华南理工大学 土木与交通学院,广东 广州 510640; 2. 华南理工大学 华南岩土工程研究院,广东 广州 510640; 3. 广州轨道交通建设监理有限公司,广东 广州 510010
Author(s):
South China University of Technology Civil Engineering and Transportation, Guangzhou 510640, South China University of Technology South China Rock and Land Engineering Research Institute, Guangzhou 510640, South China University of Technology Civil Engineering and Transportation, Guangdong Guangzhou 510640, Guangzhou Rail Transit Construction Supervision Co., Ltd.
关键词:
Keywords:
分类号:
TU94
DOI:
10.13705/j.issn.1671-6833.2022.04.009
文献标志码:
A
摘要:
为了给盾构施工开仓换刀提供参考，本文将滚刀磨损简化为多元非线性拟合问题，构建了数据分析框架，综合考虑机械、地质、管理三大类因素，对滚刀磨损量进行预测。以广州地铁18号线番禺广场到南村万博站区间盾构区间为工程背景，选取共14种参数，结合公式获得标定后数据共2386条，包含34把正面滚刀，共81次滚刀磨损量。通过SMBO方法和LM算法改进BPNN算法训练过程，充分发挥神经网络优势，所得模型对83.3%的测试样本的预测值决定系数(R2)高于0.86，相比标记样本时参考的公式，准确度有较大提高，表明该方法所训练模型对滚刀磨损量的发展趋势预测更加准确。
Abstract:
To provide a reference for manual cutter inspection in shield tunneling, our study simplifies the wear of disc cutters as a multivariate nonlinear regression problem and construct a data analysis fr＜x＞amework to predict the cutter wear quantitatively by combining the effect of three kinds of factors, which are machinery, geology, and management. Taking the shield tunnel section from Panyu Square to Nancun Wanbo station of Guangzhou Metro Line 18 as the engineering background, we select 4 parameters and obtained 2386 labeled data derived from 34 face cutters and 81 manual inspections. SMBO method. We expedite the training of BPNN with the LM algorithm, which fully exploits the regression ability of the neural network. The prediction got coefficients of determination (R2) over 0.86 for 83.3% of the test samples, and the accuracy was greatly improved compared with the reference formula used for data labeling. It shows that the model trained by this method has higher accuracy in the prediction of disc cutter wear.

参考文献/References:

[1] 张银霞, 江志强, 段留洋, 等. TBM 盘形滚刀破岩过 程的数值研究 [ J] . 郑 州 大 学 学 报 ( 工 学 版) , 2016, 37(1) : 75-78.

 ZHANG Y X, JIANG Z Q, DUAN L Y, et al. Numerical research on rock fragmentation process of TBM disc cutter [ J] . Journal of Zhengzhou university ( engineering science) , 2016, 37(1) : 75-78.
 [2] 王永喜. 复合地层中盾构机刀具磨损原因分析及更换 案例 [ J ] . 建 设 机 械 技 术 与 管 理, 2011, 24 ( 3 ) : 79-82.
 WANG Y X. Why are tools worn down and how to replace them while a shield machine operates in complex formation[ J] . Construction machinery technology & management, 2011, 24(3) : 79-82. 
[3] 杨育. 厦门轨道交通 3 号线跨海段盾构滚刀磨损预测 [J]. 隧道建设(中英文), 2018, 38(增刊 1): 182-187. 
YANG Y. Prediction of disc cutter wear of shield used in sea-crossing section on Xiamen rail transit line No. 3[ J] . Tunnel construction, 2018, 38( S1) : 182-187.
[4] 管会生, 高波. 盾构切削刀具寿命的计算[ J] . 工程 机械, 2006, 37(1) : 25-28. 
GUAN H S, GAO B. Calculation for service life of cutting tools of shields [ J] . Construction machinery and equipment, 2006, 37(1) : 25-28.
[5] 杨延栋, 陈馈, 李凤远, 等. 盘形滚刀磨损预测模型 [ J] . 煤炭学报, 2015, 40(6) : 1290-1296. 
YANG Y D, CHEN K, LI F Y, et al. Wear prediction model of disc cutter [ J] . Journal of China coal society, 2015, 40(6) : 1290-1296.
[6] 赵青, 段景川, 杨涛, 等. 风化花岗岩地层的盾构滚 刀磨损预测研究[ J] . 路基工程, 2016(2) : 94-98. ZHAO Q, DUAN J C, YANG T, et al. Research on service life prediction after abrasion of shield hob in weathered granite formation [ J] . Subgrade engineering, 2016(2) : 94-98. 
[7] 翟淑芳, 曹世豪, 冯永, 等. 断续节理岩体的 TBM 滚 刀破岩机理研究[ J] . 郑州大学学报( 工学版) , 2020, 41(1) : 20-24. 
ZHAI S F, CAO S H, FENG Y, et al. The influence of intermittent joint on rock fragmentation by TBM cutter [ J] . Journal of Zhengzhou university ( engineering science) , 2020, 41(1) : 20-24. 
[8] 李笑, 苏小江. 基于 Elman 神经网络的盾构滚刀磨损 预测方法研究[ J] . 辽宁工程技术大学学报( 自然科 学版) , 2010, 29(6) : 1121-1124. 
LI X, SU X J. A new method for forecasting shield′ s disc-cutters wearing based on Elman neural network[ J] . Journal of Liaoning technical university ( natural science) , 2010, 29(6) : 1121-1124. 
[9] 陈子义. 基于正交试验的盾构滚刀磨损分析[ D] . 郑 州: 华北水利水电大学, 2018. 
CHEN Z Y. Analysis of hob wearing of the shield′s based on orthogonal experiment [ D] . Zhengzhou: North China University of Water Resources and Electric Power, 2018. 
[10] 曾锋, 苏华友, 宋天田. 复合地层中盾构机滚刀寿命 预测研究[ J] . 地下空间与工程学报, 2016, 12( 增刊 2) : 755-759. ZENG F, SU H Y, SONG T T. Research on service life prediction for disc cutters of shield machines in complex ground[ J ] . Chinese journal of underground space and engineering, 2016, 12( S2) : 755-759. 
[11] 张伟森. 上软下硬地层盾构机滚刀磨损特性研究[ J] . 地下空间与工程学报, 2019, 15(2) : 583-588. ZHANG W S. Characteristics of disc cutter failures in mixed-face ground condition[ J] . Chinese journal of underground space and engineering, 2019, 15 ( 2 ) : 583-588. 
[12] 陈流豪. 神经网络 BP 算法研究综述[ J] . 电脑知识与 技术, 2010, 6(36) : 10364-10365. CHEN L H. Studying and summarizing of BP neural network[ J] . Computer knowledge and technology, 2010, 6 (36) : 10364-10365.
[13] 尤晓东, 苏崇宇, 汪毓铎. BP 神经网络算法改进综述 [ J] . 民营科技, 2018(4) : 146-147. YOU X D, SU C Y, WANG Y D. Review of BP neural network algorithm improvement [ J] . Private technology, 2018(4) : 146-147. 
[14] 蔡婉贞, 黄翰. 基于 BP-RBF 神经网络的组合模型预 测港口物流需求研究[ J] . 郑州大学学报( 工学版) , 2019, 40(5) : 85-91. 
CAI W Z, HUANG H. A model based on the combination of BP and RBF neural network for port logistic demand forecasting[ J] . Journal of Zhengzhou university ( engineering science) , 2019, 40(5) : 85-91.
[15] 乔金丽, 孟秋杰, 刘建琴, 等. 基于遗传规划的复杂 地层中 盾 构 滚 刀 磨 损 寿 命 预 测 [ J ] . 工 矿 自 动 化, 2018, 44(9) : 51-58. 
QIAO J L, MENG Q J, LIU J Q, et al. Prediction of wear life of shield disc cutter in complex formations based on genetic programming [ J] . Industry and mine automation, 2018, 44(9) : 51-58.
[16] ELBAZ K, SHEN S L, ZHOU A N, et al. Prediction of disc cutter life during shield tunneling with AI via the incorporation of a genetic algorithm into a GMDH-type neural network[ J] . Engineering, 2021, 7(2) : 238-251. 
[17] QIN C, KLABJAN D, RUSSO D. Improving the expected improvement algorithm[EB / OL]. (2017-05-29) [ 2021- 11-03]. https: / / arxiv. org / abs/ 1705. 10033. 
[18] 赵海鸣, 舒标, 夏毅敏, 等. 基于磨料磨损的 TBM 滚 刀磨损预测研究[ J] . 铁道科学与工程学报, 2014, 11 (4) : 152-158. 
ZHAO H M, SHU B, XIA Y M, et al. Study of wear prediction for TBM cutter based on abrasive wear mo-del [ J] . Journal of railway science and engineering, 2014, 11(4) : 152-158.

更新日期/Last Update: 2022-12-07