基于t-SNE数据驱动模型的盾构装备刀盘健康评估

doi:10.3901/JME.2019.07.019

机械工程学报 ›› 2019, Vol. 55 ›› Issue (7): 19-26.doi: 10.3901/JME.2019.07.019

• 基于深度学习的机械装备故障预测与健康管理 • 上一篇下一篇

基于t-SNE数据驱动模型的盾构装备刀盘健康评估

张康¹, 黄亦翔¹, 赵帅¹, 刘成良¹, 王吉云²

1. 上海交通大学机械系统与振动国家重点实验室上海 200240;
2. 上海隧道工程有限公司上海 200240

收稿日期:2018-08-02 修回日期:2018-11-05 出版日期:2019-04-05 发布日期:2019-04-05
通讯作者: 黄亦翔(通信作者),男,1980年出生,博士,助理研究员。主要研究方向为设备智能维护与健康评估。E-mail:huang.yixiang@sjtu.edu.cn
作者简介:张康,男,1997年出生。主要研究方向为设备智能维护与健康评估。E-mail:kangzhang@sjtu.edu.cn
基金资助:
国家重点研发计划（2017YFB1302004）和国家自然科学基金（51305258）资助项目。

Health Assessment of Shield Equipment Cutterhead Based on t-SNE Data-driven Model

ZHANG Kang¹, HUANG Yixiang¹, ZHAO Shuai¹, LIU Chengliang¹, WANG Jiyun²

1. State Key Laboratory of Mechanical System and Vibration, Shanghai Jiao Tong University, Shanghai 200240;
2. Shanghai Tunnel Engineering Co., Ltd, Shanghai 200240

Received:2018-08-02 Revised:2018-11-05 Online:2019-04-05 Published:2019-04-05

摘要/Abstract

摘要： 随着地铁等地下工程在各大城市的快速发展，盾构装备的健康维护备受关注。刀盘作为盾构装备的主要功能部件之一，其易于损耗但却不易被直接检测，并可直接影响盾构推进效率和工期的按时完成。基于刀盘机理模型的传统分析方法受限于实际工程复杂工况与盾构机复杂结构，难以进行准确评估。为此，提出一种基于数据驱动的盾构机刀盘健康评估方法，即通过t-分布随机邻域嵌入（t-distribution stochastic neighbor embedding，t-SNE）模型，建立盾构装备传感器数据在特征空间与刀盘健康状态的映射关系，从而对刀盘性能衰退进行量化评估。其方法主要步骤包括：①刀盘性能相关传感数据预处理与初步特征提取；②在特征空间进行内蕴流形分布分析，基于t-SNE模型降维得到低维优化特征；③在优化后的特征空间构造马氏距离度量，得到刀盘性能衰退的量化评估。通过在实际盾构掘进工程中验证，结果表明：基于盾构装备实际运行数据，该方法能准确地反映刀盘性能状态。

关键词: t-分布随机邻域嵌入, 盾构装备, 健康评估, 马氏距离

Abstract: With the rapid development of underground projects such as subway construction in the major cities, much attention has been paid to the health maintenance of the shield equipment. As one of the key components of the shield machine, the cutterhead is easy to wear out, but difficult to be measured directly, and may significantly affect the efficiency and delay the project of shield tunneling. The traditional analysis methods based on the cutter mechanism models usually have poor performance due to various practical engineering conditions and complicated structures of the shield machine system, which makes it difficult to accurately evaluate its health status. In this paper, a data-driven method for evaluating the health of the shield machine cutterhead is proposed, which tries to model the relationships between the sensor data of the shield machine and the health state of the cutterhead, and to quantify the degradation of the cutterheader's performance by using the t-SNE (t-distribution stochastic neighbor embedding) model. The main steps of the proposed method include:① the sensor data pre-processing and initial feature extraction; ② the analysis of the intrinsic manifold distribution in the feature space, and the optimization of the low dimensional feature space obtained by the t-SNE model; ③ a Mahalanobis distance-based metric is designed to quantify the performance degradation of the cutterhead in the optimized feature space. The results have shown that the proposed method can accurately evaluate the performance of the cutterhead based on the actual operation data of the shield equipment.

Key words: health evaluation, Mahalanobis distance, shield equipment, t-distribution stochastic neighbor embedding

中图分类号:

U455

张康, 黄亦翔, 赵帅, 刘成良, 王吉云. 基于t-SNE数据驱动模型的盾构装备刀盘健康评估[J]. 机械工程学报, 2019, 55(7): 19-26.

ZHANG Kang, HUANG Yixiang, ZHAO Shuai, LIU Chengliang, WANG Jiyun. Health Assessment of Shield Equipment Cutterhead Based on t-SNE Data-driven Model[J]. Journal of Mechanical Engineering, 2019, 55(7): 19-26.

参考文献

[1] WANG L, KANG Y, ZHAO X, et al. Disc cutter wear prediction for a hard rock TBM cutter head based on energy analysis[J]. Tunnelling & Underground Space Technology Incorporating Trenchless Technology Research, 2015, 50:324-333.
[2] ROSTAMI J. Hard rock TBM cutter head modeling for design and performance prediction[J]. Geomechanik Und Tunnelbau, 2010, 1(1):18-28.
[3] HASSANPOUR J, ROSTAMI J, ZHAO J, et al. TBM performance and disc cutter wear prediction based on ten years experience of TBM tunnelling in Iran[J]. Geomechanik Und Tunnelbau, 2015, 8(3):239-247.
[4] LIU Q, LIU J, PAN Y, et al. A wear rule and cutter life prediction model of a 20-in. TBM cutter for granite:A case study of a water conveyance tunnel in China[J]. Rock Mechanics & Rock Engineering, 2017, 50:1-18.
[5] 齐梦学,王雁军,李宏亮. 敞开式掘进机全面整修技术研究与应用[J]. 现代隧道技术, 2009, 46(4):64-70. QI Mengxue, WANG Yangjun, LI Hongliang. Research and application of overall refit of open type TBM[J]. Modern Tunnelling Technology, 2009, 46(4):64-70.
[6] SUN W, ZHU Y, WANG W Z, et al. Evaluation of TBM cutter head vibration under complicated condition[C]//Ieee/asme International Conference on Mechatronic and Embedded Systems and Applications, IEEE, 2016:1-6.
[7] ZHU X H, XIA Y M, OUYANG T, et al. Distribution law of excavating load of TBM disc cutter and cutter head[J]. Applied Mechanics & Materials, 2014, 615:22-26.
[8] WANG L, LI H, ZHAO X, et al. Development of a prediction model for the wear evolution of disc cutters on rock TBM cutter head[J]. Tunnelling & Underground Space Technology, 2017, 67:147-157.
[9] LI G, ZHU L D, YANG J Y, et al. A method to predict disc cutter specific energy for TBM based on CSM model[J]. Applied Mechanics & Materials, 2012, 236-237(12):414-417.
[10] WU L, YANG F, WANG J, et al. 3D discrete element model for TBM cutter breaking rock and dynamic loads analysis[C]//International Conference on Discrete Element Methods, Springer, Singapore, 2016:927-934.
[11] 凌静秀,孙伟,杨晓静,等. 复杂应力状态下TBM刀盘裂纹应力强度因子分析[J]. 哈尔滨工程大学学报, 2017, 38(4):633-639. LING Jingxiu, SUN Wei, YANG Xiaojing, et al. Analysis of stress intensity factors for a TBM cutterhead crack incomplex stress states[J]. Journal of Harbin Engineering University, 2017, 38(4):633-639.
[12] 孙伟,朱晔,霍军周,等. 基于裂纹失效区域划分的TBM刀盘裂纹位置预估及分析[J]. 机械工程学报, 2018, 54(1):27-35. SUN Wei, ZHU Ye, HUO Junzhou, et al. Predict and analysis the loactions of fatigue crack in TBM cutterhead based on crack failure regions division[J]. Journal of Mechanical Engineering, 2018, 54(1):27-35.
[13] 程永亮,钟掘,暨智勇,等. TBM刀盘地质适应性设计方法及其应用[J]. 机械工程学报, 2018, 54(1):1-9. CHENG Yongliang, ZHONG Jue, JI Zhiyong, et al. Geological adaptaive design method and application of TBM cutterhead[J]. Journal of Mechanical Engineering, 2018, 54(1):1-9.
[14] 夏毅敏,卞章括,胡承欢,等. 复合式土压平衡盾构机刀盘性能综合评价方法[J]. 机械工程学报, 2014, 50(21):1-9. XIA Yimin, BIAN Zhangkuo, HU Chenghuan, et al. Performance comprehensive evaluation of composite earth pressure balanced shield machine cutter head[J]. Journal of Mechanical Engineering, 2014, 50(21):1-9.
[15] SUN Wei, SHI Maolin, ZHANG Chao, et al. Dynamic load prediction of tunnel boring machine(TBM) based on heterogeneous in-situ data[J]. Automation in Construction, 2018, 92:23-34.
[16] MAATEN L V D, HINTON G. Visualizing Data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9(2605):2579-2605.
[17] MAESSCHALCK R D, JOUAN-RIMBAUD D, MASSART D L. The Mahalanobis distance[J]. Chemometrics & Intelligent Laboratory Systems, 2000, 50(1):1-18.
[18] 赵帅,黄亦翔,王浩任,等. 基于拉普拉斯特征马氏距离的滚珠丝杠健康评估[J]. 机械工程学报, 2017, 53(15):125-130. ZHAO Shuai, HUANG Yixiang, WANG Haoren, et al. Laplacian Eigenmaps and Mahalanobis distance based health assessment methodology for ball screw[J]. Journal of Mechanical Engineering, 2017, 53(15):125-130.
[19] JIA Xiaodong, JIN Chao, BUZZA M, et al. A deviation based assessment methodology for multiple machine health patterns classification and fault detection[J]. Mechanical Systems and Signal Processing, 2018, 99:244-261.
[20] 褚东升. 长沙地铁下穿湘江土压平衡盾构隧道掘进参数研究[D]. 长沙:中南大学, 2012. CHU Dongsheng. Study on the tunneling parameters of Changsha metro's earth pressure balanced shield tunneling under the Xiangjiang River[D]. Changsha:Central South University, 2012.

基于t-SNE数据驱动模型的盾构装备刀盘健康评估

Health Assessment of Shield Equipment Cutterhead Based on t-SNE Data-driven Model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	赵帅, 黄亦翔, 王浩任, 刘成良, 刘晓, 梁鑫光. 基于随机森林与主成分分析的刀具磨损评估[J]. 机械工程学报, 2017, 53(21): 181-189.
[2]	赵帅, 黄亦翔, 王浩任, 刘成良, 刘晓, 梁鑫光. 基于拉普拉斯特征马氏距离的滚珠丝杠健康评估[J]. 机械工程学报, 2017, 53(15): 125-130.