Abnormal Detection and Performance Evaluation of Main Drive Motor of Shield Tunneling Machine Cutter Head

TANG Yuxiang; TAO Jianfeng; LIU Chengliang

doi:10.7652/xjtuxb202310013

您当前的位置：

首页 >

文章列表页 >

Abnormal Detection and Performance Evaluation of Main Drive Motor of Shield Tunneling Machine Cutter Head

更新时间：2025-05-08

- Abnormal Detection and Performance Evaluation of Main Drive Motor of Shield Tunneling Machine Cutter Head
- Vol. 57, Issue 10, Pages: 132-142(2023)
- 作者机构：
  
  1. 上海交通大学机械与动力工程学院,上海,200240
  2. 上海交通大学机械系统与振动国家重点实验室,上海,200240
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202310013
  CLC： U455.3
- Online First：10 October 2023，
  
  Published：2023
- 稿件说明：
移动端阅览
TANG Yuxiang, TAO Jianfeng, LIU Chengliang. Abnormal Detection and Performance Evaluation of Main Drive Motor of Shield Tunneling Machine Cutter Head[J]. 2023, 57(10): 132-142.
DOI：

TANG Yuxiang, TAO Jianfeng, LIU Chengliang. Abnormal Detection and Performance Evaluation of Main Drive Motor of Shield Tunneling Machine Cutter Head[J]. 2023, 57(10): 132-142. DOI： 10.7652/xjtuxb202310013.

摘要

针对盾构机刀盘主驱动电机存在因高频振动和电流信号获取不易和长时间工作导致的电机异常检测准确率低和性能评估困难的问题

通过分析主驱动电机的群体特征与个体特征的相似程度

提出了一种基于多尺度循环自编码器的盾构主驱动电机异常检测和性能评估的方法。首先将正常运行时的主驱动电机原始电流数据进行异常值清洗、筛选工作阶段、归一化等预处理工作; 再根据预处理后的电流信号进行时间切片和特征提取编码

构建描述电机之间性能差距的差异性矩阵作为训练集; 然后将数据集输入多尺度循环自编码器中提取正常运行电机电流信号特征

从而实现准确地进行电机的异常检测并给出性能评估的健康指标。基于印度孟买D215工程的实际数据

对所提方法进行了验证和测试

结果表明:该方法在仅能获取到PLC数据的情况下

完成盾构主驱动电机的异常检测

准确率维持在90%以上

并能够给出一种反映主驱动电机组性能退化的健康指标。

Abstract

When it comes to the operation of the main drive motor for the shield tunneling machine cutter head

there are challenges related to low accuracy in detecting motor abnormalities and difficulties in assessing performance. These issues arise due to high-frequency vibrations

challenges in acquiring current signals

and prolonged operational durations. To address these issues

a method based on multiscale convolutional recurrent autoencoder for abnormal detection and performance evaluation of the main drive motor in a shield tunneling machine was proposed after analyzing the similarity degree of group and individual features of the main drive motor. First

the raw current data of the main drive motor during normal operation was preprocessed with outlier cleaning

filtering work segments

normalization

and so on; then the time slicing and feature extraction coding were performed based on the preprocessed current signals to construct the variance matrix describing the performance difference between motors as the training set; then the data set was input into the multiscale convolutional recurrent autoencoder to extract the features of the current signals of the motor under normal operation

thus achieving accurate motor anomaly detection and giving health indicators for performance evaluation. Based on the actual data of the D215 project in Mumbai

India

the proposed method was validated and tested

and the results show that the method is able to complete the abnormality detection of the main drive motor in a shield tunneling machine with an accuracy rate maintained above 90% and give a health indicator reflecting the performance degradation of the main drive motor.

关键词

Keywords

references

中国工程机械学会. 工程机械手册-隧道机械 [M]. 北京: 清华大学出版社, 2018.

李兴高, 袁大军, 杨全亮. 盾构施工典型故障诊断初步研究 [J]. 岩土力学, 2009, 30(Z2): 377-381.

LI Xinggao, YUAN Dajun, YANG Quanliang. Preliminary study of typical fault diagnosis in shield tunneling [J]. Rock and Soil Mechanics, 2009, 30(Z2): 377-381.

刘宣宇, 王子文, 邵诚, 等. 盾构机机械类故障诊断研究进展综述 [J]. 控制工程, 2022, 29(2): 238-245.

LIU Xuanyu, WANG Ziwen, SHAO Cheng, et al. Review on mechanical fault diagnosis of shield tunneling machine [J]. Control Engineering of China, 2022, 29(2): 238-245.

常孔磊, 赵新合, 李大伟. 盾构主驱动减速机失效原因分析 [J]. 隧道建设, 2014, 34(2): 173-177.

CHANG Konglei, ZHAO Xinhe, LI Dawei. Analysis on causes for failure of main drive reducer of shield machine [J]. Tunnel Construction, 2014, 34(2): 173-177.

CAI Baoping, HAO Keke, WANG Zhengda, et al. Data-driven early fault diagnostic methodology of permanent magnet synchronous motor [J]. Expert Systems with Applications, 2021, 177: 115000.

SUN Wenjun, SHAO Siyu, ZHAO Rui, et al. A sparse auto-encoder-based deep neural network approach for induction motor faults classification [J]. Measurement, 2016, 89: 171-178.

GANGSAR P, TIWARI R. Diagnostics of mechanical and electrical faults in induction motors using wavelet-based features of vibration and current through support vector machine algorithms for various operating conditions [J]. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2019, 41(2): 71.

GANGSAR P, TIWARI R. A support vector machine based fault diagnostics of Induction motors for practical situation of multi-sensor limited data case [J]. Measurement, 2019, 135: 694-711.

LIU Ruonan, WANG Fei, YANG Boyuan, et al. Multiscale kernel based residual convolutional neural network for motor fault diagnosis under nonstationary conditions [J]. IEEE Transactions on Industrial Informatics, 2020, 16(6): 3797-3806.

GYFTAKIS K N. A comparative investigation of interturn faults in induction motors suggesting a novel transient diagnostic method based on the Goerges phenomenon [J]. IEEE Transactions on Industry Applications,2022, 58(1): 304-313.

SAI Biaojiang, WONG P K, LIANG Yanchun. A fault diagnostic method for induction motors based on feature incremental broad learning and singular value decomposition [J]. IEEE Access, 2019, 7: 157796-157806.

SAI Biaojiang, WONG P K, GUAN Renchu, et al. An efficient fault diagnostic method for three-phase induction motors based on incremental broad learning and non-negative matrix factorization [J]. IEEE Access, 2019, 7: 17780-17790.

GLOWACZ A, GLOWACZ W, GLOWACZ Z, et al. Early fault diagnosis of bearing and stator faults of the single-phase induction motor using acoustic signals [J]. Measurement, 2018, 113: 1-9.

ASAD B, VAIMANN T, BELAHCEN A, et al. The cluster computation-based hybrid FEM-analytical model of induction motor for fault diagnostics [J]. Applied Sciences,2020, 10(21): 7572.

许伯强, 何俊驰, 孙丽玲. 基于SAE与改进LightGBM算法的笼型异步电机故障诊断方法 [J]. 电机与控制学报, 2021, 25(8): 29-36.

XU Boqiang, HE Junchi, SUN Liling. Fault detection method of cage asynchronous motor based on stacked autoencoder and improved LightGBM algorithm [J]. Electric Machines and Control, 2021, 25(8): 29-36.

李垣江, 张周磊, 李梦含, 等. 采用深度学习的永磁同步电机匝间短路故障诊断方法 [J]. 电机与控制学报, 2020, 24(9): 173-180.

LI Yuanjiang, ZHANG Zhoulei, LI Menghan, et al. Fault diagnosis of inter-turn short circuit of permanent magnet synchronous motor based on deep learning [J]. Electric Machines and Control, 2020, 24(9): 173-180.

陈勇, 梁洪, 王成栋, 等. 基于改进小波包变换和信号融合的永磁同步电机匝间短路故障检测 [J]. 电工技术学报, 2020, 35(Z1): 228-234.

CHEN Yong, LIANG Hong, WANG Chengdong, et al. Detection of stator inter-turn short-circuit fault in PMSM based on improved wavelet packet transform and signal fusion [J]. Transactions of China Electrotechnical Society, 2020, 35(Z1): 228-234.

王一棠, 庞勇, 张立勇, 等. 面向盾构机不完整数据的模糊聚类与非线性回归填补 [J/OL]. 机械工程学报: 1-10 [2022-10-10]. http://kns.cnki.net/kcms/detail/11.2187.th.20221026.1605.048.html.

WANG Yitang, PANG Yong, ZHANG Liyong, et al. Fuzzy clustering and nonlinear regression filling for incomplete data of shield machines [J/OL]. Journal of Mechanical Engineering: 1-10 [2022-10-10]. http://kns.cnki.net/kcms/detail/11.2187.th.20221026.1605.048.html.

SUN Wei, LING Jingxiu, HUO Junzhou, et al. Dynamic characteristics study with multidegree-of-freedom coupling in TBM cutterhead system based on complex factors [J]. Mathematical Problems in Engineering, 2013, 2013: 635809.

SUN Wei, MA Honghui, SONG Xueguan, et al. Modeling and dynamic analysis of cutterhead driving system in tunnel boring machine [J]. Shock and Vibration, 2017, 2017: 7156816.

郭小芳, 李锋, 宋晓宁, 等. 基于加权Euclid范数的MTS异常检测 [J]. 计算机科学, 2014, 41(5): 263-265, 295.

GUO Xiaofang, LI Feng, SONG Xiaoning, et al. Outlier detection of multivariate time series based on weighted Euclid norm [J]. Computer Science,2014, 41(5): 263-265, 295.

ZHANG Zheng, TANG Ping, DUAN Rubing. Dynamic time warping under pointwise shape context [J]. Information Sciences, 2015, 315: 88-101.

ZHU Hanhuai, HUANG Jingjing. A new method for determining the embedding dimension of financial time series based on Manhattan distance and recurrence quantification analysis [J]. Entropy, 2022, 24(9): 1298.

ZHANG Chuxu, SONG Dongjin, CHEN Yuncong, et al. A deep neural network for unsupervised anomaly detection and diagnosis in multivariate time series data [C]//Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence. Palo Alto, CA, USA: AAAI Press, 2019: 1409-1416.

SHI Xingjian, CHEN Zhourong, HAO Wang, et al. Convolutional LSTM network: a machine learning approach for precipitation nowcasting [C]//Proceedings of the 28th International Conference on Neural Information Processing Systems. Cambridge, MA, USA: MIT Press, 2015: 802-810.

刘明阳, 余宏淦, 陶建峰, 等. 基于盾构机运行参数的局部切空间排列与Xgboost融合的地质类型识别 [J]. 中南大学学报(自然科学版), 2022, 53(6): 2080-2091.

LIU Mingyang, YU Honggan, TAO Jianfeng, et al. Geological-type identification with LTSA and Xgboost algorithm based on EPB shield operating data [J]. Journal of Central South University(Science and Technology), 2022, 53(6): 2080-2091.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

On-Line Anomaly Detection Method for Network Traffic Based on Adaptive Filtering

Using Cross Entropy to Detect and Classify Network Anomalous Traffic

Performance-Evaluation-Based Meta-Task Scheduling Algorithm

A Method for Data Collection and Real-Time Anomaly Detection of Lightweight Hosts

Cavitation State Recognition of Centrifugal Pump Based on Deep Learning

Related Author

牛国林 1

郑庆华 1

颜若愚 1

郑庆华 1

胡志刚

李林

胡周君

Related Institution

School of Electronics and Information Engineering, Xi'an Jiaotong University

School of nformation Science, Guangdong Ocean University

School of Information Science, Guangdong Ocean University

School of Information Science and Engineering, Central South University

System Research Department, Wuhan Digital Engineering Institute

⁰