Please wait a minute...
工程设计学报
Chin J Eng Design  2022, Vol. 29 Issue (3): 263-271    DOI: 10.3785/j.issn.1006-754X.2022.00.030
Design Theory and Method     
Research on data-driven fault detection method of traverse mechanism of warp knitting machine
Xu-hao CUI(),Xin-fu CHI,Yi-ze SUN()
College of Mechanical Engineering, Donghua University, Shanghai 201620, China
Download: HTML     PDF(1978KB)
Export: BibTeX | EndNote (RIS)      

Abstract  

During the operation of the warp knitting machine, its traverse mechanism may fail due to the out-of-control of traverse control system or the transmission error. In order to realize the effective fault detection for the traverse mechanism of warp knitting machine, a data-driven fault detection method was proposed by combining the combined features of vibration signals and the support vector data description (SVDD) algorithm. Firstly, the vibration signal of the traverse mechanism of warp knitting machine was collected and its time-domain features were extracted. Then, the energy proportion of the vibration signal in each frequency band was obtained by using the wavelet packet decomposition, and the feature vector was constructed by combining the time-domain features. Finally, based on the feature vector of the training samples (only containing normal samples), an independent closed minimum hypersphere was established based on the SVDD algorithm, and the state evaluation for the traverse mechanism of warp knitting machine was realized through comparing the distance from the test sample to the hypersphere center and the hypersphere radius. The fault detection results based on the proposed method were compared with the fault detection results using time-domain features and the SVDD algorithm, as well as using combined features and support vector machine (SVM). The results showed that the fault detection method combining combined features of vibration signals and SVDD algorithm had higher accuracy. The research results can provide a theoretical basis for the accurate fault detection of the traverse mechanism of warp knitting machine, and then provide certain auxiliary decision-making information for the warp knitting machine managers.

Key words： traverse mechanism of warp knitting machine      fault detection      support vector data description      wavelet packet decomposition     
Received: 23 July 2021      Published: 05 July 2022
CLC:  TH 165.3  
Corresponding Authors: Yi-ze SUN     E-mail: Xuhao_Cui@126.com;sunyz@dhu.edu.cn
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Xu-hao CUI
Xin-fu CHI
Yi-ze SUN
Cite this article:

Xu-hao CUI,Xin-fu CHI,Yi-ze SUN. Research on data-driven fault detection method of traverse mechanism of warp knitting machine. Chin J Eng Design, 2022, 29(3): 263-271.

URL:

https://www.zjujournals.com/gcsjxb/10.3785/j.issn.1006-754X.2022.00.030     OR     https://www.zjujournals.com/gcsjxb/Y2022/V29/I3/263


数据驱动的经编机横移机构故障检测方法研究

在经编机运行过程中，其横移机构可能会因横移控制系统失控或传动误差而发生故障。为实现经编机横移机构故障的有效检测，结合振动信号的组合特征和支持向量数据描述（support vector data description, SVDD）算法，提出一种由数据驱动的故障检测方法。首先，采集经编机横移机构的振动信号并提取其时域特征；然后，采用小波包分解获取振动信号在各频带上的能量占比，并结合时域特征构建特征向量。最后，基于训练样本（仅含正常样本）的特征向量，利用SVDD算法构建独立封闭的最小超球体，并通过比较测试样本到超球体球心的距离与超球体半径来实现经编机横移机构的状态评估。对基于所提出方法的故障检测结果与仅使用时域特征和SVDD算法以及使用组合特征和支持向量机（support vector machine, SVM）的故障检测结果进行对比。结果表明，结合振动信号组合特征和SVDD算法的故障检测方法的准确率更高。研究结果可为经编机横移机构故障的准确检测提供理论基础，进而为经编机管理人员提供一定的辅助决策信息。


关键词： 经编机横移机构,  故障检测,  支持向量数据描述,  小波包分解 
Fig.1 Fault detection process of traverse mechanism of warp knitting machine based on SVDD algorithm
Fig.2 Vibration signal acquisition platform for traverse mechanism of warp knitting machine
特征公式
绝对均值T1=1F∑f=1Fsf
峰值T2=maxsf
有效值T3=1F∑f=1Fsf2
峰值因子T4=T2T3
峭度指标T5=1T321F∑f=1Fsf-sˉ4
裕度因子T6=T21F∑f=1F|sf?|2
Table 1 Calculation formula of time-domain feature of vibration signal
Fig.3 Energy distribution characteristics of vibration signal of traverse mechanism of warp knitting machine
Fig.4 Optimization process of penalty parameter C and kernel parameter σ in SVDD algorithm
Fig.5 Training results of SVDD model based on combined features of vibration signals
Fig.6 Test results of SVDD model based on combined features of vibration signals
Fig.7 Training results of SVDD model based on time-domain features of vibration signals
Fig.8 Test results of SVDD model based on time-domain features of vibration signals
Fig.9 Fault detection process of traverse mechanism of warp knitting machine based on SVM algorithm
Fig.10 Test results of SVM model based on combined features of vibration signals
[1]   王庆锋，卫炳坤，刘家赫，等.一种数据驱动的旋转机械早期故障检测模型构建和应用研究［J］.机械工程学报，2020，56（16）：22-32. doi：10.3901/JME.2020.16.022
WANG Qing-feng， WEI Bing-kun， LIU Jia-he， et al. Research on construction and application of data-driven incipient fault detection model for rotating machinery［J］. Journal of Mechanical Engineering， 2020， 56（16）： 22-32.
doi: 10.3901/JME.2020.16.022
[2]   雷亚国，贾峰，孔德同，等.大数据下机械智能故障检测的机遇与挑战［J］.机械工程学报，2018，54（5）：94-104. doi：10.3901/JME.2018.05.094
LEI Ya-guo， JIA Feng， KONG De-tong， et al. Opportunities and challenges of machinery intelligent fault diagnosis in big data era［J］. Journal of Mechanical Engineering， 2018， 54（5）： 94-104.
doi: 10.3901/JME.2018.05.094
[3]   刘念.高速经编机梳栉横移振动研究［D］.无锡：江南大学，2012：37-44.
LIU Nian. Vibration research of shogging motion of the guide bar on high speed warp knitting machine［D］. Wuxi： Jiangnan University， 2012： 37-44.
[4]   陈是扦，彭志科，周鹏.信号分解及其在机械故障诊断中的应用研究综述［J］.机械工程学报，2020，56（17）：91-107. doi：10.3901/JME.2020.17.091
CHEN Shi-qian， PENG Zhi-ke， ZHOU Peng. Review of signal decomposition theory and its applications in machine fault diagnosis［J］. Journal of Mechanical Engineering， 2020， 56（17）： 91-107.
doi: 10.3901/JME.2020.17.091
[5]   齐添添，陈尧，何才厚，等.损伤声发射信号小波包神经网络特征识别方法［J］.北京邮电大学学报，2021，44（1）：124-130. doi：10.13190/j.jbupt.2020-118
QI Tian-tian， CHEN Yao， HE Cai-hou， et al. A wavelet packet neural network feature recognition method for damage acoustic emission signals［J］. Journal of Beijing University of Posts and Telecommunications， 2021， 44（1）： 124-130.
doi: 10.13190/j.jbupt.2020-118
[6]   王育炜，王红军，韩秋实，等.基于小波包和IGA-BP 神经网络的滚动轴承故障识别方法［J］.机床与液压，2020，48（17）：184-187. doi：10.3969/j.issn.1001-3881.2020.17.037
WANG Yu-wei， WAGN Hong-jun， HAN Qiu-shi， et al. Rolling bearing fault identification method based on wavelet packet and IGA-BP neural network［J］. Machine Tool and Hydraulics， 2020， 48（17）： 184-187.
doi: 10.3969/j.issn.1001-3881.2020.17.037
[7]   徐晶.基于小波包和迁移学习的飞机燃油泵故障诊断［J］.液压与气动，2020（6）：183-188. doi：10.11832/j.issn.1000-4858.2020.06.029
XU Jing. Fault diagnosis of aircraft fuel pump based on wavelet packet and transfer learning［J］. Chinese Hydraulics & Pneumatics， 2020（6）： 183-188.
doi: 10.11832/j.issn.1000-4858.2020.06.029
[8]   TAX D M J， DUIN R P W. Support vector domain description［J］. Pattern Recognition Letters， 1999， 20（11/12/13）： 1191-1199. doi：10.1016/s0167-8655（99）00087-2
doi: 10.1016/s0167-8655（99）00087-2
[9]   赵小强，牟淼.基于变量分块的KDLV-DWSVDD间歇过程故障检测算法研究［J］.仪器仪表学报，2021，42（2）：244-256. doi：10.19650/j.cnki.cjsi.J2006827
ZHAO Xiao-qiang， MOU Miao. Research on fault detection algorithm of batch process based on KDLV-DWSVDD of variable blocks［J］. Chinese Journal of Scientific Instrument， 2021， 42（2）： 244-256.
doi: 10.19650/j.cnki.cjsi.J2006827
[10]   李冠男，胡云鹏，陈焕新，等.基于PCA-SVDD的冷水机组故障检测方法［J］.华中科技大学学报（自然科学版），2015，43（8）：119-122. doi：10.1016/j.enbuild.2015.12.045
LI Guan-nan， HU Yun-peng， CHEN Huan-xin， et al. PCA-SVDD-based chiller fault detection method［J］. Journal of Huazhong University of Science and Technology（Natural Science Edition）， 2015， 43（8）： 119-122.
doi: 10.1016/j.enbuild.2015.12.045
[11]   郝腾飞，陈果.基于小球大间隔方法的机械故障检测［J］. 中国机械工程，2012，23（15）：1765-1770. doi：10.3969/j.issn.1004-132X.2012.15.001
HAO Teng-fei， CHEN Guo. Machinery fault detection based on a small sphere and large margin approach［J］. China Mechanical Engineering， 2012， 23（15）： 1765-1770.
doi: 10.3969/j.issn.1004-132X.2012.15.001
[12]   周子松.基于支持向量数据描述的风电机组叶片健康声学诊断方法研究［D］.北京：北京邮电大学，2019：26-35.
ZHOU Zi-song. Acoustical diagnosis of wind turbine blade based on SVDD［D］. Beijing： Beijing University of Posts and Telecommunications， 2019： 26-35.
[13]   周建民，徐清瑶，张龙，等.结合小波包奇异谱熵和SVDD的滚动轴承性能退化评估［J］.机械科学与技术，2016，35（12）：1882-1887. doi：10.1155/2016/3086454
ZHOU Jian-min， XU Qing-yao， ZHANG Long， et al. Assessment method of rolling bearing performance degradation based on wavelet packet singular spectral entropy and SVDD［J］. Mechanical Science and Technology for Aerospace Engineering， 2016， 35（12）： 1882-1887.
doi: 10.1155/2016/3086454
[14]   林桐，陈果，滕春禹，等.基于超球优化支持向量数据描述的滚动轴承故障检测［J］.振动与冲击，2019，38（2）：204-210，225. doi：10.13465/j.cnki.jvs.2019.02.030
LIN Tong， CHEN Guo， TENG Chun-yu， et al. Rolling bearing fault detection based on the hypersphere optimization support vector data description［J］. Journal of Vibration and Shock， 2019， 38（2）： 204-210， 225.
doi: 10.13465/j.cnki.jvs.2019.02.030
[15]   朱朔，白瑞林，刘秦川.基于果蝇优化算法-小波支持向量数据描述的滚动轴承性能退化评估［J］.中国机械工程，2018，29（5）：602-608. doi：10.3969/j.issn.1004-132X.2018.05.016
ZHU Shuo， BAI Rui-lin， LIU Qin-chuan. Rolling bearing performance degradation assessment based on FOA-WSVDD［J］. China Mechanical Engineering， 2018， 29（5）： 602-608.
doi: 10.3969/j.issn.1004-132X.2018.05.016
[16]   朱启兵，刘杰，应怀樵.基于小波能量和RBF网络的钢水下渣自动检测［J］.振动、测试与诊断，2005，25（3）： 230-232. doi：10.3969/j.issn.1004-6801.2005.03.016
ZHU Qi-bing， LIU Jie， YING Huai-qiao. Outflow slag at ladle automatic detection based on wavelet-energy and RBF neural network［J］. Journal of Vibration Measurement & Diagnosis， 2005， 25（3）： 230-232.
doi: 10.3969/j.issn.1004-6801.2005.03.016
[17]   NIKOLAOU N G， ANTONIADIS I A. Rolling element bearing fault diagnosis using wavelet packets［J］. NDT & E International， 2002， 35（3）： 197-205. doi：10.1016/s0963-8695（01）00044-5
doi: 10.1016/s0963-8695（01）00044-5
[18]   丁世飞，齐丙娟，谭红艳.支持向量机理论与算法研究综述［J］.电子科技大学学报，2011，40（1）：2-10. doi：10.3969/j.issn.1001-0548.2011.01.001
DING Shi-fei， QI Bing-juan， TAN Hong-yan. An overview on theory and algorithm of support vector machines［J］. Journal of University of Electronic Science and Technology of China， 2011， 40（1）： 2-10.
doi: 10.3969/j.issn.1001-0548.2011.01.001
[19]   王周春，崔文楠，张涛.基于支持向量机的长波红外目标分类识别算法［J］.红外技术，2021，43（2）：153-161.
WANG Zhou-chun， CUI Wen-nan， ZHANG Tao. Classification and recognition algorithm for long-wave infrared targets based on support vector machine［J］. Infrared Technology， 2021， 43（2）： 153-161.
No related articles found!