Journal of Textile Research ›› 2023, Vol. 44 ›› Issue (05): 139-146.doi: 10.13475/j.fzxb.20210603501

• Textile Engineering • Previous Articles     Next Articles

Robustness algorithm for online yarn breakage detection in warp knitting machines

YANG Hongmai1, ZHANG Xiaodong1(), YAN Ning1, ZHU Linlin1, LI Na'na2   

  1. 1. Key Laboratory of Precision Measuring Technology & Instruments, Tianjin University, Tianjin 300072, China
    2. School of Textile Science and Engineering, Tiangong University, Tianjin 300387, China
  • Received:2021-06-10 Revised:2022-04-18 Online:2023-05-15 Published:2023-06-09

RichHTML

10

PDF (PC)

31

Abstract:

Objective For warp knitting machines, yarn breakage is inevitable in the working process. When a yarn breakage occurs, the warp knitting machine should be stopped immediately for yarn repair so as to avoid causing fabric defects. However, because the yarn diameter is only tens of microns, and tens of thousands of yarns are knitted at high speed at the same time in the knitting process, it brings great difficulties to the online detection of yarns in warp knitting machines.

Method Aiming at the above problem, this paper proposes a composite detection algorithm. Firstly, the defect feature enhancement method based on dimension transformation was adopted to enhance the stability of the algorithm by data processing. Secondly, on the basis of dimensional transformation data, a yarn breakage detection algorithm based on wavelet transformation was proposed, and the gray level transformation rule of the image was analyzed from the perspective of time domain to realize defect detection. Finally, deep learning was adopted to further improve the robustness of the algorithm.

Results To verify the effectiveness of the proposed algorithm, the detection system was built in KARL MAYER RD7/2-12 warp knitting machine (Fig.8). Ten cameras were adopted to shoot at a distance of 1 m. Five groups of experiments were carried out to verify the feasibility of the algorithm under different processing conditings (Tab.1). The first group of data was taken as an example and the detection processes (Fig.10). Five sets of yarn breakage experiments were conducted on three different warp knitting machines, and the methods proposed in this paper can effectively identify yarn breakage. It is shown that the algorithm proposed in this paper can effectively detect yarn breakage. The algorithm proposed in this paper was comared with STL (time series decomposition algorithm) and wavelet decomposition algorithm (Tab.2). The timeliness of different algorithms was analysed, indicating that the conventional STL decomposition algorithm had the worst timeliness (Tab.2). The proposed method and wavelet decomposition showed better timeliness, and it also proved that the introduction of deep learning had no impact on the timeliness of the algorithm. About 120 h of continuous experiment was set to verify the stability of the algorithm proposed in this paper, compared with other algorithms, the missed detection rate and the false detection rate were both decreased (Fig.11).

Conclusion Aiming at the problem of online detection of broken yarn defects in warp knitting machines, this paper proposes a robustness detection algorithm, which is proven to be feasible by a large number of experiments. An innovative method of weak defect feature enhancement based on dimension transformation is proposed to overcome the degradation of detection stability caused by various weaving processes and serious external noise interference.The problem of restricting the accuracy and timeliness of broken yarn detection on warp knitting machines has been solved. The proposed algorithm has important implications for textile defect detection. At the same time, the proposed algorithm is expected to promote the further development of textile industry towards automation and intelligence.

Key words: warp knitting machine, yarn breakage detection, wavelet transformation, image processing, deep learning

CLC Number: 

  • TS101

Fig.1

Yarn breaking highlighting method based on reflection law. (a) Shooting principle; (b) Shooting effect"

Fig.2

Algorithm flow chart"

Fig.3

Dimension transformation flow chart. (a) Actual image; (b) One-dimensional signal after dimensionality reduction; (c) Image after reduced dimension data merging"

Fig.4

Defect location algorithm based on wavelet decomposition. (a) Image after dimension transformation; (b) Time domain variation diagram of signal; (c) Wavelet transformation defect highlighting effect"

Fig.5

Principle of step feature extraction by wavelet transformation"

Fig.6

Flow chart of yarn breakage detection based on deep learning"

Fig.7

Yolov4 network model"

Fig.8

Online detection system of yarn breaking defects"

Tab.1

Process parameters of warp knitting machine"

实验编号 纱线直径/μm 经编工艺
M1T1 75 满穿
M1T2 75 一穿一空
M2T3 30 一穿一空
M2T4 75 五穿一空
M3T5 75 满穿

Fig.9

Broken yarn image"

Fig.10

Effectiveness experiment M1T1. (a) Image after dimension transformation; (b) Wavelet transform detection; (c) Deep learning detection"

Tab.2

Timeliness test"

实验
组号		 STL分解算法 小波分解算法 复合算法
帧数 时间/s 帧数 时间/s 帧数 时间/s
M1T1 55 9 31 5 31 5
M1T2 57 10 32 5 32 5
M2T3 60 10 34 6 34 6
M2T4 54 9 30 5 30 5
M3T1 56 9 30 5 30 5

Tab.3

Parameters of warp knitting machine with four guide bars"

机速/(r·min-1) 梳节编号 纱线直径/μm 经编工艺
583 T1 75 满穿
T2 30 满穿
T3 75 五穿一空
T4 75 五穿一空

Fig.11

Robustness experiments of algorithms. (a) Missed detection experiment; (b) Wrong detection experiment"

[1] 夏风林, 葛明桥, 蒋高明. 高速经编机梳栉横移运动的优化设计[J]. 纺织学报, 2009, 30(5):118-121.
XIA Fenglin, GE Mingqiao, JIANG Gaoming. Optimizing design of shogging motion of the guide bar on high speed warp knitting machine[J]. Journal of Textile Research, 2009, 30(5): 118-121.
doi: 10.1177/004051756003000202
[2] 秦志刚, 龙海如, 马晓红. 玻璃纤维经编针织物的编织工艺分析[J]. 纺织学报, 2008, 29(5):46-50.
QIN Zhigang, LONG Hairu, MA Xiaohong. Analysis of knitting technologies of warp knitted glass fiber fabrics[J]. Journal of Textile Research, 2008, 29(5): 46-50.
[3] MEI S, WANG Y, WEN G. Automatic fabric defect detection with a multi-scale convolutional denoising autoencoder network model[J]. Sensors, 2018.DOI: 10.3390/s18041064.
doi: 10.3390/s18041064
[4] CARVALHO V, PINTO J G, MONTEIRO J L, et al. Yarn parameterization based on mass analysis[J]. Sensors and Actuators A: Physical, 2004, 115(2/3): 540-548.
doi: 10.1016/j.sna.2004.04.045
[5] LU W, LU X, ZHU C, et al. Solving three key problems of the SAW yarn tension sensor[J]. IEEE Transactions on Electron Devices, 2012, 59(10): 2853-2855.
doi: 10.1109/TED.2012.2209427
[6] MUSA E. Line laser-based break sensor that detects light spots on yarns[J]. Optics and Lasers in Engineering, 2009, 47(7-8): 741-746.
doi: 10.1016/j.optlaseng.2009.03.009
[7] MUSA E. Line-laser-based yarn shadow sensing break sensor[J]. Optics and Lasers in Engineering, 2011, 49(3): 313-317.
doi: 10.1016/j.optlaseng.2010.10.003
[8] YAN N, ZHU L, YANG H, et al. Online yarn breakage detection: a reflection-based anomaly detection method[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 1-13.
[9] CHAN C, PANG G K H. Fabric defect detection by Fourier analysis[J]. IEEE Transactions on Industry Applications, 2000, 36(5): 1267-1276.
doi: 10.1109/28.871274
[10] BODNAROVA A, BENNAMOUN M, LATHAM S. Optimal gabor filters for textile flaw detection[J]. Pattern Recognition, 2002, 35(12): 2973-2991.
doi: 10.1016/S0031-3203(02)00017-1
[11] HU G H, ZHANG G H, WANG Q H. Automated defect detection in textured materials using wavelet-domain hidden markov models[J]. Optical Engineering, 2014.DOI: 10.1117/1.OE.53.9.093107.
doi: 10.1117/1.OE.53.9.093107
[12] WEI B, HAO K, TANG X, et al. A new method using the convolutional neural network with compressive sensing for fabric defect classification based on small sample sizes[J]. Textile Research Journal, 2019, 89(17): 3539-3555.
doi: 10.1177/0040517518813656
[13] ZHAO Z, GUI K, WANG P. Fabric defect detection based on cascade faster R-CNN[C]. Proceedings of the 4th International Conference on Computer Science and Application Engineering. Springer: plano, 2020: 1-6.
[14] LIU Z, CUI J, LI C, et al. Fabric defect detection based on lightweight neural network[C]// Chinese Conference on Pattern Recognition and Computer Vision (PRCV). Springer: Cham, 2019: 528-539.
[1] CHEN Zhihao, BAO Wenjie, LI Fucai, JING Bo, HUANG Chaolin, SUN Jianwen. Vibration analysis of high speed warp knitting machine based on fast empirical mode decomposition [J]. Journal of Textile Research, 2023, 44(04): 204-211.
[2] GU Bingfei, ZHANG Jian, XU Kaiyi, ZHAO Songling, YE Fan, HOU Jue. Human contour and parameter extraction from complex background [J]. Journal of Textile Research, 2023, 44(03): 168-175.
[3] LI Yang, PENG Laihu, LI Jianqiang, LIU Jianting, ZHENG Qiuyang, HU Xudong. Fabric defect detection based on deep-belief network [J]. Journal of Textile Research, 2023, 44(02): 143-150.
[4] CHEN Jia, YANG Congcong, LIU Junping, HE Ruhan, LIANG Jinxing. Cross-domain generation for transferring hand-drawn sketches to garment images [J]. Journal of Textile Research, 2023, 44(01): 171-178.
[5] WANG Bin, LI Min, LEI Chenglin, HE Ruhan. Research progress in fabric defect detection based on deep learning [J]. Journal of Textile Research, 2023, 44(01): 219-227.
[6] AN Yijin, XUE Wenliang, DING Yi, ZHANG Shunlian. Evaluation of textile color rubbing fastness based on image processing [J]. Journal of Textile Research, 2022, 43(12): 131-137.
[7] ZHANG Dongjian, GAN Xuehui, YANG Chongchang, HAN Fuyi, LIU Xiangyu, TAN Yuan, LIAO He, WANG Songlin. Research progress in non-contact fiber tension detection technology in spinning process [J]. Journal of Textile Research, 2022, 43(11): 188-194.
[8] CHEN Jinguang, LI Xue, SHAO Jingfeng, MA Lili. Lightweight clothing detection method based on an improved YOLOv5 network [J]. Journal of Textile Research, 2022, 43(10): 155-160.
[9] YUAN Yanhong, ZENG Hongming, MAO Muquan. Needle selector detection system based on image processing [J]. Journal of Textile Research, 2022, 43(10): 176-182.
[10] DENG Zhongmin, HU Haodong, YU Dongyang, WANG Wen, KE Wei. Density detection method of weft knitted fabrics making use of combined image frequency domain and spatial domain [J]. Journal of Textile Research, 2022, 43(08): 67-73.
[11] MA Yunjiao, WANG Lei, PAN Ruru, GAO Weidong. Calibration method of three-dimensional yarn evenness based on mirrored image [J]. Journal of Textile Research, 2022, 43(07): 55-59.
[12] ZHENG Baoping, JIANG Gaoming. Design of warp knitting machine data management system based on cloud server [J]. Journal of Textile Research, 2022, 43(07): 186-192.
[13] ZHOU Qihong, PENG Yi, CEN Junhao, ZHOU Shenhua, LI Shujia. Yarn breakage location for yarn joining robot based on machine vision [J]. Journal of Textile Research, 2022, 43(05): 163-169.
[14] ZHANG Ronggen, FENG Pei, LIU Dashuang, ZHANG Junping, YANG Chongchang. Research on on-line detection system of broken filaments in industrial polyester filament [J]. Journal of Textile Research, 2022, 43(04): 153-159.
[15] XIONG Jingjing, YANG Xue, SU Jing, WANG Hongbo. Testing method for fabric moisture conductivity based on image technology [J]. Journal of Textile Research, 2021, 42(12): 70-75.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
京ICP备14006648号
Copyright 2021 © Editorial office of Journal of Textile Research
Supported by Beijing Magtech Co.Ltd