Please wait a minute...
Chinese Journal of Engineering Design  2024, Vol. 31 Issue (5): 565-574    DOI: 10.3785/j.issn.1006-754X.2024.03.203
Theory and Method of Mechanical Design     
Idler fault diagnosis method fusing short-time Fourier transform and convolutional neural network
Miao XIE1(),Qingshuang MENG1(),Bo LI2,Jinnan LU1,Yuqi LI1,Zhiyong YANG1,3
1.School of Mechanical Engineering, Liaoning Technical University, Fuxin 123000, China
2.Faculty of Electrical and Control Engineering, Liaoning Technical University, Huludao 125000, China
3.Xinjiang Open-pit Mine Intelligent Production and Control Key Laboratory, Changji 831100, China
Download: HTML     PDF(5856KB)
Export: BibTeX | EndNote (RIS)      

Abstract  

Idler fault has become a common problem in the operation of belt conveyors. If the idler fault cannot be diagnosed in time, it will seriously restrict the safe operation of belt conveyors. To solve the above problems, based on the actual operating conditions of idlers in the middle section of a certain mining belt conveyor, an idler fault diagnosis method fusing short-time Fourier transform (STFT) and convolutional neural network (CNN) is proposed. Firstly, based on distributed optical fiber, the vibration signals of the idler operating under normal, bearing damage and cylinder skin fracture conditions were collected and processed by STFT to obtain corresponding time-frequency image sample set, and the sample set was divided into training set and testing set. Then, the training set was input into the CNN model for diagnostic model training, and the operating state characteristics of idlers under different working conditions were constantly updated during the training process. Finally, the trained CNN model was applied to the testing set, and the recognition result of the idler operating state was output. The results showed that the recognition accuracy of the constructed CNN model was as high as 99.6%. Based on the proposed fault diagnosis method, field experiment were carried out in a certain mine to further verify the recognition accuracy of the CNN model. The experimental results showed that the CNN model had a high recognition accuracy of 96.5% for the operating state of idlers in the middle section of the belt conveyor, which was 3.1 percentage points lower than the recognition accuracy on the testing set, indicating that the proposed fault diagnosis method had a certain reliability. Subsequently, the robustness of the fault diagnosis method can be improved by continuously increasing the operation data of idlers under different working conditions, which can provide a powerful theoretical basis for the effective diagnosis of idler faults in coal mine enterprises.



Key wordsidler      fault diagnosis      distributed optical fiber      short-time Fourier transform      convolutional neural network     
Received: 12 September 2023      Published: 30 October 2024
CLC:  TH 222  
Corresponding Authors: Qingshuang MENG     E-mail: xiemiao1121@126.com;2724127290@qq.com
Cite this article:

Miao XIE,Qingshuang MENG,Bo LI,Jinnan LU,Yuqi LI,Zhiyong YANG. Idler fault diagnosis method fusing short-time Fourier transform and convolutional neural network. Chinese Journal of Engineering Design, 2024, 31(5): 565-574.

URL:

https://www.zjujournals.com/gcsjxb/10.3785/j.issn.1006-754X.2024.03.203     OR     https://www.zjujournals.com/gcsjxb/Y2024/V31/I5/565


融合短时傅里叶变换和卷积神经网络的托辊故障诊断方法

托辊故障已成为带式输送机运行中的常见问题。若不能及时诊断托辊故障,则将严重制约带式输送机的安全运行。为了解决上述问题,基于某矿带式输送机中间段托辊的实际运行工况,提出了一种融合短时傅里叶变换(short-time Fourier transform, STFT)和卷积神经网络(convolutional neural network, CNN)的托辊故障诊断方法。首先,以分布式光纤为基础,对托辊在正常、轴承损坏及筒皮断裂工况下运行时的振动信号进行采集并作STFT处理,得到对应的时频图样本集,并将其分为训练集和测试集。然后,将训练集输入CNN模型以进行诊断模型训练,在训练过程中不断更新不同工况下托辊的运行状态特征。最后,将训练好的CNN模型应用于测试集,并输出托辊运行状态的识别结果。结果表明,所构建的CNN模型的识别准确率高达99.6%。基于所提出的故障诊断方法,在某矿上开展现场实验,以进一步验证CNN模型的识别准确率。实验结果表明,CNN模型对带式输送机中间段托辊的运行状态有较高的识别准确率,可达96.5%,与测试集上的识别准确率仅相差3.1个百分点,说明所提出的故障诊断方法具有一定的可靠性。后续可通过不断增加不同工况下托辊的运行数据来提高该故障诊断方法的鲁棒性,这可为煤矿企业有效诊断托辊故障提供有力的理论基础。


关键词: 托辊,  故障诊断,  分布式光纤,  短时傅里叶变换,  卷积神经网络 
Fig.1 Idlers in different operating states
Fig.2 Acquisition method of idler vibration signal
Fig.3 Discrete model of backward Rayleigh scattering interference effect
Fig.4 Time-domain curve of Rayleigh scattering before and after vibration
Fig.5 Structure of CNN
Fig.6 Idler fault diagnosis process based on STFT and CNN
Fig.7 Amplitude-time curve of idler under different working conditions
Fig.8 Time-frequency diagram of idler vibration signal under different working conditions
Fig.9 CNN model suitable for idler fault diagnosis
网络层特征图数量/张特征图大小/像素
输入层164×64
池化层1132×32
卷积层13232×32
池化层23216×16
卷积层26416×16
池化层3648×8
全连接层12 048
输出层11
Table 1 Structural parameters of CNN
Fig.10 Recognition accuracy of CNN model on training set and testing set
Fig.11 Loss value of CNN model on training set and testing set
Fig.12 Comparison of recognition accuracy of CNN model under different belt speeds
Fig.13 Comparison of recognition accuracy of new CNN model under different belt speeds
Fig.14 Belt conveyor operation site
Fig.15 Comparison of fault diagnosis results of CNN model and actual fault results
Fig.16 Recognition results of different idler operating states by CNN model
[1]   齐庆杰, 王欢, 董子文, 等. 矿井胶带运输巷火灾蔓延规律的数值模拟研究[J]. 中国安全科学学报, 2016, 26(10): 36-41. doi:10.16265/j.cnki.issn1003-3033.2016.10.007
QI Q J, WANG H, DONG Z W, et al. Numerical simulation of belt conveyor fire spreading law in coal mine[J]. China Safety Science Journal, 2016, 26(10): 36-41.
doi: 10.16265/j.cnki.issn1003-3033.2016.10.007
[2]   李铬, 李春广, 梁睦, 等. 煤矿带式输送机事故分析及防护措施[J]. 中国安全科学学报, 2006, 16(3): 140-144, 148. doi:10.3969/j.issn.1003-3033.2006.03.027
LI G, LI C G, LIANG M, et al. Accident analysis of belt conveyor used in coal mine and its protective measures[J]. China Safety Science Journal, 2006, 16(3): 140-144, 148.
doi: 10.3969/j.issn.1003-3033.2006.03.027
[3]   赵学智, 叶邦彦, 陈统坚. 短时傅里叶变换的时频聚集性度量准则研究[J]. 振动、测试与诊断, 2017, 37(5): 948-956, 1065. doi:10.16450/j.cnki.issn.1004-6801.2017.05.015
ZHAO X Z, YE B Y, CHEN T J. Study on measure rule of time-frequency concentration of short time Fourier transform[J]. Journal of Vibration, Measurement & Diagnosis, 2017, 37(5): 948-956, 1065.
doi: 10.16450/j.cnki.issn.1004-6801.2017.05.015
[4]   张立智, 徐卫晓, 井陆阳, 等. 基于二维深度卷积网络的旋转机械故障诊断[J]. 机械强度, 2020, 42(5): 1039-1044.
ZHANG L Z, XU W X, JING L Y, et al. Rotating machinery fault diagnosis based on two-dimensional convolution neural network[J]. Journal of Mechanical Strength, 2020, 42(5): 1039-1044.
[5]   付忠广, 王诗云, 高玉才, 等. 基于Mobile-VIT的旋转机械故障诊断方法[J]. 汽轮机技术, 2023, 65(2): 119-121, 86.
FU Z G, WANG S Y, GAO Y C, et al. A fault diagnosis method of rotating machinery based on Mobile-VIT[J]. Turbine Technology, 2023, 65(2): 119-121, 86.
[6]   隆军, 吴金强. STFT和HHT在风力机轴承故障诊断中的应用[J]. 噪声与振动控制, 2013, 33(4): 219-222. doi:10.3969/j.issn.1006-1335.2013.04.045
LONG J, WU J Q. Application of short time Fourier transform and Hilbert-Huang transform in fault diagnosis of rolling bearings of windmill[J]. Noise and Vibration Control, 2013, 33(4): 219-222.
doi: 10.3969/j.issn.1006-1335.2013.04.045
[7]   李恒, 张氢, 秦仙蓉, 等. 基于短时傅里叶变换和卷积神经网络的轴承故障诊断方法[J]. 振动与冲击, 2018, 37(19): 124-131.
LI H, ZHANG Q, QIN X R, et al. Fault diagnosis method for rolling bearings based on short-time Fourier transform and convolution neural network[J]. Journal of Vibration and Shock, 2018, 37(19): 124-131.
[8]   金江涛, 许子非, 李春, 等. 基于深度学习与混沌特征融合的滚动轴承故障诊断[J]. 控制理论与应用, 2022, 39(1): 109-116. doi:10.7641/CTA.2021.10177
JIN J T, XU Z F, LI C, et al. Rolling bearing fault diagnosis based on deep learning and chaotic feature fusion[J]. Control Theory & Applications, 2022, 39(1): 109-116.
doi: 10.7641/CTA.2021.10177
[9]   刘慧斌, 李少波, 张安思, 等. 基于深度卷积神经网络的轴承多故障诊断研究[J]. 组合机床与自动化加工技术, 2020(5): 12-16. doi:10.1109/cac51589.2020.9326576
LIU H B, LI S B, ZHANG A S, et al. Multiple damage diagnosis of bearings based on deep convolutional neural network[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2020(5): 12-16.
doi: 10.1109/cac51589.2020.9326576
[10]   JANSSENS O, SLAVKOVIKJ V, VERVISCH B, et al. Convolutional neural network based fault detection for rotating machinery[J]. Journal of Sound and Vibration, 2016, 377: 331-345.
[11]   董辛旻, 韩捷, 石来德, 等. 基于矢谱和L-M神经网络的旋转机械故障诊断研究[J]. 汽轮机技术, 2009, 51(5): 372-375.
DONG X M, HAN J, SHI L D, et al. Study on fault diagnosis for rotary machinery based on vector spectrum and L-M neural network[J]. Turbine Technology, 2009, 51(5): 372-375.
[12]   谢厚抗, 鲍久圣, 葛世荣, 等. 带式输送机承载托辊旋转阻力特性试验研究[J]. 煤炭学报, 2019, 44(): 731-736. doi:10.13225/j.cnki.jccs.2019.0902
XIE H K, BAO J S, GE S R, et al. Experimental research on rotational resistance characteristics of belt conveyor bearing idler[J]. Journal of China Coal Society, 2019, 44(): 731-736.
doi: 10.13225/j.cnki.jccs.2019.0902
[13]   李新华, 梁浩, 徐伟弘, 等. 常用分布式光纤传感器性能比较[J]. 光通信技术, 2007, 31(5): 14-18.
LI X H, LIANG H, XU W H, et al. Comparison of characteristics of commonly-used distributed optical fiber sensors[J]. Optical Communication Technology, 2007, 31(5): 14-18.
[14]   徐佳杰. 基于双树复小波与宽度学习的轴承故障诊断方法研究[D]. 包头: 内蒙古科技大学, 2020: 18-20.
XU J J. Research on diagnosis of bearing based on double tree complex wavelet and broad learning system [D]. Baotou: Inner Mongolia University of Science & Technology, 2020: 18-20.
[15]   KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 60(6): 84-90.
[16]   LECUN Y, BOSER B, DENKER J S, et al. Backpropagation applied to handwritten zip code recognition[J]. Neural Computation, 1989, 1(4): 541-551.
[17]   袁铭阳. 基于深度学习的遥感影像典型目标检测算法研究[D]. 郑州: 战略支援部队信息工程大学, 2020: 17-21.
YUAN M Y. Research on typical target detection algorithm of remote sensing image based on deep learning[D]. Zhengzhou: Strategic Support Force Information Engineering University, 2020: 17-21.
[18]   储颜雨. 基于深度残差网络的细粒度图像分类研究[D]. 南京: 南京邮电大学, 2020: 24-27.
CHU Y Y. Research on fine-grained image classification based on deep residual network[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2020: 24-27.
[19]   李大柱, 牛江, 梁树林, 等. 基于多尺度时频图与卷积神经网络的车轮故障智能诊断[J]. 铁道科学与工程学报, 2023, 20(3): 1032-1043.
LI D Z, NIU J, LIANG S L, et al. Intelligent wheel fault diagnosis based on multi-scale time-frequency map and convolutional neural network[J]. Journal of Railway Science and Engineering, 2023, 20(3): 1032-1043.
[1] Jianxiong SHEN,Yingyuan LIU,Leqin WANG. Deep learning-based method for parametrized modeling of airfoil[J]. Chinese Journal of Engineering Design, 2024, 31(3): 292-300.
[2] Zihan YE,Zhonghua WANG,Chao JIANG,Xin Lü,Zhe ZHANG. Research on fault diagnosis method based on multi-discriminator auxiliary classifier generative adversarial network[J]. Chinese Journal of Engineering Design, 2024, 31(2): 137-150.
[3] Liyong TIAN,Rui TANG,Ning YU,Hongyue CHEN. Design and application of belt lifting mechanism for replacing idler of belt conveyor[J]. Chinese Journal of Engineering Design, 2023, 30(6): 667-677.
[4] Chao JI,Liang WANG,Xiao-jing WANG,Xiao-bing LI,Wen CAO. Design of cable tunnel fault warning system based on MSSA-SVM[J]. Chinese Journal of Engineering Design, 2023, 30(1): 109-116.
[5] WU Guo-pei, YU Yin-quan, TU Wen-bing. Review of research on fault diagnosis of permanent magnet synchronous motor[J]. Chinese Journal of Engineering Design, 2021, 28(5): 548-558.
[6] SHANG Zhi-wu, ZHOU Shi-qi. Research on micropipetting technology based on image monitoring[J]. Chinese Journal of Engineering Design, 2021, 28(4): 495-503.
[7] NI Hong-qi, JIN Chi, FENG Fei. Development of fault diagnosis system for corrugated compensator[J]. Chinese Journal of Engineering Design, 2019, 26(3): 354-363.
[8] MA Tian-bing, WANG Xiao-dong, DU Fei, WANG Xin-quan. Fault diagnosis for rigid guide based on GA-SVM[J]. Chinese Journal of Engineering Design, 2019, 26(2): 170-176.
[9] HU Yi-yao, ZHU Bin, ZHANG Wei, HE Wei, SHEN Ping-sheng. Design and implementation of knowledge base building tool software[J]. Chinese Journal of Engineering Design, 2018, 25(4): 367-373.
[10] ZHANG Qiang, WANG Hai-jian, WU Ze-guang, LIU Zhi-heng, MAO Jun. Research of coal-rock cutting mechanical characteristic and test system for drum shearer[J]. Chinese Journal of Engineering Design, 2017, 24(4): 459-464,479.
[11] LI Xiao-huo, WENG Zheng-yang, QIANG Ya-sen, SHI Shang-wei, LI Yan. Fault diagnosis of hydraulic breaking hammer based on Fruit Fly Algorithm optimized fuzzy RBF neural network[J]. Chinese Journal of Engineering Design, 2015, 22(6): 540-545.
[12] LI Ling-Ling, JING Li-Ting, MA Dong-Juan, LI Zhi-Gang. Improved evidence theory and its application in fault diagnosis of power system[J]. Chinese Journal of Engineering Design, 2012, 19(6): 485-488.
[13] HAN Hai-tao,MA Hong-guang,HAN Kun,ZHENG Geng-le. Multitone stimulus signal design for identifying volterra frequency domain kernels[J]. Chinese Journal of Engineering Design, 2012, 19(2): 123-127.
[14] HAO Zhi-Yong, LIU Wei, XIA Wei, YAN Chuang. Fault diagnosis of the fan with air suction based on BP neural network[J]. Chinese Journal of Engineering Design, 2012, 19(1): 57-60.
[15] HAN Hai-Tao, MA Hong-Guang, LI Fei, ZHANG Jia-Liang-. Research on nonlinear system based on output frequency response functions[J]. Chinese Journal of Engineering Design, 2011, 18(5): 373-376.