For the complicated signal components in the early failure of the supply and delivery missile system, the failure symptoms are usually difficult to identify.Aiming at this, an intelligent fault diagnosis method was proposed based on the texture features of synchrosqueezing wavelet transform（SST）time-frequency distribution images.The EEMD method was adopted to preprocess the vibration signal of the projectile delivery system, and to calculate the correlation coefficient of the decomposed components.The first four layers with high correlation coefficient were selected to reconstruct the signal for reducing the noise effect.Then, the vibration signals of different states of the transmissive bomb system were dealt with by the time-frequency analysis with the synchrosqueezing wavelet transform to obtain two-dimensional time-frequency images reflecting different operating states, and the gray-scale processing was performed.The gray level co-occurrence matrix method and the gray gradient co-occurrence matrix were used to extract the texture features.In order to compare with the traditional method, the energy percentage of the first four layers with large correlation coefficient of the original signal was taken as a feature after the signal was decomposed by EEMD.The method of kernel-based fuzzy C-means clustering, was used to do the classification and recognition of the image texture features and the image features of three different state vibration signals of the supply and delivery bomb system respectively, and the results were compared with those of the fuzzy C-means clustering.The experimental results show that the method can effectively recognize the early failure of automatic missile systems and the recognition accuracy is 91.21%.
Key words
ammunition supply system /
synchrosqueezing wavelet transform(SST) /
texture feature extraction /
fuzzy kernel clustering /
fault diagnosis
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
References
[1] Daubechies I，Lu F J，Wu H T. Synchrosqueezed wavelet transforms：An empirical mode decomposition like tool[J]. Applied and Computational Harmonic Analysis,2011,30:
243-261.
[2]Dmytro Iatsenko, Peter V.E. McClintock. Linear and synchrosqueezed time–frequency representations revisited Overview, standards of use, resolution, reconstruction, concentration, and algorithms[J]. Digital Signal Processing,2015,42:1-26.
[3] 陶新民，徐晶，付强，等．基于样本密度KFCM新算法及其在故障诊断的应用[J]．振动与冲击，2009，28（8）：61-83．
Tao Xinmin, Xu Jing, Fu Qiang, et al. KFCM based on sample density and its application in fault diagnosis [J]. Vibration and shock，2009，28（8）：61-83．
[4] 张莉，周伟达，焦李成．核聚类算法[J]．计算机学报，2002，25(6):587-590．
Zhang Li, Zhou Weida, Jiao Licheng. Nuclear clustering algorithm [J]. Journal of Computer，2002，25(6):587-590．
[5] Zhang Rong，Rudnicky A I． A large scale clustering scheme for kernel k-means［C］．Washington，DC，USA: The Sixteenth International Conference on Pattern Recognition，2002．
[6]喻敏，王斌，王文波，等．基于 SST 的间谐波检测方法[J]．中国电机工程学报，2016，36（0）：1-8．
Yu Min, Wang Bin, Wang Wenbo, et al. Inter-harmonic detection method based on SST [J]. Chinese Society for Electrical Engineering，2016，36（0）：1-8．
[7]胡异丁,任伟新,杨 栋．基于同步压缩变换和局部替代数据的非平稳振动信号分解方法[J]．振动与冲击，2013，32（23）：43-47．
Hu Yiding, Ren Weixin, Yang Dong. Non-stationary vibration signal decomposition method based on synchronous compression transform and local substitute data [J]. Vibration and Shock，2013，32（23）：43-47．
[8]Gadelmawla ES.A vision system for surface roughness characterization using the gray level co-occurrence matrix[J]．NDT&E International，2004，37(7)：577-588．
[9]洪继光．灰度－梯度共生矩阵纹理分析方法[J]．自动化学报，1984，10（1）：22-25.
Hong Jiguang. Gray-gradient co-occurrence matrix texture analysis method [J]. Journal of Automation，1984，10（1）：22-25.
[10]白雪冰，邹丽晖．基于灰度－梯度共生矩阵的木材表面缺陷分割方法[J]．森林工程，2007，23(2):16-18．
Bai Xuebin, Zou Lihui. Segmentation method of wood surface defects based on gray-gradient co-occurrence matrix [J]. Forest Engineering，2007，23(2):16-18．
[11]王亚萍,许迪,葛江华. 基于SPWVD时频图纹理特征的滚动轴承故障诊断[J].振动、测试与诊断，2017, 37(1):115-119.
WANG Ya-ping, XU Di, GE Jiang-hua. Fault Diagnosis of Rolling Bearing Based on SPWVD Time-frequency Map Texture Feature[J]. Vibration, Test & Diagnosis，2017, 37(1):115-119.
[12]罗露，戴劲松，樊永锋，等.节片式柔性导引设计与仿真［J］.兵器装备工程学报，2019,40(1):102-105.
LUO Lu, DAI Jinsong, FAN Yongfeng, et al.Design andSimulation for Flexible Guidance of Certain Type Ammunition Feed System［J］.Journal of Ordnance Equipment Engineering, 2019,40(1): 102-105.
[13]杨松,赫雷，沈超，等. 某新型自动防暴枪自动机动力学仿真［J］.兵器装备工程学报，2017(3):57-61.
YANG Song，HE Lei，SHEN Chao，et al. Dynamic Simulation of a New Type Automatic Shot Gun[J].Journalof Ordnance Equipment Engineering,2017(3):57-61.
[14]於崇铭，任风云，田丰. 航空弹药铁路运输振动响应模型及影响因素分析［J］.兵器装备工程学报，2017(11):151-154.
YU Chongming, REN Fengyun, TIAN Feng. Aviation Ammunition Vibration Response Model and Influence Factors Analysis of Railway Transportation[J］.Journal of Ordnance Equipment Engineering, 2017(11):151-154.
[15]沈微，陶新民，高珊，常瑞，王若彤.基于同步挤压小波变换的振动信号自适应降噪方法[J]. 振动与冲击,2018，37（14）：239-247.
SHEN Wei，TAO Xinmin，GAO Shan，CHANG Rui，WANG Ruotong. Self-adaptive de-noising algorithm for vibration signals based on synchrosqueezed wavelet transforms[J]. Vibration and Shock，2018，37(14):239-247.
{{custom_fnGroup.title_en}}
Footnotes
{{custom_fn.content}}
PDF(1614 KB)
