基于变分模态分解和天牛须搜索的磁瓦内部缺陷声振检测

摘要
图/表
参考文献(26)
相关文章 (15)

全文: PDF (2274 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要在磁瓦内部缺陷声振检测中，具备可预设尺度和自适应能力的变分模态分解（Variational Mode Decomposition，VMD）在处理相关声振信号时具有明显优势。然而VMD的参数选择范围广且对分解效果影响大，为解决参数的统一预设问题，提出一种基于天牛须搜索（Beetle Antennae Search，BAS）的VMD参数优化方法，并应用于磁瓦内部缺陷检测。该方法首先根据声振信号特点建立基于模态能量和模态中心频率变化规律的目标函数；再利用BAS在参数空间中搜寻目标函数最大值，所需的VMD统一预设参数即为该最大值所对应的参数组合；最后，在该优化参数下对逐个信号进行VMD处理并提取模态中心频率特征，进而由支持向量机完成特征识别。实验结果表明，所提出的方法能有效优化VMD参数并实现磁瓦内部缺陷的快速精准检测。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	黄沁元1
	谢罗峰2
	殷国富2
	冉茂霞1
	刘鑫1

关键词 ：变分模态分解, 天牛须搜索, 磁瓦, 内部缺陷, 声振信号

Abstract：Variational mode decomposition (VMD) with not only preset scale but also self-adaptable ability possesses a significant advantage in processing the acoustic impact signal for detecting the internal defect in arc magnet using acoustic impact method. However, the performance of VMD extremely depends on the parameters selection, while these parameters have considerable quantity and wide range. In order to obtain consistent VMD parameters that are suitable for all acoustic impact signals, a novel VMD parameter optimization with beetle antennae search (BAS) algorithm was presented. Firstly, an objective function based on both mode energy distribution and mode center frequency variation was designed by the signal characteristics. Secondly, BAS was executed to search for the objective function maximum from the VMD parameter space. The parameters corresponding to the maximum were selected as the optimal VMD parameters. Finally, the signals were processed by VMD with these optimal parameters, and then the mode center frequencies associated with the internal defect were extracted as the signal features. The classifier based on support vector machine was employed for the feature identification. The experimental results demonstrate that the proposed method can efficiently optimize VMD parameters and realize a rapid and accurate detection of the internal defect in arc magnet.

Key words： variational mode decomposition beetle antennae search arc magnet internal defect acoustic impact signal

收稿日期: 2019-04-03 出版日期: 2020-08-28

引用本文:

黄沁元1，谢罗峰2，殷国富2，冉茂霞1，刘鑫1. 基于变分模态分解和天牛须搜索的磁瓦内部缺陷声振检测[J]. 振动与冲击, 2020, 39(17): 124-133.
HUANG Qinyuan1, XIE Luofeng2, YIN Guofu2, RAN Maoxia1, LIU Xin1. Acoustic-vibration detection for internal defects of magnetic tile based on VMD and BAS. JOURNAL OF VIBRATION AND SHOCK, 2020, 39(17): 124-133.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2020/V39/I17/124

[1] XIE L F, YIN M, HUANG Q Y, et al. Internal defect inspection in magnetic tile by using acoustic resonance technology [J]. Journal of Sound and Vibration, 2016, 383(24): 108-123.
[2] 邬冠华, 林俊明, 任吉林, 等. 声振检测方法的发展[J]. 无损检测, 2011, 33(2): 35-41.
WU Guanhua, LIN Junming, REN Jilin, et al. Evolution of the Acoustic Impact Testing Method [J]. Nondestructive Testing, 2011, 33(2): 35-41.
[3] HUANG Q Y, Yin Y, Yin G F. Automatic classification of magnetic tiles internal defects based on acoustic resonance analysis [J]. Mechanical Systems and Signal Processing, 2015, 60: 45-58.
[4] 黄沁元, 殷鹰, 赵越, 等. 基于双谱分析的磁瓦内部缺陷音频检测方法[J]. 四川大学学报(工程科学版), 2014, 46(5): 188-194.
HUANG Qinyuan, YIN Yin, ZHAO Yue, et al. Acoustic inspection of internal defect in magnetic tile based on bispectrum analysis [J]. Journal of Sichuan University (Engineering Science Edition), 2014, 46(5): 188-194.
[5] 谢罗峰, 徐慧宁, 黄沁元, 等. 应用双树复小波包和NCA-LSSVM检测磁瓦内部缺陷[J]. 浙江大学学报(工学版), 2017, 51(1): 184-191.
XIE Luofeng, XU Huining, HUANG Qinyuan, et al. Application of DTCWPT and NCA-LSSVM to inspect internal defects of magnetic tile [J]. Journal of Zhejiang University (Engineering Science), 2017, 51(1): 184-191.
[6] XIE L F, HUANG Q Y, ZHAO Y, et al. Inspection of magnetic tile internal cracks based on impact acoustics [J]. Nondestructive Testing and Evaluation, 2015, 30(2): 147-164.
[7] 夏均忠, 赵磊, 白云川, 等. 基于MCKD和VMD的滚动轴承微弱故障特征提取[J]. 振动与冲击, 2017, 36(20): 78-83.
XIA Junzhong, ZHAO Lei, BAI Yunchuan, et al. Feature extraction for rolling element bearing weak fault based on MCKD and VMD [J]. Journal of Vibration and Shock, 2017, 36(20): 78-83.
[8] BABU K A, RAMKUMAR B, MANIKANDAN M S. Automatic identification of S1 and S2 heart sounds using simultaneous PCG and PPG recordings [J]. IEEE Sensors Journal, 2018, 18(22): 9430-9440.
[9] 万书亭, 豆龙江, 李聪, 等. 基于VMD和样本熵的高压断路器故障特征提取及分类[J]. 振动与冲击, 2018, 37(20): 32-38.
WAN Shuting, DOU Longjiang, LI Cong, et al. Fault feature extraction and classification of high voltage circuit breakers based on VMD and sample entropy [J]. Journal of Vibration and Shock, 2018, 37(20): 32-38.
[10] YAN X A, JIA M P. Application of CSA-VMD and optimal scale morphological slice bispectrum in enhancing outer race fault detection of rolling element bearings [J]. Mechanical Systems and Signal Processing, 2019, 122: 56-86.
[11] LI H X, CHANG J H, XU F, et al. Efficient lidar signal denoising algorithm using variational mode decomposition combined with a whale optimization algorithm [J]. Remote Sensing, 2019, 11(2): 126.
[12] 蒋丽英, 卢晓东, 王景霖, 等. 基于PSO-VMD的齿轮特征参数提取方法研究[J]. 制造技术与机床, 2017, (11): 65-71.
JIANG Liying, LU Xudong, WANG Jinglin, et al. Feature parameters extraction method of gear based on PSO-VMD [J]. Manufacturing Technology and Machine Tool, 2017, (11): 65-71.
[13] ZHU Z Y, ZHANG Z Y, MAN W S, et al. A new beetle antennae search algorithm for multi-objective energy management in microgrid [C]// 2018 13th IEEE Conference on Industrial Electronics and Applications. Wuhan, Hubei, China: IEEE, 2018. 1599-1603.
[14] SUN Y T, ZHANG J F, LI G C, et al. Optimized neural network using beetle antennae search for predicting the unconfined compressive strength of jet grouting coalcretes [J]. International Journal for Numerical and Analytical Methods in Geomechanics, 2019, 43(4): 801-813.
[15] 邵良杉, 韩瑞达. 基于天牛须搜索的花朵授粉算法[J]. 计算机工程与应用, 2018, 54(18): 188-194.
SHAO Liangshan, HAN Ruida. Beetle antenna search flower pollination algorithm [J]. Computer Engineering and Applications, 2018, 54(18): 188-194.
[16] LI Z X, JIANG Y, GUO Q, et al. Multi-dimensional variational mode decomposition for bearing-crack detection in wind turbines with large driving-speed variations [J]. Renewable Energy, 2018, 116: 55-73.
[17] 任学平, 李攀, 王朝, 等. 基于改进VMD与包络导数能量算子的滚动轴承早期故障诊断[J]. 振动与冲击, 2018, 37(15): 6-13.
REN Xueping, LI Pan, WANG Chao, et al. Rolling bearing early fault diagnosis based on improved VMD and envelope derivative operator [J]. Journal of Vibration and Shock, 2018, 37(15): 6-13.
[18] BAGHERI A, OZBULUT O E, HARRIS D K. Structural system identification based on variational mode decomposition [J]. Journal of Sound and Vibration, 2018, 417(17): 182-197.
[19] 王新, 闫文源. 基于变分模态分解和SVM的滚动轴承故障诊断[J]. 振动与冲击, 2017, 36(18): 252-256.
WANG Xin, YAN Wenyuan. Fault diagnosis of roller bearings based on the variational mode decomposition and SVM [J]. Journal of Vibration and Shock, 2017, 36(18): 252-256.
[20] 邹东尧, 陈鹏伟, 刘宽. 基于天牛须搜索优化的室内定位算法[J]. 湖北民族学院学报(自然科学版), 2018, 36(4): 427-431.
ZOU Dongyao, CHEN Pengwei, LIU Kuan. Indoor location algorithm based on the search optimization of the beetle [J]. Journal of Hubei University for Nationalities (Natural Science Edition), 2018, 36(4): 427-431.
[21] LIN Z Y, MA S, MA X J, et al. Two new beetle antennae search (bas) algorithms and their comparative investigation [J]. International Journal of Robotics and Control, 2019, 2(1): 9-17.
[22] JIANG X Y, LI S. BAS: Beetle Antennae Search Algorithm for Optimization Problems [J]. International Journal of Robotics and Control, 2018, 1(1): 1-5.
[23] 赵蓉, 史红梅. 基于高阶谱特征提取的高速列车车轮擦伤识别算法研究[J]. 机械工程学报, 2017, 53(6): 102-109.
ZHAO Rong, SHI Hongmei. Research on wheel-flat recognition algorithm for high-speed train based on high-order spectrum feature extraction [J]. Journal of Mechanical Engineering, 2017, 53(6): 102-109.
[24] SHI P, YANG W X. Precise feature extraction from wind turbine condition monitoring signals by using optimised variational mode decomposition [J]. IET Renewable Power Generation, 2017, 11(3): 245-252.
[25] RAMEZAN C A, WARNER T A, MAXWELL A E. Evaluation of sampling and cross-validation tuning strategies for regional-scale machine learning classification [J]. Remote Sensing, 2019, 11(2): 185.
[26] KLEIN A, FALKNER S, BARTELS S, et al. Fast bayesian optimization of machine learning hyperparameters on large datasets [C]// The 20th International Conference on Artificial Intelligence and Statistics. Fort Lauderdale, Florida, USA: JMLR, 2017. 528-536.