Abstract:In industries that require extensive use of various types of pipelines such as ship transportation and petrochemical industry, structural health monitoring (SHM) of pipelines is of great significance for the safe and stable operation of industrial systems. In terms of pipeline crack grade identification based on ultrasonic guided wave, this paper constructs the finite element simulation model of the actual pipeline object, and synthesizes guided wave data closer to the actual detection by adding noise. Based on the finite element simulation sample database containing different pipeline crack grades, a pipeline crack grade recognition model based on multi-scale one-dimensional convolution neural network (MS-1DCNN) is proposed in this paper. The model realizes the direct use of the original waveform signal as the model input in an end-to-end manner, without the need for special design of signal noise reduction and feature extraction algorithm. The experimental results show that the model has higher accuracy than the traditional machine learning method in identifying pipeline crack grade in noise environment. In addition, this paper builds an experimental platform for crack identification based on physical pipelines, which further verifies the effectiveness of the proposed models and methods in pipeline structural health monitoring.
[1] 赵一昭, 柳勇, 白凡, 等. 管道含外表面裂纹时的疲劳寿命预测研究[J]. 石油机械, 2020, 48(8): 129-135.
ZHAO Yizhao, LIU Yong, BAI Fan, et al. Fatigue life prediction of pipe with cracks on external surface[J]. China Petroleum Machinery, 2020, 48(8): 129-135.
[2] 温宇立, 武静, 林荣, 等. 基于相轨迹的多裂纹管道超声导波检测研究[J]. 振动与冲击, 2017, 36(23): 114-122.
WEN Yuli, WU Jing, LIN Rong, et al. Multi-crack detection in pipes using ultrasonic guided wave based on phase trajectories[J]. Journal of Vibration and Shock, 2017, 36(23): 114-122.
[3] BORATE P, WANG G, WANG Y. Data-driven structural health monitoring approach using guided lamb wave responses[J]. Journal of Aerospace Engineering, 2020, 33(4): 04020033.
[4] 王晓煜, 刘海龙, 高斯佳, 等. 基于超磁致伸缩换能器的CFRP板孔裂纹缺陷检测[J]. 振动与冲击, 2020, 39(23): 202-210.
WANG Xiaoyu, LIU Hailong, GAO Sijia, et al. Hole crack damage detection of CFRP plate based on super-magneto-strictive transducer[J]. Journal of Vibration and Shock, 2020, 39(23): 202-210.
[5] 宋立忠, 郭敏, 王欣欣, 等. 城市轨道交通箱梁中高频导波特性分析[J]. 振动与冲击, 2019, 38(18): 207-214.
SONG Lizhong, GUO Min, WANG Xinxin, et al. Mid-and high-frequency wave characteristics of a rail transit box-girder bridge[J]. Journal of Vibration and Shock, 2019, 38(18): 207-214.
[6] CRUZ F C, FILHO E F S, ALBUQUERQUE M C S, et al. Efficient feature selection for neural network based detection of flaws in steel welded joints using ultrasound testing[J]. Ultrasonics, 2017, 73:1-8.
[7] LI R H, GU H J, HU B, et al. Multi-feature fusion and damage identification of large generator stator insulation based on lamb wave detection and SVM method[J]. Sensors, 2019, 19(17): 3733.
[8] LIU W X, Tang Z F, Lv F Z, et al. Multi-feature integration and machine learning for guided wave structural health monitoring: Application to switch rail foot[J]. Structural Health Monitoring, 2021(1): 2013-2034.
[9] 刘飞, 陈仁文, 邢凯玲, 等. 基于迁移学习与深度残差网络的滚动轴承快速故障诊断算法[J]. 振动与冲击, 2022, 41(3): 154-164.
LIU Fei, CHEN Renwen, XING Kailing, et al. Fast fault diagnosis algoriyhm for rolling bearing based on transfer learning and deep residual network. [J]. Journal of Vibration and Shock, 2022, 41(3): 154-164.
[10] OLIVEIRA M A, MONTEIRO A V, FILHO J V. A new structural health monitoring strategy based on PZT sensors and convolutional neural network[J]. Sensors, 2018, 18(9): 2955.
[11] XIE Y, ZHANG T. Fault diagnosis for rotating machinery based on convolutional neural network and empirical mode decomposition[J]. Shock and Vibration, 2017, 2017: 3084197.
[12] ZHANG W, PENG G L, LI C H, et al. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load[J]. Mechanical Systems and Signal Processing, 2018, 100: 439-453.
[13] YOUSEF M, HUSSAIN K F, MOHAMMED U S. Accurate, data-efficient, unconstrained text recognition with convolutional neural networks[J]. Pattern Recognition, 2020, 108: 107482.
[14] 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.
[15] INCE T, KIRANYAZ S, EREN L, et al. Real-time motor fault detection by 1D convolutional neural networks[J]. IEEE Transactions on Industrial Electronics, 2016, 63(11): 7067-7075.
[16] ABDELJABER O, AVIC O, KIRANYAZ S, et al. Real-time vibration-based structural damage detection using one dimensional convolutional neural networks[J]. Journal of Sound and Vibration, Volume, 2017, 388: 154-170.
[17] PANDEY P, RAI A, MITRA M. Explainable 1-D convolutional neural network for damage detection using lamb wave[J]. Mechanical Systems and Signal Processing, 2022, 164: 108220.
[18] CHUA C A, ALLEYNE D N, CALVA M. Crack growth monitoring using low-frequency guided waves[J]. Insight- Non-Destructive Testing Condition Monitoring, 2017, 59(2): 64-71.
[19] 钟勇, 肖福仁, 单以银, 等. 管线钢疲劳裂纹扩展速率与疲劳寿命关系的研究[J]. 金属学报, 2005(05): 523-528.
ZHONG Yong, XIAO Furen, SHAN Yiyin, et al. Study of relationship between fatigue crack growth rate and fatigue life for pipeline steels[J]. Acta Metall. Sin., 2005, 41: 523.
[20] 廖林,袁懋诞,纪轩荣, 等.钢轨中高频超声导波单模态激励技术研究[J].机械工程学报,2021,57(18):23-31.
LIAO Lin, YUAN Maodan, JI Xuanrong, et al. Research on excitation of single-mode ultrasonic guided wave in high-frequency range along rail[J]. Journal of Mechanical Engineering, 2021, 57(18): 23-31.