Identification of Corrosion Damage Degree of Guided Wave Bend Pipe Based on Neural Network and Support Vector Machine

doi:10.3901/JME.2021.12.136

Abstract

Abstract: The far-field detection advantage of guided wave and machine learning models are used to carry out the research on the intelligent identification methods for corrosion damage in pipeline bends. Different levels of corrosion defects are processed at the bends of ordinary carbon steel pipes elbow, which are divided into 10 grades according to the degree of corrosion. Two kinds of signal excitation receiving methods, self excitation receiving and one excitation receiving, are used to excite T(0,1) ultrasonic guided wave in the pipeline, and the guided wave detection signals corresponding to defects with different corrosion degrees are acquired. Characteristic values of multiple guided wave signals are extracted to represent the damage degree by analyzing the features of detection signal in time domain and frequency domain. Two classification models, BP neural network and support vector machine, are used to train and analyze the data to obtain the defect damage identification model, which can accurately identify the corrosion degree of the bending part. In the research, the influence of the super parameters of the two models on the accuracy of the defect identification model is analyzed, and the performance of the two models on the identification of the corrosion damage of the bend is compared. The experimental results show that the two damage identification models can achieve better classification effect for guided wave detection signals under different excitation and reception modes. Compared with BP neural network, support vector machine has better identification effect for rail crack damage under the condition of small sample.

Key words: ultrasonic guided waves, elbow corrosion, damage eigenvalue, bp neural network, support vector machine

CLC Number:

JG115

ZHOU Cheng, DENG Fei, LIU Yao, LIU Xiucheng, CHEN Honglei, LIU Zenghua. Identification of Corrosion Damage Degree of Guided Wave Bend Pipe Based on Neural Network and Support Vector Machine[J]. Journal of Mechanical Engineering, 2021, 57(12): 136-144.

References

[1] 偶国富, 许根富, 朱祖超, 等. 弯管冲蚀失效流固耦合机理及数值模拟[J]. 机械工程学报, 2009, 45(11):119-124. OU Guofu, XU Genfu, ZHU Zuchao, et al. Fluid-structure interaction mechanism and numerical simulation of elbow erosion failure[J]. Journal of Mechanical Engineering, 2009, 45(11):119-124.
[2] 周建民, 徐清瑶, 李鹏, 等. 钢轨无损检测中的超声导波技术[J]. 仪表技术与传感器, 2015(6):99-102. ZHOU Jianmin, XU Qingyao, LI Peng, et al. Ultrasonic guided wave technique for nondestructive testing of rails[J]. Instrument Technique and Sensor, 2015(6):99-102.
[3] 周邵萍, 张蒲根, 吕文超, 等. 基于导波的弯管裂纹缺陷的检测[J]. 机械工程学报, 2015, 51(6):58-65. ZHOU Shaoping, ZHANG Pugen, LÜ Wenchao, et al. Detection of cracks in elbow pipes using guided waves[J]. Journal of Mechanical Engineering, 2015, 51(6):58-65.
[4] HAYASHI T, KAWASHIMA K, SUN Zongqi, et al. Guided wave propagation mechanics across a pipe elbow[J]. Pressure Vessel Technology, 2005, 127(3):322-327.
[5] BAKKALI M E. Guided wave propagation and scattering in pipeworks comprising elbows[J]. AIP Conference Proceedings, 2015, 1581(1):DOI:10.1063/1.4864838.
[6] DEMMA A, CAWLEY P, LOWE M, et al. The effect of bends on the propagation of guided waves in pipes[J]. Journal of Pressure Vessel Technology, 2005, 127(3):328-335.
[7] 裴洪, 胡昌华, 司小胜, 等. 基于机器学习的设备剩余寿命预测方法综述[J]. 机械工程学报, 2019, 55(8):1-13. PEI Hong, HU Changhua, SI Xiaosheng, et al. Review of machine learning based remaining useful life prediction methods for equipment[J]. Journal of Mechanical Engineering, 2019, 55(8):1-13.
[8] 邹宁波, 谌海云, 刘全利, 等. 基于T(0, 1)模态超声导波的输气管道腐蚀检测[J]. 无损检测, 2013, 35(9):19-22. ZOU Ningbo, CHEN Haiyun, LIU Quanli, et al. Detection of gas transmission pipeline corrosion using ultrasonic guided waves of T(0, 1) mode[J]. Nondestructive Testing, 2013, 35(9):19-22.
[9] QI Minxin, ZHOU Shaoping, NI Jing, et al. Investigation on ultrasonic guided waves propagation in elbow pipe[J]. International Journal of Pressure Vessels and Piping, 2016, (139-140):250-255.
[10] QIU Lei, YUAN Shenfang, CHANG F K, et al. On-line updating Gaussian mixture model for aircraft wing spar damage evaluation under time-varying boundary condition[J]. Smart Materials and Structures, 2014, 23(12):125001.
[11] TORKAMANI S, ROY S, BARKEY M E, et al. A novel damage index for damage identification using guided waves with application in laminated composites[J]. Smart Materials and Structures, 2014, 23(9):095015.
[12] 殷书彦. 基于BP神经网络的手机病毒检测方法研[D]. 沈阳:沈阳师范大学, 2016. YIN Shuyan. Mobile phone virus detection method based on BP neural network[D]. Shenyang:Shenyang Normal University, 2016.
[13] ZUR R M, JIANG Y, PESCE L L, et al. Noise injection for training artificial neural networks:A comparison with weight decay and early stopping[J]. Medical Physics, 2009, 36(10):4810-4818.
[14] LAROCHELLE H, BENGIO Y, LOURADOUR J, et al. Exploring strategies for training deep neural networks[J]. Journal of Machine Learning Research, 2009, 1(10):1-40.
[15] 韩力群. 人工神经网络教程[M]. 北京:北京邮电大学出版社, 2006. HANG Liqun. Artificial neural network course[M]. Beijing:Beijing University of Posts and Telecommunications Press, 2016.
[16] 张清良, 李先明. 一种确定神经网络隐层节点数的新方法[J]. 吉首大学学报, 2002(1):91-93. ZHANG Qingliang, LI Xianming. A new method to determine the number of hidden nodes in neural network[J]. Journal of Jishou University, 2002(1):91-93.
[17] 王建梅, 覃文忠. 基于L-M算法的BP神经网络分类器[J]. 武汉大学学报, 2005(10):85-88. WANG Jianmei, QIN Wenzhong. BP neural network classifier based on L-M algorithm[J]. Geomatics and Information Science of Wuhan University, 2005(10):85-88.
[18] CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3):273-297.
[19] BAESENS B. An empirical assessment of kernel type performance for least squares support vector machine classifiers[C]//Fourth International Conference on Knowledge-Based Intelligent Information Engineering Systems & Allied Technologies, KES 2000, Brighton, UK, 2000, August 30-September 1. IEEE, 2000:313-316.