CEEMD-FCM模型下的管道缺陷识别方法

doi:10.16265/j.cnki.issn1003-3033.2020.01.014

中国安全科学学报 ›› 2020, Vol. 30 ›› Issue (1): 87-93.doi: 10.16265/j.cnki.issn1003-3033.2020.01.014

CEEMD-FCM模型下的管道缺陷识别方法

王超群, 梁伟教授, 梁晓斌

中国石油大学(北京) 安全与海洋工程学院,北京 102249

收稿日期:2019-11-08 修回日期:2020-01-06 出版日期:2020-01-28 发布日期:2021-01-22
作者简介:王超群 (1993—),女,黑龙江哈尔滨人,硕士研究生,研究方向为机械设备故障诊断、管道缺陷检测与诊断E-mail:965463190@qq.com; 梁伟 (1978—),男,陕西榆林人, 博士,教授,主要从事油气管道安全检测、场站设备诊断与可靠性评估等方面的研究E-mail: lw@cup.edu.cn。
基金资助:
国家自然科学基金资助(51005247);国家重点研发项目(2017YFC0805800)。

Pipeline defect recognition method based on CEEMD-FCM

WANG Chaoqun, LIANG Wei, LIANG Xiaobin

School of Safety and Ocean Engineering, China University of Petroleum (Beijing), Beijing 102249, China

Received:2019-11-08 Revised:2020-01-06 Online:2020-01-28 Published:2021-01-22

摘要/Abstract

摘要： 为提高管道缺陷识别精度,利用补充集合经验模态分解方法(CEEMD)和模糊C-均值(FCM)聚类算法,提出CEEMD-FCM的管道缺陷识别模型。首先,分析管道缺陷信号波形特征,引入粒子群优化算法(PSO)改进小波阈值降噪方法,实现管道缺陷信号的降噪;然后,采用CEEMD分解缺陷信号,并借助能量熵原理提取缺陷的特征参量;最后,利用模拟退火算法(SA)和遗传算法(GA)优化FCM,完成管道缺陷的分类。结果表明:基于CEEMD-FCM模型的管道缺陷识别方法的综合识别精度达到87.5%,可实现石油化工领域管道缺陷模式的精准识别,保障管道安全运行,降低事故发生率。

关键词: 管道, 缺陷类型识别, 特征提取, 补充集合经验模态分解方法(CEEMD), 模糊C-均值(FCM)聚类算法

Abstract: In order to improve identification accuracy of pipeline defects, CEEMD-FCM model is proposed by using CEEMD and FCM clustering algorithm. Firstly, based on analysis of defect signal waveform features, particle swarm optimization algorithm (PSO) was introduced to improve wavelet threshold de-noising method, and noise reduction of pipeline defect signals was realized. Then, defect signals were decomposed by CEEMD, and characteristic parameters of defects were extracted through principle of energy entropy. Finally, FCM was optimized by simulating annealing algorithm (SA) and genetic algorithm (GA) to complete classification of pipeline defects. The results show that comprehensive identification accuracy of the proposed identification method reaches 87.5%. It can achieve accurate identification of defect modes in petrochemical industry, therefore ensuing safe operation of pipeline and reducing accident rates.

Key words: pipeline, defect type identification, feature extraction, complete ensemble empirical mode decomposition (CEEMD), fuzzy C-means(FCM) clustering algorithm

中图分类号:

X937

王超群, 梁伟, 梁晓斌. CEEMD-FCM模型下的管道缺陷识别方法[J]. 中国安全科学学报, 2020, 30(1): 87-93.

WANG Chaoqun, LIANG Wei, LIANG Xiaobin. Pipeline defect recognition method based on CEEMD-FCM[J]. China Safety Science Journal, 2020, 30(1): 87-93.

参考文献

[1] 洪仁植,王树达,常亮.基于BP神经网络的管道缺陷模式识别与精确定量识别[J]. 东北石油大学学报,2008, 32(1): 83-85.
HONG Renzhi,WANG Shuda,CHANG Liang. Pipe defect pattern recognition and accurate quantitative recognition based on BP neural network[J]. Journal of Northeast Petroleum University, 2008, 32(1): 83-85.
[2] 王思文.经验模态分解及其在降噪方面的应用[J]. 机械制造,2011, 38(10): 26-29.
WANG Siwen.Experiential mode decomposition and its application in noise reduction[J]. Machine Manufacturing, 2011, 38(10): 26-29.
[3] 姜万录,卢传奇,朱勇.基于HHT和模糊C均值聚类的轴向柱塞泵故障识别[J].吉林大学学报:工学版,2015,45(2): 429-436.
JIANG Wanlu, LU Chuanqi, ZHU Yong.A fault identification of axial piston pump based on HHT and fuzzy C-means clustering[J].Journal of Jilin University:Engineering Science,2015,45(2): 429-436.
[4] XU Fan,TSE W T P. Roller bearing fault diagnosis using stacked denoising autoencoder in deep learning and Gath-Geva clustering algorithm without principal component analysis and data label[J]. Applied Soft Computing, 2018, 73: 898-913.
[5] 张立国,康乐,金梅,等.一种基于EEMD-SVD和FCM的轴承故障诊断方法[J].计量学报,2016,37(1): 67-70.
ZHANG Liguo,KANG Le,JIN Mei,et al. A bearing fault diagnosis method based on EEMD-SVD and FCM[J].Acta Metrologica Sinica,2016,37(1): 67-70.
[6] 王朝晖,姚德群,段礼祥.基于模糊聚类的油田往复压缩机气阀故障诊断研究[J]. 机械强度,2007, 29(3): 521-524.
WANG Zhaohui, YAO Dequn, DUAN Lixiang. Fault diagnosis of gas valves for oil field reciprocating compressors based on fuzzy clustering[J]. Mechanical Strength, 2007, 29(3): 521-524.
[7] ASKARI S, MONTAZERIN N, ZARANDI M H F, et al. Generalized entropy based possibilistic fuzzy C-means for clustering noisy data and its convergence proof[J]. Neuro-computing, 2016, 219: 186-202.
[8] 凌鹏,陈跃威.基于CEEMD互近似熵和FCM滚动轴承故障诊断[J].计算机仿真,2018,35(3):314-318,410.
LING Peng,CHEN Yuewei. Based on CEEMD mutual approximation entropy and FCM rolling bearing fault diagnosis[J].Computer Simulation,2018,35(3):314-318,410.
[9] YEH J R, SUN W Z, SHIEH J S, et al. Investigating fractal property and respiratory modulation of human heartbeat time series using empirical mode decomposition [J]. Medical Engineering & Physics, 2010, 32(5): 490-496.
[10] ABDELKADER R, KADDOUR A, BENDIABDELLAH A, et al. Rolling bearing fault diagnosis based on an improveddenoising method using the complete ensemble empirical mode decomposition and the optimized threshold ingoperation [J].IEEE Sensors Journal, 2018, 18(17): 7 166-7 172.
[11] KUMAR P, SIROHI D. Comparative analysis of FCM and HCM algorithm on iris data set [J]. International Journal of Computer Applications, 2010, 5(2): 33-37.
[12] 曾山,同小军,桑农,等.基于对应分析的冗余模糊C均值聚类算法研究[J]. 华中科技大学学报:自然科学版, 2012, 40(2): 107-111.
ZENG Shan, TONG Xiaojun, SANG Nong, et al. Research on redundant fuzzy C-means clustering algorithm based on correspondence analysis[J]. Journal of Huazhong University of Science and Technology:Natural Science, 2012, 40(2): 107-111.

[1]	张新生, 王旭业, 张莹莹, 常潆戈. 海底腐蚀管道剩余寿命预测与维修策略研究[J]. 中国安全科学学报, 2022, 32(3): 41-47.
[2]	张新生, 常潆戈. 基于FA-BAS-ELM的海洋油气管道外腐蚀速率预测^*[J]. 中国安全科学学报, 2022, 32(2): 99-106.
[3]	郑度奎, 程远鹏, 李昊燃, 何天隆. IAFSA-GRNN在油田集输管道CO₂腐蚀速率预测中的应用^*[J]. 中国安全科学学报, 2022, 32(1): 110-117.
[4]	周宁, 吴露露, 李雪, 李徐伟, 时静洁, 曹林林. 喷射火环境下石化管廊管道失效特征试验研究^*[J]. 中国安全科学学报, 2022, 32(1): 135-141.
[5]	王秋红, 王力文, 蒋军成, 张明广, 李鑫. 城镇地埋天然气管道泄漏诱发气云爆炸仿真^*[J]. 中国安全科学学报, 2021, 31(9): 75-82.
[6]	张新生, 蔡宝泉. 基于改进随机森林模型的海底管道腐蚀预测^*[J]. 中国安全科学学报, 2021, 31(8): 69-74.
[7]	陈石灵, 熊勇, 朱磊基. 室外消火栓状态综合特征提取模型^*[J]. 中国安全科学学报, 2021, 31(7): 143-150.
[8]	骆正山, 田珮琦. RS-PSO-ELM下腐蚀管道失效压力预测[J]. 中国安全科学学报, 2021, 31(3): 28-34.
[9]	王磊. 球形障碍物对瓦斯爆燃火焰影响试验研究[J]. 中国安全科学学报, 2021, 31(3): 54-59.
[10]	朱豪豪, 郭海林, ZHUMAKELDI A. 外力作用下管道内表面缺陷处裂纹扩展研究[J]. 中国安全科学学报, 2021, 31(3): 66-72.
[11]	景国勋, 贺祥, 郭绍帅, 朱斯佳. 封闭材料对分岔管道中瓦斯爆炸特性的影响^*[J]. 中国安全科学学报, 2021, 31(11): 64-70.
[12]	刘啸奔, 王宝栋, 张东, 张宏. 地表载荷作用下含缺陷燃气管道安全评价^*[J]. 中国安全科学学报, 2021, 31(10): 127-135.
[13]	段照斌, 杜海龙, 张鹏. 基于QAR2Vec模型的QAR数据特征提取[J]. 中国安全科学学报, 2021, 31(1): 145-152.
[14]	任乐峰, 孟祥坤, 陈国明. 滩海油气管道泄漏风险演化与评估[J]. 中国安全科学学报, 2021, 31(1): 159-164.
[15]	屈静, 张建彬, 李旭芳, 陆宝, 华宁, 朱晓曼. 基于贝叶斯网络的输油管道泄漏事故情景推演[J]. 中国安全科学学报, 2021, 31(1): 192-198.

CEEMD-FCM模型下的管道缺陷识别方法

Pipeline defect recognition method based on CEEMD-FCM

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价