中国安全科学学报 ›› 2024, Vol. 34 ›› Issue (6): 119-126.doi: 10.16265/j.cnki.issn1003-3033.2024.06.1137

• 安全工程技术 • 上一篇    下一篇

基于SVM的干线输气管道泄漏压降速率信号识别

吴瑕1(), 陈红环1, 贾文龙1, 孙溢彬2, 任思波3   

  1. 1 西南石油大学 石油与天然气工程学院,四川 成都 610500
    2 中海石油有限公司海南分公司,海南 海口 570100
    3 四川蜀交能源开发有限公司,四川 成都 610023
  • 收稿日期:2023-12-12 修回日期:2024-03-20 出版日期:2024-06-28
  • 作者简介:

    吴 瑕 (1987—),女,四川自贡人,博士,副教授,主要从事油气储运安全工程、油气储运工程仿真等方面的研究。E-mail:

    贾文龙 教授

  • 基金资助:
    国家自然科学基金资助(52074238); 国家自然科学基金资助(52274065); 四川省自然科学基金面上项目资助(24NSFSC0717); 四川省自然科学基金面上项目资助(2022NSFC0235); 四川省自然科学青年基金资助(2022NSFSC1018)

Dentification of leakage pressure drop rate signal of trunk gas pipeline based on SVM

WU Xia1(), CHEN Honghuan1, JIA Wenlong1, SUN Yibin2, REN Sibo3   

  1. 1 Petroleum Engineering School, Southwest Petroleum University, Chengdu Sichuan 610500, China
    2 Hainan Branch of China National Offshore Oil Corporation Limited, Haikou Hainan 570100, China
    3 Sichuan Shujiao Energy Development Corporation, Chengdu Sichuan 610023, China
  • Received:2023-12-12 Revised:2024-03-20 Published:2024-06-28

摘要:

为解决压缩机抽吸或截断阀截断形成的压降信号导致截断阀发生误关断,以及小孔泄漏因管道压降不显著导致截断阀不动作的问题,以某输气干线为对象建立仿真模型,获取压缩机抽吸、截断阀紧急截断及管道泄漏3类不同工况下的300组压降信号,根据对点检测法计算出压降信号的压降速率值;以奇异值分解(SVD)法和极差归一化方法提取压降速率信号特征,采用支持向量机(SVM)法识别不同压降速率特征值信号,获取所对应的工况类型;针对SVM模型中的核函数参数与惩罚因子设置不合理,影响算法识别准确性的问题,采用教与学优化算法(TLBO)优化核函数参数与惩罚因子,建立干线输气管道泄漏信号智能识别的TLBO-SVM模型;应用该模型,分类识别该管道在3类工况下的300组模拟压降速率信号。结果表明:该模型对3类不同工况下压降速率信号的识别准确率为92.22%;对泄漏口径为50~125 mm,压降速率范围为0.01~0.07 MPa/min的小孔泄漏,识别准确率为96.67%。针对某干线管道的实际泄漏压降速率信号,TLBO-SVM识别到的准确率为100%。

关键词: 支持向量机(SVM), 干线输气管道, 压降速率信号, 泄漏压力信号, 截断阀

Abstract:

In order to solve the problem that the pressure drop signals caused by compressor suction or upstream block valve cut-off conditions leaded to incorrect shut-off of the block valve, and the problem that the block valve failure due to insignificant pipeline pressure drop caused by small hole leakage, a simulation model was established. Taking a typical gas transmission trunk line as the research object, 300 sets of pressure drop signals under three different working conditions, namely compressor suction, emergency cut-off of the block valve and pipeline leakage, were obtained. The pressure drop rate of the pressure drop signal was calculated by point-to-point detection method. Singular value decomposition(SVD) method was used to extract the characteristics of the pressure drop rate signal, and the min-max normalization method was used to normalize the characteristic values of the pressure drop rate signal. SVM method was used to identify the characteristic value signals of different pressure drop rates, and the corresponding working conditions were obtained. To solve the problem that the unreasonable setting of kernel function parameters and penalty factors in the SVM model affected the accuracy of algorithm recognition, TLBO algorithm was used to optimize the kernel function parameters and penalty factors, and a TLBO-SVM model for intelligent identification of gas pipeline leakage signals was established. The model was applied to classify and identify 300 groups of simulated pressure drop rate signals in three working conditions. The results show that the recognition accuracy of the model is 92.22% for three kinds of pressure drop rate signals under different working conditions. The identification accuracy is 96.67% for small hole leakage with a leakage diameter of 50-125 mm and a pressure drop rate range of 0.01-0.07 MPa/min. For the actual leakage pressure drop rate signal of a main pipeline, the accuracy of TLBO-SVM is 100%.

Key words: support vector machine (SVM), trunk gas pipeline, pressure drop rate signal, pressure signal of leakage, block valve

中图分类号: