石油科技论坛

石油科技论坛 ›› 2016, Vol. 35 ›› Issue (增刊): 194-196.DOI: 10. 3969/ j. issn. 1002-302x. 2016. z1. 064

• 成果推介 • 上一篇    下一篇

管道光纤安全预警技术中的威胁事 件识别算法研究

刘　路1，2　周　琰1，2　谭东杰1，2　孙　巍1，2　王海明1，2　田孝忠1，2   

  1. 1. 油气管道输送安全国家工程实验室; 2. 中国石油管道科技研究中心
  • 出版日期:2017-02-22 发布日期:2017-02-22
  • 基金资助:
    中国石油天然气股份有限公司科学研究与技术开发项目“油气管道与关键设备风险预控及风险评价技术研究”; 国家重点研发计划“公共安全风险防控与应急技术装备” 重点专项。

Research on Algorithm of Identification of Threat Events in Technology of Pipeline Security Early Warning by Optical Fibers

Liu Lu1,2, Zhou Yan1,2, Tan Dongjie1,2, Sun Wei1,2, Wang Haiming1,2, Tian Xiaozhong1,2,   

  1. 1. National Engineering Laboratory for petroleum Pipeline Safety, Langfang 065000, China;2. PetroChina Pipeline R&D Center, Langfang 065000, China
  • Online:2017-02-22 Published:2017-02-22
  • Supported by:
     

PDF

摘要： 如何有效识别人工挖掘、机械挖掘和车辆经过等油气管道安全威胁事件, 对基于相干瑞利的管道光纤安 全预警系统是至关重要的问题。对此提出一种基于优化支持向量机的管道安全威胁事件识别方法。该方法对管道光纤 安全预警系统采集到的管道沿线振动信号进行分析, 提取各频段的归一化能量与信号持续时间作为特征向量, 利用人 工蜂群算法对支持向量机的惩罚因子和核函数参数进行优化, 采用优化后的支持向量机对特征进行分类。通过港枣成 品油管线安全实验对该方法测试, 获得了90. 7%的识别正确率, 证明了该方法的有效性和工程应用价值。

 

关键词: 油气管道, 安全预警, 支持向量机, 人工蜂群算法, 参数优化

Abstract: How to effectively identify the threats to security of oil and gas pipelines, such as manual excavation, mechanical excavation and vehicle passing, is of vital importance to the coherent Rayleigh-based pipeline fiber security warning system. This paper proposes a method of pipeline security threat event recognition based on optimized support vector machine (SVM). The method is used to analyze the vibration signals along the pipeline collected by the optic fiber safety warning system, and extract the normalized energy and signal duration of each frequency band as the eigenvectors (proper vectors). The penalty factors and kernel function parameters of the SVM are optimized by the artificial bee colony algorithm,and then the optimized SVM is used to classify the features. This method was tested by the safety experiment of the product oil pipeline of Dagang - Zaozhuang, and the correct identification rate of 90. 7% was obtained. All these proved the effectiveness of the method and its engineering application value.

中图分类号: