一种光纤管道安全预警系统的EAD 算法

1. 中国石油天然气管道通信电力工程有限公司;2. 中石油管道有限责任公司西气东输分公司;3. 中国石油集团工程股份有限公司

光纤管道安全预警系统;破土事件检测;特征提取;隐马尔科夫模型;支撑向量机分类器

An EAD algorithm for Pipeline Security Forewarning System
LI Gang1, WANG Yaozhong2, XING Haifeng3, ZHENG Dahai2, LIN Xiaohui1, ZENG Kehong1,YANG Wenming1, YAN Huipeng1,

1. China Petroleum & Gas Pipeline Telecommunication & Electricity Engineering Corporation; 2. PetroChina West-East Gas Pipeline Company; 3. China Petroleum Engineering Co. Ltd.

Pipeline Security Forewarning System (PSFS), excavation activity detection (EAD), feature extraction, hidden Markov model (HMM), support vector machine (SVM) classifier

备注

由于石油天然气的特殊性,管道周围存在多处非破坏性干扰事件,给预警系统报警的准确性带来了巨大挑战。为提高有背景干扰情况下对破土事件(Excavation Acitivity,EA)的检测水平,开发了破土事件检测(Excavation Acitivity Detection,EAD)算法。利用光纤管道安全预警系统(Pipeline Security Forewarning System,PSFS)在西气东输武汉—鄂州段的现场数据,建立了EA 和干扰事件(Non Excavation Acitivity,NEA)数据库。根据信号特性提炼了振动信号的Pisarenko谐波分解特征、相邻采样点的Itakura 距离特征、Mel 频率倒谱系数特征,设计了隐马尔科夫模型(Hidden Markov Model,HMM)和支持向量机(Support Vector Machine,SVM)双层分类结构,由HMM 计算最优状态序列,然后输入SVM 分类器区分信号中是否有EA。结果 表明:该EAD 算法结构能够有效提升有背景干扰情况下EA 信号的检出率,经现场测试EA 信号检出率为85.5%。研究结果可为光纤管道安全预警系统在开放性现场的应用提供理论依据。(图4表1,参[27]

Due to the particularity of oil and gas, there are many non-destructive interference events around oil and gas pipelines, which brings up great challenges to the warning accuracy of Pipeline Security Forewarning System (PSFS). In order to improve the detection level of excavation activity (EA) in the case of background interference, an excavation activity detection (EAD) algorithm was developed in this paper. A database inclusive of EA and non excavation activity (NEA)was established based on the field data of PSFS in Wuhan-Ezhou section of West-to-East Gas Pipeline. The Pisarenko harmonic decomposition feature of vibration signal, the Itakura distance feature of adjacent sampling points, and the Mel frequency cestrum coefficient (MFCC) feature were extracted according to signal properties. And a two-layer classification structure of hidden Markov model (HMM) and support vector machine (SVM) was designed. In this structure, after the optimal state sequence is calculated in HMM, it is input into SVM classifier to detect if there is an EA in the signals. It is shown that this EAD algorithm can effectively increase the detection rate of EA signal in the case of background interference, which is 85.5% during the field test. The research results provide the theoretical basis for the application of PSFS in open sites. (4 Figures, 1 Table, 27 References)