摘要
提出了基于小波能谱和小波信息熵的油气管道异常振动事件识别方法。基于Mach-Zehnder光纤干涉仪原理的分布式光纤油气管道安全监测系统实时检测管道沿途振动信号,对测量的时间序列进行小波变换,根据小波系数计算小波能谱与小波信息熵,通过小波能谱和小波信息熵值两种测度识别不同的管道安全异常事件。港枣线成品油管道的现场实验结果表明,该方法可以快速有效地识别管道周围发生的泄漏及其他异常情况,其总体识别准确率达到98.5%,有效降低了误报警率,具有较强的在线工况识别能力。
A recognition method for safety-detection events of oil and gas pipelines based on the wavelet energy spectrum and the wavelet information entropy was studied.It was used in a distributed optical fiber oil and gas pipeline safety detection system based on the principle of Mach-Zehnder optical fiber interferometer for the safety of oil and gas pipelines.In this pre-warning system,an optical cable was laid along a pipeline in the same ditch and three single-mode optical fibers in the optical cable built up a distributed micro-vibrant measuring sensor.The vibration signal caused by leakage and other abnormal events could be detected by using the system in real-time.The detection signals of abnormal events were decomposed into sub-signals in different frequency bands by use of wavelet transformation with multi-resolution analysis.Thus,both frequency band energy features and wavelet information entropy of the above-mentioned detection signals were extracted;the system could recognize abnormal intrusion events occurred along the pipeline through the wavelet energy spectrum and the wavelet information entropy in real-time.Finally,the experimental data obtained at GangZao product pipeline were used to evaluate the proposed method and the overall recognition accuracy rate reached 98.5%,it verified the feasibility and effectiveness of this method.
出处
《振动与冲击》
EI
CSCD
北大核心
2010年第5期1-4,共4页
Journal of Vibration and Shock
基金
国家自然科学基金重点项目(No.60534050)
教育部博士点基金项目(No.200800560020)
关键词
油气管道
分布式光纤传感器
小波能谱
小波信息熵
模式识别
petroleum pipeline
distributed optical fiber sensor
wavelet energy spectrum
wavelet information entropy
pattern recognition
