基于EMICA-KRR的长输管道压力监测与泄漏定位方法

张新生, 王哲

系统工程理论与实践 ›› 2019, Vol. 39 ›› Issue (7) : 1885-1895.

PDF(1381 KB)
中国科学院数学与系统科学研究院期刊网
PDF(1381 KB)
系统工程理论与实践 ›› 2019, Vol. 39 ›› Issue (7) : 1885-1895. DOI: 10.12011/1000-6788-2017-2207-11
论文

基于EMICA-KRR的长输管道压力监测与泄漏定位方法

    张新生, 王哲
作者信息 +

A long distance pipeline pressure monitoring and leakage location method based on EMICA-KRR

    ZHANG Xinsheng, WANG Zhe
Author information +
文章历史 +

摘要

为解决长输管道压力监测过程中泄漏突发，难以实时预警并精确定位的问题，提出一种基于集成改进独立分量分析（EMICA）和核岭回归（KRR）的管道泄漏故障检测与定位方法.首先，建立基于EMICA算法的故障检测模型，提取并分离压力数据中的高斯信号和非高斯信号并构造相关统计量，实现故障信号分离与主分量选择；然后，根据EMICA模型获得的故障信号，进一步构造基于KRR算法的故障诊断模型，拟合数据得出故障信号压力变化幅值，实现泄漏信号的选择与泄漏故障的定位；最后进行TE（田纳西-伊斯曼）过程的数值仿真实验以验证算法的性能.仿真结果表明：EMICA-KRR算法拥有更良好的信号分离能力，可以准确识别泄漏故障信号并精确定位管段失效位置，克服了传统方法的低效、延时等缺点.

Abstract

In order to deal with the problem of sudden leakage during pressure monitoring of long-distance pipelines and being difficult to give early warning and accurate leakage location, a pipeline leakage fault detection and location model is proposed by using ensemble modified independent component analysis algorithm (EMICA) and kernel ridge regression algorithm (KRR). Firstly, a fault detection model based on EMICA algorithm is established, which extracts and separates Gaussian and non-Gaussian signals from pressure data and construct related statistics to achieve fault signal separation and principal component selection. Then, based on the fault signals obtained by the EMICA model, a fault diagnosis model by using the KRR algorithm is further constructed, and the data is fitted to obtain the amplitude of the pressure change of the fault signal, and the leakage signal selection and the location of the leakage fault are achieved. Finally, numerical simulation experiments of the TE (Tennessee-Eastman) process were performed to verify the performance of the proposed algorithm. The simulation results show that the EMICA-KRR algorithm has better signal separation capability, and can accurately identify the leakage fault signal and accurately locate the failure position of the pipe segment, which overcomes the shortcomings of the traditional methods such as inefficiency and delay.

关键词

故障诊断 / 压力监测 / 独立分量分析 / 核岭回归 / 泄漏定位 / 田纳西-伊斯曼过程

Key words

fault diagnosis / pressure monitoring / independent component analysis / kernel ridge regression / leak location / Tennessee-Eastman process

引用本文

EndNote

Ris (Procite)

Bibtex

导出引用
张新生 , 王哲. 基于EMICA-KRR的长输管道压力监测与泄漏定位方法. 系统工程理论与实践, 2019, 39(7): 1885-1895 https://doi.org/10.12011/1000-6788-2017-2207-11
ZHANG Xinsheng , WANG Zhe. A long distance pipeline pressure monitoring and leakage location method based on EMICA-KRR. Systems Engineering - Theory & Practice, 2019, 39(7): 1885-1895 https://doi.org/10.12011/1000-6788-2017-2207-11
中图分类号： X913.4   

参考文献

[1] 谷雨, 徐宗本, 孙剑, 等. 基于PCA与ICA特征提取的入侵检测集成分类系统[J]. 计算机研究与发展, 2006, 43(4):633-638.Gu Y, Xu Z B, Sun J, et al. An intrusion detection ensemble system based on the features extracted by PCA and ICA[J]. Journal of Computer Research and Development, 2006, 43(4):633-638.
[2] 杨英华, 李召, 陈永禄, 等. 基于CVA-ICA与CSM的故障诊断方法[J]. 东北大学学报(自然科学版), 2012, 33(12):1685-1689.Yang Y H, Li Z, Chen Y L, et al. Fault diagnosis based on CVA-ICA and CSM[J]. Journal of Northeastern University, 2012, 33(12):1685-1689.
[3] 王普, 张亚潮, 高学金, 等. 基于MICA-OCSVM的间歇过程故障监测[J]. 北京工业大学学报, 2014, 40(11):1472-1477.Wang P, Zhang Y C, Gao X J, et al. Fault detection of batch process based on MICA-OCSVM[J]. Journal of Beijing University of Technology, 2014, 40(11):1472-1477.
[4] 辜小花, 李景哲, 李太福, 等. 基于动态核独立元统计量的石油管道泄漏检测[J]. 仪器仪表学报, 2017, 38(1):166-173.Gu X H, Li J Z, Li T F, et al. Oil pipeline leak detection based on index of dynamic Kernel independent components[J]. Chinese Journal of Scientific Instrument, 2017, 38(1):166-173.
[5] 王明达, 张来斌, 梁伟, 等. 基于独立分量分析和支持向量机的管道泄漏识别方法[J]. 石油学报, 2010, 31(4):659-663.Wang M D, Zhang L B, Liang W, et al. Pipeline leakage detection method based on independent component analysis and support vector machine[J]. Acta Petrolei Sinica, 2010, 31(4):659-663.
[6] 张宇, 靳世久, 何静菁. 基于动态压力信号的管道泄漏特征提取方法研究[J]. 石油学报, 2010, 31(2):338-342.Zhang Y, Jin S J, He J J. Extraction method for pipeline leakage feature based on dynamic pressure signal[J]. Acta Petrolei Sinica, 2010, 31(2):338-342.
[7] 林伟国, 王晓东, 戚元华, 等. 管道泄漏信号和干扰信号的数字化判别方法[J]. 石油学报, 2014, 35(6):1197-1203.Lin W G, Wang X D, Qi Y H, et al. Digital identification method for pipeline leak and interference signal[J]. Acta Petrolei Sinaica, 2014, 35(6):1197-1203.
[8] 衷路生, 吴秀江, 谭畅, 等. 基于ICA-PCA和Lasso的过程故障诊断[J]. 华中科技大学学报(自然科学版), 2016, 44(10):98-102.Zhong L S, Wu X J, Tan C, et al. Process fault detection and diagnosis based on ICA-PCA and Lasso[J]. Journal of Huazhong University of Science and Technology (Nature Science Edition), 2016, 44(10):98-102.
[9] Tong C, Lan T, Shi X. Ensemble modified independent component analysis for enhanced non-Gaussian process monitoring[J]. Control Engineering Practice, 2017, 58:34-41.
[10] Yu X, Zhang Y, Yin G, et al. Discrimination of three dimensional fluorescence spectra based on wavelet analysis and independent component analysis[J]. Spectrochimica Acta Part A:Molecular & Biomolecular Spectroscopy, 2014, 124(8):52-58.
[11] Hyvärinen A, Oja E. Independent component analysis:Algorithms and applications[J]. Neural Networks, 2000, 13(4-5):411-430.
[12] Xian L, He K, Lai K K. Gold price analysis based on ensemble empirical model decomposition and independent component analysis[J]. Physica A:Statistical Mechanics & its Applications, 2016, 454:11-23.
[13] Liu C, Li Y, Fang L, et al. Experimental study on a de-noising system for gas and oil pipelines based on an acoustic leak detection and location method[J]. International Journal of Pressure Vessels & Piping, 2017, 151:20-34.
[14] Tong C, Lan T, Shi X. Double-layer ensemble monitoring of non-gaussian processes using modified independent component analysis[J]. ISA Transactions, 2017, 68:181-188.
[15] 何小娟, 曾建潮. 基于Bayesian统计推理的分布估计算法求解柔性作业车间调度问题[J]. 系统工程理论与实践, 2012, 32(2):380-388.He X J, Zeng J C. Solving flexible job-shop scheduling problems with Bayesian statistical inference-based estimation of distribution algorithm[J]. Systems Engineering-Theory & Practice, 2012, 32(2):380-388.
[16] 刘剑, 龚志恒, 吴成东. 基于Multi-kernel和KRR的数据还原算法[J]. 控制与决策, 2014, 29(5):821-826.Liu J, Gong Z H, Wu C D. Data reconstruction algorithm based on multi-kernel and KRR[J]. Control and Decision, 2014, 29(5):821-826.
[17] Chen B W, Abdullah N N B, Park S, et al. Efficient multiple incremental computation for Kernel Ridge Regression with Bayesian uncertainty modeling[J]. Future Generation Computer Systems, 2018, 82:679-688.
[18] Zhang Y, Chen S, Li J, et al. Leak detection monitoring system of long distance oil pipeline based on dynamic pressure transmitter[J]. Measurement, 2014, 49(1):382-389.
[19] Shen Y, Ding S X, Haghani A, et al. A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process[J]. Journal of Process Control, 2012, 22(9):1567-1581.
[20] Lee J M, Qin S J, Lee I B. Fault detection and diagnosis based on modified independent component analysis[J]. Aiche Journal, 2006, 52(10):3501-3514.
[21] Exterkate P, Groenen P J F, Heij C, et al. Nonlinear forecasting with many predictors using kernel ridge regression[J]. Creates Research Papers, 2016, 32(3):736-753.
[22] Zhang S, Hu Q, Xie Z, et al. Kernel ridge regression for general noise model with its application[J]. Neurocomputing, 2015, 149(PB):836-846.
[23] 余乐安. 基于最小二乘近似支持向量回归模型的电子商务信用风险预警[J]. 系统工程理论与实践, 2012, 32(3):508-514.Yu L A. E-commerce credit risk early-warning with a least squares proximal support vector regression model[J]. Systems Engineering-Theory & Practice, 2012, 32(3):508-514.

基金

国家自然科学基金面上项目（41877527）；陕西省自然科学基金（2016JM6023）
PDF(1381 KB)

Accesses

Citation

Detail
段落导航
相关文章

/

〈 〉