[1]郝永梅,覃 妮,邢志祥,等.基于记忆模拟退火与粒子群的多点小孔泄漏信号盲分离方法[J].常州大学学报(自然科学版),2019,31(01):85-92.[doi:10.3969/j.issn.2095-0411.2019.01.013]
 HAO Yongmei,QIN Ni,XING Zhixiang,et al.BSS of Multi Points Small Leakage Signals Based on Memory Simulated Annealing and PSO[J].Journal of Changzhou University(Natural Science Edition),2019,31(01):85-92.[doi:10.3969/j.issn.2095-0411.2019.01.013]
点击复制

基于记忆模拟退火与粒子群的多点小孔泄漏信号盲分离方法()
分享到:

常州大学学报(自然科学版)[ISSN:2095-0411/CN:32-1822/N]

卷:
第31卷
期数:
2019年01期
页码:
85-92
栏目:
安全工程
出版日期:
2019-01-28

文章信息/Info

Title:
BSS of Multi Points Small Leakage Signals Based on Memory Simulated Annealing and PSO
文章编号:
2095-0411(2019)01-0085-08
作者:
郝永梅1 覃 妮1邢志祥1岳云飞2严欣明2钟 成3
(1.常州大学 环境与安全工程学院,江苏 常州 213164; 2.江苏省特种设备安全监督检验研究院 常州分院,江苏 常州 213164; 3.常州新奥燃气工程有限公司,江苏 常州 213161)
Author(s):
HAO Yongmei1 QIN Ni1 XING Zhixiang1 YUE Yunfei2 YAN Xinming2 ZHONG Cheng3
(1. School of Environmental and Safety Engineering, Changzhou University, Changzhou 213164, China; 2. Changzhou Branch, Jiangsu Institute of Special Equipment Safety Supervision and Inspection,Changzhou 213164, China; 3. Changzhou Xin’ao Gas Engineening C
关键词:
盲源分离 模拟退火粒子群 记忆模拟退火与粒子群 多点小孔泄漏 定位应用
Keywords:
blind source separation SAPSO MSAPSO multi-point leaking positioning application
分类号:
TK 8
DOI:
10.3969/j.issn.2095-0411.2019.01.013
摘要:
为了减少环境噪声及其多点泄漏信号的相互影响,提高管道泄漏定位精度,提出一种盲源分离算法,即基于记忆模拟退火与粒子群(Memory Simulated Annealing and Particle Swarm Optimization,MSAPSO)的盲源分离算法。将嵌入记忆器的模拟退火算法与粒子群算法引入盲源分离算法中,结合概率突跳性在解空间中随机寻找极大似然目标函数,通过循环迭代得出全局最优,改善迂回搜索方式,提高收敛速度与分离精度。并将MSAPSO盲源分离算法应用于城市压力管道多点小孔泄漏定位实验,结果表明:改进的MSAPSO盲源分离算法,将管道多点泄漏定位平均误差从7.7%降到3.3%。
Abstract:
In order to reduce the environmental noise and the influence of multi point leakage signal, improving pipeline leak location accuracy, a blind source separation algorithm is proposed, which is based on particle swarm memory simulated annealing(Memory Simulated Annealing and Particle Swarm Optimization, MSAPSO)algorithm for blind source separation. The simulated annealing algorithm and particle swarm algorithm is embedded into the memory of the blind source separation algorithm, combined with the probabilistic jumping property of random search for the maximum likelihood objective function in the solution space, by iterating the global optimization to improve the circuitous search methods, the convergence speed and the precision of separation. The MSAPSO blind source separation algorithm is applied to the multi holes leak location experiment of urban pressure pipeline. The results show that the improved MSAPSO blind source separation algorithm reduces the pipeline multi-point leak location error from 7.7% to 3.3%.

参考文献/References:


[1]郝永梅, 覃妮, 陆贵荣, 等. 应用独立分量分析管道两点泄漏定位[J].消防科学与技术,2017, 36(10):1454-1458.
[2]郭世旭, 刘胜, 陈秀丽, 等. 管道微小泄漏内检测近场声信号特性研究[J]. 电子测量与仪器学报, 2016, 30(6):834-844.
[3]孙洁娣, 肖启阳, 温江涛, 等. 基于LMD包络谱熵及SVM的天然气管道微小泄漏孔径识别[J]. 机械工程学报, 2014, 50(20):18-25.
[4]吴国忠, 邢畅, 齐晗兵, 等. 输油管道多点泄漏地表温度场数值模拟[J]. 油气储运, 2011, 30(9):677-680.
[5]DELGADO-AGUINAGA J A, BESANCON G, BEGOVICH O, et al. Multi-leak diagnosis in pipelines based on Extended Kalman Filter[J]. Control Engineering Practice, 2016, 49:139-148.
[6]RUI Z H, HA G Q, ZHANG H, et al. A new model to evaluate two leak points in a gas pipeline[J]. Journal of Natural Gas Science and Engineering, 2017(46)491-497.
[7]刘光晓, 孟令雅, 刘翠伟, 等. 基于盲源分离技术的泄漏音波信号滤波方法分析[J]. 振动与冲击, 2014, 33(24):192-199.
[8]殷琴. 盲源分离算法在管道泄漏检测中的应用研究[D]. 大庆:东北石油大学, 2013.
[9]高华, 王宝光, 杜振辉, 等. 双谱在管道两点泄漏定位模型中的应用[J].纳米技术与精密工程, 2009, 7(5):445-450.
[10]孙洁娣, 郝雅立, 温江涛,等. 基于EMD的高压燃气管道泄漏信号欠定盲分离方法[J]. 振动与冲击, 2013, 32(18):81-86.
[11]LEE T W, GIROAMI M, SEJNOWSKI T J. Independent component analysis using an extended infomax algorithm for mixed subgaussian and supergaussian sources[J]. Neural Computation, 1999, 11(2):417-441.
[12]张霞. 粒子群优化算法在语音信号盲源分离技术中的研究[D].沈阳:沈阳航空航天大学,2013.
[13]KENNEDY J. The particle swarm: social adaptation of knowledge[C]. New York: IEEE International Conference on Evolutionary Computation, 2002:303-308.
[14]魏秀业. 基于粒子群优化的齿轮箱智能故障诊断研究[D].太原:中北大学,2009.
[15]林梅金, 王飞. 模拟退火粒子群优化算法在异步电动机参数辨识中的应用[J]. 微特电机, 2010, 38(4):33-36.
[16]王凌. 智能优化算法及其应用[M]. 北京:清华大学出版社,2001:17-20.
[17]康立山. 非数值并行算法:第1册 模拟退火算法[M]. 北京:科学出版社, 1994:169-174.

备注/Memo

备注/Memo:
收稿日期:2018-09-24。
基金项目:江苏省重点研发计划专项(BE2018642); 常州市科技项目(CM20179060)。
作者简介:郝永梅(1970—),女,重庆万州人,硕士,副教授。E-mail:hymzcs@cczu.edu.cn
更新日期/Last Update: 2019-02-20