Spark云计算平台下的结构物理参数辨识

摘要
图/表
参考文献(19)
相关文章 (15)

全文: PDF (1348 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要结构物理参数辨识是结构损伤识别的一个关键问题。针对结构物理参数辨识精度不高、海量数据处理计算效率低下和在单机环境下运算资源不足的问题，本文提出一种云平台下改进并行化多粒子群协同优化算法(IPMPSCO)的结构物理参数辨识方法。在云计算平台下，引入Apache Spark云计算平台的弹性分布式数据集RDD，对传统多粒子群协同优化算法(MPSCO)的结构物理参数辨识进行分布式并行化改进。为了验证所提方法的准确性和处理海量数据的能力，在8节点的云计算集群上对一个30层框架数值试验和一个7层钢框架试验进行结构物理参数辨识。结果表明，本文所提方法具有良好的精度和稳定性，在执行效率上优于单机，且具有较好的并行能力。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	骆剑彬
	姜绍飞
	任晖
	赵剑

关键词 ： Apache Spark, 粒子群算法, 结构物理参数辨识, 分布式并行处理

Abstract：The physical parameters identification of structures is a key topic in structural damage detection. Considering the problem of low accuracy and computation efficiency and insufficient computation resources in the physical parameters identification of structures, an improved parallel multiparticle swarm cooperative optimization(IPMPSCO) algorithm was proposed. Based on the apache spark cloud computing platform, the resilient distributed datasets(RDD) was introduced to parallelly and distributedly improve the traditional multiparticle swarm cooperative optimization (MPSCO) algorithm for the identification of physical parameters. In order to verify the accuracy of the proposed method and the ability to deal with the huge number of data, a 30story frame numerical simulation and a 7story steel frame test were conducted to identify the physical parameters on the cloud computing cluster of 8 nodes. The results show that the approach proposed has excellent precision, stability, and fairly parallel ability in the computation efficiency.

Key words： Apache Spark particle swarm optimization ( PSO ) physical parameter identification; distributed parallel computing

收稿日期: 2016-12-29 出版日期: 2018-07-15

引用本文:

骆剑彬，姜绍飞，任晖，赵剑. Spark云计算平台下的结构物理参数辨识[J]. 振动与冲击, 2018, 37(14): 67-73.
LUO Jianbin, JIANG Shaofei, REN Hui, ZHAO Jian. Structural physical parameter identification based on the spark cloud computing patform. JOURNAL OF VIBRATION AND SHOCK, 2018, 37(14): 67-73.

链接本文:

http://jvs.sjtu.edu.cn/CN/ 或 http://jvs.sjtu.edu.cn/CN/Y2018/V37/I14/67

[1] 姜绍飞. 结构健康监测-智能信息处理及应用[J]. 工程力学，2009，26(2)：184-212.
JIANG Shao-fei. Structuralhealth monitoring-intelligent information processing and apllication[J]. Engineering Mechamics, 2009,26(2):184-212.
[2] 林健富，程瀛，黄建亮，等. 结构健康监测-智能信息处理及应用[J]. 振动与冲击，2010，29(12)：55-59.
LIN Jian-fu,CHENG Ying,HUANG Jian-liang,et al. Massive data processing in large-scale structural health monitoring and the corresponding database development[J]. Journalofvibration and shock, 2010,29(12):55-59.
[3]Wikipedia. Clound computing[EB/OL].http://zh.wikipedia.org/wiki,2013-07-24.
[4] 潘巍，李战怀. 大数据环境下并行计算模型的研究进展[J]. 华东师范大学学院：自然科学版，2014(5)：43-54.
PAN Wei;LI Zhan-huai. Development of parallel computing models in the big data era[J]. Journal of East China Normal University:Natural Science, 2014(5):43-54.
[5] 朱晓斌，周应新，杨建喜，等. 基于大数据的桥梁监测信息聚类分析[J]. 公路交通科技：应用技术版，2015(4)：167-169.
[6] Ventura, Carlos E., Bebamzadeh, etc. Efficient performance‐based design using parallel and cloud computing [J]. Structural Design of Tall and Special Buildings, 2015, 24(17):989 -1001.
[7] 陈亮. 结构健康监测物联网系统的云计算应用研究[D]. 哈尔滨：哈尔滨工业大学，2013.
CHEN Liang. Study on application of cloud computing in structural health monitoring of things system [D]. Harbin: Harbin industrial university, 2013.
[8] 段梦凡. 基于Hadoop平台的二维悬梁应力计算的有限元方法设计与实现[D]. 天津：南开大学，2013.
DUAN Meng-fan. Design and Implement of Finite Element Methodof 2D Cantilever Stress Analysis on Hadoop Platform[D]. Tianjin: Nankai University,2013.
[9] 林菁淳. 基于云计算的结构损伤检测[D]. 广州：暨南大学，2014.
JC Lin. Structural Damage Detection Based on Cloud Computing [D]. Guangzhou: Jinan University, 2014.
[10]L Yu, JC Lin. Cloud Computing-Based Time Series Analysis for Structural Damage Detection[J]. Journal of Engineering Mechanics, 2015(C4015002): 1-14.
[11] 雷学智. 云计算平台下分布式支持向量机在煤炭行业分类预测应用[J]. 煤炭技术，2013，32(11)：248-250.
LEI Xue-zhi. Application of Distributed Support Vector Machine Based on Cloud Platform in Coal System[J].Coal Technology, 2013, 32(11): 248-250.
[12] M Chowdhury. Performance and Scalability of Broadcast in Spark[EB/OL].http://www.cs.berkeley.edu/~agearh/cs267.sp10/files/mosharaf-spark-bc-report-spring10.pdf, 2014-10-08.
[13] 范炜玮，赵东升. 大数据处理平台Spark及其生物医学应用[J].中国中医药图书情报杂志，2015，39(2)：1-5.
FAN Wei-wei. Big Data Processing Platform Spark and Its Biomedical Applications[J]. Chinese Journal of Library and Information Science for Traditional Chinese Medicine,2015,39(2):1-5.
[14] Kennedy J, EberhartR. Particle swarm optimization[C] //Proceedings of IEEE International Conference on Neural Networks. Piscataway: IEEE Service Center, 1995,1942-1948.
[15]李爱国. 多粒子群协同优化算法[J]. 复旦学报：自然科学版，2004，43(5)： 923-925.
LI Ai-guo.Particle Swarms Cooperative Optimizer[J]. Journal of Fudan University:Natural Science,2004,43(5):923-925.
[16] 王保义，王冬阳，张少敏. 基于Spark和IPPSO_LSSVM的短期分布式电力负荷预测算法[J].电力自动化设备，2016，36(1)：117-122.
WANG Baoyi,WANG Dongyang, ZHANG Shaomin. Distributed short-term load forecasting algorithm based on Spark and IPPSO_LSSVM[J]. Electric Power Automation Equipment, 2016,36(1):117-122.
[17] 吴思瑶.基于改进协同PSO的时变非线性结构损伤识别研究[D].福州：福州大学，2014.
WU Si-yao. Damage Identification for Time-varying Nonlinear Structure based on Improved Multi-Particle Swarm Coevolution Optimization Algorithm[D]. Fuzhou: Fuzhou University, 2014.
[18] Corporation H P. A time-domain structural damage detection method based on improved multiparticle swarm coevolution optimization algorithm[J]. Mathematical Problems in Engineering, 2014, 44(1): 77-85.
[19]陈倩. 并行程序性能分析系统的研究与实现[D]. 长沙：国防科学技术大学，2005.
CHEN Jin. Research and Implementation of Parallel Program Performance Analysis System [D]. Changsha: National University of Defence Technology, 2015.