Cluster Analysis of Signals of Storage Tank Acoustic Emission Testing
摘 要
聚类分析作为一种先进的无监督模式识别技术, 能在无先验知识的情况下对数据进行分类并揭示数据内部结构。通过优化K均值聚类算法, 并应用浮动门槛值重新计算声发射检测波形数据的常用特征参量作为聚类算法的输入向量, 采用浮动门槛计算得到的特征向量更能反映声发射波形特征, 取得良好的聚类效果。通过现场储罐声发射检测数据实例的聚类分析, 结果表明K均值聚类能有效地区别不同声源和传播途径的声发射信号, 具有很好的去噪效果, 能有效提高罐底声发射检测评价准确度。
Abstract
Cluster analysis is an advanced unsupervised pattern recognition technology, which can classify data and reveal the data internal structure without prior knowledge. In this paper, the application of floating threshold value to calculate the characteristic parameters of acoustic emission test common waveform data is used as input vector clustering algorithm by optimizing K means clustering calculation. The featuring vector by floating threshold calculation has more acoustic emission waveform characters, obtaining good clustering effect. By analysis of acoustic emission test data of storage tank, the results show that K means clustering can determine different sound signals from different sound sources and propagation paths, affording excellent de-noise effect and effectively improving acoustic emission test accuracy of tank bottom.
中图分类号 TG115.28,TB52
所属栏目 实践经验
基金项目
收稿日期 2013/9/16
修改稿日期
网络出版日期
作者单位点击查看
备注沈书乾(1979-), 男, 工程师, 主要从事承压类特种设备先进检测方法的研究工作。
引用该论文: SHEN Shu-qian,LI Hai-san. Cluster Analysis of Signals of Storage Tank Acoustic Emission Testing[J]. Nondestructive Testing, 2014, 36(9): 54~58
沈书乾,李海三. 储罐声发射检测信号的聚类分析[J]. 无损检测, 2014, 36(9): 54~58
共有人对该论文发表了看法,其中:
人认为该论文很差
人认为该论文较差
人认为该论文一般
人认为该论文较好
人认为该论文很好
参考文献
【1】KWON J R,LYN G J,LEE T H, et al.Acoustic emission testing of repaired storage tank[J]. International Journal of Pressure Vessels and Piping,2001(78):373-378.
【2】李一博,孙立瑛,靳世久,等.大型常压储罐底板的声发射在线检测[J].天津大学学报,2008,41(1):11-16.
【3】戴光.压力容器安全工程学[M].哈尔滨: 黑龙江科学技术出版社,1995.
【4】MURTHY CRL, DATTAGURU B, RAO AK. Application of pattern recognition concepts to acoustic emission dignals analysis[J]. Acoustic Emission 1987,6(1):19-28.
【5】MOEVUS M, ROUBY D, GODIN N, et al. Analysis of damage mechanism sandas sociated acoustic emission int woSiC/[Si–B–C] composites exhibiting different tensile curves. PartII: Unsupervised acoustic emission data clustering[J]. Compos Sci Technol,2008,68(6):1258-1265.
【6】MAC QUEEN J. Some methods for classification and analysis of multivariate observations[C]. Proceedings of the 5th Berkeley symposium on mathematical statistcs and probability. University of California Press;1967:281-97.
【2】李一博,孙立瑛,靳世久,等.大型常压储罐底板的声发射在线检测[J].天津大学学报,2008,41(1):11-16.
【3】戴光.压力容器安全工程学[M].哈尔滨: 黑龙江科学技术出版社,1995.
【4】MURTHY CRL, DATTAGURU B, RAO AK. Application of pattern recognition concepts to acoustic emission dignals analysis[J]. Acoustic Emission 1987,6(1):19-28.
【5】MOEVUS M, ROUBY D, GODIN N, et al. Analysis of damage mechanism sandas sociated acoustic emission int woSiC/[Si–B–C] composites exhibiting different tensile curves. PartII: Unsupervised acoustic emission data clustering[J]. Compos Sci Technol,2008,68(6):1258-1265.
【6】MAC QUEEN J. Some methods for classification and analysis of multivariate observations[C]. Proceedings of the 5th Berkeley symposium on mathematical statistcs and probability. University of California Press;1967:281-97.
相关信息