|
|
Mass estimation of loose parts in nuclear power
plant based on SVM |
ZHENG Hua-wen1, CAO Yan-long1, YANG Jiang-xin1, HE Yuan-feng1,
FANG Li-xian2, XIE Yong-cheng3 |
1. Institute of Modern Manufacturing Engineering, Zhejiang University, Hangzhou 310027, China;
2. Hangzhou Dianzi University, Hangzhou 310018, China;
3. Shanghai Nuclear Engineering Research and Design Institute, Shanghai 200233, China |
|
|
Abstract By the analysis of traditional mass estimation methods, a new method for mass estimation of loose parts in Nuclear Power Plant (NPP) based on the support vector machine (SVM) was proposed. A vector was obtained which represent the burst signal’s spectrum by analyzing the relationship between the burst signals frequency spectrum and the mass of loose parts. Set the vector as input data and the mass of loose part as the output data to train the SVM, and then the mass of loose part can be estimated by the trained SVM model. Experimental results show that the method has higher accuracy and easier to achieve than the traditional methods. It provides a new way for mass estimation of loose parts in Nuclear power plants.
|
Published: 21 September 2010
|
|
基于支持向量机的核电站松动件质量估计方法
在分析传统松动件质量估计方法的基础上,提出一种基于支持向量机(SVM)的核电站松动件质量估计方法.分析松动件跌落碰撞信号的频率分布特征与松动件质量之间的关系,提取表征信号频谱的特征向量.以该特征向量为SVM的输入,松动件质量为输出,实现对核电站松动件质量大小的估计.最后进行平板实验验证,实验结果表明,该方法比传统方法具有更高的计算精度和实现方便性,为核电站松动件质量估计提供了一种新的方法.
|
|
[1] BECHYTOLD B, KUNZE U. KUES’95: the modern diagnostic system for loose parts monitoring [J].Progress in Nuclear Energy,1999,34(3):221230.
[2] MAYO W. Loose part mass and energy estimation [J]. Progress in Nuclear Energy,1999,34(3):263282.
[3] FIGEDY S, OKSA G. Modern methods of signal processing in the loose part monitoring system [J].Progress in Nuclear Energy,2005,46(3):253267.
[4] 潘翔,李洁冰. 一种基于支持向量机的目标定位方法[J],浙江大学学报:工学版,2006,40(3):482489.
PAN xiang, LI jiebing. Support vector machinebased algorithm for target localization [J].Journal of Zhejiang University:Engineering Science,2006,40(3):482489.
[5] VAPNIK V, GOLOWICH S, SMOLA A. Support vector method for function approximation, regression estimation, and signal processing [C]∥ Advances in Neural Information Processing Systems 1996. Cambridge: MIT Press,1997:281287.
[6] CORTES C,VAPNIK V.Supportvector networks [J].Machine learning,1995,20(1): 125.
[7] 刘金汇. 模式识别技术用于核电站松动件质量估计模型研究[J].核动力工程,2001,22(5),465470.
LIU jinhui. Model study of mass estimation of loose parts in PWRs using pattern recognition [J]. Nuclear Power Engineering, 2001, 22(5):465469. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|