VMD和随机森林在反应堆金属撞击信号识别中的应用研究

PDF(758 KB)

振动与冲击 ›› 2021, Vol. 40 ›› Issue (5) : 102-107.

论文

者娜,刘才学,杨泰波,何攀,简捷,王广金

作者信息 +

Application of VMD and random forest in reactor metal impact signal recognition

ZHE Na, LIU Caixue, YANG Taibo, HE Pan, JIAN Jie, WANG Guangjin

Author information +

文章历史 +

摘要

反应堆中脱落部件或金属遗留件的存在会与压力边界产生碰撞而严重影响反应堆的安全，为有效解决由于特征信息不足和模型构建不合理而导致的反应堆中金属撞击信号识别精度低的问题，提出了一种基于变分模态分解（Variational Mode Decomposition，VMD）和随机森林算法（Random Forest, RF）的反应堆金属撞击信号识别方法。利用变分模态分解方法对原始信号进行分解得到若干分量信号，从各分量信号中提取分量特征以构成原始信号特征向量，将其作为输入建立VMD_RF模型来对撞击信号、自检信号、脉冲尖峰信号、噪声波动信号、通道闪断信号、噪声信号六类信号进行分类以识别出金属撞击信号。采用核电现场LPMS监测系统所采集的数据对该方法的可行性和有效性进行验证，结果表明，该方法在反应堆金属撞击信号的识别方面能够获得良好的识别效果。

Abstract

If loose parts or remaining metal exist in the reactor, they will collide with the pressure boundary and endanger the safety of the reactor. In order to effectively solve the problem of inaccurate identification of reactor metal impact signals caused by insufficient features and unsuitable model, a recognition approach based on variational mode decomposition (VMD) and random forest (RF) was proposed in this paper. The original signal was decomposed into several component signals through the variational mode decomposition method, then the component features were extracted from each component signals to form the original signal eigenvector. To recognize reactor metal impact signal, the original signal eigenvector were used as inputs to build the VMD_RF model to classify impact signal, self-checking signal, pulse spike signal, noise fluctuation signal, channel break signal and noise signal. The feasibility and validity of the method were verified by the data collected by LPMS in nuclear power plant, and the results showed that good recognition results could be obtained by this method.

导出引用

者娜,刘才学,杨泰波,何攀,简捷,王广金. VMD和随机森林在反应堆金属撞击信号识别中的应用研究[J]. 振动与冲击, 2021, 40(5): 102-107

ZHE Na, LIU Caixue, YANG Taibo, HE Pan, JIAN Jie, WANG Guangjin. Application of VMD and random forest in reactor metal impact signal recognition[J]. Journal of Vibration and Shock, 2021, 40(5): 102-107

参考文献

[1] Y. W. Chang, J. C. Jung, P. H. Seong. Algorithm automation for nuclear power plant Loose Parts Monitoring System [J]. Nuclear Engineering and Design, 2004,231(1):99-107.
[2] 蔡金锭, 鄢仁武. 基于小波分析与随机森林算法的电力电子电路故障诊断[J]. 电力科学与技术学报, 2011, 26(2):54-60.
Cai Jin-ding, Yan Ren-wu. Fault diagnosis of power electronic circuit based on wavelet analysis and random forests algorithm[J]. Journal of Electric Power Science and Technology, 2011, 26(2):54-60.
[3] VAPNIK V. The Nature of Statistical Learning Theory[M]. New York: Springer-Verlag, 1995.
[4] 袁胜发, 褚福磊. 支持向量机及其在机械故障诊断中的应用[J]. 振动与冲击, 2007, 36(11):29-35.
Yuan Sheng-fa, Chu Fu-lei. Support vector machines and its application in machine fault diagnosis[J]. Journal of Vibration and Shock, 2007, 36(11):29-35.
[5] 王小美. 特征维数对支持向量机分类器性能影响的研究——以高光谱遥感影像为例[J]. 测绘科学, 2011,36(1):55-57.
Wang Xiaonei-mei. Impacts of feature dim ensionality to the support vector machine classifier for hyperspectral remote sensing image[J]. Science of surveying and mapping, 2011, 36(1):55-57.
[6] BREIMAN L. Random Forests[J]. Machine Learning, 2001, 45: 5-32.
[7] DRAGOMIRETSKIY K，ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3)：531-544.
[8] 杜必强, 孙立江. 变分模态分解和熵理论在超声信号降噪中的应用[J]. 中国工程机械学报, 2017, 15(04):32-39.
Du Bi-qiang, Sun Li-jiang. Application of variational mode decomposition and entropy theory in ultrasonic signal de-noising[J]. Chinese Journal of Construction Machine, 2017, 15(04):32-39.
[9] 钱林, 康敏, 傅秀清, 等. 基于VMD的自适应形态学在轴承故障诊断中的应用[J].振动与冲击, 2017, 36(03):227-233.
QIAN Lin, KANG Min, FU Xiuqing, et al. Application of adaptive morphology in bearing fault diagnosis based on VMD[J].Journal of Vibration and Shock,2017,36(03):227-233.
[10] 黄衍, 查伟雄. 随机森林与支持向量机分类性能比较[J]. 软件, 2012, 33(6):107-110.
Huang Yan, Zha Wei-xiong. Comparison on Classification Performance Between Random Forests and Support Vector Machine[J]. Software, 2012, 33(6):107-110.
[11] 董绍江.基于优化支持向量机的空间滚动轴承寿命预测方法研究[D].重庆:重庆大学,2012.
Dong Shao-jiang. Research on Space Bearing Life Prediction Method Based on Optimized Support Vector Machine[D]. Chongqing: Chongqing University, 2012.
[12] Liu F, Liu Y, Chen F, et al. Residual life prediction for ball bearings based on joint approximate diagonalization of eigen matrices and extreme learning machine[J]. ARCHIVE Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science 1989-1996 (vols 203-210), 2015, 231(9).
[13] 马增强, 李亚超, 刘政, 等. 基于变分模态分解和Teager能
量算子的滚动轴承故障特征提取[J]. 振动与冲击, 2016, 13:134-139.
Ma Zeng-qiang, Li Ya-chao, Liu Zheng, et al. Rolling bearing fault feature extraction based on variational mode decomposition and Teager energy operator[J]. Journal of Vibration and Shock, 2016, 13:134-139.