基于参数化小波的主冷却剂泵故障特征识别  

Feature recognition of the RCP fault based on the parameterized wavelet

作　　者：李彬 夏虹 

机构地区：[1]哈尔滨工程大学核安全与仿真技术国防重点学科实验室,黑龙江哈尔滨150001

出　　处：《哈尔滨工程大学学报》2014年第2期261-266,共6页Journal of Harbin Engineering University

基　　金：国家自然科学基金资助项目(51379046)

摘　　要：针对核反应堆冷却剂泵在经过长期运行之后,转子可能出现的裂纹故障,利用小波分析技术,能够实现对这些故障特征的识别。在研究中,不同于以往的直接利用现有小波分析信号特征,而是从小波滤波器的角度出发,利用紧支撑正交小波的二尺度方程及尺度系数和小波系数的特点,结合滤波器的多相表示以及无损FIR滤波器的矩阵计算方法,对小波滤波器系数进行了参数化。通过选取不同的序列长度和消失矩,计算得到一系列小波滤波器系数。最后取其中一组参数化小波以及具有相同消失矩的db小波分别对反应堆主冷却剂泵的振动仿真信号进行分析,结果显示该参数化小波可以清晰准确地识别出转子的裂纹故障特征。Focusing on the possibility of a crack fault appearing in a rotor after the reactor coolant pump （ RCP ） has operated for a long time, the wavelet analysis technology may be utilized for the identification of these fault features. This research offered a different method from the previous way of analyzing the signal feature by directly utilizing the existing wavelet, from the viewpoint of the wavelet filter, by utilizing the characteristics of the two-scale equation compactly supported orthogonal wavelet, the scale coefficients and the wavelet coefficients, in combination with the polyphase expression of the filters and the matrix calculation method of the lossless FIR filters, the wavelet filter co-efficients are parameterized. A series of wavelet filter coefficients are calculated by choosing different sequential lengths and vanishing moments. Finally, the vibration simulation signal of the RCP is analyzed respectively by ap-plying a group of parameterized wavelets and the db wavelets which have the same vanishing moment. The results show that the fault feature of a rotor crack may be identified clearly and accurately by the parameterized wavelets.

关 键 词：反应堆冷却剂泵 裂纹故障 参数化小波 特征识别 转子裂纹 小波滤波器 小波分析 

分 类 号：TL37[核科学技术—核技术及应用]