摘要
控制棒驱动机构(CRDM)转子部件工作在高温高压的冷却剂中,一旦发生故障,其维修或更换的成本高、耗时长、牵连工程大。针对CRDM转子在运行过程中噪声影响过大的问题,提出一种集合经验模态分解(EEMD)结合小波阈值(WTM)的去噪方法,对CRDM转子振动信号进行去噪处理后提取时域特征、频域特征、IMF的能量和样本熵特征等信号作为标签,输入核极限学习机(KELM)分类模型中进行分类识别,并引入了鲸鱼优化算法(WOA)对KELM的重要参数进行自寻优,提高了模型的识别准确率。通过对比实验,证明了论文所提方法在CRDM转子的状态识别上具有比同类方法更高的准确率。
The rotor components of the Control Rod Drive Mechanism(CRDM)operate in high-temperature and high-pressure coolant.Once a malfunction occurs,its maintenance or replacement costs high,takes a long time,and involves a large amount of engineering.A denoising method combining ensemble empirical mode decomposition(EEMD)and wavelet thresholding(WTM)is proposed to address the issue of excessive noise impact on CRDM rotors during operation.After denoising the CRDM rotor vibration signal,time-domain features,frequency-domain features,IMF energy,and sample entropy features are extracted as labels and input into the kernel extreme learning machine(KELM)classification model for classification and recognition.The Whale Optimization Algorithm(WOA)is introduced to self optimize important parameters of KELM,thus improving the recognition accuracy of the model.Through comparative experiments,it has been proven that the method proposed in this paper has higher accuracy than similar methods in the state recognition of CRDM rotors.
作者
罗菁栋
陈玲
张黎明
蒋立志
LUO Jingdong;CHEN Ling;ZHANG Liming;JIANG Lizhi(College of Nuclear Science and Technology,Naval University of Engineering,Wuhan 430033;Chongqing Pump Industry Co.,Ltd.,Chongqing 400030)
出处
《舰船电子工程》
2023年第9期173-177,共5页
Ship Electronic Engineering
关键词
控制棒驱动机构
集合经验模态分解
核极限学习机
control rod drive mechanism
ensemble empirical mode decomposition
nuclear extreme learning machine