融合IMF能量矩和BiLSTMNN的水电机组振动故障诊断  

Vibration fault diagnosis of hydropower units based on IMF energy moment and BiLSTMNN

作　　者：邓晓琴 瞿卫华 陈金保 王云鹤 邹屹东 胡文庆 肖志怀[1] DENG Xiaoqin;QU Weihua;CHEN Jinbao;WANG Yunhe;ZOU Yidong;HU Wenqing;XIAO Zhihuai(School of Power and Mechanical Engineering,Wuhan University,Wuhan 430072,China;China Yangtze Power International(Hong Kong)Co.,Limited,Beijing 102609,China)

机构地区：[1]武汉大学动力与机械学院,武汉430072 [2]中国长电国际(香港)有限公司,北京102609

出　　处：《水力发电学报》2023年第10期86-95,共10页Journal of Hydroelectric Engineering

基　　金：国家自然科学基金(51979204)。

摘　　要：针对水电机组振动信号存在非平稳和非线性,提出一种结合IMF能量矩和双向长短期记忆神经网络(bidirection long short term memory neural network,BiLSTMNN)的故障诊断方法。首先采用互补集合经验模态分解(complementary ensemble empirical mode decomposition,CEEMD)方法对正常和故障振动信号样本进行处理,得到频率各异的本征模态函数(intrinsic mode functions,IMF)和剩余分量。然后计算IMF能量矩,并将其作为故障特征。进一步,将故障特征作为输入、故障类别作为输出,训练BiLSTMNN得到水电机组故障识别器。结合故障识别器和实时振动信号IMF能量矩特征,即可识别水电机组运行状态为正常或具体故障类型。最后,结合转子实验台数据和实际电站机组样本数据,设计对比实验,验证了所提方法在挖掘信号特征方面的有效性及较高的故障诊断准确率。Aimed at the nonstationary and nonlinear vibration signals of hydropower units,a fault identification method is constructed combining the IMF energy moment and the bi-direction long short-term memory neural network(BiLSTMNN).First,we use the complementary ensemble empirical mode decomposition(CEEMD)method to process the normal and fault vibration signals from a hydropower unit,and obtain the intrinsic mode functions(IMF)and the residual components with different frequencies.Then,the IMF energy moment is calculated and used as the fault feature.And we use the fault features as inputs and the fault categories as outputs,and train BiLSTMNN to obtain a fault identifier for the unit.The operation state of the unit can be identified as a normal or specific fault type by combining this identifier with the IMF energy moment characteristics of the real-time signals.Finally,two sets of comparative experiments are designed based on the sample data collected on a rotor test stand and from the on-site observation of a hydropower unit.The results show our new method is effective in mining signal features and can achieve a high accuracy of fault diagnosis.

关 键 词：本征模态函数 能量矩 双向长短期记忆神经网络 故障诊断 水电机组振动信号 

分 类 号：TV734.1[水利工程—水利水电工程] TK05[动力工程及工程热物理]