基于BP神经网络的转子振动预警方法研究  

Research on Early Warning Method for Rotor Vibration Based on BP Neural Network

作　　者：黄杨森 Huang Yangsen(Dongfang Electric Machinery Co.,Ltd.,Deyang 618000,Sichuan Province,China)

机构地区：[1]东方电气集团东方电机有限公司,四川德阳618000

出　　处：《发电设备》2023年第3期186-191,共6页Power Equipment

基　　金：东方电气集团东方电机有限公司自筹科研项目(708-F-1908);四川省科技攻关计划电厂智能关键技术研究项目资助(2020YFG0350)。

摘　　要：基于逆向传播(BP)神经网络构建发电机转子振动预测模型,利用滑动窗口构建BP神经网络训练样本,依据发电机状态及转子振动的运行值与预测值的相对偏差构建转子振动预警方法,并且使用某电厂发电机运行数据测试该预警方法.测试结果表明:所提出的发电机转子振动预警方法切实可行,满足转子振动在线预警应用需要.A prediction model was established for the vibration of an electric generator rotor based on back propagation(BP)neural network,and the training sample of BP neural network was constructed by using the sliding window.The early warning method of the rotor vibration was proposed with the operation condition of the electric generator and the relative deviation between the operation value and the predicted value of the rotor vibration,while the early warning method was verified by the operation data of an electric generator in a power plant.Results show that,the proposed early warning method for the rotor vibration of the electric generator is feasible,and this can satisfy the application requirements for the online early warning of the rotor vibration.

关 键 词：发电机 转子振动 BP神经网络 滑动窗口 预警 

分 类 号：TM621[电气工程—电力系统及自动化]