Computer Engineering and Applications ›› 2014, Vol. 50 ›› Issue (12): 263-265.

Previous Articles     Next Articles

Steam turbine vibration prediction research based on wavelet analysis

LI Huijun1, YANG Jiming1, DENG Tongtian2, ZHONG Jingliang2   

  1. 1.Power and Mechanical Engineering College, North China Electric Power University, Baoding, Hebei 071003, China
    2.Guizhou Electric Power Test Research Institute, Guiyang 550000, China
  • Online:2014-06-15 Published:2015-05-08

基于小波分析的汽轮机振动预测研究

李慧君1,杨继明1,邓彤天2,钟晶亮2   

  1. 1.华北电力大学 能源动力与机械工程学院,河北 保定 071003
    2.贵州电力试验研究院,贵阳 550000

Abstract: As the power plant prediction of steam turbine rotor vibration time series is difficult, the wavelet decomposition to realize trend prediction is proposed. Some non-stationary time series can be decomposed into several approximate stationary time series with wavelet decomposition. Decomposed time series are forecasted with auto-regression model, to obtain forecasting results of the original time series. Experiments with a power plant vibration signal show that the local and overall effect of the algorithm is better than neural network approaches. The result shows rotor vibration time series forecasting accuracy of this model.

Key words: wavelet analysis, time series, dynamic neural network, fault, predict

摘要: 针对电厂汽轮机转子振动时间序列的预测比较困难,提出采用小波分解实现趋势预测。小波分解将非平稳时间序列分解成多层近似意义上的平稳时间序列,采用自回归模型对分解后的时间序列进行预测,从而得到原始时间序列的预测值。以某电厂振动信号进行预测结果表明,该算法局部及整体效果优于神经网络模型预测法,验证了该模型对转子振动时间序列预测的精确性。

关键词: 小波分析, 时间序列, 动态神经网络, 故障, 预测