基于两因素模糊时间序列的一次风机指标预测

Index prediction of primary air fan based on two factor fuzzy time series

一次风机是电厂生产的重要辅机设备,对其指标进行准确预测,有利于保障该设备乃至系统整体的安全、可靠运行。文中采用一种两因素模糊时间序列的预测算法,实现了对一次风机指标数据的精准预测。该算法克服了传统单因素模糊时间序列预测的有限性,能够有效利用两因素的数据信息。基于采集到的一次风机数据集展开测试,将一次风机轴承的X向振动指标作为待预测因素,并以一次风机总一次风量为辅助因素,构建了两因素模糊时间序列预测模型,完成了对一次风机轴承X向振动未来值的预测。实验结果表明,该方法预测误差低、预测效果良好,且平均绝对百分比误差最低仅为0.005 3。

Primary air fan equipment is an important auxiliary equipment in power plant production.Accurate prediction of the indicators of primary air fan equipment is conducive to ensure the safe and reliable operation of primary air fan equipment and even system equipment.In this paper,a two factor fuzzy time series prediction algorithm is used to accurately predict the index data of primary air fan.It overcomes the limitation of traditional single factor fuzzy time series prediction and can effectively use the data information of two factors.Based on the collected primary air fan data set,this paper takes the Xdirection vibration index of primary air fan bearing as the factor to be predicted,and takes the total primary air volume of primary air fan as the auxiliary factor,constructs a two factor fuzzy time series prediction model,and completes the prediction of the future value of X-direction vibration of primary air fan bearing.The experimental results show that this method has low prediction error and good prediction effect,and MAPE is only 0.0053.