基于经验模态分解的火力发电厂锅炉给水泵振动故障监测

Vibration Fault Monitoring of Boiler Feedwater Pumps in Thermal Power Plants Based on Empirical Mode Decomposition

常规的给水泵振动故障监测方法以振动故障分布特征分析为主,受到给水泵运行环境的影响,故障监测存在失误的问题。因此,文章设计了基于经验模态分解的火力发电厂锅炉给水泵振动故障监测方法。提取火力发电厂锅炉给水泵振动信号特征,采集锅炉给水泵的振动信号,反映水泵在不同频率的故障状态。基于经验模态分解构建给水泵振动故障监测模型,利用经验模态分析处理给水泵振动信号,得到IMFs幅值、频率、能量分布等参数,进一步表征给水泵振动故障状态。在线监测发电厂锅炉给水泵振动效率,设置给水泵振动效率阈值,评估给水泵的振动异常情况,从而避免故障监测失误的问题。采用对比实验,验证了设计方法的故障监测准确性更高,能够应用于实际生产中。

The conventional monitoring methods for vibration faults in water pumps mainly focus on analyzing the distribution characteristics of vibration faults.However,due to the influence of the operating environment of water pumps,there are errors in fault monitoring.Therefore,a vibration fault monitoring method for boiler feedwater pumps in thermal power plants based on empirical mode decomposition was designed.Extract vibration signal characteristics of boiler feedwater pumps in thermal power plants,collect vibration signals of boiler feedwater pumps,and reflect the fault status of water pumps at different frequencies.Based on empirical mode decomposition,a vibration fault monitoring model for water supply pumps is constructed.Empirical mode analysis is used to process the vibration signals of water supply pumps,obtaining parameters such as the amplitude,frequency,and energy distribution of IMFs,further characterizing the vibration fault status of water supply pumps.Online monitoring of the vibration efficiency of the boiler feedwater pump in power plants,setting a threshold for the vibration efficiency of the feedwater pump,and evaluating the abnormal vibration of the feedwater pump to avoid the problem of fault monitoring errors.Through comparative experiments,it was verified that the fault monitoring accuracy of this method is higher and can be applied in practical life.