Application Research On Fault Diagnosis Technology Of 350MW Steam Turbine In Hohhot

Turbine is the core machinery in the power production industry,and it is one of the “three major mainframes” of power stations.Once it fails,it will not work properly,and it will bring huge economic losses to the power station.Therefore,the monitoring of turbine faults Diagnostic technology is urgently needed by modern power plants.When different faults occur in the steam turbine,the vibration signals presented by the rotor are also different.The analysis of vibration signals is one of the main methods for turbine fault monitoring and diagnosis.This paper studies the monitoring and diagnosis technology of turbine faults based on vibration signals.Firstly,the mechanism of various common faults of steam turbines is analyzed in detail.Faults are categorized according to the causes of faults,and the characteristics of the various types of fault signals are given.The existing fault diagnosis theory and method of steam turbine are systematically summarized,and fault diagnosis methods based on different theories are studied.The basic theories of Fourier analysis,continuous and discrete wavelet transform,multi-resolution analysis and wavelet packet analysis are studied in turn.For signal de-noising,analysis of frequency fluctuation signals,and analysis of step signals,Matlab r2015 b compares the results of traditional Fourier analysis and wavelet analysis.Finally,a four-layer wavelet packet decomposition method was used to decompose the vibration signal of the steam turbine.The frequency of each frequency region was observed by observing the frequency band and compared with the vibration characteristics of the turbine.The results showed that this method of analysis and theoretical inference Completely suitable.Finally,the analysis method is applied to the actual situation.The results of the case diagnosis are completely consistent with the results of the on-site inspection.The results show that there is a good diagnostic effect in the verification of the measured signal,which shows that the wavelet analysis method has a great effect on the fault diagnosis and diagnosis of the steam turbine.Good engineering application value.