Gas turbine inlet guide vane system fault diagnosis method based on feature information fusion

Abstract

The invention discloses a gas turbine inlet guide vane system fault diagnosis method based on feature information fusion. The method comprises the steps of collecting original vibration signals; performing fault mechanism analysis; performing variational mode decomposition (VMD) parameter optimization and decomposition; extracting fault features; normalizing state feature vectors; performing feature vector coding; and performing spiking neural network (SNN) fault diagnosis. According to the method, the dolphin group algorithm is adopted to optimize VMD parameters, and the decomposition accuracy is improved; IMF components sensitive to fault information are screened on the basis of kurtosis-mutual information entropy, and fault feature sensitive modal functions with poor distribution rules and few impact components are removed; fault feature extraction is carried out in a time-frequency domain by adopting a multi-feature entropy algorithm, so that the situation that fault feature information cannot be comprehensively reflected by a single feature is avoided, and accurate diagnosis of faults is guaranteed; the SpikeProp algorithm is adopted to optimize the SNN, the nonlinear classification problem solving capability is achieved, and the training result is more accurate.

Description

technical field [0001] The invention belongs to the technical field of gas turbine fault diagnosis, in particular to a method for fault diagnosis of a gas turbine inlet guide vane system based on feature information fusion. Background technique [0002] Gas turbine is an internal combustion power machine that uses continuous flow of natural gas as the working medium to drive the impeller to rotate at high speed. It has been widely used in aerospace, chemical and other fields. Heavy-duty gas turbines for industrial power generation are important power systems for energy conservation and environmental protection in my country. The inlet guide vane is a series of stationary blades in front of the first-stage moving blade of the gas turbine compressor. As the core component of the gas turbine compressor, it bears the heavy responsibility of energy conversion. By changing the angle of the guide vane to control the angle and flow of the airflow entering the compressor, once the i...

AI Technical Summary

Problems solved by technology

Most of the current signal analysis methods are Empirical Mode Decomposition (EMD), Local Mean Decomposition (LMD), etc. EMD is prone to the problem of mode aliasing; LMD is likely to cause the loss of signal singularity characteristics

Images