A Fault Diagnosis Method for Fan Blades Based on vmd Decomposition Algorithm

Abstract

The present invention is a fan blade fault diagnosis method based on the VMD decomposition algorithm, comprising step 1, collecting the sound signal of the fan blade and filtering the sound signal to obtain the filtered sound signal; step 2, using the VMD decomposition algorithm to filter the sound signal The sound signal of the sound signal is decomposed into a plurality of modal components; step 3, carries out frame processing to each modal component, divides each modal component into multi-frame sound signals; carries out window processing to the sound signal after the frame processing , to obtain the sound signal after windowing processing; step 4, calculate the short-term energy of each frame of sound signal, and then add the short-time energy of all frames of sound signals corresponding to each modal component to obtain the short-term energy of each modal component time energy; step 5, the short-time energy of each modal component constitutes the feature vector of the signal sample, the feature vector is input into the support vector machine for training, and the trained model is used for fault diagnosis. The diagnostic accuracy and efficiency of this method are high.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis, in particular to a fault diagnosis method for fan blades based on a VMD decomposition algorithm. Background technique [0002] Since wind energy is a green and environmentally friendly renewable energy, under the background of energy shortage and increasingly important environmental protection requirements, it has become a trend to vigorously develop and utilize wind energy for power generation. In wind power equipment, blades are a key part of wind turbines. Due to the long-term operation of wind turbines in harsh and changeable environments, fan blades are prone to defects such as cracks and corrosion. If they are not found and repaired in time, the normal operation of the fan will be affected. Cause huge economic losses, so it is very necessary to carry out fault diagnosis on fan blades. [0003] At present, there are many methods for fault diagnosis of fan blades, such as vibration d...

AI Technical Summary

Problems solved by technology

The EMD algorithm decomposes nonlinear and non-stationary signals into several intrinsic mode function (IMF) components with different frequency components, which has the characteristics of adaptability, orthogonality and completeness, but the recursive mode decomposition adopted by the EMD algorithm will Lead to endpoint effect and modal aliasing phenomenon, affecting the identification accuracy of faults

Images