Multi-scale self-adaptive weighted generalized morphological filtering method for screw-type compressor fault diagnosis

Abstract

The invention provides a multi-scale self-adaptive weighted generalized morphological filtering method for screw-type compressor fault diagnosis. The technical scheme adopted by the method comprises the following steps that based on morphological filtering processing of a compressor vibration signal, firstly, the optimal scale subset of SEs in different shapes is determined; secondly, self-adaptive weighting is carried out on scale elements basing on the optimal scale subset of the SEs in the different shapes, and an ant colony hill-climbing algorithm is used for determining the optimal weight; then, based on the optimal scale subset and the optimal weight coefficient of the scale elements, the self-adaptive weighting of shapes is carried out through combining the SEs in the different shapes, and the ant colony hill-climbing algorithm is used for determining the optimal weight; finally, based on the optimal weights of the scales and the shapes, the multi-structure and multi-scale optimal weighted morphological filtering processing is carried out on an original signal, the spectral analysis is carried out on the Hilbert envelope demodulation of a filtering signal, and finally the fault of the compressor is diagnosed. According to the method, noise can be effectively eliminated, and fault feature information can be extracted.

Description

technical field [0001] The invention belongs to the field of mechanical equipment fault diagnosis, in particular to a screw compressor fault diagnosis and an improved multi-structure multi-scale self-adaptive weighted generalized morphological filtering method based on an ant colony climbing algorithm. Background technique [0002] As a double-shaft rotary compressor that works according to the principle of volume change, the screw compressor has a series of unique advantages such as simple structure, reliable operation and good volume efficiency, and is widely used in various processes of aerodynamics, refrigeration and air conditioning, and petrochemical industry. The most used in the process. As the most core part of the pressure system, if the operating status of the compressor cannot be accurately judged in time, it will lead to sudden failure, affect the normal operation and service life of the unit, and even cause greater economic losses. Therefore, the fault diagnos...

AI Technical Summary

Problems solved by technology

In traditional morphological filtering, a structural element and a single scale element are often used, which usually cannot achieve satisfactory results

Even considering multi-structure or multi-scale, since the filtering ability mainly depends on the scale and single scale, its filtering ability is still limited

Images