Hierarchical cluster aviation pump multiple fault diagnostic method based on frequency multiplication relative energy sum

Abstract

The invention discloses a hierarchical cluster aviation pump multiple fault diagnostic method based on frequency multiplication relative energy sum. In the method, firstly fault mode effect influence analysis technology is used for carrying out sensor optimal distribution on an aviation hydraulic pump and acquiring sensor signal; then common faults of the aviation hydraulic pump are classified by hierarchical cluster to determine the sequence and hierarchy of fault diagnosis; and finally fault diagnosis of a first diagnosis layer, a second diagnosis layer and a third diagnosis layer is carried out to complete the multiple fault diagnosis on the aviation pump. The method realizes the multiple fault diagnosis of the aviation pump with high accuracy; a extraction method of fault feature and frequency doubling relative energy sum is designed aiming that typical gradual fault of the aviation hydraulic pump is extremely weak at fault initial signature, the method can effectively realize the fault feature extraction of weak signal, and the method is proved to be accurate and efficient by plenty of experiments.

Description

technical field [0001] The invention belongs to the field of state monitoring and fault diagnosis of aviation hydraulic pumps. Aiming at the requirements of the health management system of airborne aviation hydraulic pumps on the rapidity of the fault diagnosis algorithm of aviation hydraulic pumps, the invention provides a layered aggregation method based on the relative energy sum of frequency multiplication Multi-fault diagnosis method for aircraft-like hydraulic pumps. Background technique [0002] With the increase of mission attendance rate and readiness rate of combat aircraft in modern warfare, coupled with the rapid development of testing technology, signal analysis technology and computer technology, advanced foreign aircraft have adopted a complete failure prediction and health management system (PHM system) To achieve condition monitoring, fault diagnosis and life prediction, thereby effectively reducing the aircraft accident rate and saving maintenance costs. F...

AI Technical Summary

Problems solved by technology

[0006] At present, scholars have used multi-sensor information fusion technology in the fault diagnosis process of aviation hydraulic pumps to extract the fault characteristics of aviation hydraulic pumps for fault diagnosis, and achieved good results, but there are still defects: most fault diagnosis methods are limited to aviation hydraulic pumps. However, in the actual aviation hydraulic pump source system, due to the harsh working environment of the aviation hydraulic pump, multiple faults may occur simultaneously in a short period of time. At this time, the coupling between fault features makes the fault diagnosis method for a single fault variable It is very difficult; although a few fault diagnosis methods can realize multi-fault diagnosis, they only analyze and process the vibration signals of different positions of the aviation hydraulic pump, and then use the same fault feature extraction method for diagnosis research, while the actual aviation hydraulic pump has different fault modes. There are different sensitive fault representations, and some faults are not the most sensitive to vibration signals, so this type of fault diagnosis method cannot realize high-precision fault diagnosis for different types of faults at the same time; most of the common fault diagnosis methods at present are based on neural network technology. Neural network realizes fault classification, and the disadvantage of neural network technology is that the number of training samples is large, the learning time is long, and the amount of calculation is large, which cannot meet the rapidity requirements of online fault diagnosis of aviation hydraulic pumps. The number of samples is closely related. Insufficient or too many samples will cause insufficient model training or overfitting, resulting in insufficient accuracy or poor generalization ability of the diagnostic model. However, there is currently no general method for determining the number of training samples, and it can only be determined by experience. These reasons lead to the limitations of fault diagnosis methods based on neural networks in the application of aviation hydraulic pump fault diagnosis

Images