A method for concurrent diagnosis of multiple faults of aeroengine

Abstract

A method for concurrent diagnosis of multiple faults of an aeroengine. The total number of tags q is determined according to the number of sub-components of the engine object to be diagnosed, and thenthe total objective function is established according to the number. The objective function can be decomposed into q independent sub-problems, which can be solved by basic classification algorithm, such as SVM. When the engine training data set is class unbalanced, different penalty factors can be added to each sub-objective function based on SVM to keep the sub-classification boundary in the ideal position, A sub-classifier with good classification performance is established, which eliminates the defect of classic SVM that all errors are the same penalty coefficient, and it is inconvenient to adjust the sub-classifier boundary to the ideal position in the class imbalance data. The resulting q sub-classifiers are synthesized to obtain an overall classifier. The final overall classifier can diagnose both the concurrent instances of aero-engine multi-faults and the single fault instances of aero-engine.

Description

technical field [0001] Aiming at concurrent diagnosis of multiple faults of aero-engines, the present invention uses an improved algorithm proposed by combining a multi-label learning strategy with a support vector machine (Support Vector Machine) to solve technical problems existing in the fields of multiple faults concurrent diagnosis of aero-engines, etc. . Background technique [0002] As one of the effective components of the engine health management system, the aeroengine fault diagnosis system has always been a hot spot in the industry and academia, and the failure probability of engine gas circuit components can account for more than 90% of the overall engine failure, so the establishment of An effective method for fault diagnosis of gas circuit components is particularly important. Currently, available methods for engine fault diagnosis mainly focus on model-based methods and data-driven methods. The model-based method mainly establishes a mathematical model of th...

AI Technical Summary

Problems solved by technology

However, with the increase of the number of parts in this method, the categories to be recognized will increase exponentially, and the training data under some categories will be very small. When applying multi-classification algorithms, this is an extreme class imbalance problem. , which seriously affects the classification accuracy of the algorithm

In addition, multi-fault concurrent data acquisition is also a big problem, because such data is rarer than single-fault data

Moreover, for the problem of aircraft engine fault diagnosis, the actual obtained data set has a high probability of class imbalance

All kinds of unfavorable factors make it difficult to solve the problem of concurrent diagnosis of multiple faults of aero-engines

Images