The aero-engine is an extremely complex and precise mechanical system. Due to the changing working conditions, there are many factors that cause structural vibrations. The normal operation of each component is related to the stability and safety of the entire system. Failure of components can cause huge disasters. This paper analyzes the aero-engine bearing vibration failure caused by the low-pressure rotor imbalance, and finds that the main difficulty in constructing a fault diagnosis model of aero-engine lies in the processing of imbalance data and the extraction of multidimensional feature data. To solve these problems, a fault diagnosis method is proposed. This method first uses the border-line smote method to balance the data, and then proposes a weight-based Gini coefficient feature extraction method for feature extraction. Finally, the extracted features are used to construct an aero-engine fault diagnosis model. The principle of the fault diagnosis model is to build classifiers to distinguish between normal classes and fault classes. This paper mainly studies the classification effect of the three algorithms xgboost, GDBT and adaboost, and discusses the superiority of different algorithms. And using the bench data of a research institute for testing, it is found that the fault diagnosis model constructed by using the xgboost algorithm has a better fault diagnosis accuracy. It shows that this method has a good application in aero-engine fault diagnosis.
Ensemble Learning Based Decision-Making Models on the Aero-Engine Bearing Fault Diagnosis
Lect. Notes Electrical Eng.
2021-10-30
12 pages
Article/Chapter (Book)
Electronic Resource
English
Ensemble Learning Based Decision-Making Models on the Aero-Engine Bearing Fault Diagnosis
British Library Conference Proceedings | 2022
|Fault fusion diagnosis of aero-engine based on deep learning
British Library Online Contents | 2018
|