In order to improve the accuracy and efficiency of aero-engine working condition recognition in the real-time monitoring process of flight test, reduce the excessive dependence on expert experience, reduce the misjudgment of manual identification and the time-consuming and labor-intensive problems, an intelligent recognition method based on principal component analysis (PCA) feature extraction method and random forest was proposed. Firstly, the flight data is preprocessed, and the principal component analysis method is used to reduce the dimension of the data for attribute reduction. Secondly, the samples were grouped according to the working state of the engine, and the classifier was trained by the random forest method. Finally, the method is used to identify and verify the actual aircraft engine working state. The results show that the proposed method can accurately and quickly identify the stable working state of the aero-engine, and the recognition accuracy reaches 95.68%. It can be used for the related research and application of aero-engine working state in the field of flight test monitoring.
Online Recognition of Aero Engine State Based on Improved Random Forest
2024-12-13
1281525 byte
Conference paper
Electronic Resource
English
Aero-engine working condition recognition based on MKSVDD optimized by improved BA
British Library Online Contents | 2018
|Aero-Engine Control Based on Improved Neural Network
IEEE | 2016
|Aero-engine transfer trolley and aero-engine transfer equipment
European Patent Office | 2024
|