Abstract
In order to improve the accuracy and calculation efficiency of aeroengine rotor vibration reliability analysis, a time-varying rotor vibration reliability analysis method under the aeroengine operating state is proposed. Aiming at the highly nonlinear and strong coupling of factors affecting the reliability of aeroengine rotor vibration, an intelligent neural network modeling framework (short form-INNMF) is proposed. The proposed method is based on DEA, with QAR information as the analysis data, and four factors including engine working state, fuel/oil working state, aircraft flight state, and external conditions are considered to analyse the rotor vibration reliability. INNMF is based on the artificial neural network (ANN) algorithm through improved particle swarm optimization (PSO) algorithm and Bayesian Regularization (BR) optimization. Through the analysis of the rotor vibration reliability of the B737-800 aircraft during a flight mission from Beijing to Urumqi, the time-varying rotor vibration reliability was obtained, which verified the effectiveness and feasibility of the method. The comparison of INNMF, random forest (RF), and ANN shows that INNMF improves analysis accuracy and calculation efficiency. The proposed method and framework can provide useful references for aeroengine rotor vibration analysis, special treatment, maintenance, and design.
Highlights
As the core of the aircraft, aeroengines operate under extreme conditions such as high speeds, high temperatures, and variable loads. eir reliability is the most important factor supporting the performance and survivability of the aircraft [1,2,3]
Aeroengine rotor vibration value prediction and vibration trend analysis are considered to be one of the important concerns. erefore, in order to avoid safety accidents caused by aeroengine vibration failures, it is necessary for researchers to explore methods for evaluating the reliability of aeroengine rotor vibration during operation. e evaluation results can provide the basis for scientifically formulating engine maintenance plans, extending the service life of engines, and ensuring aircraft flight safety
Vibration has been proven to be one of the most reliable and sensitive technical methods for fault diagnosis of rotating and transmission components. e relative maturity of vibration testing methods makes fault diagnosis methods based on vibration analysis effective for popularization and application [5]
Summary
As the core of the aircraft, aeroengines operate under extreme conditions such as high speeds, high temperatures, and variable loads. eir reliability is the most important factor supporting the performance and survivability of the aircraft [1,2,3]. With the development of the aviation industry, the traditional methods cannot meet the needs of the industry, so the ability of rotor vibration reliability analysis during the operation of aeroengines needs to be improved urgently. In this study, based on the extracted QAR data, combined with engine operating state, fuel/oil operating state, aircraft flight state, and aircraft operation environment, the rotor vibration reliability of the aeroengine during operation is analysed. In the process of fitting time-varying and highly nonlinear functions, over fitting and local optimization problems often occur in the training process, which affects the prediction accuracy and limits its further application in operational vibration reliability analysis. E purpose of this study is to propose a time-varying rotor vibration reliability analysis method based on Data Envelopment Analysis (DEA), which considers four factors: aeroengine operating status, fuel/oil operating status, aircraft operating status, and aircraft operating environment. The improved particle swarm optimization (PSO) algorithm is used to search the initial weights and thresholds of ANN, and the final weights and thresholds are trained based on the training performance function of the Bayesian Regularization (BR) algorithm. e feasibility and effectiveness of the proposed method and framework are verified by the vibration safety analysis of the aeroengine running in a specific aircraft mission
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
