Aero-engine local balance empirical angle prediction method based on deep learning and related device
CN118940406APending Publication Date: 2024-11-12NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Patent Information
- Application Number
- CN202410986837.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-23
- Publication Date
- 2024-11-12
Smart Images

Figure CN118940406A_ABST
Abstract
The invention provides an aero-engine local balance empirical angle prediction method based on deep learning and a related device, and the method comprises the steps: collecting key-phase signals and vibration acceleration signals of an aero-engine at different rotating speeds, and conditioning the key-phase signals; inputting the conditioned key phase signal and vibration acceleration signal into a pre-trained prediction model to obtain the balance empirical angle of the aircraft engine at different rotating speeds; wherein the prediction model is a double-input deep learning model constructed based on a deep learning method, the input of the double-input deep learning model is a key-phase signal and a vibration acceleration signal of the aero-engine, and the output of the double-input deep learning model is a local balance experience angle of the aero-engine. According to the method, the empirical angle when the aircraft is balanced is directly calculated by using a deep learning method, end-to-end empirical angle prediction is directly realized, the dependence on expert experience in a traditional method is abandoned, the calculation efficiency is improved, and technical support is provided for aircraft engine local balance.
Need to check novelty before this filing date? Find Prior Art
Citation Information
Cited By
State monitoring method and device, computer equipment, readable storage medium and program product
CN120105867A
Intelligent dynamic balance method for aero-engine rotor based on multi-model fusion
CN121479730A
