Gas path parameter prediction of aero-engine based on an autoregressive discrete convolution sum process neural network

Abstract The eccentricity of rotor seriously affect the vibration and reliability of aero-engine. Due to the machining error of parts, it is very important to accurately predict the error propagation in assembly. A method based on image recognition and machine learning is proposed to predict the eccentricity of rotor. Firstly, by analyzing and calculating the axial and radial runout error data, the error is mainly concentrated in the first 30 orders of the Fourier series. Secondly, based on the mapping relationship between profile trajectory and eccentricity of rotor, the feature information of the profile trajectory is extracted by constructing the complex domain autoregressive (CAR) model for the radial and axial direction error profile trajectory. Then use the finite element method to calculate the rotor eccentricity. Using the feature information as the input of the neural network, the rotor eccentricity is assembled as the output of the neural network, and the radial basis function (RBF) neural network is built to predict the rotor eccentricity. Theoretical and experimental results show that the proposed method has good enforceability, high accuracy, short calculation time and high engineering application value. In addition, this method can not only be applied to predict the eccentricity of aero-engine rotor flange assembly, but also can be used in the general field of interference fit of assembly.

Download Full-text

Aero-engine Fault Diagnosis Based on Kernel Principal Component Analysis and Wavelet Neural Network

2019 Chinese Control And Decision Conference (CCDC) ◽

10.1109/ccdc.2019.8832740 ◽

2019 ◽

Author(s):

Jianguo Cui ◽

Guoqing Li ◽

Mingyue Yu ◽

Liying Jiang ◽

Zeli Lin

Keyword(s):

Neural Network ◽

Principal Component Analysis ◽

Fault Diagnosis ◽

Principal Component ◽

Component Analysis ◽

Wavelet Neural Network ◽

Kernel Principal Component Analysis ◽

Aero Engine

Download Full-text

Aero-engine Sensor Fault Diagnosis Based on Convolutional Neural Network

2019 Chinese Control And Decision Conference (CCDC) ◽

10.1109/ccdc.2019.8832487 ◽

2019 ◽

Cited By ~ 1

Author(s):

Liu Weimin ◽

Hu Zhongzhi

Keyword(s):

Neural Network ◽

Fault Diagnosis ◽

Convolutional Neural Network ◽

Sensor Fault ◽

Aero Engine

Download Full-text

Machining Parameter Optimization of Aero-Engine Blade in Electrochemical Machining Based on BP Neural Network

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.121-122.893 ◽

2010 ◽

Vol 121-122 ◽

pp. 893-899 ◽

Cited By ~ 2

Author(s):

Zhi Yong Li ◽

Hua Ji ◽

Hong Li Liu

Keyword(s):

Neural Network ◽

Bp Neural Network ◽

Electrochemical Machining ◽

Machining Accuracy ◽

Machining Parameters ◽

Parameter Combination ◽

Aero Engine ◽

Engine Blade ◽

Blade Machining ◽

Machining Parameter

Because the process of blade in electrochemical machining(EMC) can be effected by many factors, such as blade shapes, machining electrical field, electrolyte fluid field and anode electrochemical dissolution, different ECM machining parameters maybe result in great affections on blade machining accuracy. Regard some type of aero-engine blade as research object, five main machining parameters, applied voltage, initial machining gap, cathode feed rate, electrolyte temperature and pressure difference between electrolyte inlet and outlet, have been evaluated and optimized based on BP neural network technique. From 3125 possible machining parameter combinations, 657 optimized parameter combinations are discovered. To verify the validity of the optimized ECM parameter combination, a serial of machining experiments have been conducted on an industrial scale ECM machine, and the experiment results demonstrates that the optimized ECM parameter combination not only can satisfy the manufacturing requirements of blade fully but has excellent ECM process stability.

Download Full-text