A Neural Network-Based Correction Method of Aeroengine Compression Parts Characteristics
An aero-engine and neural network technology, applied in the field of aero-engine model correction, can solve problems such as difficult correction of component characteristics
Active Publication Date: 2020-12-11
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Utilizing the high-efficiency and flexibility of the neural network, it effectively solves the problem that the component characteristics are difficult to correct, and improves the simulation accuracy of the engine component-level model
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0053] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.
[0054] figure 1 Corrected flowcharts for neural network based component characterization. Such as figure 1 As shown, the neural network-based aeroengine compression component characteristic correction method of the present invention specifically includes the following steps:
[0055] Step 1) Establishing the component-level mathematical model of the aero-engine, deriving the error transfer equation according to the gradient, and transferring the model error to the neural network output data of each compression part;
[0056] In step 1), the specific steps of using the design point simulation data and test measurement data to calculate the deviation using the small perturbation method are as follows:
[0057] Step 1.1) using the component-level model iterative algorithm and the small perturbation method to obtain the partial derivative coeffi...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an aero-engine compression part characteristic correction method based on a neural network. The method comprises the following steps: 1) establishing a mathematical model of neural network output and component-level model output parameters, calculating deviation by using design point simulation data and test measurement data through a small disturbance method, and transmitting the model deviation to each compression component neural network output data; and 2) training the corresponding neural network according to the neural network output deviation of each compressionpart obtained in the step 1), and correcting the characteristics of the parts through network weight updating. According to the invention, the problem of low engine model precision caused by inaccurate component characteristics in the prior art is solved. The stability and the generalization ability of the model are ensured. The accuracy of the characteristics of the component can be improved by using a small calculated amount. The problem that the correction of the characteristics of the compression component is inaccurate or difficult is effectively solved, and the method is suitable for gasturbine engine models of any model.
Description
technical field [0001] The invention relates to a neural network-based method for modifying characteristics of aero-engine compression components, which belongs to the technical field of aero-engine model modification. Background technique [0002] In the field of overall performance and control of aero-engines, researchers need to keep abreast of the accurate performance status of each typical component of the current engine, that is, the characteristics of the engine components, to calculate or diagnose the overall performance of the engine. When a new engine leaves the factory, the engine manufacturer will establish an engine benchmark performance calculation model based on the component characteristics obtained through component characteristic tests or theoretical calculations before the new engine leaves the factory. However, due to some reasons, such as blades being dirty or worn due to long-term service, the performance of engine components will naturally degrade with...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F30/17G06F30/15G06F30/27G06N3/04G06N3/08
Inventor 周文祥商航梁彩云
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS