Aero-engine top speed performance digital twinning method based on artificial intelligence

An aero-engine and artificial intelligence technology, applied in neural learning methods, electrical digital data processing, computer-aided design, etc., can solve problems such as efficiency discounts, algorithms cannot meet close tracking, extremely fast response, and comprehensive performance cannot be fully displayed. The effect of improving training speed and accuracy

Active Publication Date: 2020-11-20
NORTHWESTERN POLYTECHNICAL UNIV
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aeroengines are extremely complex thermomechanical systems, and the complexity of their structures/aerodynamics/thermals/information/controls puts forward higher requirements for the "depth" of data learning in digital twin technology; currently popular big data mining algorithms and widely used Intelligent algorithms such as image/target processing and video/voice recognition are not fully applicable to aero-engine engineering
At the same time, aero-engines are completely different from ground thermomechanical systems. They are in a rapidly changing flight working environment. New algorithms must be used to analyze and judge data a

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Aero-engine top speed performance digital twinning method based on artificial intelligence
  • Aero-engine top speed performance digital twinning method based on artificial intelligence
  • Aero-engine top speed performance digital twinning method based on artificial intelligence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] Such as figure 2 , 3 As shown in Fig. 1, a schematic diagram of establishing a digital twin network for the extreme speed performance of a two-shaft mixed-displacement turbofan engine with afterburner, the specific implementation steps are as follows:

[0047] Step 1: Take the aeroengine flight parameters, control law variables and state parameters as the components of the independent variable vector of the training point, and use the aerodynamic thermodynamic parameters measured by the sensor as the components of the dependent variable vector of the training point; where the aeroengine flight parameters, control law Variables and state parameters are: aero-engine flight parameters include aero-engine flight Mach number and flight altitude; aero-engine control law variables include adjustable tail nozzle area; aero-engine state parameters include fuel flow and speed; aero-engine aerodynamics measured by sensors Parameters include: engine inlet pressure, compressor out...

Embodiment 2

[0055] Such as Figure 4 , 5 As shown in Fig. 1, a schematic diagram of establishing a digital twin network for extreme speed performance of a twin-shaft mixed-displacement turbofan engine with afterburner considering the accessory system, the specific implementation steps are as follows:

[0056] Step 1: Select the aero-engine turbine outlet temperature measured by the sensor after data processing to form the dependent variable y of the training sample, and the aero-engine flight Mach number, flight altitude, adjustable tail nozzle area, fuel flow rate, and speed composition corresponding to the sensor data The training sample argument x. Finally, N pieces of data (x, y) are selected to obtain training samples with a total number of samples of N and a single sample dimension of (5,1).

[0057] Step 2: In accordance with the principle of "the components with the greatest influence are placed in front, and the components with the least influence are placed in the rear", consi...

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

No PUM Login to view more

Abstract

The invention provides an aero-engine top speed performance digital twinning method based on artificial intelligence. Two sets of deep neural networks with similar structures are adopted, and by meansof an aero-engine numerical simulation performance model established according to the aero-engine principle and the aerodynamic thermodynamic process, the two pain points of low precision and large required data volume caused by neglecting the actual physical process only depending on data of a data driving model are effectively solved. Based on an artificial intelligence deep learning method, anaero-engine brand new performance digital twinning model is constructed, and the training speed and precision of digital twinning are greatly improved by adopting artificial intelligence, a maximum entropy principle acceleration strategy and other key technologies.

Description

technical field [0001] The invention belongs to the field of digital models of aero-engines, and in particular relates to an artificial intelligence-based digital twin method for extreme-speed performance of aero-engines. Background technique [0002] The working principle of aero-engine is complicated, there are many control parameters, structured data and unstructured data are cross-integrated, the frequency of parameter collection is high, the volume is large, the structure is diverse, and the timeliness is strong. How to accurately discover the engine hidden in aero-engine parameters in real time The mode of change poses a huge challenge to existing technologies. [0003] Digital twin is a digital simulation of the physical world that integrates multiple physical quantities and multiple spatial scales. It uses effective physical models, sensor data updates, and operating history to mirror the living state of the corresponding twin object, that is, to establish a dynamic ...

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
no application Login to view more
IPC IPC(8): G06F30/28G06F30/17G06N3/04G06N3/08
CPCG06F30/28G06F30/17G06N3/08G06F2119/14G06F2113/08G06N3/045Y02T90/00
Inventor 肖洪林志富
Owner NORTHWESTERN POLYTECHNICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap