BP (Back Propagation) neural network-based method for measuring air data in flight state with high angle of attack

A BP neural network and atmospheric data technology, which is applied to the measurement of atmospheric data in the state of high angle of attack flight, and the field of air data measurement of aircraft in the state of high angle of attack flight, can solve the problem of difficult establishment of flight dynamics model, high technical difficulty, Problems such as atmospheric data estimation cannot be realized

Inactive Publication Date: 2012-07-25
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF2 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In response to this problem, at present, the measurement of atmospheric data at large angles of attack is realized by researching embedded air data systems and optical air data systems at home and abroad. However, this method of researching new air data systems is technically difficult, calibration and maintenance. The cost is high; in addition, foreign countries have also proposed a method based on the flight dynamics model, using the output data of the inertial navigation system, flight control system, and air data system to estimate the angle of attack and sideslip angle. Flight dynamics model, however, it is difficult to establish an accurate flight dynamics model in practical applications, and this method can only estimate the angle of attack and sideslip angle, and cannot realize the estimation of other atmospheric data

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
  • BP (Back Propagation) neural network-based method for measuring air data in flight state with high angle of attack
  • BP (Back Propagation) neural network-based method for measuring air data in flight state with high angle of attack
  • BP (Back Propagation) neural network-based method for measuring air data in flight state with high angle of attack

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The technical scheme of the present invention is described in detail below in conjunction with accompanying drawing:

[0024] The method of the invention makes full use of the output data of the existing airborne inertial navigation system, satellite positioning system and flight control system, and realizes large Accurate estimation of atmospheric data in angle-of-attack flight regimes. Specifically include the following steps:

[0025] (1) Sample data collection and processing steps:

[0026] (a) Periodically Read three attitude angles, three attitude angular velocities and three linear acceleration information in the inertial navigation system, the three attitude angle information are the pitch angle , roll angle , yaw angle ; The three attitude angular velocity information are respectively in the body coordinate system axis, axis and roll angular velocity in the axial direction , Pitch angular velocity , yaw rate ; The three linear acceleration in...

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 discloses a BP (Back Propagation) neural network-based method for measuring air data in a flight state with a high angle of attack. According to the method, on the premise of not changing the configuration of an aircraft and not adding extra measurement devices and hardware equipment, the traditional airborne inertial navigation system, a global positioning system (GPS) and a flight control system are sufficiently utilized to output parameters, and the precise estimation of air data in a flight state with a high angle of attack is realized on the basis of a BP neural network. The method is beneficial to aircraft stealth, and meanwhile, the measurement range and the measurement precision of an air data system and the adaptability to a flight environment with a high angle of attract are improved, so that the method has the advantages of relative economy and easy engineering realization and has important practical significance to enlarging the measurement range of a new generation of aircrafts in the flight state with a high angle of attract and improving the flight performance of the aircrafts.

Description

technical field [0001] The invention relates to a method for measuring atmospheric data, in particular to a method for measuring atmospheric data based on a BP neural network in a flight state with a large angle of attack, which is used for measuring atmospheric data of an aircraft in a flight state with a large angle of attack. Background technique [0002] Atmospheric data is an important flight parameter of an aircraft. The accuracy and measurement range of atmospheric data are directly related to the normal operation and performance of the aircraft's automatic control system, navigation system, fire control system, flight management system, and cockpit instrument display / warning system. With the development of a new generation of aircraft, the measurement of atmospheric data is facing new problems and challenges. All countries in the world regard the maneuverability and agility of aircraft as important tactical and technical indicators in design. The instantaneous high ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G01D21/00G06N3/08
Inventor 李荣冰马航帅刘建业雷廷万郭毅曾庆化陆辰李素娟
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
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