Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Undercarriage remaining use frequency model training method and device and computer equipment

A model training and landing gear technology, which is applied to computer parts, calculation, character and pattern recognition, etc., can solve problems affecting the performance of the landing gear retraction system, leakage of the actuator, and extended retraction time.

Pending Publication Date: 2020-12-29
BEIJING AERONAUTIC SCI & TECH RES INST OF COMAC +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Viscosity and air content of hydraulic oil, leakage of hydraulic pump, leakage of actuator, insufficient opening of electromagnetic reversing valve, blockage of oil filter and other frequent failures will affect the working performance of the landing gear retraction system, resulting in slow landing gear retraction process, Extended playback time

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
  • Undercarriage remaining use frequency model training method and device and computer equipment
  • Undercarriage remaining use frequency model training method and device and computer equipment
  • Undercarriage remaining use frequency model training method and device and computer equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] like figure 1 As shown, the embodiment of the present invention provides a model training method for the number of remaining times of use of the landing gear, including the following steps:

[0028] S10, acquiring the time-series historical sample data of the retracting or lowering time of the landing gear of the aircraft.

[0029] Among them, the time series historical sample data includes m historical samples {S 1 , S 2 ,...,S m}, each historical sample {S 1 , S 2 ,...,S m} contains the monotonically increasing sequence of landing gear retraction or extension time, and the lowering process is taken as an example here. The kth historical sample is denoted as x 1 represents the time required for the landing gear to be lowered for the first time, x 2 Represents the time required for the landing gear to be lowered for the second time, historical samples {x 1 , x 2 ,...,x m} contains the landing gear down time is increasing, that is, x i+1 time greater than x...

Embodiment 2

[0038] like figure 2 As shown, in one embodiment provided by the present invention, after step S10 obtains the time-series historical sample data of the landing gear down time of the aircraft, the method further includes:

[0039] S101, if the number of historical samples is less than a predetermined value, then divide the historical samples into multiple subsequences

[0040] Among them, n k =L k -n 0 +1 for said historical sample S k The total number of subsequences that can be divided, n 0 is the minimum segment length, historical sample S k The maximum subsequence length before an abnormal element in is l k , which is S k The corresponding number of normal use of the landing gear. For example, historical sample S k ={x 1 , x 2 , x 3 , x 4 , x 5}, n 0 is 2, the subsequences that can be divided are:

[0041] S k1 ={x 1 , x 2}

[0042] S k2 ={x 1 , x 2 , x 3}

[0043] S k3 ={x 1 , x 2 , x 3 , x 4}

[0044] S k4 ={x 1 , x 2 , x 3 , x 4 , ...

Embodiment 3

[0061] like image 3 As shown, in one embodiment provided by the present invention, a method for predicting the number of remaining uses of landing gear is provided, including the following steps:

[0062] S11, acquiring the time series data of landing gear down to be predicted.

[0063] Wherein, the time series data of landing gear down to be predicted may be the time series data from the time when the landing gear fails to the current time.

[0064] S12, extracting the predicted length feature, the predicted degradation rate feature, the predicted differential degradation rate feature and the predicted relative degradation rate feature from the landing gear down time series data to be predicted.

[0065] In the embodiment of the present invention, the length feature to be predicted, the degradation rate feature to be predicted, the differential degradation rate feature to be predicted, and the relative degradation rate feature to be predicted are extracted from the landing ...

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 an undercarriage remaining use frequency model training method and device, computer equipment and a storage medium, relates to the technical field of undercarriage folding andunfolding, and is used for predicting the remaining use frequency of an aircraft undercarriage. According to the main technical scheme, the method comprises the following steps: acquiring time serieshistorical sample data of folding or unfolding time of an aircraft landing gear; extracting a sample length feature, a sample degradation rate feature, a sample differential degradation rate feature and a sample relative degradation rate feature of the undercarriage from the historical sample, and the number of remaining use times of the sample of the undercarriage; forming a feature vector by thesample length feature, the sample degradation rate feature, the sample differential degradation rate feature and the sample relative degradation rate feature of the undercarriage, and determining theremaining use frequency of the undercarriage as a label; and training a model according to the feature vector and the label to obtain an undercarriage remaining use frequency model.

Description

technical field [0001] The present invention relates to the technical field of landing gear retraction, in particular to a training method, device, computer equipment and storage medium for a model training method for the number of remaining times of use of landing gear. Background technique [0002] The aircraft landing gear system provides support for aircraft takeoff, landing, taxiing and ground parking. The working performance of the landing gear retractable system directly affects the aircraft takeoff, landing performance and flight safety. Aircraft landing gear generally uses the hydraulic system as the power source for normal retraction and deployment. The hydraulic energy system outputs hydraulic oil at a certain pressure, and flows to the retraction or deployment circuit of the landing gear retraction system through the retraction or deployment channel of the selection valve to drive retraction. Each lock actuator and retractable actuator in the system moves to comp...

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): G06K9/62
CPCG06F18/214
Inventor 王兆兵唐剑王轶崔世蒙蒋欣常硕张秩铭钟昊天
Owner BEIJING AERONAUTIC SCI & TECH RES INST OF COMAC
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products