Sensitivity analysis method based on civil aviation maintenance quality assessment and heterogeneous ensemble learning

A technique of sensitivity analysis and quality assessment, applied in the field of sensitivity analysis, can solve problems such as complex parameter setting and lack of guiding parameter selection, and achieve the effect of reducing control costs

Active Publication Date: 2019-01-01
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF1 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The current semi-supervised regression mainly includes the difference-based method and the manifold-based method. The parameter setting of the latter is relatively complicated, and there is a lack of a method for guiding the selection of parameters. Therefore, a sensitivity analysis method based on semi-supervised heterogeneous ensemble learning is proposed.

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
  • Sensitivity analysis method based on civil aviation maintenance quality assessment and heterogeneous ensemble learning
  • Sensitivity analysis method based on civil aviation maintenance quality assessment and heterogeneous ensemble learning
  • Sensitivity analysis method based on civil aviation maintenance quality assessment and heterogeneous ensemble learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The present invention will be further described below in conjunction with the accompanying drawings.

[0055] (1) Data processing:

[0056] (1) Selection of significant variables: the quality index system of aviation maintenance reflects the internal requirements of aviation maintenance management, and provides a judgment standard for the control and inspection of maintenance work, so as to facilitate the comprehensive grasp of the maintenance engineering situation, qualitative or quantitative analysis, and correct Instruct maintenance to be carried out as planned. The indicators related to the overall maintenance safety performance can be seen in Table 1. It can be seen that the number of variables is close to 20. If all of them are used as input variables, it will seriously prolong the learning and regression time of the trainer, and the sensitivity will be difficult to calculate. We need to use Limited labeled samples reduce input variables. First, the multi-factor...

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 sensitivity analysis method based on civil aviation maintenance quality evaluation and heterogeneous ensemble learning, which comprises the following steps: (1) data analysisprocessing: a maximum-minimum method, a multi-factor unitary variance analysis; (2) semi-supervised heterogeneous ensemble learning machine training and regression: semi-supervised ensemble learninguses a small number of unlabeled samples for initial training, and then unlabeled samples are put in, and the initial base learning machine is adjusted according to the result of heterogeneous ensemble, until the error is no longer small; (3) sensitivity analysis: variance decomposition method, using the trained heterogeneous integration to expand the labeled samples, calculating the main effect index and the total effect index of each input; (4) example analysis: through the analysis of the maintenance safety data of a certain airline company in recent years, the sensitivity of the month withlow overall safety performance is regulated, and the safety standard is finally reached.

Description

Technical field: [0001] The invention relates to a sensitivity analysis method based on civil aviation maintenance quality evaluation and heterogeneous integrated learning, which belongs to the field of airline maintenance and the research field of overall maintenance safety performance control. Background technique: [0002] With the rapid development of my country's civil aviation industry and the continuous improvement of airlines and passengers' requirements for flight punctuality, the importance of maintenance safety is self-evident. According to accident investigation statistics in the past 20 years, aviation accidents caused by maintenance errors have increased by 4 percentage points. [0003] Aircraft maintenance is one of the important guarantees for the safe operation of aircraft. Driven by airworthiness management, my country's civil aviation maintenance field has been continuously developed on the basis of applying the theory and methods of system engineering, a...

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): G06N99/00G06Q10/00
CPCG06Q10/20
Inventor 刘君强张振良左洪福张曦黄亮
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

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