Railway wagon swing bolster spring breaking fault image identification method

A railway freight car and image recognition technology, applied in the field of fault identification and railway freight car fault identification, can solve the problems of heavy workload of staff and missed inspections, and achieve the effect of improving accuracy, reducing false alarms, and improving stability and precision.

Inactive Publication Date: 2020-04-28
HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
View PDF8 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Aiming at the problem that the existing method of manual image observation for detecting broken bolster spring faults of freight cars is likely to cause missed detection and the workload of staff is heavy, the present invention provides an image recognition method for broken bolster spring faults of railway freight cars

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
  • Railway wagon swing bolster spring breaking fault image identification method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0032] Specific implementation mode one: the following combination figure 1 Describe this embodiment mode, a method for fault image recognition of railway freight car bolster spring breakage described in this embodiment mode, the method specifically includes:

[0033] S1. Collect images on both sides of the railway wagon to construct a sample data set;

[0034] The sample data set includes a rough positioning component grayscale image data set and a component breaking mark data set;

[0035] S2. Using the Faster R-CNN network to train the sample data set to obtain the weight coefficient of the target detection;

[0036] S3, collect the bolster spring image of the railway freight car in real time, roughly locate and preprocess the collected bolster spring image of the railway freight car, and combine the trained Faster R-CNN network in S2 to obtain the target detection result of the bolster spring image; The target detection result includes target category and target confiden...

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 railway wagon swing bolster spring breaking fault image identification method, relates to a fault identification method, and belongs to the field of railway wagon fault identification. In order to solve the problem that in the prior art, truck swing bolster spring breaking fault detection is performed by using a manual image observation mode, such that missed detection iseasily caused, and the workload of workers is large. The method includes: collecting images on the two sides of a rail wagon, constructing a sample data set, adopting a Faster R-CNN network to trainthe sample data set, and obtaining a weight coefficient of target detection; acquiring a railway wagon swing bolster spring image in real time, performing coarse positioning and preprocessing on the acquired railway wagon swing bolster spring image, and acquiring a target detection result of the swing bolster spring image in combination with the trained Faster R-CNN network, wherein the target detection result comprises a target category and a target confidence degree; and judging whether the spring has a breaking fault or not by adopting a logic judgment mode and utilizing a target detectionresult of the swing bolster spring image.

Description

technical field [0001] The invention relates to a fault identification method and belongs to the field of fault identification of railway freight cars. Background technique [0002] A broken bolster spring fault will cause the car body to tilt, which is a fault that endangers driving safety. In the detection of bolster spring faults, manual inspection of images is used for fault detection. Due to the fact that the inspectors are prone to fatigue and omissions during the work process, resulting in missed inspections and wrong inspections, which affect driving safety. Contents of the invention [0003] Aiming at the problems that the existing method of manual image observation for detection of broken bolster spring faults of freight cars is likely to cause missed detection and the workload of staff is heavy, the present invention provides an image recognition method for broken bolster spring faults of railway freight cars. [0004] A method for fault image recognition of br...

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): G06T7/00G06T7/90G06N3/04G06N3/08
CPCG06T7/0004G06T7/90G06N3/08G06T2207/30164G06N3/045
Inventor 刘丹丹
Owner HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
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