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

Image recognition method for breaking faults of wagon brake beam strut

A railway freight car and image recognition technology, which is applied in image enhancement, image analysis, image data processing, etc., can solve the problems of low detection accuracy and poor stability, and achieve the effect of unified operation standards, high accuracy, and fast speed

Active Publication Date: 2020-05-01
HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problem of low accuracy and poor stability of the fault detection of the existing railway freight car brake beam pillar fault, and propose a fault image recognition method for the broken fault of the railway freight car brake beam pillar

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
  • Image recognition method for breaking faults of wagon brake beam strut
  • Image recognition method for breaking faults of wagon brake beam strut
  • Image recognition method for breaking faults of wagon brake beam strut

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0029] Specific implementation mode 1: The specific process of the fault image recognition method for the breakage of the brake beam pillar of the railway freight car in this implementation mode is as follows:

[0030] Step 1. Create a sample data set;

[0031] Step 2. Based on the sample data set, find the optimal weight coefficient and obtain the trained SSD deep learning network; the specific process is:

[0032] Step 21: Initialize the weight coefficients in a random manner;

[0033] Step 2 and 2: Extract multi-scale features from the sample data set to increase the receptive field; SSD is a multi-scale feature map detection network structure, which extracts feature maps of different scales for detection, large-scale feature maps (the earlier feature map) can be used to detect small objects, while small-scale feature maps (later feature maps) are used to detect large objects. The receptive fields included in the feature map selected by the model are: 38, 19, 10, 5, 3, 1....

specific Embodiment approach 2

[0040] Embodiment 2: The difference between this embodiment and Embodiment 1 is that the sample data set is established in the step 1; the specific process is:

[0041] Set up high-definition equipment around the truck track respectively. After the truck passes through the equipment, obtain all-round high-definition images of the sides, bottom and upper part of the truck; the image is a clear grayscale image; because the parts of the truck may be affected by rain, mud, oil , black paint, foreign matter, ice and snow, chalk writing and other natural or man-made conditions. Also, there may be differences in the images taken by different sites. Therefore, brake beam strut images vary wildly from one to another. Therefore, in the process of collecting the image data of the brake beam pillar, it is necessary to ensure the diversity, and try to collect all the images of the brake beam pillar under various conditions.

[0042] In freight car bogies of different models, the shape of...

specific Embodiment approach 3

[0053] Specific embodiment three: the difference between this embodiment and specific embodiment one or two is that the default frame (anchor box) is generated in the step two or three; the specific process is:

[0054] For each feature map, k default boxes (default boxes [default box]) are generated according to different sizes (scale) and aspect ratios (ratio);

[0055] The formula for each default box size is:

[0056] Among them, m is the number of feature maps, s min is the size of the feature map at the bottom layer, s max Default box size for the topmost feature map;

[0057] The aspect ratio of each default box is calculated according to the ratio value, and the ratio value is {1,2,3,1 / 2,1 / 3};

[0058] For the default box with a scale of 1, add an additional scale of the default box;

[0059] In the formula, s' k For the increased ratio ({1,2,3,1 / 2,1 / 3}, there are a total of 5 silent boxes (one number represents one), this is the size of the increased default bo...

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 relates to a railway wagon fault image recognition method, in particular to an image recognition method for breaking faults of a wagon brake beam strut. The objective of the invention isto solve the problems of low fault detection accuracy and poor stability of a brake beam strut of an existing rail wagon. The method comprises the steps of 1, establishing a sample data set; 2, finding an optimal weight coefficient based on the sample data set to obtain a trained SSD deep learning network; initializing a weight coefficient in a random mode; performing feature extraction on the sample data set; generating a default box; pretreating marks; adopting an SSD target loss function; performing weight optimization through an optimizer Adam; and calculating a new weight coefficient through a loss function and the optimizer, and repeatedly executing to obtain a trained SSD deep learning network; inputting a real vehicle passing image into the trained SSD deep learning network, and judging the breaking faults of the brake beam strut. The method is applied to the field of fault image recognition.

Description

technical field [0001] The invention relates to a fault image recognition method for railway wagons. Background technique [0002] During the operation of the train, the accidents caused by brake failure accounted for a large proportion of the whole road. They were inertial accidents in the vehicle department. In the slightest, the brake beam and the lower rod fell off, which constituted a dangerous accident; in severe cases, the driving equipment was damaged. Causing the train to derail and overturn may constitute a major traffic accident. Due to the failure of the manufacture of the brake beam strut and poor assembly, etc., the breakage of the brake beam strut is a high proportion of brake failures. The breaking fault of the brake beam strut is a kind of fault that endangers the driving safety. In the fault detection of the brake beam strut, the fault detection is carried out by manually checking the image. Due to the fact that the inspectors are prone to fatigue and omi...

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): G06T7/00G06K9/62
CPCG06T7/0006G06T2207/10004G06T2207/20081G06T2207/20084G06T2207/30164G06F18/24
Inventor 刘丹丹
Owner HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com