Brake shoe breaking target detection method

A target detection and brake shoe technology, applied in neural learning methods, image data processing, biological neural network models, etc., can solve the problems of low efficiency, high cost, low accuracy, etc., to improve accuracy, save labor costs, The effect of improving work efficiency

Active Publication Date: 2020-05-01
HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
View PDF6 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problems of high cost, low efficiency, and low accuracy in the existing method for inspecting train brake shoe images, and propose a brake shoe broken target detection method

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
  • Brake shoe breaking target detection method
  • Brake shoe breaking target detection method
  • Brake shoe breaking target detection method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0033] Specific implementation mode one: the specific process of the brake shoe broken target detection method in this implementation mode is as follows:

[0034] Step 1, line array image acquisition;

[0035] Step 2, coarse positioning;

[0036] Step 3: Generate a confrontation network DCGAN, and generate a fault image based on the confrontation network DCGAN;

[0037] Since there are few real fault forms of brake shoe breakage collected, better multi-modal fault identification cannot be achieved, so it is necessary to use a deep generative adversarial network to generate multi-modal fault images. Such as figure 2 Schematic diagram of the generative confrontation network structure. The generation model generates pseudo-fault data according to random noise, and then puts the fault data and pseudo-fault data into the discriminant model for discrimination. The discriminant model cooperates with the generative model to adjust the generated data, and the cycle repeats until a c...

specific Embodiment approach 2

[0044] Embodiment 2: The difference between this embodiment and Embodiment 1 is that the linear array image is acquired in the step 1; the specific process is:

[0045] Use fixed equipment to carry cameras or video cameras to shoot high-speed moving railway wagons, and take images of the entire vehicle on the upper part, both sides and bottom of the railway wagon; only scan one line of the railway wagon at a time, which can realize seamless splicing and generate a field of view Large, high-resolution 2D images.

[0046] Other steps and parameters are the same as those in Embodiment 1.

specific Embodiment approach 3

[0047] Specific embodiment three: the difference between this embodiment and specific embodiment one or two is that the rough positioning in the step two; the specific process is:

[0048] According to the prior knowledge such as the wheelbase information of the hardware and the position of the parts, the area of ​​the brake shoe parts to be recognized is cut out from the image information of the whole vehicle, so as to reduce the amount of calculation and improve the speed of recognition.

[0049] Other steps and parameters are the same as those in Embodiment 1 or Embodiment 2.

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 brake shoe breaking target detection method, and relates to a rail wagon fault detection method. The objective of the invention is to solve the problems of high cost, low efficiency and low accuracy in train brake shoe image inspection in the prior art. The method comprises the steps of 1, acquiring a linear array image; 2, performing coarse positioning; 3, generating anadversarial network DCGAN, and generating a fault image based on the adversarial network DCGAN; wherein the adversarial network is composed of a discrimination model and a generation model, down-sampling convolution is adopted in a discriminator, and up-sampling convolution is adopted in a generator. The step 3 comprises the further steps of 3.13, constructing an adversarial network DCGAN discrimination model; 3.2, constructing an adversarial network DCGAN generation model. The method also comprises the following steps of 4, establishing a deep learning training data set; 5, segmenting a faulttarget; and 6, performing prediction based on the trained segmentation network model to obtain information of the fault component. The beneficial effect of the invention is that the method is used inthe field of railway freight car fault detection.

Description

technical field [0001] The invention relates to a fault detection method for railway wagons. Background technique [0002] In the high-speed development of railway truck transportation industry, its safe transportation is undoubtedly the most important. The railway freight car brake device includes three parts: air brake, foundation brake device and hand brake, and these three parts organically form the whole of the railway freight car brake device. The basic braking device is composed of a series of levers, pull rods, brake beams, brake shoe holders, brake shoes and other parts after the brake cylinder push rod to the brake shoe. When braking, the thrust on the push rod of the brake cylinder is increased several times and then evenly transmitted to each brake shoe, so that the brake shoe hugs the wheel set tread. The brake shoe is composed of a brake shoe back and a brake shoe surface. The brake shoe back is used to fix the brake shoe on the Zawato, and the brake shoe sur...

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): G06T7/00G06N3/04G06N3/08
CPCG06T7/0004G06N3/084G06T2207/30236G06T2207/20084G06T2207/20081G06V2201/07G06N3/048G06N3/045
Inventor 孙晶
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