A Method for Abnormal Detection of Train Brake Parts
An anomaly detection and detection method technology, applied in computer components, instruments, biological neural network models, etc., can solve the problems of huge gap in the ratio of positive and negative samples, failure to train models, etc., to improve sensitivity and reduce dependence on negative samples , the effect of fast detection speed
Active Publication Date: 2022-05-31
SOUTHWEST JIAOTONG UNIV
View PDF8 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, in actual engineering projects, there is a huge gap in the proportion of positive and negative samples, and there are few negative samples, so it is often impossible to train a model with satisfactory results.
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
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
Login to View More Abstract
The invention discloses a method for abnormal detection of train brake pad parts, the steps are as follows: Step 1, image preprocessing is performed on the collected brake pad data; Step 2, using Yo l oV4-t i ny target detection model to load and train With a good weight file, locate the hook part and detect the abnormality of the pin part on the brake pad picture, and the Yo l oV4‑t i ny target detection model will detect the pin in one step and output the detection result; step 3, use Yo l oV4 at the same time ‑t i ny target detection model locates the hook part, cuts out the hook part area, and then uses the improved OC‑CNN anomaly detection network to detect the hook screenshot; step 4, obtains the abnormal score through OC‑CNN detection of the hook screenshot, and judges the hook Whether there is an abnormality and output the detection result; step five, integrate the detection results of Yo l oV4-t i ny and improved OC-CNN, and obtain the detailed abnormal information of the entire brake pad. Yo l oV4-t i ny and OC-CNN of the present invention form a complete abnormal detection model of brake pads, which can quickly, accurately and efficiently complete abnormal detection of brake pads.
Description
A method for abnormal detection of train brake pad components technical field The present invention relates to the field of abnormality detection of train parts, in particular to a kind of abnormality detection for train brake pad parts. method. Background technique [0002] With the rapid development of my country's economy, the track mileage in mainland China ranks first in the world. Both speed and efficiency, have made great progress. In the maintenance of trains, traditional manual inspection still accounts for the vast majority. Traditional Troubleshooting During the test, the maintenance personnel had a harsh working environment, a large number of trains, requiring a lot of manpower and material resources, low efficiency and poor reliability, etc. Today's era of continuous automation and intelligence is out of tune. There is an urgent need for a high-efficiency, high-accuracy and low-cost technology It can automatically detect train faults and ensure the s...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06V10/774G06V10/75G06V10/22G06N3/04
CPCG06V10/22G06V10/751G06N3/045G06F18/214
Inventor 秦娜周重合黄德青张宗泓刘龙凯宋晨健
Owner SOUTHWEST JIAOTONG UNIV
Features
- R&D
- Intellectual Property
- Life Sciences
- Materials
- Tech Scout
Why Patsnap Eureka
- Unparalleled Data Quality
- Higher Quality Content
- 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com



