A fault detection method for subway brake shoes based on 3D point cloud
A fault detection and three-dimensional point cloud technology, applied in neural learning methods, details of processing steps, image analysis, etc., can solve problems such as loss of subway traffic safety hazards, and achieve comprehensiveness and reliability. The effect of ensuring robustness and measurement accuracy
Active Publication Date: 2022-01-25
SOUTHWEST JIAOTONG UNIV
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Its wear and tear will cause great harm to the safety of subway traffic
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
[0044] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific implementation methods.
[0045] The method of data collection in the present invention is that the intelligent inspection trolley is accurately positioned at the designated collection location, and the three-dimensional point cloud data (XYZ) and color information (RGB) of the corresponding parts at the bottom of the subway car are collected by the three-dimensional industrial camera mounted on the robotic arm of the trolley. Several steps are required to realize the fault detection of the brake shoe. It needs to train the segmentation model, realize preprocessing, point cloud segmentation, point cloud processing, parameter calculation and other steps to complete the entire algorithm. By calculating the thickness of the brake shoe, it is possible to accurately judge whether there is wear or not, which is more accurate and reliable than the naked eye...
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 detecting faults of subway brake shoes based on three-dimensional point clouds, specifically: using a three-dimensional industrial camera to collect three-dimensional point cloud data of brake shoe parts; down-sampling and processing point clouds, and controlling the number of point clouds; after down-sampling, Calculate the centroid, traverse each point and calculate the distance from the centroid, and filter out point clouds that do not belong to the principal component; the pointCNN point cloud segmentation network based on deep learning divides brake shoes, and judges whether there are brake shoes missing; point cloud processing and calculation Check the thickness of the brake shoe to determine whether wear has occurred. The invention improves the accuracy of subway brake shoe fault detection, and at the same time scientifically measures and refines the wear degree of the brake shoe, which is relatively clear and intuitive, and provides a more comprehensive guarantee for the operation safety of the subway.
Description
technical field [0001] The invention belongs to the field of subway brake shoe fault detection, in particular to a method for detecting a subway brake shoe fault based on a three-dimensional point cloud. Background technique [0002] Urban rail transit is of great significance in the development of China. With the rapid development of my country's economy, the technical level and construction scale of China's railway tracks have made great progress. At present, the scale of operating lines in my country, the scale of lines under construction and the scale of passenger flow all rank first in the world, and my country has become a veritable "urban rail power". More and more operating lines are bound to pose a great challenge to safety, so the establishment of a train safety guarantee system has become an indispensable part of the construction of the railway system. As an important part of "smart city", the construction of "smart subway" will surely promote the innovation of p...
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): G06T7/00G06T7/10G06T7/50G06T17/20G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06T7/0004G06T7/10G06T7/50G06T17/20G06N3/08G06T2207/10028G06T2207/20081G06T2207/20084G06T2207/30108G06T2200/08G06N3/048G06N3/045G06F18/241
Inventor 黄德青蔡重阳秦娜万字朋周重合
Owner SOUTHWEST JIAOTONG UNIV