Faster R-CNN-based railway bullet train hood front opening and closing damage fault identification method

A technology of fault identification and front opening and closing, which is applied in the field of hood image recognition, can solve problems such as time-consuming and labor-consuming, visual fatigue, missed detection, etc., and achieve the effect of improving recognition accuracy, avoiding recognition errors, and improving detection efficiency

Inactive Publication Date: 2021-04-06
HARBIN KEJIA GENERAL MECHANICAL & ELECTRICAL CO LTD
View PDF12 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The manual method is a time-consuming and labor-intensive method, and the inspector will have visual fatigue, resulting in missed inspections and false inspections.

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
  • Faster R-CNN-based railway bullet train hood front opening and closing damage fault identification method
  • Faster R-CNN-based railway bullet train hood front opening and closing damage fault identification method
  • Faster R-CNN-based railway bullet train hood front opening and closing damage fault identification method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0037] according to Figure 1 to Figure 3 As shown, the present invention provides a method for identifying faults of opening and closing damage in front of the railway moving car hood based on Faster R-CNN, and the specific scheme is as follows:

[0038] A method for identifying a fault of a front opening and closing of a vehicle hood, comprising the following steps:

[0039] Step 1: Collect the original image of the front opening and closing of the vehicle hood;

[0040] Step 2: According to the collected original image, mark the fault and obtain the training sample;

[0041] Step 3: According to the obtained training samples, perform deep learning model training to obtain a trained fault identification model;

[0042] Step 4: According to the trained fault identification model, the damage fault identification of the front opening and closing of the hood of the vehicle under test is carried out.

specific Embodiment 2

[0044] Before fault marking, it also includes preprocessing the collected original image to reduce image noise, specifically:

[0045] Step 2.1: Select two filters to filter the original image, cut the filtered original image according to the position of the front opening and closing of the hood, and obtain the front opening and closing sub-image of the hood;

[0046] Step 2.2: Simulate the morphological faults of cracks, paint peeling and holes caused by the impact on the sub-graph, and simulate faults of different sizes, positions, and shapes on the front opening and closing of the hood of different models;

[0047] Step 2.3: Perform data enhancement on the simulated image to obtain a preprocessed image.

specific Embodiment 3

[0049] Data augmentation methods include adjusting brightness, adjusting contrast, and translation.

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 Faster R-CNN-based railway bullet train hood front opening and closing damage fault identification method. The invention relates to the technical field of headstock cover image recognition. The method comprises the steps of collecting an original image of a headstock cover; preprocessing the collected original image to reduce image noise; performing deep learning according to the preprocessed image to obtain a training sample; performing deep learning model training according to the obtained training sample to obtain a trained fault identification model; and according to the trained fault identification model, carrying out damage fault identification on the headstock cover. According to the method, the train hood front opening and closing damage fault is identificated and detected through a deep learning method, and identification errors caused by fatigue and personal judgment differences during manual detection are effectively avoided. Compared with manual detection, the deep learning method can improve the detection efficiency.

Description

technical field [0001] The invention relates to the technical field of locomotive hood image recognition, and relates to a FasterR-CNN-based fault identification method for front opening and closing damage of a railway locomotive hood. Background technique [0002] The opening and closing mechanism is a mechanical component installed at the front end of the motor car, and is connected with the driver's cab hood to form the overall front end shape of the vehicle. The function of the opening and closing mechanism is mainly to meet the appearance requirements and streamlined aerodynamic requirements of the front end of the vehicle, while protecting other parts of the front end of the vehicle and effectively blocking the entry of debris such as flying stones and branches. The opening and closing of the front hood of the train will be damaged due to the impact of flying stones, branches and other sundries during operation. It is a necessary work to identify the damage fault of t...

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): G06K9/62G06K9/40G06N3/04G06N3/08
CPCG06N3/08G06V10/30G06V2201/08G06N3/045G06F18/217G06F18/214
Inventor 闫学慧
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