Motor train unit running gear abnormity identification method and equipment based on picture-picture fusion
A technology of abnormal recognition and running part, applied in mechanical equipment, neural learning method, character and pattern recognition, etc., can solve the problems of low efficiency and poor accuracy, and achieve the effect of improving recognition accuracy, difficult convergence, and good recognition effect.
Inactive Publication Date: 2022-08-05
WUHAN INSTITUTE OF TECHNOLOGY +2
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] Traditional component anomaly identification mainly uses human eye recognition, which has low efficiency and poor accuracy
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
[0069] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.
[0070] like Figure 4 As shown in the present invention, a picture-photo fusion-based abnormality identification method for the running part of an EMU includes the following steps:
[0071] S100 collects pictures of the running part of the EMU, collects the actual photos of the running part of the EMU, and preprocesses the images;
[0072] S200 builds a triplet network structure and trains a tripl...
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 motor train unit running gear abnormity identification method and device based on picture-picture fusion, and the method comprises the following steps: collecting a motor train unit running gear picture, collecting a motor train unit running gear actual picture, and carrying out the preprocessing of the image; constructing a triple network structure, and training a triple network model based on picture-photo recognition; and using the trained triple network model based on picture-picture recognition to recognize the actual picture of the walking part. Picture-picture recognition is carried out through a triple network, an Xception network is selected to be added into some full connection layers to serve as sub-networks of the triple network, a'difficult triple 'sampling method is adopted aiming at the characteristics that the triple network is slow in training and difficult in convergence, triple loss is improved, efficient and accurate bullet train running gear anomaly recognition is achieved, and the accuracy of bullet train running gear anomaly recognition is improved. And a powerful guarantee is provided for safe operation of the train.
Description
technical field [0001] The invention belongs to the technical field of abnormality detection of the running part of an EMU, and more particularly relates to a method and equipment for identifying the abnormality of the running part of an EMU based on picture-photo fusion. Background technique [0002] High-speed rail trains have become the main way for people to travel because of their high efficiency and high safety. As an important part of the high-speed rail EMU, the running part of the running part will bring a series of hidden dangers to the high-speed railway. The abnormal detection of running part components becomes particularly important. [0003] The traditional component anomaly recognition mainly uses human eye recognition, which has low efficiency and poor accuracy. With the development of deep learning technology due to its high precision and convenient and fast processing, the component anomaly identification technology has undergone major changes and has been...
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 Applications(China)
IPC IPC(8): G06V10/764G06N3/04G06N3/08G06K9/62G06T5/00G06T5/20G06T7/00G06V10/82
CPCG06V10/764G06V10/82G06T7/0004G06T5/20G06N3/08G06T2207/20032G06T2207/20081G06T2207/20084G06T2207/30108G06N3/045G06F18/2433G06T5/70Y02T90/00
Inventor 何毅斌李铭史铁林甘沐阳陈宇晨马东詹小斌唐权胡明涛
Owner WUHAN INSTITUTE OF TECHNOLOGY