CN115018752A - Train rail defect positioning and identifying system - Google Patents

Abstract

The invention discloses a train steel rail defect positioning and identifying system, which relates to the technical field of trains and mainly comprises a light source module, acquisition equipment, an image algorithm processing module, a server storage module and display equipment, wherein the output end of the light source module is electrically connected with the input end of the acquisition equipment, the output end of the acquisition equipment is electrically connected with the input end of the image algorithm processing module, the output end of the image algorithm processing module is electrically connected with the input end of the server storage module in a bidirectional mode, and the output end of the server storage module is electrically connected with the input end of the display equipment in a bidirectional mode. The system can analyze the train steel rail defects on line in real time, can solve a large amount of labor and time cost, has incomparable advantages on railway sections which are inconvenient to reach by some people, can learn on line continuously only by an analysis module, optimizes the defect detection effect, and has good popularization value.

Description

Train rail defect positioning and identifying system

Technical Field

The invention relates to the technical field of trains, in particular to a train steel rail defect positioning and identifying system.

Background

Trains, i.e. train sets, are divided into two main types, railway trains: i.e. trains, which is a general form, road trains: the train is the most important mechanical vehicle in human history, is called a steam locomotive in the early days and is also called a train, and the train runs on an independent track. The railway train can be divided into freight cars for carrying goods and passenger cars for carrying passengers according to loads; there are also passenger and freight vehicles, a plurality of consecutive vehicles, generally trains, and in particular trains consisting of a traction engine and a freight or passenger carriage, which are linked in series, the train defining: the train is a train of vehicles which are linked together for a certain purpose, is different from a train, the vehicles forming the train are divided into a locomotive and a vehicle, the locomotive is used for providing power for the train, the vehicle is used for realizing the function of the train, the motor train unit is also a train, the train is mainly used for transportation and transportation, the influence on public life is more and more extensive, and the safety and the humanity of the train are particularly important for life and property.

With the rapid development of big data analysis, the product falls to the ground to become reality, more and more technologies are applied to the short-term test, and train as a main transportation and transport means, train safety is very important, in case the accident will cause huge life threat and property loss. In the conventional method for detecting the defects of the train steel rail, the defects of the steel rail are determined by manual inspection to influence the train safety, and the system is used as a huge railway network system in a large-traffic country.

Therefore, the invention provides a method for replacing manual detection, and qualitative and quantitative analysis such as fault defect positioning, defect type identification and the like can be completed only by installing the system on the train.

Disclosure of Invention

Aiming at the defects of the prior art, the invention provides a train steel rail defect positioning and identifying system to solve the problems in the background technology.

In order to achieve the purpose, the invention provides the following technical scheme: the train steel rail defect positioning and identifying system mainly comprises a light source module, a collecting device, an image algorithm processing module, a server storage module and a display device, wherein the output end of the light source module is electrically connected with the input end of the collecting device, the output end of the collecting device is electrically connected with the input end of the image algorithm processing module, the output end of the image algorithm processing module is electrically connected with the input end of the server storage module in a bidirectional mode, and the output end of the server storage module is electrically connected with the input end of the display device in a bidirectional mode.

Further optimize this technical scheme, collection equipment includes the image acquisition module, the image acquisition module contains optics light filling device, industrial grade high speed CCD and gathers the train bottom image.

Further optimize this technical scheme, the optical light filling device confirms the light filling intensity at different railway sections, different time, has avoided excessive illumination to cause the loss of picture detail, industrial grade high-speed CCD ensures that the collection image is continuous not the disappearance, and has the different environment of fine adaptation, and the replacement is convenient.

Further optimizing the technical scheme, the image algorithm processing module comprises a server and a processing module, and the processing module comprises data preprocessing, Deeplabv3+ steel rail defect positioning, steel rail ROI area calculation and steel rail defect type identification.

Further optimizing the technical scheme, the output end of the data preprocessing is electrically connected with an input end of Deeplabv3+ steel rail defect positioning, the output end of the Deeplabv3+ steel rail defect positioning is electrically connected with an input end of a steel rail ROI area calculation, and the output end of the steel rail ROI area calculation is electrically connected with an input end of steel rail defect type identification.

Further optimizing the technical scheme, the processing module flow comprises: the image collected by the high-speed CCD is preprocessed by using an image algorithm, a defect ROI area is formed by using deep Labv3+ defect positioning, the defects are finely classified by using an identification model, and an output result integrating defect positioning and fine identification types is formed.

Further optimizing the technical scheme, the system designs a set of WEB-based human-computer interaction interface, obtains a defect positioning result and a fine identification type through the algorithm analysis when a train picture is collected, and prompts workers to pay attention to the defect in real time.

Further optimize this technical scheme, server storage module includes storage module, storage module carries out the database storage, train vehicle bottom data and the analysis data that storage module gathered are saved in the database according to the regulation, are convenient for look up and trace to the source with tracing to the root.

Further optimizing the technical scheme, the display device comprises a display module, and the display module comprises defect location type and real-time display.

Compared with the prior art, the invention provides a train steel rail defect positioning and identifying system, which has the following beneficial effects:

the train steel rail defect positioning and identifying system can analyze train steel rail defects on line in real time, can solve a large amount of labor and time cost, has incomparable advantages on railway sections which are inconvenient to reach by some people, can learn on line continuously only by an analysis module, optimizes defect detection effect, and has good popularization value.

Drawings

Fig. 1 is a schematic diagram of a control system of a train rail defect locating and identifying system provided by the invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Example (b):

referring to fig. 1, a train rail defect locating and identifying system mainly comprises at least one light source module, a collecting device, an image algorithm processing module, a server storage module and a display device, wherein an output end of the light source module is electrically connected with an input end of the collecting device, an output end of the collecting device is electrically connected with an input end of the image algorithm processing module, an output end of the image algorithm processing module is bidirectionally electrically connected with an input end of the server storage module, and an output end of the server storage module is bidirectionally electrically connected with an input end of the display device, and the system can analyze train rail defects on line in real time, solve a large amount of labor and time costs, has incomparable advantages on certain railway sections which are inconvenient to reach, can learn on line only by the analyzing module, and optimize a defect detection effect, has good popularization value.

As the specific optimization scheme of this embodiment, collection equipment includes the image acquisition module, the image acquisition module contains optics light filling device, the high-speed CCD of industrial grade and gathers the train bottom image, optics light filling device is at different railway sections, the different time determination light filling intensity, has avoided excessive illumination to cause the picture detail to be lacked, the high-speed CCD of industrial grade ensures to gather the continuous not disappearance of image, and has the different environment of fine adaptation, and the replacement is convenient.

As a specific optimization scheme of this embodiment, the image algorithm processing module includes a server and a processing module, the processing module includes data preprocessing, deplabv 3+ rail defect location, calculation of a rail ROI region, and rail defect type identification, an output end of the data preprocessing is electrically connected to an input end of the deplabv 3+ rail defect location, an output end of the deplabv 3+ rail defect location is electrically connected to an input end of the calculation of the rail ROI region, and an output end of the calculation of the rail ROI region is electrically connected to an input end of the rail defect type identification.

As a specific optimization scheme of this embodiment, the processing module flow includes: the image collected by the high-speed CCD is preprocessed by using an image algorithm, a defect ROI (region of interest) is formed by using deep Labv3+ defect positioning, and the defects are finely classified by using an identification model to form an output result integrating defect positioning and fine identification types.

As a specific optimization scheme of the embodiment, the system designs a set of WEB-based human-computer interaction interface, and when a train picture is acquired, a defect positioning result and a fine identification type are obtained through the algorithm analysis, and workers are prompted to pay attention to the defect in real time.

As a specific optimization scheme of this embodiment, the server storage module includes a storage module, the storage module stores a database, and train bottom data and analysis data acquired by the storage module are stored in the database according to regulations, so as to facilitate looking up and tracing.

As a specific optimization scheme of this embodiment, the display device includes a display module, and the display module includes defect location type and real-time display.

The beneficial effects of the invention are: the train steel rail defect positioning and identifying system can analyze train steel rail defects on line in real time, can solve a large amount of labor and time cost, has incomparable advantages on railway sections which are inconvenient to reach by some people, can learn on line continuously only by an analysis module, optimizes defect detection effect, and has good popularization value.

The related modules involved in the system are all hardware system modules or functional modules combining computer software programs or protocols with hardware in the prior art, and the computer software programs or the protocols involved in the functional modules are all known in the technology of persons skilled in the art, and are not improvements of the system; the improvement of the system is the interaction relation or the connection relation among all the modules, namely the integral structure of the system is improved, so as to solve the corresponding technical problems to be solved by the system.

It should be noted that, in the embodiment of the above search apparatus, each included unit and module are merely divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.

It should be noted that the foregoing is only a preferred embodiment of the invention and the technical principles employed, and those skilled in the art will understand that the invention is not limited to the specific embodiments described herein, and that various obvious changes, rearrangements and substitutions can be made by those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in some detail by the above embodiments, the invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the invention, and the scope of the invention is determined by the scope of the appended claims.

Claims (9)

1. The utility model provides a train rail defect location and identification system, its major constituent part contains a light source module, collection equipment, image algorithm processing module, server storage module and display device at least, its characterized in that, light source module's output electricity is connected with collection equipment's input, collection equipment's output electricity is connected with image algorithm processing module's input, the two-way electricity of image algorithm processing module's output is connected with server storage module's input, the two-way electricity of server storage module's output is connected with display device's input.

2. The train steel rail defect positioning and identifying system of claim 1, wherein the collecting device comprises an image collecting module, and the image collecting module comprises an optical supplementary lighting device, an industrial grade high-speed CCD and collects a train bottom image.

3. The train steel rail defect positioning and identifying system as claimed in claim 2, wherein the optical light supplementing device determines the light supplementing intensity at different railway sections and different times, thereby avoiding the loss of picture details caused by excessive illumination, and the industrial grade high speed CCD ensures that the collected images are continuous and are not lost, and has good adaptability to different environments and convenient replacement.

4. The train steel rail defect positioning and identifying system of claim 1, wherein the image algorithm processing module comprises a server and a processing module, and the processing module comprises data preprocessing, Deeplabv3+ steel rail defect positioning, steel rail ROI area calculation and steel rail defect type identification.

5. The train steel rail defect positioning and identifying system as claimed in claim 4, wherein the output end of the data preprocessing is electrically connected with an input end of Deeplabv3+ steel rail defect positioning, the output end of the Deeplabv3+ steel rail defect positioning is electrically connected with an input end of a steel rail ROI area calculation, and the output end of the steel rail ROI area calculation is electrically connected with an input end of steel rail defect type identification.

6. The train steel rail defect positioning and identifying system according to any one of claims 1 to 5, wherein the processing module flow comprises: the image collected by the high-speed CCD is preprocessed by using an image algorithm, a defect ROI area is formed by using deep Labv3+ defect positioning, the defects are finely classified by using an identification model, and an output result integrating defect positioning and fine identification types is formed.

7. The train steel rail defect positioning and identifying system according to claim 6, wherein the system designs a set of WEB-based man-machine interface, and when a train picture is collected, the system obtains a defect positioning result and a fine identification type through the algorithm analysis, and prompts workers to pay attention to the defect in real time.

8. The train steel rail defect positioning and identifying system as claimed in claim 1, wherein the server storage module comprises a storage module, the storage module stores a database, and train bottom data and analysis data acquired by the storage module are stored in the database according to regulations, so as to facilitate reference, root tracing and source tracing.

9. The train steel rail defect positioning and identifying system of claim 1, wherein the display device comprises a display module, and the display module comprises defect positioning type and real-time display.

Images