CN108921845A - Wheel tread rehabilitation plan generation method and device - Google Patents
Wheel tread rehabilitation plan generation method and device Download PDFInfo
- Publication number
- CN108921845A CN108921845A CN201810748373.5A CN201810748373A CN108921845A CN 108921845 A CN108921845 A CN 108921845A CN 201810748373 A CN201810748373 A CN 201810748373A CN 108921845 A CN108921845 A CN 108921845A
- Authority
- CN
- China
- Prior art keywords
- wheel tread
- terminal
- image
- defect
- rehabilitation plan
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30236—Traffic on road, railway or crossing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a kind of wheel tread rehabilitation plan generation method and devices, are applied to detection technique field.This method includes:The image of wheel tread is obtained from terminal, and whether the quality for analyzing the image meets preset condition.If the quality of the image meets preset condition, which is handled, and identifies the defect type and defects count of the wheel tread from treated image.Generation and the defect type and the matched wheel tread rehabilitation plan of the defects count, and be sent to the terminal and shown.The wheel tread rehabilitation plan generation method can reduce technical difficulty and reduce cost.
Description
Technical field
The present invention relates to detection technique field more particularly to a kind of wheel tread rehabilitation plan generation method and devices.
Background technique
With the rapid development of our country's economy, the continuous expansion of city size, the floating population in city are significantly increased, resident
It goes on a journey more frequent, the contradiction of Urban traffic demand is also more and more prominent.Compared with traditional public transport, rail traffic is by only
Vertical right of way, transport capacity is big, punctuality rate is high and it is environmentally friendly the advantages that, big city at home has been widely used.It is positive because
To have the characteristics that transport capacity is big, the safety of rail traffic is paid more and more attention.
The wheel of vehicle plays a crucial role the safe operation of vehicle, one to being the main building block of vehicle
Wheel is constituted to by wheel and axle, wherein tyre tread is the contact surface of wheel and rail.It takes turns to receiving from rail vehicle whole
Dynamic and static load, be easy to occur in operation the abrasion, scratch of various abrasions, especially wheel tread surface and its near surface,
The defects of glass, crackle, will injure the traffic safety of railcar, it is therefore desirable in time detection Railway wheelset state and
Shi Faxian wheel is to problem, replacement or maintenance overrun wheel pair, to avoid the generation of driving accident.And current domestic rail vehicle
The detection method of wheel tread is mainly detected using mechanically or electrically magnetic mode, and needs to consult operation card before reparation, is existed
The problem of technical difficulty is larger and higher cost.
Summary of the invention
The main purpose of the embodiment of the present invention is to provide a kind of wheel tread rehabilitation plan generation method and device, can drop
Low technical difficulty simultaneously reduces cost.
First aspect of the embodiment of the present invention provides a kind of wheel tread rehabilitation plan generation method, the method includes:
The image of wheel tread is obtained from terminal, and whether the quality for analyzing described image meets preset condition;If the matter of described image
Amount meets preset condition, then handles described image, and the defect of the wheel tread is identified from treated image
Type and defects count;Generation and the defect type and the matched wheel tread rehabilitation plan of the defects count, and send
It is shown to the terminal.
Second aspect of the embodiment of the present invention provides a kind of wheel tread rehabilitation plan generating means, and described device includes:
Module is obtained, for obtaining the image of wheel tread from terminal;Whether analysis module, the quality for analyzing described image meet
Preset condition;Processing module, if the quality for analysis module analysis described image meets preset condition, to the figure
As being handled;Identification module, for identifying the defect type and defects count of the wheel tread from treated image;
Generation module, for generating and the defect type and the matched wheel tread rehabilitation plan of the defects count;Sending module,
It is shown for being sent to the terminal.
From above-described embodiment it is found that after handling first by the image to wheel tread, wheel is automatically identified to stepping on
The defect type and defects count in face are manually detected without passing through, to reduce human cost and technical difficulty;
In addition, automatically generating wheel tread rehabilitation plan by being matched with the defect type of wheel tread and defects count, avoiding
Renovation technique card is consulted, to reduce time cost and technical difficulty.
Detailed description of the invention
Fig. 1 is the implementation process signal of the wheel tread rehabilitation plan generation method in first embodiment provided by the invention
Figure;
Fig. 2 is the image processing process schematic diagram in first embodiment provided by the invention;
Fig. 3 is the application schematic diagram in first embodiment provided by the invention;
Fig. 4 is the implementation process signal of the wheel tread rehabilitation plan generation method in second embodiment provided by the invention
Figure;
Fig. 5 is the application schematic diagram in second embodiment provided by the invention;
Fig. 6 is the first application note schematic diagram in second embodiment provided by the invention;
Fig. 7 is the second application note schematic diagram in second embodiment provided by the invention;
Fig. 8 is the third application note schematic diagram in second embodiment provided by the invention;
Fig. 9 is the structural schematic diagram of the wheel tread rehabilitation plan generating means in 3rd embodiment provided by the invention.
Specific embodiment
In order to make the invention's purpose, features and advantages of the invention more obvious and easy to understand, below in conjunction with the present invention
Attached drawing in embodiment, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described reality
Applying example is only a part of the embodiment of the present invention, and not all embodiments.Based on the embodiments of the present invention, those skilled in the art
Member's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Referring to Fig. 1, Fig. 1 is the reality of the wheel tread rehabilitation plan generation method in first embodiment provided by the invention
Existing flow diagram, this method can be applied in server.As shown in Figure 1, this method mainly includes the following steps that:
101, the image of wheel tread is obtained from terminal, and whether the quality for analyzing the image meets preset condition.
Specifically, in vehicle operation, vehicle wheel is to bearing the load from rail vehicle whole, and wheel tread
It is the contact surface of wheel of vehicle and rail, therefore wheel tread is easy to that various abrasions occur, in order to guarantee the peace of vehicle driving
Quan Xing, the image for obtaining wheel tread from terminal detect wheel tread.And the quality of the image of tread can be very big
The reliability for influencing subsequent image processing, such as the quality of image bad the problems such as will cause False Rate and high omission factor, in turn
The testing result of wheel tread is influenced, therefore whether the quality for analyzing the image first meets preset condition, it is current to judge
Whether the image of the wheel tread of acquisition can be used.Optionally, server can be used sharpness function and carry out to the quality of image
Evaluation amount evaluation, then preset condition is the definition values of image.
If 102, the quality of the image meets preset condition, which is handled, and from treated image
Identify the defect type and defects count of the wheel tread.
Specifically, if the quality of image meets preset condition, after illustrating that the image of the wheel tread currently obtained can be used for
It is continuous to use, therefore image is handled, and identify from treated image the defect type and defects count of wheel tread.
Illustratively, as shown in Fig. 2, server detects the quality of image, then after the image that terminal obtains wheel tread
Image is successively carried out to greyscale transformation, adaptively adjusts, filter out illumination effect, confirmation defect color characteristic, edge extracting, connection
Domain processing judges defect area morphological feature, carries out erroneous judgement error correction, finally to determine the defect type and defect number of wheel tread
Amount.
103, generation and the defect type and the matched wheel tread rehabilitation plan of the defects count, and it is sent to the terminal
It is shown.
Specifically, server generates and the defect type and quantity phase according to the defect type and defects count identified
Matched wheel tread rehabilitation plan, and be sent to terminal and shown, so that the staff of terminal side obtains wheel pair in time
The detection case of tyre tread simultaneously consults wheel tread rehabilitation plan.Optionally, as shown in figure 3, installing light additional in the top of wheel tread
Source shoots wheel tread with image-pickup device, and the image for the wheel tread that camera will acquire is adopted by data
Truck and data line are transferred to terminal, and terminal is then transmitted to server and is analyzed and processed, and generate wheel tread rehabilitation plan
The display for being sent to terminal afterwards is shown, so that the staff of terminal checks.
Optionally, the image for the wheel tread that server will acquire, treated image, image is corresponding with treated
Defect type and defects count and the rehabilitation plan to match storage in the server.
In embodiments of the present invention, after handling first by the image to wheel tread, wheel is automatically identified to stepping on
The defect type and defects count in face are manually detected without passing through, to reduce human cost and technical difficulty;
In addition, automatically generating wheel tread rehabilitation plan by being matched with the defect type of wheel tread and defects count, avoiding
Renovation technique card is consulted, to reduce time cost and technical difficulty.
Referring to fig. 4, Fig. 4 is the realization of the wheel tread rehabilitation plan generation method in second embodiment provided by the invention
Flow diagram is applied to server.As shown in figure 4, this method mainly includes the following steps that:
201, the image of wheel tread is obtained from terminal, and whether the quality for analyzing the image meets preset condition.
Specifically, in vehicle operation, vehicle wheel is to bearing the load from rail vehicle whole, and wheel tread
It is the contact surface of wheel of vehicle and rail, therefore wheel tread is easy to that various abrasions occur, in order to guarantee the peace of vehicle driving
Quan Xing, the image for obtaining wheel tread from terminal detect wheel tread.And the quality of the image of tread can be very big
The reliability for influencing subsequent image processing, such as the quality of image bad the problems such as will cause False Rate and high omission factor, in turn
The testing result of wheel tread is influenced, therefore whether the quality for analyzing the image meets preset condition, to judge current obtain
Wheel tread image it is whether reliable.If the quality of the image is unsatisfactory for the preset condition, 202 are thened follow the steps:From end
End obtains the new images of wheel tread.If the quality of the image meets preset condition, 203 are thened follow the steps.
203, the image is handled, the edge feature in image after extraction process.
Specifically, illustrating that the image of the wheel tread obtained can be used for subsequent make if the quality of image meets preset condition
With, therefore image is handled, and wheel tread occurs the region of defect, the normal region of defect not occurring with wheel tread
Edge there is mutation, therefore, after server gets that treated image, extracted from the image of treated wheel tread
Edge feature, to determine the defect type and defects count of wheel tread.Wherein, edge feature is the handover in different attribute region
Place is the place that the attribute of different zones mutates, is the most basic feature of image, therefore the edge feature can illustrate wheel pair
The feature in the region of defect occurs on the image of tyre tread.
Optionally, image is handled using NI Vision Builder for Automated Inspection, and the edge feature in the image after extraction process,
And then defect type and defects count are confirmed according to the edge feature.Wherein, NI Vision Builder for Automated Inspection refers to is filled by image capture
It sets, such as CMOS (Complementary Metal Oxide Semiconductor, complementary metal oxide semiconductor) or CCD
(Charge-coupled Device, charge coupled cell) will be ingested target and be converted into picture signal, send to dedicated
Image processing system is handled, and the shape information of target subject is obtained, and according to the information such as pixel distribution and brightness, color, is turned
Becoming digitized signal, image processing system carries out various operations to digitized signal and is ingested clarification of objective to extract, into
And the device action at scene is controlled according to the result of differentiation.In the present embodiment, the image of wheel tread is obtained using CCD
Afterwards, by the image transmitting to terminal, the image of server receiving terminal transmission is simultaneously handled.
204, according to default recognition rule, the defects of wheel tread type and defect number are identified from the edge feature
Amount, and according to preset confidence factor information, confidence factor is assigned for the defect type and the defects count.
Specifically, the edge feature that server extracts can illustrate the feature that the region of defect occurs in image, and preset
The corresponding relationship of edge feature Yu defect type and defects count is defined in recognition rule, therefore can be according to default recognition rule
The defects of wheel tread type and defects count are determined from edge feature.Illustratively.If edge feature illustrates wheel to stepping on
Occur on face defect region have that area is small and quantity more than feature, then can determine the defect for fiber crops according to default recognition rule
The position distribution of point, the quantity of point and point;If edge feature illustrates that the region that defect occurs on wheel tread has face
The feature that product is big and quantity is few can then determine that the defect is the quantity and recess of recess, recess according to default recognition rule
Position distribution.The threshold value of the size and quantity of defect area can be carried out according to technical manual or actual needs in practical applications
Setting.
Wherein, after server determines defect type and defects count, the thing is assigned according to preset confidence factor information
In fact with corresponding confidence factor, to illustrate the confidence level of the recognition result.
205, by this, treated that image, the defect type, the defects count and the confidence factor are sent to the terminal
It is shown;
Specifically, after server determines defect type, defects count and confidence factor, will treated image, this lacks
It falls into type, defects count and confidence factor to be sent to terminal and shown, so that the staff of terminal side passes through terminal
Display screen obtains defect type, defects count and the confidence factor of wheel tread, to ensure the working condition to wheel tread
Understanding.
206, the defect more new command for receiving terminal return, updates the defect type, the defects count or the confidence level
The factor;
Specifically, the staff of terminal side obtains wheel tread image, defect type and the defects count and confidence
After spending the factor, treated the defects of image type and defects count are judged according to the technological know-how of itself, if eventually
The staff of end side thinks that the recognition result is unreliable, then defect more new command can be inputted by input equipment to terminal, clothes
Business device obtains the defect more new command by terminal, and updates defect type, defects count according to the defect more new command or set
Belief factor.
207, the design data and history detection data of the wheel tread are obtained from the terminal.
Specifically, in wheel tread rehabilitation plan generating process, the defect type that not only needs wheel tread current and
Defects count, it is also necessary to the design data and history detection data of wheel tread, to improve the wheel tread rehabilitation plan generated
Reliability.Wherein, design data can be metastable supplemental characteristic, and such as wheel is to nominal parameter, wheel tread circular wear
Depth, distance between backs of wheel flanges from etc. data, history detection data can be the supplemental characteristic in operational process, as certain detects hour wheel pair
The parameters data such as tyre tread glass length, wheel tread scratch and local depth of recess.
208, receive the terminal return defect confirmation instruction, in response to the defect confirmation instruct, according to the defect type,
The defects count, the confidence factor, the design data and the history detection data generate wheel tread rehabilitation plan.
Specifically, the staff of terminal side thinks the defect type and lack that server goes out according to treated image recognition
It is reliable to fall into quantity, then defect confirmation is inputted by input unit and instructed to terminal, the defect that server receives terminal return is true
Recognize instruction, according to existing defect type, defects count, confidence factor, design data and history detection data, generates wheel
To tyre tread rehabilitation plan.
209, the defect consulting instruction for receiving terminal return, by treated image, the defect type, the defect number
Amount and the confidence factor are sent to specified counseling services device, and the defect opinion for obtaining counseling services device return is sent to
The terminal is shown.
The defect type and defects count result that image recognition goes out specifically, the staff of terminal side thinks that treated
It can not determine, then input defect consulting instruction to terminal by input unit, the defect consulting that server receiving terminal returns refers to
It enables, image, defect type, defects count and the confidence factor of resulting treated wheel tread is sent to specified official communication
The defect opinion ask server, and obtain counseling services device return is sent to terminal and is shown.In practical applications, it seeks advice from
Server can be to produce vendor server, maintenance department's server or research department's server, as shown in Figure 5.
210, treated the image and the wheel tread rehabilitation plan are sent to the terminal and shown.
Specifically, after server generates, treated image and wheel tread rehabilitation plan are sent to terminal and shown
Show, so that the staff of terminal side obtains the image of wheel tread by the display screen of terminal and corresponding wheel tread is repaired
Multiple plan, to hold the repair process of wheel tread.
211, in response to the terminal return reparation confirm instruction, control wheel tread prosthetic device to the wheel tread into
Row is repaired.
Specifically, the staff of terminal side thinks reliable according to the wheel tread rehabilitation plan, then pass through input unit
Input repairs confirmation instruction to terminal, and server receives the reparation confirmation instruction of terminal return, according to wheel tread reparation meter
Control wheel tread prosthetic device is drawn to repair wheel tread.Illustratively, if the defect on wheel tread is fatigue stripping
From then wheel tread rehabilitation plan is that wheel Xuan cuts or polishes;If the defect of wheel tread is dotted scratch, wheel tread is repaired
Multiple plan is to carry out built-up welding to wheel rim, then machined on a small quantity.
212, instruction is seeked advice from response to the reparation that the terminal returns, by treated the image and the wheel tread reparation meter
The reparation opinion drawn and be sent to specified counseling services device, and obtain counseling services device return is sent to the terminal and is shown
Show.
Specifically, the staff of terminal side thinks the wheel pair according to current treated image can not determine generation
When whether tyre tread rehabilitation plan is reliable, inputted by input unit and repair consulting instruction to terminal, server receiving terminal returns
Reparation seek advice from instruction, the image of resulting treated wheel tread and wheel tread rehabilitation plan are sent to specified official communication
The reparation opinion ask server, and obtain counseling services device return is sent to terminal and is shown.In practical applications, it seeks advice from
Server can be production vendor server, maintenance department's server or research department's server.
Optionally, as shown in Figure 6 and Figure 8, server is using defect type of the production KR to wheel tread, defect
Quantity and wheel tread rehabilitation plan is determined and reasoning, then server includes knowledge base, database and inference machine.Its
In, knowledge base is used to store during the knowledge of wheel tread reparation, experience, book knowledge and vehicle operate wheel to being likely to occur
Various State Knowledges and common sense memory.Database is used to store the field of the fact that reflection wheel tread current state data
Institute.Inference machine is one group for controlling, coordinating the computer program of whole system, can utilize knowledge base according to the input data
Knowledge goes gradually reasoning until obtaining corresponding conclusion according to certain inference strategy, and inference machine includes inference method and control
Tactful two parts.
Optionally, as shown in fig. 6, user passes through design data, history detection data and the wheel of terminal typing wheel tread
It, can also be by the design data and history detection data of terminal modifications wheel tread, if the figure of wheel tread to the image of tyre tread
Image quality amount is unsatisfactory for preset condition, then the image of new wheel tread can be reacquired by terminal.Then, server is taken turns
To the defect dipoles of tyre tread, the defect kind and defects count that include in the image to confirm wheel tread.Then, server into
Row wheel carries out defect repair decision to Rehabilitation decision, after finally being repaired wheel tread, can obtain decision-making results.
Wherein, defect kind, defects count and the defect repair decision of server confirmation are storable in knowledge base.
Optionally, server is judged and is repaired to the defect of wheel tread using forward and reverse hybrid inference method.Such as
Shown in Fig. 7 and Fig. 8, after server obtains detection data, data are pre-processed, it then will be after the pretreatment by inference machine
Detection data make inferences after, the data that export.
Wherein, different wheel tread defect informations is collected due to that may need to identify, inference machine use is not smart
True inference method makes inferences, and on the basis of scheduled rule intensity and uncertain original evidence, defines one group of function, asks
The uncertain factor of conclusion out.To certain certainty factor of uncertain knowledge everywhere, in reasoning process, according to intelligent algorithm
The certainty factor of intermediate result is calculated, and propagates this uncertainty along reasoning, until drawing a conclusion.
Wherein, control strategy is primarily referred to as the control of inference direction and the selection strategy of inference rule, adopts in the present embodiment
With forward and reverse hybrid inference method better than the unidirectional inference method such as forward reasoning and backward reasoning, it can according to important symptom,
It is obtained by forward reasoning it is assumed that finding necessary condition repeatedly again to assume backward reasoning.
In embodiments of the present invention, in a first aspect, after handling by the image to wheel tread, wheel is automatically identified
To the defect type and defects count of tyre tread, manually detected without passing through, to reduce human cost and technology
Difficulty;Second aspect automatically generates wheel tread reparation by being matched with the defect type of wheel tread and defects count
Plan avoids consulting renovation technique card, to reduce time cost and technical difficulty.The third aspect, user is by updating clothes
Defect type, defects count or the confidence factor that business device identifies, can be improved the wheel tread rehabilitation plan being subsequently generated
Reliability.Fourth aspect can further improve subsequent life by obtaining defect opinion from other counseling services devices and repairing opinion
At wheel tread rehabilitation plan reliability, and reduce technical costs.
Referring to Fig. 9, Fig. 9 is the structure of the wheel tread rehabilitation plan generating means in 3rd embodiment provided by the invention
Schematic diagram.Device as shown in Figure 9 mainly includes:
Module 301 is obtained, for obtaining the image of wheel tread from terminal.
Whether analysis module 302, the quality for analyzing image meet preset condition.
Processing module 303, if the quality for analysis module analysis image meets preset condition, at image
Reason.
Identification module 304, for identifying the defect type and defects count of wheel tread from treated image.
Generation module 305, for generating and defect type and the matched wheel tread rehabilitation plan of defects count.
Sending module 306 is shown for being sent to terminal.
Further, identification module 304 includes:
Extracting sub-module 3041, for the edge feature in the image after extraction process.
Submodule 3042 is identified, for identifying the defects of wheel tread from edge feature according to default recognition rule
Type and defects count, and according to preset confidence factor information, it is that defect type and defects count assign confidence factor.
Further, module 301 is obtained, is also used to obtain the design data and history testing number of wheel tread from terminal
According to.
Generation module 305 is also used to be detected according to defect type, defects count, confidence factor, design data and history
Data generate wheel tread rehabilitation plan.
Sending module 306, is also used to that image, wheel tread rehabilitation plan and certainty factor are sent to end by treated
End is shown.
Module 301 is obtained, if the quality for being also used to analysis module analysis image is unsatisfactory for preset condition, is obtained from terminal
The new images of wheel tread.
Further, sending module 306, be also used to by treated image, defect type, defects count and confidence level because
Son is sent to terminal and is shown.
Device further includes:Instruction module 307 is received, for receiving the defect more new command of terminal return, updates defect class
Type, defects count or confidence factor.
Instruction module 307 is received, is also used to receive the defect confirmation instruction of terminal return, is instructed in response to defect confirmation,
According to defect type, defects count, confidence factor, design data and history detection data, wheel tread rehabilitation plan is generated.
Instruction module 307 is received, is also used to receive the defect consulting instruction of terminal return, it will treated image, defect
Type, defects count and confidence factor are sent to specified counseling services device, and obtain the defect meaning of counseling services device return
See that being sent to terminal is shown.
Instruction module 307 is received, the reparation confirmation instruction for being also used to return in response to terminal, control wheel tread reparation dress
It sets and wheel tread is repaired.
Instruction module 307 is received, the reparation consulting instruction for being also used to return in response to terminal will treated image and wheel
Specified counseling services device is sent to tyre tread rehabilitation plan, and the reparation opinion for obtaining the return of counseling services device is sent to terminal
It is shown.
In embodiments of the present invention, after handling first by the image to wheel tread, wheel is automatically identified to stepping on
The defect type and defects count in face are manually detected without passing through, to reduce human cost and technical difficulty;
In addition, automatically generating wheel tread rehabilitation plan by being matched with the defect type of wheel tread and defects count, avoiding
Renovation technique card is consulted, to reduce time cost and technical difficulty.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, there is no the portion being described in detail in some embodiment
Point, reference can be made to the related descriptions of other embodiments.
The above are the descriptions of wheel tread rehabilitation plan generation method provided by the present invention and device, for this field
Those skilled in the art, thought according to an embodiment of the present invention have change place in specific embodiments and applications, comprehensive
On, the contents of this specification are not to be construed as limiting the invention.
Claims (10)
1. a kind of wheel tread rehabilitation plan generation method, which is characterized in that the method includes:
The image of wheel tread is obtained from terminal, and whether the quality for analyzing described image meets preset condition;
If the quality of described image meets preset condition, described image is handled, and is identified from treated image
The defect type and defects count of the wheel tread;
Generate with the defect type and the matched wheel tread rehabilitation plan of the defects count, and be sent to the terminal into
Row display.
2. wheel tread rehabilitation plan generation method as described in claim 1, which is characterized in that described from treated image
The middle defect type for identifying the wheel tread and defects count include:
The edge feature in image after extraction process;
According to default recognition rule, the defects of wheel tread type and defects count are identified from the edge feature,
It is that the defect type and the defects count assign confidence factor and according to preset confidence factor information.
3. wheel tread rehabilitation plan generation method as claimed in claim 2, which is characterized in that the generation and the defect
Before type and the matched wheel tread rehabilitation plan of the defects count, including:
The design data and history detection data of the wheel tread are obtained from the terminal;
The then generation and the defect type and the matched wheel tread rehabilitation plan of the defects count, and be sent to described
Terminal carries out display:
According to the defect type, the defects count, the confidence factor, the design data and the history testing number
According to generation wheel tread rehabilitation plan;
Treated the image and the wheel tread rehabilitation plan are sent to the terminal and shown.
4. wheel tread restorative procedure as described in claim 1, which is characterized in that whether the quality of the analysis described image
After meeting preset condition, including:
If the quality of described image is unsatisfactory for the preset condition, the new images of the wheel tread are obtained from the terminal.
5. wheel tread rehabilitation plan generation method as claimed in claim 3, which is characterized in that described according to preset confidence
Spend factor information, be that the defect type and the defects count assign confidence factor, with it is described according to the defect type,
The defects count, the confidence factor, the design data and the history detection data generate wheel tread reparation meter
Between drawing, including:
Treated that image, the defect type, the defects count and the confidence factor are sent to the end by described
End is shown;
The defect more new command that the terminal returns is received, the defect type, the defects count or the confidence level are updated
The factor;
It is described to be examined according to the defect type, the defects count, the confidence factor, the design data and the history
Measured data, generating wheel tread rehabilitation plan includes:
The defect confirmation instruction that the terminal returns is received, is instructed in response to the defect confirmation, according to the defect type, institute
Defects count, the confidence factor, the design data and the history detection data are stated, wheel tread reparation meter is generated
It draws;
The method also includes:
The defect consulting instruction that the terminal returns is received, it will treated image, the defect type, the defect number
Amount and the confidence factor are sent to specified counseling services device, and obtain the defect opinion hair that the counseling services device returns
The terminal is given to be shown.
6. wheel tread rehabilitation plan generation method as claimed in claim 3, which is characterized in that described treated by described in
Image and the wheel tread rehabilitation plan are sent to after the terminal shown, including:
Instruction is confirmed in response to the reparation that the terminal returns, and control wheel tread prosthetic device repairs the wheel tread
It is multiple;
Instruction is seeked advice from response to the reparation that the terminal returns, treated by described in image and the wheel tread rehabilitation plan
The reparation opinion for being sent to specified counseling services device, and obtaining the counseling services device return is sent to the terminal and is shown
Show.
7. a kind of wheel tread rehabilitation plan generating means, which is characterized in that described device includes:
Module is obtained, for obtaining the image of wheel tread from terminal;
Whether analysis module, the quality for analyzing described image meet preset condition;
Processing module, if for the analysis module analysis described image quality meet preset condition, to described image into
Row processing;
Identification module, for identifying the defect type and defects count of the wheel tread from treated image;
Generation module, for generating and the defect type and the matched wheel tread rehabilitation plan of the defects count;
Sending module is shown for being sent to the terminal.
8. wheel tread rehabilitation plan generating means as claimed in claim 7, which is characterized in that the identification module includes:
Extracting sub-module, for the edge feature in the image after extraction process;
Submodule is identified, for identifying the defects of described wheel tread from the edge feature according to default recognition rule
Type and defects count, and according to preset confidence factor information, it is set for the defect type and defects count imparting
Belief factor.
9. wheel tread rehabilitation plan generating means as claimed in claim 8, which is characterized in that
The acquisition module is also used to obtain the design data and history detection data of the wheel tread from the terminal;
The generation module is also used to according to the defect type, the defects count, the confidence factor, the design
Data and the history detection data generate wheel tread rehabilitation plan;
The sending module is also used to treated the image and the wheel tread rehabilitation plan being sent to the terminal
It is shown;
The acquisition module, if the quality for being also used to the analysis module analysis described image is unsatisfactory for the preset condition,
The new images of the wheel tread are obtained from the terminal.
10. wheel tread rehabilitation plan generating means as claimed in claim 9, which is characterized in that
The sending module is also used to treated image, the defect type, the defects count and the confidence
The degree factor is sent to the terminal and is shown;
Described device further includes:
Instruction module is received, the defect more new command returned for receiving the terminal updates the defect type, the defect
Quantity or the confidence factor;
The reception instruction module is also used to receive the defect confirmation instruction that the terminal returns, in response to the defect confirmation
Instruction is detected according to the defect type, the defects count, the confidence factor, the design data and the history
Data generate wheel tread rehabilitation plan;
The reception instruction module is also used to receive the defect consulting instruction that the terminal returns, will treated the image,
The defect type, the defects count and the confidence factor are sent to specified counseling services device, and obtain the official communication
The defect opinion for asking server return is sent to the terminal and is shown;
The reception instruction module, the reparation confirmation instruction for being also used to return in response to the terminal, controls wheel tread reparation
Device repairs the wheel tread;
The reception instruction module is also used to the reparation consulting instruction in response to terminal return, and treated by described in schemes
Picture and the wheel tread rehabilitation plan are sent to specified counseling services device, and obtain the reparation that the counseling services device returns
Opinion is sent to the terminal and is shown.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810748373.5A CN108921845A (en) | 2018-07-10 | 2018-07-10 | Wheel tread rehabilitation plan generation method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810748373.5A CN108921845A (en) | 2018-07-10 | 2018-07-10 | Wheel tread rehabilitation plan generation method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108921845A true CN108921845A (en) | 2018-11-30 |
Family
ID=64411368
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810748373.5A Pending CN108921845A (en) | 2018-07-10 | 2018-07-10 | Wheel tread rehabilitation plan generation method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108921845A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114351522A (en) * | 2021-12-31 | 2022-04-15 | 武汉大学 | Steel rail polishing method and equipment based on machine vision and water jet |
CN114381976A (en) * | 2022-01-20 | 2022-04-22 | 武汉大学 | Expert system-based self-adaptive water jet steel rail grinding method and equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1734228A (en) * | 2004-08-13 | 2006-02-15 | Mv研究有限公司 | Machine vision analysis system and method |
CN104608799A (en) * | 2014-12-12 | 2015-05-13 | 郑州轻工业学院 | Information fusion technology based train wheel set tread damage online detection and recognition method |
KR20150061359A (en) * | 2013-11-27 | 2015-06-04 | 주식회사 우진산전 | Three-dimensional shape measurement device of train wheels |
CN106971133A (en) * | 2016-01-14 | 2017-07-21 | 芋头科技(杭州)有限公司 | One kind improves image recognition precision device and method |
CN107146224A (en) * | 2017-05-03 | 2017-09-08 | 石家庄铁道大学 | The online image detecting system of train wheel thread defect and method |
-
2018
- 2018-07-10 CN CN201810748373.5A patent/CN108921845A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1734228A (en) * | 2004-08-13 | 2006-02-15 | Mv研究有限公司 | Machine vision analysis system and method |
KR20150061359A (en) * | 2013-11-27 | 2015-06-04 | 주식회사 우진산전 | Three-dimensional shape measurement device of train wheels |
CN104608799A (en) * | 2014-12-12 | 2015-05-13 | 郑州轻工业学院 | Information fusion technology based train wheel set tread damage online detection and recognition method |
CN106971133A (en) * | 2016-01-14 | 2017-07-21 | 芋头科技(杭州)有限公司 | One kind improves image recognition precision device and method |
CN107146224A (en) * | 2017-05-03 | 2017-09-08 | 石家庄铁道大学 | The online image detecting system of train wheel thread defect and method |
Non-Patent Citations (1)
Title |
---|
李峰: "激光熔覆技术在轮对踏面修复中的工艺流程及经济效益分析", 《神华科技》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114351522A (en) * | 2021-12-31 | 2022-04-15 | 武汉大学 | Steel rail polishing method and equipment based on machine vision and water jet |
CN114381976A (en) * | 2022-01-20 | 2022-04-22 | 武汉大学 | Expert system-based self-adaptive water jet steel rail grinding method and equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108961217B (en) | Surface defect detection method based on regular training | |
CN115516500A (en) | Anomaly detection based on autoencoder and clustering | |
CN110264444B (en) | Damage detection method and device based on weak segmentation | |
CN111986172A (en) | Infrared image fault detection method and device for power equipment | |
CN105549573A (en) | Intelligent internet-of-things car washing system and control method | |
CN108921845A (en) | Wheel tread rehabilitation plan generation method and device | |
CN112633149A (en) | Domain-adaptive foggy-day image target detection method and device | |
CN112184667A (en) | Defect detection and repair method, device and storage medium | |
US11908127B2 (en) | Internet of Things systems for industrial data processing, control methods, and storage medium thereof | |
CN116297199B (en) | Detection system for automatically detecting lithium battery parameters based on machine vision | |
CN101826159B (en) | Method for realizing partitioned binarization of gray scale image and data processing equipment | |
CN112183311A (en) | Transformer substation equipment fault detection method based on bimodal data fusion | |
CN116385430A (en) | Machine vision flaw detection method, device, medium and equipment | |
US20220164990A1 (en) | Image processing apparatus, image processing method, and nontransitory computer readable medium storing program | |
CN110490118A (en) | Image processing method and device | |
Balu et al. | Smart traffic congestion control system | |
CN111242914B (en) | Photovoltaic module hot spot defect positioning method based on pane detection and linear regression algorithm | |
CN115830302B (en) | Multi-scale feature extraction fusion power distribution network equipment positioning identification method | |
CN116958035A (en) | Product part defect detection method, device, medium and electronic equipment | |
CN116091976A (en) | Station room defect identification detection method, system, device and storage medium | |
Anily et al. | An optimal lot-sizing and offline inspection policy in the case of nonrigid demand | |
CN115272284A (en) | Power transmission line defect identification method based on image quality evaluation | |
CN115904916A (en) | Hard disk failure prediction method and device, electronic equipment and storage medium | |
CN113516593B (en) | Human eye image detection and restoration method | |
CN114998889A (en) | Intelligent identification method and system for immersive three-dimensional image |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181130 |