CN102346844A - Device and method for identifying fault of losing screw bolts for truck center plates - Google Patents
Device and method for identifying fault of losing screw bolts for truck center plates Download PDFInfo
- Publication number
- CN102346844A CN102346844A CN2011101669743A CN201110166974A CN102346844A CN 102346844 A CN102346844 A CN 102346844A CN 2011101669743 A CN2011101669743 A CN 2011101669743A CN 201110166974 A CN201110166974 A CN 201110166974A CN 102346844 A CN102346844 A CN 102346844A
- Authority
- CN
- China
- Prior art keywords
- image
- center bearing
- bearing bolt
- coordinate
- lorry
- 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.)
- Granted
Links
Images
Abstract
The invention provides a device and a method for identifying a fault of losing screw bolts for truck center plates, wherein the identification device comprises an image collector, an image processor and an output unit; and the identification method comprises the following steps: (1) receiving vehicle information sent from the image collector; (2) selecting and reading in a to-be-identified image; (3) zooming out the image in equal proportion; (4) initially positioning the image according to the filename suffix of an image of a screw bolt for truck center plates; (5) carrying out primary preprocessing on the image zoomed out in equal proportion; (6) positioning a candidate region; (7) extracting the image features of the candidate region; (8) identifying and calculating feature data; and (9) outputting an identification result. The device and method disclosed by the invention has the advantages that: a detailed classification can be performed on vehicle types, the adaptive capacity is strong, and new vehicle types are easily added; the normal operation of train inspectors on a TFDS (trouble of moving freight car detection system) system is not affected; and automatic identification results can be stored in a friendly mode, thereby providing a convenient and fast reinspection mode for the train inspectors.
Description
Technical field
The invention belongs to railway freight-car operation troubles detection technique field, be specifically related to a kind of lorry center bearing bolt and lose Fault Identification device and recognition methods thereof.
Background technology
Railway freight-car fault rail edge graph is a cover collection high-speed figure image acquisition as detection system, high capacity image real-time processing technique, and placement technology, networking technology and automatic control technology are called for short TFDS in the system of one.The invention belongs to TFDS railway freight-car operation troubles rail edge graph as detection range, relate to a kind of lorry operation troubles image automatic identification equipment, specifically is the automatic identification equipment that lorry center bearing bolt is lost the fault graph picture.
The TFDS system mainly carries out Fault Identification with manual work mode with the aid of pictures to the image of gathering at present, and human cost is high, and labour intensity is big.The effect of Fault Identification receives train-examiner's physiological status and the restriction of examining subjective factors such as car experience.
The automatic Recognition Theory of image has obtained in a plurality of fields such as recognition of face, fingerprint recognition, production line safety checks using widely, but also relatively limited as the research in the automatic identification field in the lorry fault graph, this type of application also do not occur.
Summary of the invention
To the problem that exists in the prior art; The present invention proposes a kind of lorry center bearing bolt and loses Fault Identification device and recognition methods thereof; Do not influence the operate as normal of station inspector in existing TFDS system; Preserve automatic recognition result with close friend's mode, the mode of rechecking easily is provided to station inspector; Can carry out careful classification to type of vehicle, adaptive faculty is strong, also is easy to increase new type of vehicle.
A kind of lorry center bearing bolt that the present invention proposes is lost the Fault Identification device and is comprised image acquisition device, image processor and output unit; Described image acquisition device is responsible for gathering the center bearing bolt image at position, lorry center bearing bolt place, and this image is transferred to image processor; Image processor is responsible for center bearing bolt image is handled and discerned; Finally judge the fault that whether exists the center bearing bolt to lose in the center bearing bolt image; And mark location of fault; Discern the image that finishes to output unit output then, the image output that output unit is responsible for identification is finished shows.
A kind of lorry center bearing bolt is lost the recognition methods of failed equipment, it is characterized in that: specifically comprise following step:
(1) train through the time, receive the information of vehicles of the lorry body in service that sends from image acquisition device, information of vehicles comprises vehicle, vehicle number and view data.
(2) choose and read in image to be identified: image processor is according to information of vehicles and picture naming rule; From the truck body image library, extract image that this train contains the center bearing bolt member as image to be identified, the naming rule of described image is: x_y_z; X is the numbering of vehicle in the train number train, since 1 layout; Y is the position of this vehicle, and y=1 representes the bogie position of vehicle, and y=2 representes vehicle braked beam position, and y=3 representes vehicle pars intermedia position, and y=4 representes that hitch colludes slow portion; Z is the numbering of this station diagram picture of train, and since 1 layout, vehicle model is different.
(3) scaled down:
Image processor carries out the size scaled down with the center bearing bolt image that receives; Adopt the image drop sampling disposal route that the size of images that receives is carried out scaled down; Be specially in original image in every n pixel; Get n pixel value as dwindling corresponding pixel value in the image of back; The scaling of corresponding equal proportion convergent-divergent is 1/n, and wherein 1/n generally chooses 1/8～1/2.
(4) just locate according to the filename suffix of center bearing bolt image:
Corresponding numeral according to z in the center bearing bolt image file name suffix is tentatively selected the scope of center bearing bolt member this image from image center to be identified; Obtain the image of location just; Specifically obtaining just, the method for positioning image is: getting the upper left summit of image to be identified is true origin; To pass this level direction to the right is x axle positive dirction, to pass this some direction y axle positive dirction straight down; When z=1 or 7, the center bearing bolt member is on image to be identified right side, and then just the scope of positioning image is more than or equal to an A
1, the some B
1, the some C
1With a D
1The quadrilateral area that constitutes; Its mid point A
1Coordinate be (106,453), the some B
1Coordinate be that upper right coordinate does, the some C
1Coordinate be the position, bottom right, the some D
1Coordinate be (396,453), when z=4 or 10, the center bearing bolt member is in image to be identified left side, then just the scope of positioning image is more than or equal to an A
2, the some B
2, the some C
2With a D
2The quadrilateral area that constitutes; Its mid point A
2Coordinate be (106,225), the some B
2Coordinate be that upper right coordinate is (106,345), the some C
2The coordinate of (lower-right most point) is position, bottom right (396,345), some D
2Coordinate be (396,225).
(5) image after the scaled down is carried out preliminary pre-service:
The image processor just image transitions of location is a gray level image, then gray level image is carried out the brightness adjustment; Described brightness is adjusted into the interval of pixel value in the first positioning image zone of search; Interval two ends are the minimum pixel value and the max pixel value in zone; The difference of each position pixel value and minimum pixel value in the zoning, and this difference is evenly distributed in the interval of pixel value.
(6) candidate region, location:
Preliminary pretreated image is carried out the pointwise traversal; Judge whether to be candidate point; Determination methods is: the horizontal direction and the vertical gradient value of image after the calculating pre-service; Through judging the size of each point in image Grad summation of horizontal direction and vertical direction in 100～200 adjacent pixel values of upper and lower, left and right four direction; When the value of summation greater than 75 the time; Become candidate point, the set of all candidate points constitutes the candidate region.
(7) characteristics of image of extraction candidate region:
Utilize edge feature, corner characteristics and ridge Feature Extraction method that feature extraction is carried out in the candidate region, form feature extraction vector data group, it is 3 groups that the characteristic vector data data set is divided into, every group of 10 proper vectors; First group is Edge Gradient Feature, and second group is that corner characteristics extracts, and the 3rd group is the extraction of ridge detected characteristics.
(8) characteristic is carried out recognition operation:
After the neural network with the input of the characteristic vector data group that extracts, export a monodrome, judge this monodrome, if this monodrome, is then thought the fault that image to be identified exists the center bearing bolt to lose greater than 0.5.
(9) output recognition result:
The location of fault that the center bearing bolt that identifies is lost is marked on the image to be identified, and output shows.
The invention has the advantages that:
(1) a kind of lorry center bearing bolt of proposing of the present invention is lost Fault Identification device and recognition methods thereof, does not influence the operate as normal of station inspector in existing TFDS system;
(2) a kind of lorry center bearing bolt of the present invention's proposition is lost Fault Identification device and recognition methods thereof, preserves automatic recognition result with close friend's mode, to station inspector the mode of rechecking easily is provided;
(3) a kind of lorry center bearing bolt of proposing of the present invention is lost Fault Identification device and recognition methods thereof, automatically starts, stops, and does not in servicely need manual intervention;
(4) a kind of lorry center bearing bolt of the present invention's proposition is lost Fault Identification device and recognition methods thereof, and type of vehicle is carried out careful classification, and adaptive faculty is strong, also is easy to increase new type of vehicle;
(5) a kind of lorry center bearing bolt of the present invention's proposition is lost the Fault Identification device, and the name of image file has the predefine rule, makes automatic identification algorithm simpler and more direct.
Description of drawings
Fig. 1: the present invention proposes the structural representation that a kind of lorry center bearing bolt is lost the Fault Identification device;
Fig. 2: the structural drawing of neural network among the present invention.
Among the figure: the 1-image acquisition device; The 2-image processor; The 3-output unit.
Embodiment
To combine accompanying drawing that the present invention is done further detailed description below.
The present invention proposes a kind of lorry center bearing bolt and loses the Fault Identification device, comprises image acquisition device 1, image processor 2 and output unit 3.Described image acquisition device 1 is responsible for gathering the center bearing bolt image at position, lorry center bearing bolt place, and this image is transferred to image processor; Image processor 2 is responsible for center bearing bolt image is handled and discerned; Finally judge the fault that whether exists the center bearing bolt to lose in the center bearing bolt image; And mark location of fault; Discern the image that finishes to output unit 3 outputs then, the images output that output unit 3 is responsible for identification is finished shows.
The present invention also proposes the recognition methods that a kind of lorry center bearing bolt is lost failed equipment, specifically comprises following step:
(1) train through the time, receive the information of vehicles of the lorry body in service that sends from image acquisition device 1.Described information of vehicles specifically refers to: a row lorry probably is made up of 40～70 cars and 1 locomotive, and the information of vehicles data owner that collects will comprise vehicle, vehicle number and view data.
(2) choose and read in image to be identified: image processor 2 is according to information of vehicles and picture naming rule, from the truck body image library, extracts image that this train contains the center bearing bolt member as image to be identified.The naming rule of described image is: x_y_z, x are the numbering of vehicle in the train number train, since 1 layout; Y is the position of this vehicle, and y=1 representes the bogie position of vehicle, and y=2 representes vehicle braked beam position, and y=3 representes vehicle pars intermedia position, and y=4 representes that hitch colludes slow portion; Z is the numbering of this position of train (y value corresponding position) image, and since 1 layout, vehicle model is different, and its vehicle length is different, so amount of images is also different.The 8th image representing the 3rd car brake beam position of this train like 3_2_8.The center bearing bolt is the parts at brake beam position, so the center bearing bolt only can appear in the x_2_z image, and the present invention is through lot of statistics, and the center bearing bolt generally is present in the image of x_2_1, x_2_4, x_2_7, x_2_10; The naming rule of image meets in promulgation equipment department of Tiedaobu Transportation Bureau in March, 2008 " TFDS image recognition and utilization software platform technical standard " in " annex one TFDS equipment and TFDS image recognition and use the software platform interface standard " 2.1 standard among the present invention.
(3) scaled down:
(4) just locate according to the filename suffix of center bearing bolt image:
Tentatively select the approximate range (range size be roughly 290 * 120) of center bearing bolt member this image according to last 1 bit digital in the center bearing bolt image file name suffix (being the corresponding numeral of the z of x_y_z kind), obtain the image of location just from image center to be identified.Specifically obtaining just, the method for positioning image is: getting the upper left summit of image to be identified (being the point of the top, the leftmost side) for true origin, is x axle positive dirction to pass this level direction to the right, to pass this some direction y axle positive dirction straight down.When z=1 or 7, the center bearing bolt member is on image to be identified right side, and then just the scope of positioning image is more than or equal to an A
1, the some B
1, the some C
1With a D
1The quadrilateral area that constitutes; Its mid point A
1The coordinate of (taking a little) is (106,453), some B
1The coordinate of (upper right point) is that upper right coordinate is (106,573), some C
1The coordinate of (lower-right most point) is position, bottom right (396,573), some D
1The coordinate of (left side is point down) is (396,453), and when z=4 or 10, the center bearing bolt member is in image to be identified left side, and then just the scope of positioning image is more than or equal to an A
2, the some B
2, the some C
2With a D
2The quadrilateral area that constitutes; Its mid point A
2The coordinate of (taking a little) is (106,225), some B
2The coordinate of (upper right point) is that upper right coordinate is (106,345), some C
2The coordinate of (lower-right most point) is position, bottom right (396,345), some D
2The coordinate of (left side is point down) is (396,225).It is thus clear that the area of the first positioning image that obtains needs more than or equal to (120 * 290).Prove that through after analyzing a large amount of lorry types and consulting tens million of fault graph pictures the position with this corresponding relation failure judgement candidate region is feasible.
(5) image after the scaled down is carried out preliminary pre-service:
The image transitions that image processor 2 at first will just be located is a gray level image, then gray level image is carried out the brightness adjustment.Described brightness adjustment generally is that the brightness value with interested partial pixel in the image promotes; Purpose is the difference degree for increase prospect and background; Mainly be convenient to the extraction of center bearing bolt member characteristic vector in image here; Concrete method is: the interval of pixel value in the first positioning image zone of search; Interval two ends are the minimum pixel value and the max pixel value in zone; The difference of each position pixel value and minimum pixel value in the zoning, and this difference is evenly distributed in the interval of pixel value (promptly utilizing the pixel value of this difference as correspondence position).In the above-mentioned preprocessing process image is changed to gray level image from coloured image, in the process of conversion, can accomplishes to abandon colouring information, but do not lose fault characteristic information.
(6) candidate region, location:
Preliminary pretreated image is carried out the pointwise traversal, judge whether to be candidate point (having the center bearing bolt to lose the image slices vegetarian refreshments of fault).Concrete determination methods is: the horizontal direction and the vertical gradient value (sobel value) of image after the calculating pre-service; Through judging the size of each point in image Grad summation of horizontal direction and vertical direction in 100～200 adjacent pixel values of upper and lower, left and right four direction; When the value of summation greater than 75 the time; Become candidate point, the set of all candidate points constitutes the candidate region.
(7) characteristics of image of extraction candidate region:
Utilize edge feature, corner characteristics and ridge Feature Extraction method that feature extraction is carried out in the candidate region, form feature extraction vector data group, it is 3 groups that the characteristic vector data data set is divided into, every group of 10 proper vectors.First group is Edge Gradient Feature, and second group is that corner characteristics extracts, and the 3rd group is the extraction of ridge detected characteristics.Wherein, on the mathematics, the ridge detected characteristics is extracted median ridge and is defined as the extreme point on the largest face curvature direction, can detect through the eigenwert of calculating the Hessian matrix.Fixed size ridge vector is highstrung to target width.It makes scale parameter along with ridge structure in the image automatically adjusts.
(8) characteristic is carried out recognition operation:
After the neural network with the input of the characteristic vector data group that extracts, export a monodrome, judge this monodrome, if this monodrome, is then thought the fault that image to be identified exists the center bearing bolt to lose greater than 0.5.
The training sample of described neural network is divided into fault sample and non-fault sample, and all the mode of choosing figure through manual work is obtained from the train view data; Neural network is the BP neural network, is made up of the forward-propagating of information and two processes of backpropagation of error.Each neuron of input layer is responsible for receiving the input information that comes from the outside, and passes to each neuron of middle layer; The middle layer is the internal information processing layer, is responsible for information conversion, and according to the demand of information change ability, the middle layer can be designed as single latent layer or many latent layer structures; Last latent layer is delivered to output layer, and each neuronic information is accomplished the forward-propagating processing procedure of once learning after further handling, by output layer to extraneous output information result.When reality output is not inconsistent with desired output, get into the back-propagation phase of error.Error is through output layer, by each layer of mode correction weights of error gradient decline, to latent layer, input layer anti-pass successively.Information forward-propagating that goes round and begins again and error back propagation process; Be the constantly processes of adjustment of each layer weights; It also is the process of neural network learning training; The error that this process is performed until neural network output reduces to the acceptable degree; Promptly during less than 1, stop training up to the error of training sample.
(9) output recognition result:
The location of fault that the center bearing bolt that identifies is lost is marked on the image to be identified, and output shows.Data result can directly be checked by manual work, also can be visited automatically with programmable mode by other system.
Described image acquisition device is that a cover disposes the image capturing system of control device and video camera, described control device be when railway freight-car through the time can connect the control device of car automatically.Described video camera adopts the high-speed figure ccd video camera.The compensatory light of described image acquisition device is selected xenon lamp for use, has the advantage that light efficiency height, temperature are low, the life-span is long.When train passed through, image acquisition device carried out counting shaft with axle counter, image acquisition and transmission in real time, had realized crossing the car real time image collection; Image acquisition device can be adjusted time shutter and gain automatically according to external environment condition during image acquisition, guarantees under any circumstance, all obtains best image as far as possible; Video camera and compensatory light all are sealed in the protection box, and rail edge equipment power supply (comprising gate, light source) is 24V low pressure, and is safe and reliable.
Claims (7)
1. a lorry center bearing bolt is lost the Fault Identification device, it is characterized in that: comprise image acquisition device, image processor and output unit; Described image acquisition device is responsible for gathering the center bearing bolt image at position, lorry center bearing bolt place, and this image is transferred to image processor; Image processor is responsible for center bearing bolt image is handled and discerned; Finally judge the fault that whether exists the center bearing bolt to lose in the center bearing bolt image; And mark location of fault; Discern the image that finishes to output unit output then, the image output that output unit is responsible for identification is finished shows.
2. a kind of lorry center bearing bolt according to claim 1 is lost the Fault Identification device, and it is characterized in that: described image acquisition device has the image capturing system of control device and video camera.
3. a kind of lorry center bearing bolt according to claim 2 is lost the Fault Identification device, it is characterized in that: described video camera adopts the high-speed figure ccd video camera.
4. a kind of lorry center bearing bolt according to claim 2 is lost the Fault Identification device, and it is characterized in that: the compensatory light of described image acquisition device is selected xenon lamp for use.
5. a lorry center bearing bolt is lost the recognition methods of failed equipment, it is characterized in that: comprise following step:
(1) train through the time, receive the information of vehicles of the lorry body in service that sends from image acquisition device, information of vehicles comprises vehicle, vehicle number and view data;
(2) choose and read in image to be identified: image processor is according to information of vehicles and picture naming rule; From the truck body image library, extract image that this train contains the center bearing bolt member as image to be identified, the naming rule of described image is: x_y_z; X is the numbering of vehicle in the train number train, since 1 layout; Y is the position of this vehicle, and y=1 representes the bogie position of vehicle, and y=2 representes vehicle braked beam position, and y=3 representes vehicle pars intermedia position, and y=4 representes that hitch colludes slow portion; Z is the numbering of this station diagram picture of train, and since 1 layout, vehicle model is different;
(3) scaled down:
Image processor carries out the size scaled down with the center bearing bolt image that receives; Adopt the image drop sampling disposal route that the size of images that receives is carried out scaled down; Be specially in original image in every n pixel; Get n pixel value as dwindling corresponding pixel value in the image of back, the scaling of corresponding equal proportion convergent-divergent is 1/n;
(4) just locate according to the filename suffix of center bearing bolt image:
Corresponding numeral according to z in the center bearing bolt image file name suffix is tentatively selected the scope of center bearing bolt member this image from image center to be identified, obtains the image of location just;
Specifically obtaining just, the method for positioning image is: getting the upper left summit of image to be identified is true origin, is x axle positive dirction to pass this level direction to the right, to pass this some direction y axle positive dirction straight down; When z=1 or 7, the center bearing bolt member is on image to be identified right side, and then just the scope of positioning image is more than or equal to an A
1, the some B
1, the some C
1With a D
1The quadrilateral area that constitutes; Its mid point A
1Coordinate be (106,453), the some B
1Coordinate be that upper right coordinate does, the some C
1Coordinate be the position, bottom right, the some D
1Coordinate be (396,453), when z=4 or 10, the center bearing bolt member is in image to be identified left side, then just the scope of positioning image is more than or equal to an A
2, the some B
2, the some C
2With a D
2The quadrilateral area that constitutes; Its mid point A
2Coordinate be (106,225), the some B
2Coordinate be that upper right coordinate is (106,345), the some C
2The coordinate of (lower-right most point) is position, bottom right (396,345), some D
2Coordinate be (396,225);
(5) image after the scaled down is carried out preliminary pre-service:
The image processor just image transitions of location is a gray level image, then gray level image is carried out the brightness adjustment; Described brightness is adjusted into the interval of pixel value in the first positioning image zone of search; Interval two ends are the minimum pixel value and the max pixel value in zone; The difference of each position pixel value and minimum pixel value in the zoning, and this difference is evenly distributed in the interval of pixel value;
(6) candidate region, location:
Preliminary pretreated image is carried out the pointwise traversal; Judge whether to be candidate point; Determination methods is: the horizontal direction and the vertical gradient value of image after the calculating pre-service; Through judging the size of each point in image Grad summation of horizontal direction and vertical direction in 100～200 adjacent pixel values of upper and lower, left and right four direction; When the value of summation greater than 75 the time; Become candidate point, the set of all candidate points constitutes the candidate region;
(7) characteristics of image of extraction candidate region:
Utilize edge feature, corner characteristics and ridge Feature Extraction method that feature extraction is carried out in the candidate region, form feature extraction vector data group, it is 3 groups that the characteristic vector data data set is divided into, every group of 10 proper vectors; First group is Edge Gradient Feature, and second group is that corner characteristics extracts, and the 3rd group is the extraction of ridge detected characteristics;
(8) characteristic is carried out recognition operation:
After the neural network with the input of the characteristic vector data group that extracts, export a monodrome, judge this monodrome, if this monodrome, is then thought the fault that image to be identified exists the center bearing bolt to lose greater than 0.5;
(9) output recognition result:
The location of fault that the center bearing bolt that identifies is lost is marked on the image to be identified, and output shows.
6. a kind of lorry center bearing bolt according to claim 5 is lost the recognition methods of failed equipment, it is characterized in that: the neural network in the step (8) is the BP neural network.
7. a kind of lorry center bearing bolt according to claim 5 is lost the recognition methods of failed equipment, it is characterized in that: the 1/n value in the step (5) is 1/8～1/2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201110166974 CN102346844B (en) | 2011-06-21 | 2011-06-21 | Device and method for identifying fault of losing screw bolts for truck center plates |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201110166974 CN102346844B (en) | 2011-06-21 | 2011-06-21 | Device and method for identifying fault of losing screw bolts for truck center plates |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102346844A true CN102346844A (en) | 2012-02-08 |
| CN102346844B CN102346844B (en) | 2012-12-19 |
Family
ID=45545507
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201110166974 Active CN102346844B (en) | 2011-06-21 | 2011-06-21 | Device and method for identifying fault of losing screw bolts for truck center plates |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102346844B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102867182A (en) * | 2012-08-17 | 2013-01-09 | 中国神华能源股份有限公司 | Method and system for detecting water plug loss failure of freight wagon |
| CN103049762A (en) * | 2013-01-24 | 2013-04-17 | 中国神华能源股份有限公司 | Method and device for detecting center plate bolt loss fault |
| CN103600752B (en) * | 2013-09-18 | 2016-04-20 | 大连华锐重工集团股份有限公司 | Special gondola coupling of vehicles mistake automatic checkout equipment and method of inspection thereof |
| CN106394609A (en) * | 2016-08-25 | 2017-02-15 | 北京康拓红外技术股份有限公司 | Device and method for truck axle counting, and truck counting and bottom key component positioning |
| CN106778740A (en) * | 2016-12-06 | 2017-05-31 | 北京航空航天大学 | A kind of TFDS non-faulting image detecting methods based on deep learning |
| CN109902569A (en) * | 2019-01-23 | 2019-06-18 | 上海思立微电子科技有限公司 | Conversion method, device and the fingerprint identification method of fingerprint image |
| CN111079746A (en) * | 2019-12-12 | 2020-04-28 | 哈尔滨市科佳通用机电股份有限公司 | Railway wagon axle box spring fault image identification method |
| CN115879036A (en) * | 2023-02-15 | 2023-03-31 | 慧铁科技有限公司 | Method for analyzing and processing faults of train release valve pull rod |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103034850B (en) * | 2012-12-21 | 2014-04-16 | 湖北工业大学 | Trouble of moving freight car detection system (TFDS) block key loss fault automatic identification method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2513860Y (en) * | 2001-11-29 | 2002-10-02 | 贺雄明 | Dynamic monitor for train quality |
| CN1562686A (en) * | 2004-04-09 | 2005-01-12 | 北京瑞威世纪软件科技发展有限公司 | Dynamic fault detection device for bed timber type vehicle |
| CN201016002Y (en) * | 2006-12-26 | 2008-02-06 | 曹亮 | Structural light recognizing railway vehicle fittings application state test apparatus |
-
2011
- 2011-06-21 CN CN 201110166974 patent/CN102346844B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2513860Y (en) * | 2001-11-29 | 2002-10-02 | 贺雄明 | Dynamic monitor for train quality |
| CN1562686A (en) * | 2004-04-09 | 2005-01-12 | 北京瑞威世纪软件科技发展有限公司 | Dynamic fault detection device for bed timber type vehicle |
| CN201016002Y (en) * | 2006-12-26 | 2008-02-06 | 曹亮 | Structural light recognizing railway vehicle fittings application state test apparatus |
Non-Patent Citations (1)
| Title |
|---|
| 戴鹏: "基于计算机视觉的故障自动识别系统的设计和实现", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102867182A (en) * | 2012-08-17 | 2013-01-09 | 中国神华能源股份有限公司 | Method and system for detecting water plug loss failure of freight wagon |
| CN103049762A (en) * | 2013-01-24 | 2013-04-17 | 中国神华能源股份有限公司 | Method and device for detecting center plate bolt loss fault |
| CN103600752B (en) * | 2013-09-18 | 2016-04-20 | 大连华锐重工集团股份有限公司 | Special gondola coupling of vehicles mistake automatic checkout equipment and method of inspection thereof |
| CN106394609A (en) * | 2016-08-25 | 2017-02-15 | 北京康拓红外技术股份有限公司 | Device and method for truck axle counting, and truck counting and bottom key component positioning |
| CN106778740A (en) * | 2016-12-06 | 2017-05-31 | 北京航空航天大学 | A kind of TFDS non-faulting image detecting methods based on deep learning |
| CN109902569A (en) * | 2019-01-23 | 2019-06-18 | 上海思立微电子科技有限公司 | Conversion method, device and the fingerprint identification method of fingerprint image |
| CN111079746A (en) * | 2019-12-12 | 2020-04-28 | 哈尔滨市科佳通用机电股份有限公司 | Railway wagon axle box spring fault image identification method |
| CN115879036A (en) * | 2023-02-15 | 2023-03-31 | 慧铁科技有限公司 | Method for analyzing and processing faults of train release valve pull rod |
| CN115879036B (en) * | 2023-02-15 | 2023-05-16 | 慧铁科技有限公司 | Method for analyzing and processing faults of train relief valve pull rod |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102346844B (en) | 2012-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102346844B (en) | Device and method for identifying fault of losing screw bolts for truck center plates | |
| Liu et al. | A review of applications of visual inspection technology based on image processing in the railway industry | |
| CN102332089B (en) | Railway wagon brake shoe key going-out fault recognition method based on artificial neural network | |
| CN107154040A (en) | A kind of tunnel-liner surface image crack detection method | |
| CN107122747A (en) | A kind of railway carriage state non-contact detection device and method | |
| CN109948416A (en) | A kind of illegal occupancy bus zone automatic auditing method based on deep learning | |
| CN111476767B (en) | High-speed rail fastener defect identification method based on heterogeneous image fusion | |
| KR102017870B1 (en) | Real-time line defect detection system | |
| CN206446603U (en) | A kind of locomotive running part detection means being imaged based on linear array scanning and 3D | |
| CN110991466A (en) | Highway road surface condition detecting system based on novel vision sensing equipment | |
| CN109489724A (en) | A kind of tunnel safe train operation environment comprehensive detection device and detection method | |
| CN109766746A (en) | A kind of track foreign matter detecting method of unmanned plane video | |
| CN111489339A (en) | Method for detecting defects of bolt spare nuts of high-speed railway positioner | |
| CN112528979B (en) | Transformer substation inspection robot obstacle distinguishing method and system | |
| CN111768417A (en) | Railway wagon overrun detection method based on monocular vision 3D reconstruction technology | |
| CN111079748A (en) | Method for detecting oil throwing fault of rolling bearing of railway wagon | |
| CN114648669A (en) | Motor train unit fault detection method and system based on domain-adaptive binocular parallax calculation | |
| CN111598855A (en) | 2C equipment high-speed rail contact net dropper defect detection method based on deep learning and transfer learning | |
| Hsieh et al. | Offline Deep-learning-based Defective Track Fastener Detection and Inspection System. | |
| CN115841477A (en) | Multi-mode visual fusion ballastless track structure hidden defect detection method and system | |
| CN106320173B (en) | Vehicle-mounted unmanned aerial vehicle bridge routine safety detection system and detection method | |
| CN112508911A (en) | Rail joint touch net suspension support component crack detection system based on inspection robot and detection method thereof | |
| CN115719475B (en) | Three-stage trackside equipment fault automatic detection method based on deep learning | |
| CN111091553A (en) | Method for detecting loss of blocking key | |
| CN115857040A (en) | Dynamic visual detection device and method for foreign matters on locomotive roof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |