CN104200464A - Train anomaly recognition detection method and system - Google Patents
Train anomaly recognition detection method and system Download PDFInfo
- Publication number
- CN104200464A CN104200464A CN201410406535.9A CN201410406535A CN104200464A CN 104200464 A CN104200464 A CN 104200464A CN 201410406535 A CN201410406535 A CN 201410406535A CN 104200464 A CN104200464 A CN 104200464A
- Authority
- CN
- China
- Prior art keywords
- train
- depth information
- full car
- detected
- information
- 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
Landscapes
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses a train anomaly recognition detection method and system and belongs to the technical field of automatic image recognition. The recognition method includes the steps of collecting whole train depth information of a train to be detected and a reference train, matching a train model and a train number with the whole train depth information of the train to be detected and the reference train for recognizing faulty components, and matching depth information of the faulty components with that of reference parts for determining faulty parts. The recognition system comprises a collection module for collecting the whole train depth information of the train to be detected, a reference train information acquisition module and a faulty part detection module. A method of collecting three-dimensional image information of a running train with the depth information overcomes the visual function limitation of traditional two-dimensional image information so as to facilitate quick find of actual faulty points of a detection worker, reduce the false positive rate of the system and improve the maintenance efficiency of the detection worker.
Description
Technical field
The invention discloses a kind of abnormal detection method of train and system identified, belong to the technical field of image automatic identification.
Background technology
The common employing of the full car parts of traditional train abnormality detection manually detects, this mode detects when needing train to enter the station or putting in storage, because train (comprising the track train of lorry, passenger vehicle, motor train unit and other type) dwell time is shorter, add the numerous and complex structure of parts on train, maintainer is difficult to pay close attention in a short period of time the normal condition of each parts.Especially, between the parts at train bottom and top, existence is blocked and has vision dead zone, and this had both further increased the abnormal false dismissal probability of Train Parts, also further reduced abnormality detection efficiency and accuracy.
In addition, the train most of the time is in running status, track train in operational process because foreign material impact, relative motion, impact, vibrations etc. can cause the wearing and tearing of parts, the problem such as get loose extremely, after train enters the station or after completing operation milimeter number warehouse-in, just overhaul, this can cause train bottom parts to occur extremely can not being found in time and overhaul, and causes great potential safety hazard to the most at last the operation of track traffic.
Summary of the invention
Technical matters to be solved by this invention is the deficiency for above-mentioned background technology, and a kind of abnormal detection method of train and system identified is provided.
The present invention adopts following technical scheme for achieving the above object:
Identify the abnormal detection method of train, comprise the steps:
Gather full car depth information and the vehicle vehicle number information of train to be detected,
Vehicle vehicle number information coupling by described train to be detected obtains reference train, and obtains the full car depth information of described reference train, and,
The full car depth information of train to be detected is mated to detection failure part with the full car depth information of reference train;
Full car depth information described in above-mentioned steps is at least one in train bottom depth information, train sidepiece depth information and train top depth information.
As the further prioritization scheme of the abnormal detection method of described identification train, the full car depth information of reference train is:
The full car depth information of the normal train setting in advance,
At the full car depth information of same the train passing through with the current the most contiguous moment of sampling instant,
At many groups of full car depth informations of same the train passing through with the contiguous moment of current sampling instant, and
To above-mentioned full car depth information merge or statistical study after at least one in the full car depth information that obtains.
As the further prioritization scheme of the abnormal detection method of described identification train, the full car depth information of train to be detected is mated with the full car depth information of reference train, the step of detection failure part, specific as follows:
The full car depth information of train to be detected being mated with the full car depth information of reference train, from full car depth information, extract abnormal depth information, is faulty components by the corresponding module sets of abnormal depth information of extracting;
The depth information of faulty components is mated with the depth information with reference to part, from the depth information of faulty components, further extract abnormal depth information, be set as failed part by further extracting the corresponding part of abnormal depth information obtaining.
As the further prioritization scheme of the abnormal detection method of described identification train, be at least one in corresponding part in the corresponding part of reference train and default parts library with reference to part.
As the further prioritization scheme of the abnormal detection method of described identification train, the full car depth information of train to be detected is mated with the full car depth information of reference train, from full car depth information, extract abnormal depth information, in the step that is faulty components by the corresponding module sets of abnormal depth information of extracting, set as follows faulty components:
Extract the geometric element of described reference train different depth hierarchical data, the geometric element taking assembly as the each depth layer secondary data of unit matching, obtains the full car geometric properties standard profile hum pattern that contains depth information;
Extract the geometric element of described train different depth hierarchical data to be detected, the geometric element taking assembly as the each depth layer secondary data of unit matching, obtains the full car geometric properties distributed intelligence figure that contains depth information;
By mating of described rain model vehicle number information to be detected and described reference train vehicle vehicle number information, the full car geometric properties distributed intelligence figure of described train to be detected and the full car geometric properties standard profile hum pattern of described reference train are compared and mated;
The full car geometric properties standard profile hum pattern of the full car geometric properties distributed intelligence figure of described train to be detected and described reference train is faulty components by the corresponding module sets of unmatched depth information hum pattern after comparing.
As the further prioritization scheme of the abnormal detection method of described identification train, the depth information of faulty components is mated with the depth information with reference to part, from the depth information of faulty components, further extract abnormal depth information, be set as, in the step of failed part, setting as follows failed part by further extracting the corresponding part of abnormal depth information obtaining:
Extract the geometric element of described faulty components different depth hierarchical data, the geometric element taking part as the each depth layer secondary data of unit matching, obtains the faulty components geometric properties distributed intelligence figure that contains depth information;
Extract the geometric element of described reference train in different depth hierarchical data, taking described with reference to part the geometric element as the each depth layer secondary data of unit matching, obtain the reference component geometric properties standard profile hum pattern that matches with described faulty components and contain depth information;
Described faulty components geometric properties distributed intelligence figure and described reference component geometric properties standard profile hum pattern are set as failed part by the corresponding part of unmatched depth information hum pattern after comparing.
Further, the acquisition method of the full car depth information of train to be detected is at least one in laser triangulation, binocular telemetry and pulse ranging method.
Further, identification train abnormal detection method is also included in describedly mates the full car depth information of train to be detected with the full car depth information of reference train, after detection failure part step, to the step of failed part alarm indication.
Identify the abnormal detection system of train, comprising:
Acquisition module, for gathering the full car depth information of train to be detected and the vehicle vehicle number information of train to be detected;
Reference train acquisition of information module, obtains reference train by the vehicle vehicle number information coupling of described train to be detected, and obtains the full car depth information of described reference train; And,
Failed part detection module, mates the full car depth information of described train to be detected detection failure part with the full car depth information of described reference train.
Further, the abnormal detection system of above-mentioned identification train also comprises the alarm display module for failed part described in alarm indication.
The full car depth information of the some groups of trains to be detected that the present invention gathers by multi-angle, and obtain reference train by the vehicle vehicle number information coupling of described train to be detected, and obtain the full car depth information of described reference train, through mating of the full car depth information of train to be detected and the full car depth information of reference train, thereby detect failed part.This depth information that utilizes is to crossing the method for carrying out three-dimensional image information collection of car, can be real-time the vitals on the full car of track train and/or part are carried out to abnormality identification, thereby change traditional work pattern, greatly improved China Express Railway security of operation monitoring capability.In addition, the method that this three-dimensional image information gathers, can also overcome the restriction of conventional two-dimensional image information visual performance, can shield the warning of some non-trouble spots such as water stain dust, thereby facilitate testing staff to find fast actual fault point, reduce misreport of system rate, and improve testing staff's overhaul efficiency.
Brief description of the drawings
Fig. 1 is the process flow diagram of the abnormal detection method of the first identification train.
Fig. 2 is the process flow diagram of the abnormal detection method of the second identification train.
Embodiment
Below in conjunction with accompanying drawing, the technical scheme of invention is elaborated.
Process flow diagram of the present invention as shown in Figure 1.Here row are set forth the present invention for two example two.
Specific embodiment one:
Step 1, gather the full car depth information of train to be detected: to carrying out real-time detection by train speed, control system is according to the image acquisition of speed of a motor vehicle adjustment in real time pulse mode, in modularization binocular acquisition subsystem, embedded timing generator circuit is resolved acquisition pulse, and the collection sequential of each camera in module is carried out to timing synchronization, guarantee that three-dimensional data meets image co-registration specification on time and space.The acquisition method of the full car depth information of above-mentioned train to be detected can be pulse ranging method or laser triangulation, but is also not limited to said method.
Step 2, sets up vehicle license number index: obtain vehicle and the license number of each car by AEI car number identification system, for match reference train, obtain the full car depth information of reference train.
Wherein, the full car depth information of above-mentioned reference train can be the full car depth information of the normal train that sets in advance, such as the full car depth information of measuring in the time using first with a train; In addition, the full car depth information of reference train can also be the full car depth information at same the train passing through with the current the most contiguous moment of sampling instant, or at many groups of full car depth informations of same the train passing through with the contiguous moment of current sampling instant, or to above-mentioned full car depth information merge or statistical study after the full car depth information that obtains.
Step 3, the full car depth information of train to be detected is mated with the full car depth information of reference train, detection failure part: by the full car depth information of train to be detected is mated with the full car depth information of reference train, from full car depth information, extract abnormal depth information, part corresponding to abnormal depth information extracting is defined as to failed part.Wherein, above-mentioned can be the corresponding part of reference train with reference to part, can also be corresponding part in default parts library.
The travelling speed of mating in order to improve the full car depth information of train to be detected and the full car depth information of reference train, can also be refined as following steps by above-mentioned steps:
Steps A, the full car depth information of train to be detected is mated with the full car depth information of reference train, from full car depth information, extract abnormal depth information, assembly corresponding to abnormal depth information extracting be defined as to faulty components (being first order positioning parts result):
Steps A-1, by the pre-service such as cluster, denoising, extract the profile of reference train different depth hierarchical data, with geometric elements such as line, rectangles, geometric element taking assembly as the each depth layer secondary data of unit matching, obtains the full car geometric properties standard profile hum pattern that contains depth information;
Steps A-2, extract the geometric element of train different depth hierarchical data to be detected, and the geometric element taking assembly as the each depth layer secondary data of unit matching, obtains the full car geometric properties distributed intelligence figure that contains depth information;
Steps A-3, by mating of rain model vehicle number information to be detected and reference train vehicle vehicle number information, associate the full car geometric properties distributed intelligence figure that contains depth information with the full car geometric properties standard profile hum pattern that contains depth information;
Steps A-4, the full car geometric properties standard profile hum pattern that contains depth information that coupling is associated, the full car geometric properties distributed intelligence figure that contains depth information, be defined as faulty components by assembly corresponding to unmatched depth information hum pattern.
Step B, the depth information of faulty components is mated with the depth information with reference to part, from the depth information of faulty components, further extract abnormal depth information, be defined as failed part (being second level positioning parts result) by further extracting the corresponding part of abnormal depth information obtaining:
Step B-1, the geometric element of extraction faulty components different depth hierarchical data, taking part as unit matching
The geometric element of each depth layer secondary data, obtains the trouble unit geometric properties distributed intelligence figure that contains depth information;
Step B-2, extracts reference train at the geometric element of different depth hierarchical data, taking with reference to part as single
The geometric element of the each depth layer secondary data of position matching, obtains the reference component geometric properties standard profile hum pattern that matches with faulty components and contain depth information;
Step B-3, coupling faulty components geometric properties distributed intelligence figure, reference component geometric properties standard profile
Hum pattern, is defined as failed part by the corresponding part of unmatched depth information hum pattern.
Adopt geometric element matching mode to detect deep anomalies, can greatly reduce the operand of matching detection for multipart labyrinth imaging, also higher to the tolerance of acquisition noise; Because this coupling is relevant to vehicle number information, each information of vehicles only does and mates with the historical data of specific license number, has also reduced the interference that between vehicle, otherness causes simultaneously.
Specific embodiment two:
Step 1, the mode layout camera array of linear array, two sides battle array in the middle of adopting in train working direction, and by the full car three-dimensional image information of camera array Real-time Collection and middle linear array, two sides battle array information, when collection by the trigger rate of timesharing exposure technique control laser rays, thereby obtain some three-dimensional image information that multi-angle gathers, and from above-mentioned three-dimensional image information, extract the full car depth information of train to be detected.
Wherein, the acquisition method of the full car depth information of above-mentioned train to be detected can be but be not limited at least one in pulse ranging method, binocular telemetry and laser triangulation.
Step 2, sets up vehicle license number index, obtains reference train, and obtain the full car depth information of described reference train by the vehicle vehicle number information coupling of train to be detected.
Step 3, according to the method for step 3 in specific embodiment one mate the depth information of the train to be detected under each angle, the full car depth information of reference train obtains the recognition result of the failed part of each angle.
Step 4, merges the depth information that extracts faulty components after each angle trouble unit recognition result, then according to the refinement step classification location failed part of the method for step 4 in specific embodiment one.
On the basis of specific embodiment one, the present embodiment utilizes multi-angle depth information coupling to carry out the classification location of faulty components, failed part, can shield some non-trouble spots such as water stain dust, and can improve the degree of accuracy of failed part matching result, thereby facilitate testing staff to find fast actual fault point, reduce misreport of system rate, and improve testing staff's overhaul efficiency.In addition the three-dimensional image information that, above-mentioned multi-angle image extracts can effectively be improved depth information that single imaging obtains and can cover the defect of less depth information.
In specific embodiment one, specific embodiment two steps 4, the method for matching block depth information has: according to faulty components geometric properties distributed intelligence figure, the assembly geometric properties standard profile hum pattern of the association of vehicle license number index coupling vehicle license number, this has realized the coupling between particular data; Do not limit vehicle license number, coupling faulty components geometric properties distributed intelligence figure, the likely assembly geometric properties distributed intelligence figure of type of institute, to adapt to the needs of train assembly exchange.The present invention also comprises the step that faulty components, failed part are carried out to alarm indication, to feed back in time abnormal information to operating personnel.
In addition, the present invention has also disclosed the abnormal detection system of identification train of carrying the abnormal detection method of above-mentioned identification train, and this system mainly comprises: for gathering the acquisition module of the full car depth information of train to be detected and the vehicle vehicle number information of train to be detected; Vehicle vehicle number information coupling by train to be detected obtains reference train, and obtains the reference train acquisition of information module of the full car depth information of reference train; And, the full car depth information of train to be detected is mated to the failed part detection module of detection failure part with the full car depth information of reference train.In preferred version, said system also comprises the alarm display module for failed part described in alarm indication.
Claims (10)
1. identify the abnormal detection method of train, it is characterized in that, comprise the steps:
Gather full car depth information and the vehicle vehicle number information of train to be detected,
Vehicle vehicle number information coupling by described train to be detected obtains reference train, and obtains the full car depth information of described reference train, and,
The full car depth information of train to be detected is mated to detection failure part with the full car depth information of reference train;
Full car depth information described in above-mentioned steps is at least one in train bottom depth information, train sidepiece depth information and train top depth information.
2. identify according to claim 1 the abnormal detection method of train, it is characterized in that, the full car depth information of described reference train is:
The full car depth information of the normal train setting in advance,
At the full car depth information of same the train passing through with the current the most contiguous moment of sampling instant,
At many groups of full car depth informations of same the train passing through with the contiguous moment of current sampling instant, and
To above-mentioned full car depth information merge or statistical study after at least one in the full car depth information that obtains.
3. according to identifying the abnormal detection method of train described in claim 1 or 2, it is characterized in that, described the full car depth information of train to be detected is mated with the full car depth information of reference train, the step of detection failure part, specific as follows:
The full car depth information of train to be detected being mated with the full car depth information of reference train, from full car depth information, extract abnormal depth information, is faulty components by the corresponding module sets of abnormal depth information of extracting;
The depth information of faulty components is mated with the depth information with reference to part, from the depth information of faulty components, further extract abnormal depth information, be set as failed part by further extracting the corresponding part of abnormal depth information obtaining.
4. identify according to claim 3 the abnormal detection method of train, it is characterized in that, described is at least one in corresponding part in the corresponding part of reference train and default parts library with reference to part.
5. identify according to claim 3 the abnormal detection method of train, it is characterized in that, described the full car depth information of train to be detected is mated with the full car depth information of reference train, from full car depth information, extract abnormal depth information, in the step that is faulty components by the corresponding module sets of abnormal depth information of extracting, set as follows faulty components:
Extract the geometric element of described reference train different depth hierarchical data, the geometric element taking assembly as the each depth layer secondary data of unit matching, obtains the full car geometric properties standard profile hum pattern that contains depth information;
Extract the geometric element of described train different depth hierarchical data to be detected, the geometric element taking assembly as the each depth layer secondary data of unit matching, obtains the full car geometric properties distributed intelligence figure that contains depth information;
By mating of described rain model vehicle number information to be detected and described reference train vehicle vehicle number information, the full car geometric properties distributed intelligence figure of described train to be detected and the full car geometric properties standard profile hum pattern of described reference train are compared and mated;
The full car geometric properties standard profile hum pattern of the full car geometric properties distributed intelligence figure of described train to be detected and described reference train is faulty components by the corresponding module sets of unmatched depth information hum pattern after comparing.
6. identify according to claim 3 the abnormal detection method of train, it is characterized in that: described the depth information of faulty components is mated with the depth information with reference to part, from the depth information of faulty components, further extract abnormal depth information, be set as, in the step of failed part, setting as follows failed part by further extracting the corresponding part of abnormal depth information obtaining:
Extract the geometric element of described faulty components different depth hierarchical data, the geometric element taking part as the each depth layer secondary data of unit matching, obtains the faulty components geometric properties distributed intelligence figure that contains depth information;
Extract the geometric element of described reference train in different depth hierarchical data, taking described with reference to part the geometric element as the each depth layer secondary data of unit matching, obtain the reference component geometric properties standard profile hum pattern that matches with described faulty components and contain depth information;
Described faulty components geometric properties distributed intelligence figure and described reference component geometric properties standard profile hum pattern are set as failed part by the corresponding part of unmatched depth information hum pattern after comparing.
7. identify the abnormal detection method of train according to described in any one in claim 1,2,4,5 and 6, it is characterized in that, the acquisition method of the full car depth information of described train to be detected is at least one in laser triangulation, binocular telemetry and pulse ranging method.
8. according to identifying the abnormal detection method of train described in claim 1, it is characterized in that, described, the full car depth information of train to be detected is mated with the full car depth information of reference train, after detection failure part step, comprise the step to failed part alarm indication.
9. identify the abnormal detection system of train, it is characterized in that, comprising:
Acquisition module, for gathering the full car depth information of train to be detected and the vehicle vehicle number information of train to be detected;
Reference train acquisition of information module, obtains reference train by the vehicle vehicle number information coupling of described train to be detected, and obtains the full car depth information of described reference train; And,
Failed part detection module, mates the full car depth information of described train to be detected detection failure part with the full car depth information of described reference train.
10. the abnormal detection system of identification train according to claim 9, is characterized in that, also comprises the alarm display module for failed part described in alarm indication.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410406535.9A CN104200464B (en) | 2014-08-19 | 2014-08-19 | A kind of detection method and system for identifying that train is abnormal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410406535.9A CN104200464B (en) | 2014-08-19 | 2014-08-19 | A kind of detection method and system for identifying that train is abnormal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104200464A true CN104200464A (en) | 2014-12-10 |
| CN104200464B CN104200464B (en) | 2018-03-09 |
Family
ID=52085750
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410406535.9A Active CN104200464B (en) | 2014-08-19 | 2014-08-19 | A kind of detection method and system for identifying that train is abnormal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104200464B (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104567726A (en) * | 2014-12-17 | 2015-04-29 | 苏州华兴致远电子科技有限公司 | Vehicle operation fault detection system and method |
| CN104567725A (en) * | 2014-12-17 | 2015-04-29 | 苏州华兴致远电子科技有限公司 | Vehicle operation fault detection system and method |
| CN104809427A (en) * | 2014-12-31 | 2015-07-29 | 朱金良 | 3D information based fault automatic identification and detection system and detection method |
| CN105243381A (en) * | 2015-11-25 | 2016-01-13 | 朱金良 | Automatic fault recognition and detection system and method based on 3D information |
| WO2016095490A1 (en) * | 2014-12-17 | 2016-06-23 | 苏州华兴致远电子科技有限公司 | Vehicle operation fault detection system and method |
| CN106198559A (en) * | 2016-08-31 | 2016-12-07 | 成都铁安科技有限责任公司 | A kind of dynamic detection system of roof of train image |
| CN106468914A (en) * | 2015-08-21 | 2017-03-01 | 苏州华兴致远电子科技有限公司 | Train overhaul method and system |
| CN106557773A (en) * | 2015-09-25 | 2017-04-05 | 北汽福田汽车股份有限公司 | A kind of method and system of car fault diagnosis |
| CN106940884A (en) * | 2015-12-15 | 2017-07-11 | 北京康拓红外技术股份有限公司 | A kind of EMUs operation troubles image detecting system and method comprising depth information |
| CN107220609A (en) * | 2017-05-22 | 2017-09-29 | 哈尔滨市科佳通用机电股份有限公司 | A kind of motor-car failure automatic detection method |
| CN107697098A (en) * | 2017-09-29 | 2018-02-16 | 佘以道 | A kind of measuring method at compartment gradient scene |
| CN108711152A (en) * | 2018-05-23 | 2018-10-26 | 深圳市阡丘越科技有限公司 | A kind of image analysis method, device and user terminal based on AI technologies |
| CN110095061A (en) * | 2019-03-31 | 2019-08-06 | 唐山百川智能机器股份有限公司 | Vehicle morpheme detection system and method based on profile scan |
| CN110580748A (en) * | 2018-06-08 | 2019-12-17 | 苏交科集团股份有限公司 | Daily inspection and evaluation system and method for load-bearing support based on image processing |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102323070A (en) * | 2011-06-10 | 2012-01-18 | 北京华兴致远科技发展有限公司 | Method and system for detecting abnormality of train |
| CN103077526A (en) * | 2013-02-01 | 2013-05-01 | 苏州华兴致远电子科技有限公司 | Train abnormality detection method and system with deep detection function |
| CN202952978U (en) * | 2012-11-06 | 2013-05-29 | 苏州华兴致远电子科技有限公司 | Train part information collector |
| CN103512762A (en) * | 2012-06-29 | 2014-01-15 | 北京华兴致远科技发展有限公司 | Image processing method and device and train fault detection system |
| US20140056507A1 (en) * | 2012-08-27 | 2014-02-27 | Joseph D. Doyle | Methods and systems for inspecting a workpiece |
-
2014
- 2014-08-19 CN CN201410406535.9A patent/CN104200464B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102323070A (en) * | 2011-06-10 | 2012-01-18 | 北京华兴致远科技发展有限公司 | Method and system for detecting abnormality of train |
| CN103512762A (en) * | 2012-06-29 | 2014-01-15 | 北京华兴致远科技发展有限公司 | Image processing method and device and train fault detection system |
| US20140056507A1 (en) * | 2012-08-27 | 2014-02-27 | Joseph D. Doyle | Methods and systems for inspecting a workpiece |
| CN202952978U (en) * | 2012-11-06 | 2013-05-29 | 苏州华兴致远电子科技有限公司 | Train part information collector |
| CN103077526A (en) * | 2013-02-01 | 2013-05-01 | 苏州华兴致远电子科技有限公司 | Train abnormality detection method and system with deep detection function |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016095490A1 (en) * | 2014-12-17 | 2016-06-23 | 苏州华兴致远电子科技有限公司 | Vehicle operation fault detection system and method |
| CN104567725A (en) * | 2014-12-17 | 2015-04-29 | 苏州华兴致远电子科技有限公司 | Vehicle operation fault detection system and method |
| CN104567726A (en) * | 2014-12-17 | 2015-04-29 | 苏州华兴致远电子科技有限公司 | Vehicle operation fault detection system and method |
| CN104567726B (en) * | 2014-12-17 | 2017-12-08 | 苏州华兴致远电子科技有限公司 | Vehicle operation troubles detecting system and method |
| WO2016095328A1 (en) * | 2014-12-17 | 2016-06-23 | 苏州华兴致远电子科技有限公司 | Vehicle operation fault detection system and method |
| CN104809427B (en) * | 2014-12-31 | 2019-02-15 | 朱金良 | Failure automatic identification detection system and detection method based on 3D information |
| CN104809427A (en) * | 2014-12-31 | 2015-07-29 | 朱金良 | 3D information based fault automatic identification and detection system and detection method |
| CN106468914A (en) * | 2015-08-21 | 2017-03-01 | 苏州华兴致远电子科技有限公司 | Train overhaul method and system |
| CN106468914B (en) * | 2015-08-21 | 2023-04-28 | 苏州华兴致远电子科技有限公司 | Train maintenance method and system |
| CN106557773A (en) * | 2015-09-25 | 2017-04-05 | 北汽福田汽车股份有限公司 | A kind of method and system of car fault diagnosis |
| CN106557773B (en) * | 2015-09-25 | 2020-04-24 | 北京宝沃汽车有限公司 | Vehicle fault diagnosis method and system |
| CN105243381A (en) * | 2015-11-25 | 2016-01-13 | 朱金良 | Automatic fault recognition and detection system and method based on 3D information |
| CN105243381B (en) * | 2015-11-25 | 2019-04-19 | 朱金良 | Failure automatic identification detection system and method based on 3D information |
| CN106940884A (en) * | 2015-12-15 | 2017-07-11 | 北京康拓红外技术股份有限公司 | A kind of EMUs operation troubles image detecting system and method comprising depth information |
| CN106198559A (en) * | 2016-08-31 | 2016-12-07 | 成都铁安科技有限责任公司 | A kind of dynamic detection system of roof of train image |
| CN107220609A (en) * | 2017-05-22 | 2017-09-29 | 哈尔滨市科佳通用机电股份有限公司 | A kind of motor-car failure automatic detection method |
| CN107697098B (en) * | 2017-09-29 | 2018-08-03 | 金辉 | A kind of compartment gradient in-site measurement platform |
| CN107697098A (en) * | 2017-09-29 | 2018-02-16 | 佘以道 | A kind of measuring method at compartment gradient scene |
| CN108711152A (en) * | 2018-05-23 | 2018-10-26 | 深圳市阡丘越科技有限公司 | A kind of image analysis method, device and user terminal based on AI technologies |
| CN110580748A (en) * | 2018-06-08 | 2019-12-17 | 苏交科集团股份有限公司 | Daily inspection and evaluation system and method for load-bearing support based on image processing |
| CN110095061A (en) * | 2019-03-31 | 2019-08-06 | 唐山百川智能机器股份有限公司 | Vehicle morpheme detection system and method based on profile scan |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104200464B (en) | 2018-03-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104200464A (en) | Train anomaly recognition detection method and system | |
| CN110738846B (en) | Vehicle behavior monitoring system based on radar and video group and implementation method thereof | |
| CN102323070B (en) | Method and system for detecting abnormality of train | |
| CN108491758B (en) | Track detection method and robot | |
| CN103186982B (en) | Intelligent access system for public security | |
| CN103512762B (en) | Image processing method, device and train failure detection system | |
| CN105809679B (en) | Mountain railway side slope rockfall detection method based on visual analysis | |
| CN211731391U (en) | Intelligent online detection device for track surface defects | |
| CN105243381B (en) | Failure automatic identification detection system and method based on 3D information | |
| CN102854191B (en) | Real-time visual detection and identification method for high speed rail surface defect | |
| CN104809427B (en) | Failure automatic identification detection system and detection method based on 3D information | |
| CN102628814B (en) | Automatic detection method of steel rail light band abnormity based on digital image processing | |
| CN105241679B (en) | A kind of hidden fault detection method of EMUs | |
| CN103077526B (en) | There is train method for detecting abnormality and the system of depth detection function | |
| CN104567725A (en) | Vehicle operation fault detection system and method | |
| CN105067287A (en) | Motor train unit running fault dynamic image detecting system and method | |
| CN105426864A (en) | Multiple lane line detecting method based on isometric peripheral point matching | |
| CN104463235A (en) | Fault recognition method and device based on operation images of motor train unit | |
| CN204461369U (en) | Vehicle operating fault detection system | |
| CN202147697U (en) | High-speed online video detection device of maglev track routing inspection truck | |
| CN203246483U (en) | Intelligent detection system for moving state of locomotive walking part | |
| CN104243935A (en) | Target monitoring method for airport field monitoring system on basis of video recognition | |
| CN206074832U (en) | A kind of railcar roof pantograph foreign matter detection system | |
| CN104049281A (en) | Device and method for automatically detecting foreign matter between screen door of curve subway platform and train | |
| CN104316782A (en) | Pantograph monitoring method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |