CN115187048A - Method and system for identifying condition of foreign matter invasion event of multi-domain boundary of track line - Google Patents
Method and system for identifying condition of foreign matter invasion event of multi-domain boundary of track line Download PDFInfo
- Publication number
- CN115187048A CN115187048A CN202210795400.0A CN202210795400A CN115187048A CN 115187048 A CN115187048 A CN 115187048A CN 202210795400 A CN202210795400 A CN 202210795400A CN 115187048 A CN115187048 A CN 115187048A
- Authority
- CN
- China
- Prior art keywords
- data
- foreign matter
- domain
- event
- intrusion
- 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
- 230000009545 invasion Effects 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 60
- 238000001514 detection method Methods 0.000 claims abstract description 36
- 238000012544 monitoring process Methods 0.000 claims abstract description 21
- 230000008569 process Effects 0.000 claims abstract description 19
- 238000004458 analytical method Methods 0.000 claims abstract description 7
- 230000003068 static effect Effects 0.000 claims description 29
- 238000004364 calculation method Methods 0.000 claims description 23
- 230000033001 locomotion Effects 0.000 claims description 21
- 230000008859 change Effects 0.000 claims description 20
- 238000013139 quantization Methods 0.000 claims description 15
- 238000007781 pre-processing Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 13
- 238000007689 inspection Methods 0.000 claims description 12
- 230000006399 behavior Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 11
- 238000007405 data analysis Methods 0.000 claims description 10
- 238000011002 quantification Methods 0.000 claims description 9
- 230000002194 synthesizing effect Effects 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 6
- 238000012502 risk assessment Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 3
- 238000009432 framing Methods 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims 1
- 230000002265 prevention Effects 0.000 abstract description 6
- 206010070245 Foreign body Diseases 0.000 description 56
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 239000000463 material Substances 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L23/00—Control, warning or like safety means along the route or between vehicles or trains
- B61L23/04—Control, warning or like safety means along the route or between vehicles or trains for monitoring the mechanical state of the route
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Mechanical Engineering (AREA)
- Multimedia (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a rail line multi-domain limit foreign matter invasion event condition identification method and a rail line multi-domain limit foreign matter invasion event condition identification system, which belong to the technical field of railway disaster prevention risk early warning, and are characterized in that rail surface state acquisition sensor equipment is selected to acquire rail surface state data according to the monitoring requirement of the whole process of occurrence of a foreign matter invasion event; dividing a rail surface limit area into an attention area, an early warning area and a safety area, and identifying, tracking and extracting characteristics of the foreign matters invading the limit; defining a state description model of the violation event; and based on the state characteristics of the intrusion event, the identified intrusion foreign matter characteristic data is used as the quantitative risk value of the dynamic characteristic parameters of the intrusion event state description model, and the detection rates of the intrusion foreign matter event of the rail surface boundary security domain, the early warning domain and the attention domain are calculated. The invention realizes the monitoring, identification and analysis of the track line limit-invasion event characteristics and the event occurrence process, further improves the risk prevention and control capacity of the track traffic system, and has good application and popularization values.
Description
Technical Field
The invention relates to the technical field of railway disaster prevention risk early warning, in particular to a method and a system for identifying the condition of a foreign matter invasion event of a multi-domain boundary of a track line.
Background
The landform change difference along the railway is large, the geological condition is complex, and foreign matters invade the safety clearance (foreign matter invasion) of the railway, so that the accidents are frequent. The foreign matter intrusion event can cause line faults, train late points, even train derailment and other serious consequences.
The rail surface limit area is a contour line which is defined for protecting the rail line transportation safety and limits the foreign matters to be insurmountable. At present, aiming at the problem of foreign matter invasion of a track line, the prior art mainly adopts modes of double cable sensors, microwave monitoring sensors, fiber grating sensors or monitoring videos and the like in a rail surface limit area to mainly use an identification and alarm mode, namely, whether foreign matter invades the limit is detected, and if the foreign matter is found, the alarm is directly triggered, and then the foreign matter is intervened and processed manually.
In the prior art, in practical application, the detection mode is direct, the detection speed is high, the alarm effectiveness is low, but the defect that the characteristics of the intrusion object cannot be identified exists, and meanwhile, the dynamic change of the intrusion foreign matter is difficult to analyze due to the fact that the limited area is not finely divided, and the risk degree of the intrusion event of the foreign matter and the development situation of the intrusion event need to be judged by means of manual experience; on the other hand, the existing foreign matter intrusion detection method can only identify and alarm the first foreign matter intrusion in the limited area, and can only work again after manual processing and manual resetting, and cannot identify the occurrence of the second foreign matter intrusion, so that the identification and processing efficiency of the track line intrusion event is low.
Disclosure of Invention
The invention aims to provide a method and a system for identifying the condition of a railway line multi-domain limit foreign matter limit invasion event, which realize the monitoring, identification and analysis of the characteristics of the railway line multi-domain limit invasion event and the occurrence process of the event and improve the risk prevention and control capability of a railway traffic system, so as to solve at least one technical problem in the background technology.
In order to achieve the purpose, the invention adopts the following technical scheme:
in one aspect, the invention provides a method for identifying a condition of a railway line multi-domain boundary foreign object intrusion event, which comprises the following steps:
according to the monitoring requirement of the whole process of occurrence of a foreign matter invasion event, rail surface state acquisition sensor equipment is selected to acquire rail surface state data, the acquired data types and data formats are different, and data analysis, data preprocessing and data enhancement operations are performed according to the characteristics of the acquired original data;
acquiring sensor data types according to different rail surface states, analyzing different data characteristics of a limiting area, dividing the rail surface limiting area into an attention area, an early warning area and a safety area, and identifying, tracking and extracting characteristics of foreign matters invading the limiting area;
defining an infringement event state description model, taking the identified infringement foreign matter characteristics as dynamic characteristics of the infringement event state description model, and taking the track type and the track condition as static characteristics of the infringement event state description model;
based on the state characteristics of the intrusion event, the identified intrusion foreign matter feature data are used as dynamic feature parameter quantization risk values of the intrusion event state description model, the risk early warning grades under the attention grade, the early warning grade and the safety grade are provided according to the risk degree of the intrusion event occurring in the attention field, the early warning field and the safety field, and the detection rate of the intrusion foreign matter event in the rail surface boundary safety field, the early warning field and the attention field is calculated.
Preferably, when the rail surface state acquisition sensor equipment is arranged, data in the safety state of the monitored rail line is acquired and the rail surface limit area is acquired in response, and the rail surface limit area is divided into a safety domain, an early warning domain and an attention domain, wherein the safety domain is a rail contour dimension line, and the early warning domain and the attention domain are expanded outwards; identifying the foreign matters and the types thereof by using a neural network model; further, identifying and judging whether the foreign object is in a security domain, an early warning domain or an attention domain, if so, performing frame selection on the foreign object target, and further judging whether the foreign object target is tracked; otherwise, continuously acquiring the state data of the track line to be identified;
if the foreign object target is tracked, calculating, updating and acquiring size data, moving speed data, moving direction, time length data and position data of the limit as multi-level characteristics of the limit-invading foreign object; otherwise, adding the foreign object into the tracker, and acquiring the planar image of the track line to be identified again for identification;
and judging and carrying out data validity inspection on the foreign matter type data, the invasion limit foreign matter size data, the moving speed data, the moving direction, the invasion limit time length data and the located limit position data.
Preferably, the intrusion event state description model is composed of static features and dynamic features, wherein the static features include track types and environment risk types, and the dynamic features include foreign matter attributes and foreign matter motion behavior attributes. In the static characteristics, the track type describes the characteristics of the track line, and the geological environment type describes the scene where the track line is located; in the dynamic characteristics, the foreign matter attribute describes the self characteristics of the invasion limit foreign matter, and is specifically subdivided into the type of the foreign matter and the size of the foreign matter, wherein the size of the foreign matter is the plane surface area, the plane projection area and the volume in the multi-level characteristics of the foreign matter; the attribute of the foreign matter motion behavior describes dynamic change of a limit invasion event, which is specifically represented as the tendency of limit invasion foreign matters to invade different rail surface limit areas, such as change of foreign matter moving speed, foreign matter moving direction, change of limit invasion duration and change of occupied limit positions; the foreign matter moving direction describes that the invasion foreign matter moves towards a security domain or moves towards a direction outside a region of interest.
Preferably, the real-time risk assessment model based on the state of the infringement event comprises:
firstly, determining the weight of each parameter of the intrusion event state description model, determining the track type weight W of the track line by expert experience in the face of different track line foreign object intrusion detection requirements RT Geological environment type W ET Foreign object attribute weight W OA Foreign body motion attribute weight W OMA ；
Analyzing the orbit type risk quantification score RS of the static feature RT And a geologic environment type risk quantification score RS ET (ii) a Synthesizing a foreign matter attribute risk quantization score RS according to the real-time limit-invading foreign matter multi-level characteristics and according to the foreign matter type and the foreign matter size data OAs (ii) a Synthesizing a foreign matter motion attribute risk quantization score RS from the foreign matter moving speed, the invasion limit duration and the limit position data OMA (ii) a Defining a real-time risk value calculation model of the intrusion limit event as shown in the following formula, and obtaining a real-time risk value of the intrusion limit event by inputting index weights and risk quantitative scores of static characteristics and dynamic characteristics of an intrusion limit event state description model;
R＝W RT ×RS RT +W ET ×RS ET +W 0A ×RS OA +W OMA ×RS OMA 。
preferably, the detection rate of the intrusion foreign matter event of the rail surface boundary safety domain, the early warning domain and the attention domain is concentrated aiming at the intrusion event of the foreign matter within a period of time, and indicates how many intrusion events of the foreign matter in different boundary regions are detected correctly and early warned, and the calculation formula is defined as follows:
the detection rate of the attention level is the ratio of the number of detected events to all the occurred events in the infringement events occurring in the attention area, and the calculation method is that
The detection rate of the early warning level is the ratio of the number of detected events to all the occurred events in the threshold violation events occurring in the early warning domain, and the calculation mode is
The detection rate of the safety level is the ratio of the number of detected events to all the occurred events in the threshold-violating events occurring in the safety domain, and the calculation method is that
Preferably, the threshold-invading foreign object refinement feature analysis based on the track multi-domain live data comprises the following steps:
step S201: acquiring data of a monitored track line in a safe state, correspondingly dividing a rail surface limited area into a safety domain, an early warning domain and an attention domain, and acquiring data characteristics of the rail limited area, wherein the safety domain is a rail contour dimension line, and the early warning domain and the attention domain are expanded outwards;
step S202: inputting track line state data after data preprocessing and data enhancement;
step S203: identifying the type characteristics of the invasion limiting foreign matters by using models such as a neural network, a support vector machine and the like, and performing frame selection;
step S204: judging the area where the intrusion foreign matter is located, and starting to track the foreign matter target when the foreign matter is located in the attention area;
step S205: comparing and matching the type characteristics and the framing characteristics of the intrusion foreign bodies with the records of the target tracker, and judging whether the foreign body target is tracked or not; if the foreign object target has been tracked, go to step S207, otherwise go to step S206;
step S206: adding the foreign object into a target tracker for recording, and returning to the step S202 to obtain the next frame of data;
step S207: calculating and updating the size data of the intrusion foreign matter;
step S208: calculating and updating data of the moving direction of the intrusion foreign body;
step S209: calculating and updating foreign matter moving speed data;
step S210: calculating and updating foreign matter invasion duration data;
step S211: calculating and updating limit position data of the foreign matters;
step S212: judging whether the foreign matter type data, the invasion limit foreign matter size data, the moving speed data, the invasion limit time length data and the located limit position data are subjected to data validity inspection, and if the inspection is passed, entering a step S213, otherwise, entering a step S214;
step S213: the data is valid, and the multi-level characteristics of the limit-invading foreign matter are output;
step S214: and if the data is invalid, discarding the frame data.
In a second aspect, the present invention provides a system for identifying a condition of a rail road multi-domain boundary foreign object intrusion event, including:
the processing module is used for selecting the rail surface state acquisition sensor equipment to acquire rail surface state data according to the monitoring requirement of the whole process of occurrence of the foreign matter invasion event, the acquired data types and data formats are different, and data analysis, data preprocessing and data enhancement operations are performed according to the characteristics of the acquired original data;
the extraction module is used for collecting sensor data types according to different rail surface states, analyzing different data characteristics of a limiting area, dividing the rail surface limiting area into an attention area, an early warning area and a safety area, and identifying, tracking and extracting characteristics of foreign matters invading the limiting area;
the definition module is used for defining an infringement event state description model, taking the identified infringement foreign matter characteristics as dynamic characteristics of the infringement event state description model, and taking the track type and the track condition as static characteristics of the infringement event state description model;
and the calculation module is used for taking the identified characteristic data of the intrusion foreign matters as the dynamic characteristic parameter quantization risk value of the intrusion event state description model based on the state characteristics of the intrusion event, providing the attention level, the early warning level and the risk early warning level under the safety level according to the risk degree of the intrusion event occurring in the attention domain, the early warning domain and the safety domain, and calculating the detection rate of the intrusion foreign matters in the rail surface boundary safety domain, the early warning domain and the attention domain.
In a third aspect, the present invention provides a computer device comprising a memory and a processor, the processor and the memory being in communication with each other, the memory storing program instructions executable by the processor, the processor invoking the program instructions to perform the method for track-bound multi-domain bound foreign object violation event condition identification as described above.
In a fourth aspect, the present invention provides an electronic device comprising a memory and a processor, the processor and the memory being in communication with each other, the memory storing program instructions executable by the processor, the processor invoking the program instructions to perform the method for track-bound multi-domain bound foreign object violation event condition identification as described above.
In a fifth aspect, the present invention provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the method for identifying a track-line multi-domain boundary foreign-object intrusion event condition as described above.
The invention has the beneficial effects that: the method and the system realize monitoring, identification and analysis of the characteristics of the track line intrusion event and the occurrence process of the event, further improve the risk prevention and control capability of the track traffic system, and have good application and popularization values.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a method for identifying a condition of a railway line multi-domain boundary foreign body intrusion event and analyzing a risk according to an embodiment of the present invention.
Fig. 2 is a flowchart of a method for analyzing an infringement/alien material refinement feature based on track multi-domain live data according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are illustrative only and should not be construed as limiting the invention.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
For the purpose of facilitating an understanding of the present invention, the present invention will be further explained by way of specific embodiments with reference to the accompanying drawings, which are not intended to limit the present invention.
It should be understood by those skilled in the art that the drawings are merely schematic representations of embodiments and that the elements shown in the drawings are not necessarily required to practice the invention.
Example 1
This embodiment 1 provides a track line multi-domain boundary foreign object intrusion event condition identification system, which includes:
the processing module is used for selecting the rail surface state acquisition sensor equipment to acquire rail surface state data according to the monitoring requirement of the whole process of occurrence of the foreign matter invasion event, the acquired data types and the acquired data formats are different, and data analysis, data preprocessing and data enhancement operations are performed on the acquired original data characteristics;
the extraction module is used for acquiring sensor data types according to different rail surface states, analyzing different data characteristics of a limiting area, dividing the rail surface limiting area into an attention area, an early warning area and a safety area, and identifying, tracking and extracting characteristics of the foreign matters invading the limiting area;
the definition module is used for defining an infringement event state description model, taking the identified infringement foreign matter characteristics as dynamic characteristics of the infringement event state description model, and taking the track type and the track condition as static characteristics of the infringement event state description model;
and the calculation module is used for taking the identified characteristic data of the intrusion foreign matters as the dynamic characteristic parameter quantization risk value of the intrusion event state description model based on the state characteristics of the intrusion event, providing the attention level, the early warning level and the risk early warning level under the safety level according to the risk degree of the intrusion event occurring in the attention domain, the early warning domain and the safety domain, and calculating the detection rate of the intrusion foreign matters in the rail surface boundary safety domain, the early warning domain and the attention domain.
In this embodiment 1, with the above system, a method for identifying a condition of a multi-domain boundary foreign object intrusion event of a track line is implemented, including:
according to the monitoring requirement of the whole process of occurrence of a foreign matter invasion event, rail surface state acquisition sensor equipment is selected to acquire rail surface state data, the acquired data types and data formats are different, and data analysis, data preprocessing and data enhancement operations are performed on the acquired original data characteristics;
acquiring sensor data types according to different rail surface states, analyzing different data characteristics of a limiting area, dividing the rail surface limiting area into an attention area, an early warning area and a safety area, and identifying, tracking and extracting characteristics of foreign matters invading the limiting area;
defining an infringement event state description model, taking the identified infringement foreign matter characteristics as dynamic characteristics of the infringement event state description model, and taking the track type and the track condition as static characteristics of the infringement event state description model;
based on the state characteristics of the intrusion event, the identified intrusion foreign matter feature data are used as dynamic feature parameter quantization risk values of the intrusion event state description model, the risk early warning grades under the attention grade, the early warning grade and the safety grade are provided according to the risk degree of the intrusion event occurring in the attention field, the early warning field and the safety field, and the detection rate of the intrusion foreign matter event in the rail surface boundary safety field, the early warning field and the attention field is calculated.
When the rail surface state acquisition sensor equipment is arranged, acquiring data of a monitored rail line in a safe state, responding to the data to acquire a rail surface limiting area of the monitored rail line, and dividing the rail surface limiting area into a safety domain, an early warning domain and an attention domain, wherein the safety domain is a rail contour dimension line, and the early warning domain and the attention domain are expanded outwards; identifying the foreign matters and the types thereof by using a neural network model; further, identifying and judging whether the foreign object is in a security domain, an early warning domain or a concern domain, if so, performing frame selection on the foreign object target, and further judging whether the foreign object target is tracked; otherwise, continuously acquiring the state data of the track line to be identified;
if the foreign object target is tracked, calculating, updating and acquiring size data, moving speed data, moving direction, time length data and position data of the limit as multi-level characteristics of the limit-invading foreign object; otherwise, adding the foreign object into the tracker, and acquiring the planar image of the track line to be identified again for identification;
and judging and carrying out data validity inspection on the foreign matter type data, the limit-invading foreign matter size data, the moving speed data, the moving direction, the limit-invading time-length data and the limit position data.
The intrusion event state description model is composed of static characteristics and dynamic characteristics, wherein the static characteristics comprise track types and environment risk types, and the dynamic characteristics comprise foreign matter attributes and foreign matter motion behavior attributes. In the static characteristics, the track type describes the characteristics of the track line, and the geological environment type describes the scene where the track line is located; in the dynamic characteristics, the foreign matter attribute describes the self characteristics of the invasion limit foreign matter, and is specifically divided into a foreign matter type and a foreign matter size, wherein the foreign matter size is the plane surface area, the plane projection area and the volume in the foreign matter multi-level characteristics; the attribute of the foreign matter motion behavior describes dynamic change of a limit invasion event, which is specifically represented as the tendency of limit invasion foreign matters to invade different rail surface limit areas, such as change of foreign matter moving speed, foreign matter moving direction, change of limit invasion duration and change of occupied limit positions; the foreign matter moving direction describes that the invasion foreign matter moves to a security domain or moves to a direction outside the attention domain.
A real-time risk assessment model based on infringement event states, comprising:
firstly, determining the weight of each parameter of the intrusion event state description model, facing different track line foreign object intrusion detection requirements, and passing through an expertDetermining the track type weight W of the track line RT Geological environment type W ET Foreign object Attribute weight W OA Foreign object motion attribute weight W OMA ；
Analyzing the orbit type risk quantification score RS of the static feature RT And a geologic environment type risk quantification score RS ET (ii) a Synthesizing a foreign matter attribute risk quantization score RS according to the real-time limit-infringing foreign matter multi-level characteristics and according to the foreign matter type and foreign matter size data OAs (ii) a Synthesizing a foreign matter motion attribute risk quantization score RS from the foreign matter moving speed, the invasion limit duration and the limit position data OMA (ii) a Defining a real-time risk value calculation model of the intrusion limit event as shown in the following formula, and obtaining a real-time risk value of the intrusion limit event by inputting index weights and risk quantitative scores of static characteristics and dynamic characteristics of an intrusion limit event state description model;
R＝W RT ×RS RT +W ET ×RS ET +W 0A ×RS OA +W OMA ×RS OMA 。
according to the detection rate calculation method for the invasion limit foreign matter events of the rail surface limit safety domain, the early warning domain and the attention domain, the detection rate is concentrated aiming at the invasion limit events of the foreign matters within a period of time, and shows how many invasion limit events of the foreign matters in different limit regions are detected correctly and are early warned, and the calculation formula is defined as follows:
the detection rate of the attention level is the ratio of the number of detected events to all the occurred events in the invasion events occurring in the attention area, and the calculation method is that
The detection rate of the early warning level is the ratio of the number of detected events to all the occurred events in the threshold violation events occurring in the early warning domain, and the calculation mode is
The detection rate of the security level is the ratio of the number of detected events to all the occurring events in the threshold-violating events occurring in the security domain, and the calculation method is that
Based on the infringement foreign matter fine feature analysis of the track multi-domain live data, the method comprises the following steps:
step S201: acquiring data of a monitored track line in a safe state, correspondingly dividing a rail surface limited area into a safety domain, an early warning domain and an attention domain, and acquiring data characteristics of the rail limited area, wherein the safety domain is a rail contour dimension line, and the early warning domain and the attention domain are expanded outwards;
step S202: inputting track line state data after data preprocessing and data enhancement;
step S203: identifying the type characteristics of the invasion foreign matters by using models such as a neural network and a support vector machine, and performing frame selection;
step S204: judging the area where the intrusion foreign matter is located, and starting to track the foreign matter target when the foreign matter is located in the attention area;
step S205: comparing and matching the type characteristics and the framing characteristics of the intrusion foreign bodies with the records of the target tracker, and judging whether the foreign body target is tracked or not; if the foreign object target has been tracked, go to step S207, otherwise go to step S206;
step S206: adding the foreign object into a target tracker for recording, and returning to the step S202 to obtain the next frame of data;
step S207: calculating and updating size data of the intrusion foreign matters;
step S208: calculating and updating the data of the moving direction of the invasion limit foreign matter;
step S209: calculating and updating foreign body moving speed data;
step S210: calculating and updating foreign matter invasion duration data;
step S211: calculating and updating limit position data of the foreign matters;
step S212: judging whether the foreign matter type data, the invasion limit foreign matter size data, the moving speed data, the invasion limit time length data and the located limit position data are subjected to data validity inspection, and if the inspection is passed, entering a step S213, otherwise, entering a step S214;
step S213: the data is valid, and the multi-level characteristics of the limit-invading foreign matter are output;
step S214: and if the data is invalid, discarding the frame data.
Example 2
Referring to fig. 1, in this embodiment 2, a method for identifying a condition of a multi-domain boundary foreign object intrusion event and analyzing a risk is provided, where the method specifically includes:
step S101: the rail surface state acquisition sensor equipment is arranged in a key monitoring area of a rail line, and in order to meet the requirement of monitoring the whole process of the occurrence of the foreign matter invasion limit event, the rail surface state acquisition sensor equipment needs to have the functions of (1) distinguishing a rail limit area from sensing data and (2) acquiring plane or three-dimensional data of the invasion limit foreign matter. In practical application, any one of the rail surface state acquisition sensor devices can be selected to operate independently or be combined and matched for use according to the condition of the rail line scene and the monitoring requirement.
Step S102: different rail surface state acquisition sensor equipment types are different in acquired data types and data formats, data analysis, data preprocessing and data enhancement operations are carried out on the original data characteristics acquired by the rail surface state acquisition sensor equipment, and cutting, deblurring and defogging processing are carried out on the data of the image type; and carrying out segmentation, noise reduction and down-sampling processing on the point cloud type data. Further, the track line state data to be recognized is obtained, and the process proceeds to step S103.
Step S103: when the rail surface state acquisition sensor equipment is arranged, data in the safety state of the monitored rail line are acquired and the rail surface limit area is acquired in response, and the rail surface limit area is divided into a safety domain, an early warning domain and an attention domain, wherein the safety domain is a rail contour dimension line, and the early warning domain and the attention domain are outwards expanded.
Secondly, inputting the track line state data to be identified in the step S102, and identifying the foreign matters and the types thereof by using a neural network model; further, identifying and judging whether the foreign object is in the attention area, if so, performing frame selection on the foreign object target, and further judging whether the foreign object target is tracked; otherwise, the track line state data to be identified in step S102 is continuously acquired.
If the foreign object target is tracked, further calculating, updating and acquiring size data (plane surface area, plane projection area and volume), moving speed data, moving direction data, limit invasion time length data and located limit area data of the foreign object as the multi-level characteristics of the limit invasion foreign object; otherwise, adding the foreign object into the tracker, and acquiring the to-be-identified track line plane image of the step S102 again for identification.
And further, judging whether the foreign matter type data, the invasion limit foreign matter size data, the moving speed data, the invasion limit time length data and the located limit position data are subjected to data validity inspection, if the inspection is passed, entering a step S104, and if the inspection is not passed, judging that the data are invalid, and discarding the data.
Step S104: when the track line is invaded by foreign matters, the risk of the invasion event has certain relevance with the invasion foreign matters, the environment where the track is located and the track type. In order to quantitatively evaluate the intrusion risk degree, an intrusion event state description model is defined as follows, wherein the intrusion event state description model is composed of static features and dynamic features, the static features comprise track types and environment risk types, and the dynamic features comprise foreign body attributes and foreign body motion behavior attributes. In the static characteristics, the track type describes the characteristics of the track line, and the geological environment type describes the scene where the track line is located; in the dynamic characteristics, the foreign matter attribute describes the self characteristics of the invasion limit foreign matter, and is specifically subdivided into the type of the foreign matter and the size of the foreign matter, wherein the size of the foreign matter is the plane surface area, the plane projection area and the volume in the multi-level characteristics of the foreign matter; the foreign matter motion behavior attribute describes dynamic change of the intrusion event, and is specifically represented as the tendency of intrusion of the intrusion foreign matter into different rail surface boundary areas, such as change of moving speed of the foreign matter, change of moving direction of the foreign matter, change of intrusion time length and change of occupied boundary positions. The foreign matter moving direction describes that the invasion foreign matter moves towards a security domain or moves towards a direction outside a region of interest. The model parameters are described for the infringement event states as shown in table 1.
TABLE 1
Step S105: establishing a real-time risk assessment model based on an infringement event state, firstly determining the weight of each parameter of the infringement event state description model, facing different track line foreign object infringement detection requirements, and determining the track type weight W of the track line through expert experience RT Geological environment type W ET Foreign object attribute weight W OA Foreign object motion attribute weight W OMA 。
Secondly, analyzing the orbit type risk quantification fraction RS of the static characteristics RT And a geologic environment type risk quantification score RS ET 。
Further, synthesizing a foreign matter attribute risk quantization score RS according to the real-time limit-invading foreign matter multi-level characteristics output by the steps S103, S104 and S105 and according to the foreign matter type and the foreign matter size data OAs (ii) a Synthesizing a foreign matter motion attribute risk quantization score RS from the foreign matter moving speed, the invasion limit time and the limit position data OMA . The process advances to step S106.
The probability that the limit-invading foreign bodies cause rail traffic accidents in different rail surface limit areas is different, when the corresponding limit-invading foreign bodies are in different rail surface limit areas, the state of the limit-invading event pays attention to different limit-invading foreign body characteristic parameters, when the limit-invading foreign bodies are in the attention area, the risk grade is the attention grade, the movement behavior attribute of the foreign bodies mainly evaluates the change of the movement speed and the movement direction of the foreign bodies, and the two parameters describe whether the risk of the limit-invading event has the possibility of improvement or not; when the limit-invading foreign matter enters the early warning domain, the risk level belongs to the early warning level, all the foreign matter motion behavior attributes are mainly evaluated, and whether the risk of the limit-invading event is possible to be further improved or not is evaluated; when the limit-invading foreign matter enters the safety domain, the risk level belongs to the safety level, all the foreign matter motion behavior attributes are mainly referred to, and the influence of the limit-invading event on the railway safety operation is evaluated.
Step S106: the real-time risk value calculation model of the intrusion limit event is defined as shown in a formula 1, and the real-time risk value of the intrusion limit event is obtained by inputting index weights and risk quantitative scores of static characteristics and dynamic characteristics of an intrusion limit event state description model.
R＝W RT ×RS RT +W ET ×RS ET +W OA xRS OA +W OMA ×RS OMA
TABLE 2 Limit event Risk values and corresponding Risk ratings
Further, the real-time risk value of the intrusion event is subjected to normalization processing, the early warning interval where the real-time risk value of the intrusion event is located is analyzed according to the table 2, and the track intrusion risk level is determined.
Step S107: and verifying the detection rates of the invasion foreign matter events of the rail surface boundary security domain, the early warning domain and the attention domain. The method adopts the detection rate to evaluate the early warning precision of the intrusion events, and the detection rate is concentrated aiming at the intrusion events of the foreign objects in a period of time, and shows how many intrusion events of the foreign objects in different boundary areas are detected correctly and early warned. The detection rate of the attention level is the ratio of the number of detected events to all the occurred events in the invasion events occurring in the attention area, and the calculation method is that
The detection rate of the early warning level is the ratio of the number of detected events to all the occurred events in the threshold violation events occurring in the early warning domain, and the calculation mode is
The detection rate of the safety level is the ratio of the number of detected events to all the occurred events in the threshold-violating events occurring in the safety domain, and the calculation method is that
Referring to fig. 2, the method for analyzing the infringement foreign object fine feature based on the track multi-domain live data specifically includes the following steps:
step S201: the method comprises the steps of obtaining data of a monitored track line in a safe state, correspondingly dividing a track surface limiting area into a safety domain, an early warning domain and an attention domain, and obtaining data characteristics of the track limiting area, wherein the safety domain is a track outline dimension line, and the early warning domain and the attention domain are expanded outwards. (ii) a
Step S202: inputting track line state data after data preprocessing and data enhancement;
step S203: identifying the type characteristics of the invasion limiting foreign matters by using models such as a neural network, a support vector machine and the like, and performing frame selection;
step S204: judging the area where the intrusion foreign matter is located, and starting to track the foreign matter target when the foreign matter is located in the attention area;
step S205: comparing and matching the type characteristics and the frame selection characteristics of the intrusion foreign matters with the record of the target tracker, and further judging whether the foreign matter target is tracked; if the foreign object target has been tracked, go to step S207, otherwise go to step S206;
step S206: adding the foreign object into a target tracker for recording, and returning to the step S202 to obtain the next frame of data;
step S207: calculating and updating size data (plane surface area, plane projection area and volume) of the invasion limiting foreign matter;
step S208: calculating and updating the data of the moving direction of the invasion limit foreign matter
Step S209: calculating and updating foreign body moving speed data;
step S210: calculating and updating the foreign matter invasion limit duration data;
step S211: calculating and updating limit position data of the foreign body;
step S212: further, judging whether the data of the foreign matter type, the data of the size of the invasion limit foreign matter, the data of the moving speed, the data of the invasion limit time and the data of the limit position are subjected to data validity check, and if the data pass the check, entering a step S213, otherwise, entering a step S214;
step S213: the data is valid, and the multi-level characteristics of the limit-invading foreign matter are output;
step S214: and if the data is invalid, discarding the frame data.
Example 3
An embodiment 3 of the present invention provides an electronic device, including a memory and a processor, where the processor and the memory are in communication with each other, the memory stores a program instruction executable by the processor, and the processor invokes the program instruction to execute a method for identifying a condition of a rail circuit multi-domain bound foreign object intrusion event, where the method includes the following steps:
according to the monitoring requirement of the whole process of occurrence of a foreign matter invasion event, rail surface state acquisition sensor equipment is selected to acquire rail surface state data, the acquired data types and data formats are different, and data analysis, data preprocessing and data enhancement operations are performed according to the characteristics of the acquired original data;
acquiring sensor data types according to different rail surface states, analyzing different data characteristics of a limiting area, dividing the rail surface limiting area into an attention area, an early warning area and a safety area, and identifying, tracking and extracting characteristics of foreign matters invading the limiting area;
defining an infringement event state description model, taking the identified infringement foreign matter characteristics as dynamic characteristics of the infringement event state description model, and taking the track type and the track condition as static characteristics of the infringement event state description model;
based on the state characteristics of the intrusion event, the identified intrusion foreign matter feature data are used as dynamic feature parameter quantization risk values of the intrusion event state description model, the risk early warning grades under the attention grade, the early warning grade and the safety grade are provided according to the risk degree of the intrusion event occurring in the attention field, the early warning field and the safety field, and the detection rate of the intrusion foreign matter event in the rail surface boundary safety field, the early warning field and the attention field is calculated.
Example 4
An embodiment 4 of the present invention provides a computer-readable storage medium, in which a computer program is stored, where the computer program, when executed by a processor, implements a method for identifying a condition of a track route multi-domain boundary foreign object intrusion event, where the method includes the following steps:
according to the monitoring requirement of the whole process of occurrence of a foreign matter invasion event, rail surface state acquisition sensor equipment is selected to acquire rail surface state data, the acquired data types and data formats are different, and data analysis, data preprocessing and data enhancement operations are performed on the acquired original data characteristics;
acquiring sensor data types according to different rail surface states, analyzing different data characteristics of a limiting area, dividing the rail surface limiting area into an attention area, an early warning area and a safety area, and identifying, tracking and extracting characteristics of foreign matters invading the limiting area;
defining an infringement event state description model, taking the identified infringement foreign matter characteristics as dynamic characteristics of the infringement event state description model, and taking the track type and the track condition as static characteristics of the infringement event state description model;
based on the state characteristics of the intrusion event, the identified intrusion foreign matter feature data are used as dynamic feature parameter quantization risk values of the intrusion event state description model, the risk early warning grades under the attention grade, the early warning grade and the safety grade are provided according to the risk degree of the intrusion event occurring in the attention field, the early warning field and the safety field, and the detection rate of the intrusion foreign matter event in the rail surface boundary safety field, the early warning field and the attention field is calculated.
Example 5
Embodiment 5 of the present invention provides a computer device, including a memory and a processor, where the processor and the memory are in communication with each other, the memory stores a program instruction executable by the processor, and the processor invokes the program instruction to execute a method for identifying a condition of a track-bound multi-domain boundary foreign object intrusion event, where the method includes:
according to the monitoring requirement of the whole process of occurrence of a foreign matter invasion event, rail surface state acquisition sensor equipment is selected to acquire rail surface state data, the acquired data types and data formats are different, and data analysis, data preprocessing and data enhancement operations are performed according to the characteristics of the acquired original data;
acquiring sensor data types according to different rail surface states, analyzing different data characteristics of a limiting area, dividing the rail surface limiting area into an attention area, an early warning area and a safety area, and identifying, tracking and extracting characteristics of foreign matters invading the limiting area;
defining an infringement event state description model, taking the identified infringement foreign matter characteristics as dynamic characteristics of the infringement event state description model, and taking the track type and the track condition as static characteristics of the infringement event state description model;
based on the state characteristics of the intrusion event, the identified intrusion foreign matter feature data are used as dynamic feature parameter quantization risk values of the intrusion event state description model, the risk early warning grades under the attention grade, the early warning grade and the safety grade are provided according to the risk degree of the intrusion event occurring in the attention field, the early warning field and the safety field, and the detection rate of the intrusion foreign matter event in the rail surface boundary safety field, the early warning field and the attention field is calculated.
In summary, the method for identifying the condition of the track circuit multi-domain boundary foreign object intrusion event and analyzing the risk in the embodiment of the present invention. Aiming at key problems that the existing track foreign matter invasion monitoring mode causes low invasion event processing efficiency, lacks of invasion foreign matter feature identification and effective monitoring of invasion event occurrence process and the like, a track foreign matter invasion event condition identification and risk analysis method is designed, and a multilayer characteristic and an identification method of invasion event state based on a track boundary area attention area, an early warning area and a safety area are provided for different track surface state acquisition sensor properties and data characteristics, and risk assessment is carried out based on invasion event state, so that accurate risk early warning of invasion events is realized. Firstly, acquiring real-time rail surface state data through rail surface state acquisition sensor equipment; secondly, respectively carrying out data enhancement pretreatment and identifying refined characteristics of the type, size, invasion limit duration, moving speed, moving direction and invasion limit position of the foreign matters according to the data types of the different rail surface state acquisition sensors; constructing an intrusion limit event state description model based on the intrusion limit foreign matter fine feature and the requirement of track line safety, and realizing the depiction of the occurrence situation and key information of the intrusion limit event; and finally, constructing a track foreign matter intrusion event risk evaluation model for the intrusion event characteristics, acquiring the risk value of the intrusion event, and providing a risk early warning classification method under the attention level, the early warning level and the safety level according to the risk degree of the intrusion event. The method and the system realize monitoring, identification and analysis of the characteristics of the track line intrusion event and the occurrence process of the event, further improve the risk prevention and control capability of the track traffic system, and have good application and popularization values.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts based on the technical solutions disclosed in the present invention.
Claims (10)
1. A rail line multi-domain boundary foreign matter invasion event condition identification method is characterized by comprising the following steps:
according to the monitoring requirement of the whole process of occurrence of a foreign matter invasion event, rail surface state acquisition sensor equipment is selected to acquire rail surface state data, the acquired data types and data formats are different, and data analysis, data preprocessing and data enhancement operations are performed according to the characteristics of the acquired original data;
acquiring sensor data types according to different rail surface states, analyzing different data characteristics of a limiting area, dividing the rail surface limiting area into an attention area, an early warning area and a safety area, and identifying, tracking and extracting characteristics of foreign matters invading the limiting area;
defining an infringement event state description model, taking the identified infringement foreign matter characteristics as dynamic characteristics of the infringement event state description model, and taking the track type and the track condition as static characteristics of the infringement event state description model;
based on the state characteristics of the intrusion event, the identified feature data of the intrusion foreign matters are used as dynamic feature parameter quantitative risk values of the state description model of the intrusion event, risk early warning grades under the attention grade, the early warning grade and the safety grade are provided according to the risk degree of the intrusion event occurring in the attention field, the early warning field and the safety field, and the detection rates of the intrusion foreign matters in the safety field, the early warning field and the attention field of the rail surface boundary are calculated.
2. The method for identifying the condition of the railway line multi-domain boundary foreign matter intrusion event according to claim 1, wherein when a railway surface state acquisition sensor device is arranged, data in a monitored railway line safety state are acquired, a railway surface boundary region is acquired in response, the railway surface boundary region is divided into a safety domain, an early warning domain and an attention domain, wherein the safety domain is a railway rail contour dimension line, and the early warning domain and the attention domain are expanded outwards; identifying the foreign matters and the types thereof by using a neural network model; further, identifying and judging whether the foreign object is in a security domain, an early warning domain or an attention domain, if so, performing frame selection on the foreign object target, and further judging whether the foreign object target is tracked; otherwise, continuously acquiring the state data of the track line to be identified;
if the foreign object target is tracked, calculating, updating and acquiring size data, moving speed data, moving direction, time length data and position data of the limit as multi-level characteristics of the limit-invading foreign object; otherwise, adding the foreign object into the tracker, and acquiring the planar image of the track line to be identified again for identification;
and judging and carrying out data validity inspection on the foreign matter type data, the limit-invading foreign matter size data, the moving speed data, the moving direction, the limit-invading time-length data and the limit position data.
3. The method of claim 1, wherein the state description model of the confinement event comprises static features and dynamic features, wherein the static features include track type and environmental risk type, and the dynamic features include foreign object property and foreign object motion behavior property. In the static characteristics, the track type describes the characteristics of the track line, and the geological environment type describes the scene where the track line is located; in the dynamic characteristics, the foreign matter attribute describes the self characteristics of the invasion limit foreign matter, and is specifically divided into a foreign matter type and a foreign matter size, wherein the foreign matter size is the plane surface area, the plane projection area and the volume in the foreign matter multi-level characteristics; the attribute of the foreign matter motion behavior describes dynamic change of a limit invasion event, which is specifically represented as the tendency of limit invasion foreign matters to invade different rail surface limit areas, such as change of foreign matter moving speed, foreign matter moving direction, change of limit invasion duration and change of occupied limit positions; the foreign matter moving direction describes that the invasion foreign matter moves towards a security domain or moves towards a direction outside a region of interest.
4. The method for identifying the status of the railway line multi-domain boundary foreign object intrusion event according to claim 1, wherein the real-time risk assessment model based on the state of the intrusion event comprises:
firstly, determining the weight of each parameter of the intrusion event state description model, determining the track type weight W of the track line by expert experience in the face of different track line foreign object intrusion detection requirements RT Geological environment type W ET Foreign object attribute weight W OA Foreign object motion attribute weight W OMA ；
Analyzing the orbit type risk quantification score RS of the static feature RT And a geologic environment type risk quantification score RS ET (ii) a According to real-time invasion limit foreign matter multilayerClass characteristics, synthesizing a foreign object attribute risk quantification score RS from the foreign object type and foreign object size data OAs (ii) a Synthesizing a foreign matter motion attribute risk quantization score RS from the foreign matter moving speed, the invasion limit time and the limit position data OMA (ii) a Defining a real-time risk value calculation model of the intrusion limit event as shown in the following formula, and obtaining a real-time risk value of the intrusion limit event by inputting index weights and risk quantitative scores of static characteristics and dynamic characteristics of an intrusion limit event state description model;
R＝W RT ×RS RT +W ET ×RS ET +W OA ×RS OA +W OMA ×RS OMA 。
5. the method for identifying the condition of the railway line multi-domain boundary foreign matter intrusion events according to claim 1, wherein the detection rate of the intrusion foreign matter events of the railway surface boundary security domain, the early warning domain and the attention domain is concentrated aiming at the occurrence of the foreign matter intrusion events in a period of time, and shows how many foreign matter intrusion events in different boundary regions are detected correctly and early warned, and the calculation formula is defined as follows:
the detection rate of the attention level is the ratio of the number of detected events to all the occurred events in the infringement events occurring in the attention area, and the calculation method is that
The detection rate of the early warning level is the ratio of the number of detected events to all the occurred events in the threshold violation events occurring in the early warning domain, and the calculation mode is
The detection rate of the security level is the ratio of the number of detected events to all the occurring events in the threshold-violating events occurring in the security domain, and the calculation method is that
6. The method for identifying the status of the track line multi-domain boundary foreign object intrusion event according to claim 1, wherein the characteristic analysis based on the intrusion foreign object refinement of the track multi-domain live data comprises:
step S201: acquiring data of a monitored track line in a safe state, correspondingly dividing a rail surface limited area into a safety domain, an early warning domain and an attention domain, and acquiring data characteristics of the rail limited area, wherein the safety domain is a rail contour dimension line, and the early warning domain and the attention domain are expanded outwards;
step S202: inputting track line state data after data preprocessing and data enhancement;
step S203: identifying the type characteristics of the invasion limiting foreign matters by using models such as a neural network, a support vector machine and the like, and performing frame selection;
step S204: judging the area where the intrusion foreign matter is located, and starting to track the foreign matter target when the foreign matter is located in the attention area;
step S205: comparing and matching the type characteristics and the framing characteristics of the intrusion foreign bodies with the records of the target tracker, and judging whether the foreign body target is tracked or not; if the foreign object target has been tracked, go to step S207, otherwise go to step S206;
step S206: adding the foreign object into a target tracker for recording, and returning to the step S202 to obtain next frame data;
step S207: calculating and updating size data of the intrusion foreign matters;
step S208: calculating and updating the data of the moving direction of the invasion limit foreign matter;
step S209: calculating and updating foreign body moving speed data;
step S210: calculating and updating foreign matter invasion duration data;
step S211: calculating and updating limit position data of the foreign matters;
step S212: judging whether the foreign matter type data, the limit-invading foreign matter size data, the moving speed data, the limit-invading time-length data and the limit position data are subjected to data validity inspection, if the data pass the inspection, entering a step S213, and if not, entering a step S214;
step S213: the data is valid, and the multi-level characteristics of the limit-invading foreign matter are output;
step S214: and if the data is invalid, discarding the frame data.
7. A rail line multi-domain boundary foreign body intrusion event condition identification system, comprising:
the processing module is used for selecting the rail surface state acquisition sensor equipment to acquire rail surface state data according to the monitoring requirement of the whole process of occurrence of the foreign matter invasion event, the acquired data types and data formats are different, and data analysis, data preprocessing and data enhancement operations are performed according to the characteristics of the acquired original data;
the extraction module is used for collecting sensor data types according to different rail surface states, analyzing different data characteristics of a limiting area, dividing the rail surface limiting area into an attention area, an early warning area and a safety area, and identifying, tracking and extracting characteristics of foreign matters invading the limiting area;
the definition module is used for defining an infringement event state description model, taking the identified infringement foreign matter characteristics as dynamic characteristics of the infringement event state description model, and taking the track type and the track condition as static characteristics of the infringement event state description model;
and the calculation module is used for taking the identified characteristic data of the intrusion foreign matters as the dynamic characteristic parameter quantization risk value of the intrusion event state description model based on the state characteristics of the intrusion event, providing the attention level, the early warning level and the risk early warning level under the safety level according to the risk degree of the intrusion event occurring in the attention domain, the early warning domain and the safety domain, and calculating the detection rate of the intrusion foreign matters in the rail surface boundary safety domain, the early warning domain and the attention domain.
8. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out a method according to any one of claims 1 to 6 for identifying a railway line multi-zone boundary foreign body violation event situation.
9. A computer device comprising a memory and a processor, the processor and the memory in communication with each other, the memory storing program instructions executable by the processor, the processor invoking the program instructions to perform the method of any of claims 1-6.
10. An electronic device comprising a memory and a processor, the processor and the memory being in communication with each other, the memory storing program instructions executable by the processor, the processor invoking the program instructions to perform the method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210795400.0A CN115187048B (en) | 2022-07-07 | 2022-07-07 | Rail line multi-domain limit foreign matter intrusion event condition identification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210795400.0A CN115187048B (en) | 2022-07-07 | 2022-07-07 | Rail line multi-domain limit foreign matter intrusion event condition identification method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115187048A true CN115187048A (en) | 2022-10-14 |
| CN115187048B CN115187048B (en) | 2023-05-23 |
Family
ID=83516747
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210795400.0A Active CN115187048B (en) | 2022-07-07 | 2022-07-07 | Rail line multi-domain limit foreign matter intrusion event condition identification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115187048B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116834802A (en) * | 2023-07-03 | 2023-10-03 | 湖北空间智能技术有限公司 | Method, equipment and storage medium for detecting and positioning invaded objects in operation train track |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013121344A2 (en) * | 2012-02-17 | 2013-08-22 | Balaji Venkatraman | Real time railway disaster vulnerability assessment and rescue guidance system using multi-layered video computational analytics |
| CN104787084A (en) * | 2015-04-16 | 2015-07-22 | 北京交通大学 | Railway foreign matter clearance intrusion detection system and method |
| CN107097810A (en) * | 2017-04-30 | 2017-08-29 | 中南大学 | A kind of Along Railway foreign body intrusion UAV Intelligent identification and method for early warning and system |
| CN108995675A (en) * | 2018-06-28 | 2018-12-14 | 上海工程技术大学 | A kind of rail transportation operation risk intelligent recognition early warning system and method |
| CN112776856A (en) * | 2021-01-15 | 2021-05-11 | 中国神华能源股份有限公司神朔铁路分公司 | Track foreign matter intrusion monitoring method, device and system and monitoring host equipment |
| CN113903009A (en) * | 2021-12-10 | 2022-01-07 | 华东交通大学 | Railway foreign matter detection method and system based on improved YOLOv3 network |
| CN114419616A (en) * | 2022-01-19 | 2022-04-29 | 北京全路通信信号研究设计院集团有限公司 | Foreign matter identification method, device, equipment and storage medium |
| CN114529880A (en) * | 2020-11-09 | 2022-05-24 | 中南大学 | Urban rail foreign matter intrusion detection method, device and system and storage medium |
-
2022
- 2022-07-07 CN CN202210795400.0A patent/CN115187048B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013121344A2 (en) * | 2012-02-17 | 2013-08-22 | Balaji Venkatraman | Real time railway disaster vulnerability assessment and rescue guidance system using multi-layered video computational analytics |
| CN104787084A (en) * | 2015-04-16 | 2015-07-22 | 北京交通大学 | Railway foreign matter clearance intrusion detection system and method |
| CN107097810A (en) * | 2017-04-30 | 2017-08-29 | 中南大学 | A kind of Along Railway foreign body intrusion UAV Intelligent identification and method for early warning and system |
| CN108995675A (en) * | 2018-06-28 | 2018-12-14 | 上海工程技术大学 | A kind of rail transportation operation risk intelligent recognition early warning system and method |
| CN114529880A (en) * | 2020-11-09 | 2022-05-24 | 中南大学 | Urban rail foreign matter intrusion detection method, device and system and storage medium |
| CN112776856A (en) * | 2021-01-15 | 2021-05-11 | 中国神华能源股份有限公司神朔铁路分公司 | Track foreign matter intrusion monitoring method, device and system and monitoring host equipment |
| CN113903009A (en) * | 2021-12-10 | 2022-01-07 | 华东交通大学 | Railway foreign matter detection method and system based on improved YOLOv3 network |
| CN114419616A (en) * | 2022-01-19 | 2022-04-29 | 北京全路通信信号研究设计院集团有限公司 | Foreign matter identification method, device, equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116834802A (en) * | 2023-07-03 | 2023-10-03 | 湖北空间智能技术有限公司 | Method, equipment and storage medium for detecting and positioning invaded objects in operation train track |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115187048B (en) | 2023-05-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | A Vision‐Based Video Crash Detection Framework for Mixed Traffic Flow Environment Considering Low‐Visibility Condition | |
| CN101286239A (en) | Aerial shooting traffic video frequency vehicle rapid checking method | |
| Bello-Salau et al. | A new measure for analysing accelerometer data towards developing efficient road defect profiling systems | |
| Ki et al. | A traffic accident detection model using metadata registry | |
| Wong et al. | Developing advanced traffic violation detection system with RFID technology for smart city | |
| CN117152156B (en) | Railway anomaly detection method and system based on multi-mode data fusion | |
| Ou et al. | A data‐driven approach to determining freeway incident impact areas with fuzzy and graph theory‐based clustering | |
| KR20220146670A (en) | Traffic anomaly detection methods, devices, devices, storage media and programs | |
| CN113496213A (en) | Method, device and system for determining target perception data and storage medium | |
| Yaghoobi Ershadi et al. | Vehicle tracking and counting system in dusty weather with vibrating camera conditions | |
| CN115187048A (en) | Method and system for identifying condition of foreign matter invasion event of multi-domain boundary of track line | |
| Ki | Accident detection system using image processing and MDR | |
| Chern et al. | Impact of loss functions on semantic segmentation in far‐field monitoring | |
| Namazi et al. | Geolocation estimation of target vehicles using image processing and geometric computation | |
| Javadzadeh et al. | Fast vehicle detection and counting using background subtraction technique and prewitt edge detection | |
| CN117557961A (en) | Public safety management method and system based on big data intelligent analysis | |
| Kumar et al. | The Real Time Vehicle License Plate Identification System | |
| Changalasetty et al. | Identification and classification of moving vehicles on road | |
| Lucas et al. | Online travel time estimation without vehicle identification | |
| Khalid et al. | An Android Application for Unwanted Vehicle Detection and Counting | |
| Thallinger et al. | Near-miss accidents–classification and automatic detection | |
| CN112633163A (en) | Detection method for realizing illegal operation vehicle detection based on machine learning algorithm | |
| CN113012430A (en) | Vehicle queuing length detection method, device, equipment and readable storage medium | |
| Khalaf Hussein et al. | Towards Safer Roads: An Automated Traffic Control System with Enhanced Vehicle Speed Detection and Measurement Algorithm | |
| Jehad et al. | Developing and validating a real time video based traffic counting and classification |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |