CN117593705A - Intelligent operation and maintenance management system and method for vehicle - Google Patents
Intelligent operation and maintenance management system and method for vehicle Download PDFInfo
- Publication number
- CN117593705A CN117593705A CN202311612438.0A CN202311612438A CN117593705A CN 117593705 A CN117593705 A CN 117593705A CN 202311612438 A CN202311612438 A CN 202311612438A CN 117593705 A CN117593705 A CN 117593705A
- Authority
- CN
- China
- Prior art keywords
- fault
- data
- video image
- equipment
- dynamic video
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000012423 maintenance Methods 0.000 title claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 25
- 238000001514 detection method Methods 0.000 claims abstract description 15
- 238000007499 fusion processing Methods 0.000 claims abstract description 9
- 238000004458 analytical method Methods 0.000 claims abstract description 6
- 230000007246 mechanism Effects 0.000 claims abstract description 5
- 238000007726 management method Methods 0.000 claims description 39
- 238000012544 monitoring process Methods 0.000 claims description 15
- 238000010586 diagram Methods 0.000 claims description 12
- 238000007405 data analysis Methods 0.000 claims description 7
- 238000013523 data management Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 5
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000013075 data extraction Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 239000003086 colorant Substances 0.000 claims description 3
- 238000011897 real-time detection Methods 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims description 2
- 230000007613 environmental effect Effects 0.000 claims 1
- 230000006870 function Effects 0.000 abstract description 6
- 238000007689 inspection Methods 0.000 abstract description 3
- 230000008447 perception Effects 0.000 abstract description 2
- 238000012790 confirmation Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 241000533950 Leucojum Species 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000008014 freezing Effects 0.000 description 1
- 238000007710 freezing Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 230000033772 system development Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Classifications
-
- 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
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
Abstract
The invention relates to the technical field of intelligent management and maintenance, in particular to a vehicle intelligent operation and maintenance management system and a method thereof, wherein the system comprises a data acquisition layer: the system is used for collecting real-time state information of the outfield equipment and the running state of equipment in the machine room; data access layer: the method is used for carrying out standardization processing, data fusion processing and grouping storage of data and detection of video images; application layer: the method is used for realizing function display and fault alarm through a call flow mechanism. The invention carries out quality discrimination on the video source in real time through background video quality perception analysis, can effectively improve the inspection efficiency of video quality, and in order to prevent serious consequences caused by untimely discovery of faults, establishes data indexes through real-time data acquisition, discovers the fault seedling head in advance through early warning indexes, gives event early warning in time and reduces the occurrence of accidents.
Description
Technical Field
The invention relates to the technical field of intelligent management and maintenance, in particular to a vehicle intelligent operation and maintenance management system and a vehicle intelligent operation and maintenance management method.
Background
The intelligent operation and maintenance management system of the vehicle is generated under the background that the urban development is continuous, and the traffic jam and pollution problems are increasingly prominent. The system can solve traffic problems caused by a large number of vehicles from the source, so that a traffic system is safer, more convenient, energy-saving and environment-friendly. Meanwhile, the intelligent vehicle management system can improve driving safety and comfort of drivers, provides new market opportunities for development of future vehicle industries, in the prior art, the problems existing in video pictures are checked by means of manual inspection, a large number of video quality fault judgment cannot be completed, and the problem of long fault judgment period exists in the traditional manual operation and maintenance management process, so that fault discovery is not timely, and diagnosis efficiency is low. In view of the above, the present invention provides a vehicle intelligent operation and maintenance management system and method thereof to solve the above problems.
Disclosure of Invention
The invention mainly aims to provide a vehicle intelligent operation and maintenance management system and a method thereof, which are used for solving the problems in the related art.
To achieve the above object, according to one aspect of the present invention, there is provided a vehicle intelligent operation and maintenance management system comprising:
data acquisition layer: the system is used for collecting real-time state information of the outfield equipment and the running state of equipment in the machine room;
data access layer: the method is used for carrying out standardization processing, data fusion processing and grouping storage of data and detection of video images;
application layer: the method is used for realizing function display and fault alarm through a call flow mechanism.
Further, the step of detecting the quality of the video image is as follows:
obtaining an image picture of a video and performing preliminary processing;
carrying out analysis and detection on the image picture in two parts;
directly comparing and judging with a pre-stored template when a set judgment standard exists;
the method comprises the steps that a series of data extraction modes are adopted for comprehensive judgment, feature quantities in an image picture are extracted class by class, and comprehensive comparison is carried out on various discrimination thresholds arranged in a system to generate a judgment result;
and integrating the detection results of the two parts, and judging once and finally outputting.
Further, the step of extracting the characteristic quantity in the image picture is based on a convolutional neural network algorithm, and comprises the following steps:
firstly, a feature map N of the whole monitoring video image is established, and the formula is as follows:
N＝∑|I(x)-I(P)|
wherein, I (x) is the image gray value of any point on the monitoring video image, and I (P) is the gray value of the point P to be selected on the central pixel point of the video monitoring image;
the bilinear interpolation method is used for sampling dynamic video image feature graphs on different levels, and the expression of the dynamic video image feature graph F is as follows:
F＝[up(F 1 )，up(F 2 )，...，up(F L )]×N
where up is the motion video image sample and L is the total number of motion video image features.
Further, in the dynamic video image, a method of information entropy and region average is introduced to describe feature graphs of a low-level layer and a high-level layer of the dynamic video image, and a calculation formula is as follows:
the method for introducing information entropy describes a low-level characteristic diagram H of a dynamic video image as follows:
wherein P is i Is the total number of pixels of the dynamic video image;
the method for introducing region average describes a high-level layer characteristic diagram R of a dynamic video image as follows:
wherein d min To obtain the distance of the best feature matching region, d i And identifying the local characteristics of the dynamic video image target.
Further, the outfield device is: the system comprises a signal control device, an identification device, a video monitoring device and a flow detector; the equipment in the machine room is as follows: server, computer lab ring accuse and network equipment.
Further, the data access layer includes:
the data processing unit is used for carrying out standardized fusion processing on the acquired data and detecting the quality of the video image;
the data management unit is used for adjusting relevant parameters issued by the application layer according to the acquired data;
and the data analysis unit is used for judging whether the data is a fault event or not.
Further, the application layer includes:
the unified display platform is used for displaying monitored pictures, event flows and real-time alarm information of faults;
the fault management platform is used for alarming fault events and deducing the root cause of the faults;
and the management integration platform is used for managing departments, users, roles, alarm information, data backup and available resources.
Further, the fault alarming mode includes:
automatically displaying fault nodes on a map, and displaying different colors according to the severity of the fault;
displaying fault alarm information in an alarm status bar;
when faults occur, an alarm sound is sent out through external sound equipment;
the number of alarms exceeding the prescribed level alerts attention in the manner of flashing an icon.
Further, the fault management platform deduces the root cause of the fault as follows:
judging potential problems of the equipment, namely fault events of the equipment by utilizing data acquisition indexes;
for fault events of equipment, establishing a probability model of faults, combining the superposition reasons of fault chains to form a fault probability matrix relation, and screening out faults with high probability;
and for the collected facility fault events, establishing fault source tracing according to the relevance of the faults, so that intelligent event relevance matching and event filtering are carried out, and a truly valuable fault source is found out.
The intelligent operation and maintenance management method for the vehicle comprises the following steps:
s1: collecting, processing and analyzing the real-time state information of the external field equipment and the running state of the equipment in the machine room;
s2: according to the data after real-time detection processing, the application layer issues the adjustment of the related parameters;
s3: and alarming and deducing the source of the fault to the event analyzed as the fault, and processing and recording the event.
Compared with the prior art, the invention has the following beneficial effects:
the invention carries out quality discrimination on the video source in real time through background video quality perception analysis, can effectively improve the inspection efficiency of video quality, and in order to prevent serious consequences caused by untimely discovery of faults, establishes data indexes through real-time data acquisition, discovers the fault seedling head in advance through early warning indexes, gives event early warning in time and reduces the occurrence of accidents.
Drawings
FIG. 1 is a system block diagram of the overall invention;
FIG. 2 is a system block diagram of a data access layer according to the present invention;
FIG. 3 is a system block diagram of an application layer in the present invention;
fig. 4 is a flow chart of the method of the present invention.
Illustration of:
1. a data acquisition layer;
2. a data access layer;
21. a data processing unit; 22. a data management unit; 23. a data analysis unit;
3. an application layer;
31. a unified display platform; 32. a fault management platform; 33. and managing the integration platform.
Detailed Description
In order to further describe the technical means and effects adopted by the invention for achieving the preset aim, the following detailed description is given below of the specific implementation, structure, characteristics and effects according to the invention by combining the attached drawings and the preferred embodiment:
referring to fig. 1-4, the present invention provides a vehicle intelligent operation and maintenance management system, comprising:
data acquisition layer 1: the system is used for collecting real-time state information of the outfield equipment and the running state of equipment in the machine room;
data access layer 2: the method is used for carrying out standardization processing, data fusion processing and grouping storage of data and detection of video images;
application layer 3: the method is used for realizing function display and fault alarm through a call flow mechanism.
The outfield device is: the system comprises a signal control device, an identification device, a video monitoring device and a flow detector; the equipment in the machine room is as follows: server, computer lab ring accuse and network equipment.
The data access layer 2 includes:
a data processing unit 21, where the data processing unit 21 is configured to perform standardized fusion processing on the acquired data, and detect quality of the video image;
the data management unit 22, the data management unit 22 is used for distributing the adjustment of the related parameters to the application layer 3 according to the collected data;
a data analysis unit 23, where the data analysis unit 23 is configured to determine whether the data is a fault occurrence event.
The step of detecting the quality of the video image is as follows:
obtaining an image picture of a video and performing preliminary processing;
carrying out analysis and detection on the image picture in two parts;
directly comparing and judging with a pre-stored template when a set judgment standard exists;
comprehensively judging, extracting characteristic quantities in an image picture class by adopting a series of data extraction modes, and comprehensively comparing various judging thresholds arranged in the system to generate a judging result;
and integrating the detection results of the two parts, and judging once and finally outputting.
The feature quantity in the extracted image picture is based on a convolutional neural network algorithm, and the method comprises the following steps:
firstly, a feature map N of the whole monitoring video image is established, and the formula is as follows:
N＝∑|I(x)-I(P)|
wherein, I (x) is the image gray value of any point on the monitoring video image, and I (P) is the gray value of the point P to be selected on the central pixel point of the video monitoring image;
the bilinear interpolation method is used for sampling dynamic video image feature graphs on different levels, and the expression of the dynamic video image feature graph F is as follows:
F＝[up(F 1 )，up(F 2 )，...，up(F L )]×N
where up is the motion video image sample and L is the total number of motion video image features.
In the dynamic video image, a method for introducing information entropy and region average is used for describing feature graphs of a low-level layer and a high-level layer of the dynamic video image, and a calculation formula is as follows:
the method for introducing information entropy describes a low-level layer characteristic diagram H of a dynamic video image as follows:
wherein P is i Is the total number of pixels of the dynamic video image;
the method for introducing region average describes a high-level layer characteristic diagram R of a dynamic video image as follows:
wherein d min To obtain the distance of the best feature matching region, d i And identifying the local characteristics of the dynamic video image target.
The application layer 3 includes:
the unified display platform 31 is used for displaying monitored pictures, the flow of events and real-time alarm information of faults;
a fault management platform 32, wherein the fault management platform 32 is used for alarming fault events and deducing the root cause of faults;
and the management integration platform 33 is used for managing departments, users, roles, alarm information, data backup and available resources.
The fault alarming mode comprises the following steps:
automatically displaying fault nodes on a map, and displaying different colors according to the severity of the fault;
displaying fault alarm information in an alarm status bar;
when faults occur, an alarm sound is sent out through external sound equipment;
the number of alarms exceeding the prescribed level alerts attention in the manner of flashing an icon.
The fault management platform 32 deduces the source of the fault as follows:
judging potential problems of the equipment, namely fault events of the equipment by utilizing data acquisition indexes;
for fault events of equipment, establishing a probability model of faults, combining the superposition reasons of fault chains to form a fault probability matrix relation, and screening out faults with high probability;
and for the collected facility fault events, establishing fault source tracing according to the relevance of the faults, so as to intelligently perform event relevance matching and event filtering and find out the truly valuable fault source.
Referring to fig. 4, a vehicle intelligent operation and maintenance management method is provided, which includes the following steps:
s1: collecting, processing and analyzing the real-time state information of the external field equipment and the running state of the equipment in the machine room;
s2: according to the data after real-time detection processing, the application layer 3 issues the adjustment of the related parameters;
s3: and alarming and deducing the source of the fault to the event analyzed as the fault, and processing and recording the event.
In this embodiment, the logic level may be divided into: the system comprises a data acquisition layer 1, a data access layer 2 and an application layer 3, wherein the data acquisition layer 1 is mainly used for acquiring and converging real-time state information of external intelligent traffic equipment such as signal control equipment, identification equipment, video monitoring equipment and flow detectors, simultaneously monitoring the running states of servers in a machine room, machine room ring control and network equipment in real time, acquiring related information, uploading acquired and converged data to the data access layer 2 through a data gateway, and ensuring standardized processing, data fusion processing and data storage of the data by the data access layer 2, ensuring that the application layer 3 can timely and conveniently call various real-time data and result data required by the system, and meanwhile, the data layer is also responsible for storing and processing systematic data such as a use management role and authority of the system. The application layer 3 mainly realizes the service functions of function display, fault alarm, event flow circulation and the like by calling various model algorithms and flow mechanisms, thereby providing a standardized and humanized operation interface and function interface for a user and realizing various targets of system development and construction, and the specific method is as follows:
the data processing unit 21 in the data access layer 2 can perform standardized fusion processing on the acquired data and detect the quality of the video image; the detection steps are as follows: obtaining an image picture of a video and performing preliminary processing; carrying out analysis and detection on the image picture in two parts; the first part is where established decision criteria exist, such as: signal loss detection and picture freezing detection are directly compared with a pre-stored template for judgment; comprehensively determined, for example: detecting image color cast, snowflake noise, stripe interference, brightness abnormality and image blurring, extracting characteristic quantities in an image picture class by adopting a series of data extraction modes, comprehensively comparing various discrimination thresholds arranged in a system, and generating a judgment result; and integrating the detection results of the two parts, and judging once and finally outputting. The method comprises the steps of extracting feature quantity in an image picture, generating a dynamic video image feature map according to feature parameters based on a convolutional neural network algorithm, selecting a feature map of a convolutional output layer, constructing a dynamic video image hierarchical structure, introducing an information entropy method, describing a low-level feature map of the dynamic video image, introducing a region averaging method, describing a high-level feature map of a human motion video image, finally constructing a human motion video image with strong expression capability, and extracting target local features, wherein the specific process is as follows:
firstly, a feature map N of the whole monitoring video image is established, and the formula is as follows:
N＝∑|I(x)-I(P)|
wherein, I (x) is the image gray value of any point on the monitoring video image, and I (P) is the gray value of the point P to be selected on the central pixel point of the video monitoring image;
and constructing the image target local feature by taking the selection of the dynamic video image feature map on the convolution output layer as the basis of constructing the image hierarchical structure. Each layer of feature map in the target local feature hierarchical structure of the dynamic video image represents the dynamic video image information from various different aspects, and has stronger expression capability according to the information description of the dynamic video image feature map.
Because the feature images of the dynamic video images on different levels are different in size, when the level is higher, the size of the feature images of the dynamic video images is smaller, and in order to facilitate the extraction of the target local features of the feature images of the level of the dynamic video images, the feature images of the dynamic video images on different levels need to be adjusted to the original image size. The bilinear interpolation method is used for sampling the dynamic video image feature images on different levels, and the three-dimensional matrix of the dynamic video image feature images is constructed as follows:
F∈RN×H×W，
wherein H is the height of the dynamic video image, and W is the width of the dynamic video image.
The bilinear interpolation method is used for sampling dynamic video image feature graphs on different levels, and the expression of the dynamic video image feature graph F is as follows:
F＝[up(F 1 )，up(F 2 )，...，up(F L )]×N
where up is the motion video image sample and L is the total number of motion video image features.
The method for introducing information entropy describes a low-level characteristic diagram H of a dynamic video image as follows:
H＝-i＝1LP i log 2 P i
wherein P is i Is the total number of pixels of the dynamic video image; the information entropy is a magnitude for measuring the chaotic degree of the dynamic video image information, when the entropy rate is low, the positions of the significant changes of the local features of the target are relatively concentrated, and when the entropy rate is high, the positions of the significant changes of the local features of the target are scattered in the whole feature area;
the method for introducing region average describes a high-level layer characteristic diagram R of a dynamic video image as follows:
wherein d min To obtain the distance of the best feature matching region, d i And identifying the local characteristics of the dynamic video image target. Based on the method of introducing information entropy and region average, the method finally constructs the extraction of the local features of the human motion video image target with stronger expression capacity, shortens the time for completing the extraction, the recall ratio and the recall ratioThe accuracy is higher, and the target local information extraction task can be efficiently and accurately completed.
Further, the data management unit 22 may issue an adjustment of the relevant parameters to the application layer 3 according to the collected data; the main parameters are as follows:
alarm period: and when the automatically calculated release state is inconsistent with the outfield state and can not be directly released, and when the manual confirmation is needed, the alarm prompting period is carried out.
Manual intervention period: in the automatic release mode, the valid period of the release state of manual release is reserved, and in the valid period, the state which is automatically calculated cannot cover the state which is manually released, and if the period is exceeded, the state which is automatically calculated is mainly used.
When the automatically calculated distribution state accuracy is low or some states have a large influence, such as blocking, a manual confirmation mode is adopted. When the current automatic calculation state is confirmed, the current automatic calculation state is issued; when the confirmation is canceled, the alarm is not prompted in the alarm period.
Conditions for manual confirmation: in the manual mode, all automatic calculation states are released and need to be confirmed manually, in the automatic mode, configuration parameters can be modified to confirm which states are released and need to be confirmed manually, and if all states are set and need to be confirmed manually, the automatic mode is equivalent to the manual mode.
Further, the data analysis unit 23 determines whether the data is a fault event, and then transmits the fault event to the unified presentation platform 31, the fault management platform 32 and the management integration platform 33, wherein the unified presentation platform 31 presents the fault event in the alarm status bar at the first time; the fault management platform 32 alarms the fault event and infers the source of the fault; the management integration platform 33 stores information of fault events, wherein, in order to prevent serious consequences caused by untimely fault discovery, data indexes are established by collecting and matching service data in real time, fault seedlings are discovered in advance by early warning indexes, event early warning is given in time, occurrence of accidents is reduced, and the fault management platform 32 deduces the root cause of the faults as follows:
judging potential problems of the equipment, namely fault events of the equipment by utilizing data acquisition indexes; for fault events of equipment, establishing a probability model of faults, combining the superposition reasons of fault chains to form a fault probability matrix relation, and screening out faults with high probability; and for the collected facility fault events, establishing fault source tracing according to the relevance of the faults, so as to intelligently perform event relevance matching and event filtering and find out the truly valuable fault source. Wherein, data acquisition index: the method uses mathematical operators, inclusion and non-inclusion relations to determine the threshold value of the equipment, and once the threshold value exceeds the specified range of the threshold value, the matching of the event rule base is completed, and the data is converted into the event. The data of a single event is often insufficient to reflect the occurrence of the event, by collecting the event, after the number of the gauge templates reaches a certain quantification, we count his rules for the event, extract some data indexes, and after the indexes reach the trend of the event alarm, we can convert the statistical data into the event, where the indexes include: a communication success rate index, a data integrity index and a data validity index.
The present invention is not limited to the above embodiments, but is capable of modification and variation in detail, and other modifications and variations can be made by those skilled in the art without departing from the scope of the present invention.
Claims (7)
1. An intelligent operation and maintenance management system for a vehicle, comprising:
data acquisition layer (1): the system is used for collecting real-time state information of the outfield equipment and the running state of equipment in the machine room;
data access layer (2): the method is used for carrying out standardization processing, data fusion processing and grouping storage of data and detection of video images;
application layer (3): the system is used for realizing function display and fault alarm through a call flow mechanism;
the step of detecting the quality of the video image is as follows:
obtaining an image picture of a video and performing preliminary processing;
carrying out two-part analysis and detection on the image picture;
directly comparing and judging with a pre-stored template when a set judgment standard exists;
the method comprises the steps that a series of data extraction modes are adopted for comprehensive judgment, feature quantities in an image picture are extracted class by class, and comprehensive comparison is carried out on various discrimination thresholds arranged in a system to generate a judgment result;
and comprehensively judging the detection results of the two parts once and finally outputting.
The feature quantity in the extracted image picture is based on a convolutional neural network algorithm, and the method comprises the following steps:
firstly, a feature map N of the whole monitoring video image is established, and the formula is as follows:
N＝∑|I(x)-I(P)|
wherein, I (x) is the image gray value of any point on the monitoring video image, and I (P) is the gray value of the point P to be selected on the central pixel point of the video monitoring image;
the bilinear interpolation method is used for sampling dynamic video image feature graphs on different levels, and the expression of the dynamic video image feature graph F is as follows:
F＝[up(F 1 )，up(F 2 )，...，up(F L )]×N
wherein up is the sampling of the dynamic video image, and L is the total number of the characteristics of the dynamic video image;
in the dynamic video image, the information entropy and the region averaging method are introduced to describe the feature diagrams of the low-level layer and the high-level layer of the dynamic video image, and the calculation formula is as follows:
the method for introducing information entropy describes a low-level characteristic diagram H of a dynamic video image as follows:
wherein P is i Is the total number of pixels of the dynamic video image;
the method for introducing region average describes a high-level layer characteristic diagram R of a dynamic video image as follows:
wherein d min To obtain the distance of the best feature matching region, d i And identifying the local characteristics of the dynamic video image target.
2. The intelligent operation and maintenance management system for vehicles according to claim 1, wherein the outfield equipment is a signal control equipment, an identification equipment, a video monitoring equipment and a flow detector; the equipment in the machine room is a server, a machine room environmental control and network equipment.
3. A vehicle wisdom operation and maintenance management system according to claim 1, wherein the data access layer (2) comprises:
the data processing unit (21) is used for carrying out standardized fusion processing on the acquired data and detecting the quality of the video image;
the data management unit (22), the said data management unit (22) is used for distributing the adjustment of the relevant parameter to the application layer (3) according to the data gathered;
and a data analysis unit (23), wherein the data analysis unit (23) is used for judging whether the data is a fault event or not.
4. A vehicle wisdom operation and maintenance management system according to claim 1, wherein the application layer (3) comprises:
the unified display platform (31) is used for displaying monitored pictures, event flows and real-time alarm information of faults;
-a fault management platform (32), the fault management platform (32) being adapted to alert to a fault event and infer a root cause of the fault;
and the management integration platform (33) is used for managing departments, users, roles, alarm information, data backup and available resources.
5. The intelligent operation and maintenance management system for vehicles according to claim 1, wherein the fault alarming means comprises:
automatically displaying fault nodes on the map, and displaying different colors according to the severity of the fault;
displaying fault alarm information in an alarm status bar;
when faults occur, an alarm sound is sent out through external sound equipment;
the number of alarms exceeding the prescribed level alerts attention in the manner of flashing an icon.
6. The vehicle intelligent operation and maintenance management system according to claim 5, wherein the fault management platform (32) deduces the source of the fault as follows:
judging potential problems of the equipment, namely fault events of the equipment by utilizing data acquisition indexes;
for fault events of equipment, establishing a probability model of faults, combining the superposition reasons of fault chains to form a fault probability matrix relation, and screening out faults with high probability;
and for the collected facility fault events, establishing fault source tracing according to the relevance of the faults, so that intelligent event relevance matching and event filtering are carried out, and a truly valuable fault source is found out.
7. A vehicle intelligent operation and maintenance management method based on the vehicle intelligent operation and maintenance management system of any one of claims 1-6, characterized in that: the method comprises the following steps:
s1: collecting, processing and analyzing the real-time state information of the external field equipment and the running state of the equipment in the machine room;
s2: according to the data after real-time detection processing, the application layer (3) issues the adjustment of the related parameters;
s3: and alarming and deducing the source of the fault to the event analyzed as the fault, and processing and recording the event.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311612438.0A CN117593705A (en) | 2023-11-29 | 2023-11-29 | Intelligent operation and maintenance management system and method for vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311612438.0A CN117593705A (en) | 2023-11-29 | 2023-11-29 | Intelligent operation and maintenance management system and method for vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117593705A true CN117593705A (en) | 2024-02-23 |
Family
ID=89909575
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311612438.0A Pending CN117593705A (en) | 2023-11-29 | 2023-11-29 | Intelligent operation and maintenance management system and method for vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117593705A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2853972A2 (en) * | 2013-09-30 | 2015-04-01 | YPF Tecnologia S.A. | Device and method for detection and/or diagnosis of faults in a process, equipment and sensors |
| CN107633685A (en) * | 2016-07-19 | 2018-01-26 | 北京易华录信息技术股份有限公司 | A kind of transit equipment condition monitoring system and method |
| CN109768889A (en) * | 2019-01-16 | 2019-05-17 | 高正民 | A kind of visualization safety management wisdom operation platform |
| CN114518736A (en) * | 2022-02-22 | 2022-05-20 | 上海有间建筑科技有限公司 | Intelligent construction industry integrated management and control system |
| WO2022130789A1 (en) * | 2020-12-17 | 2022-06-23 | 株式会社日立パワーソリューションズ | Cause inference system and cause inference method |
| CN115508672A (en) * | 2022-11-22 | 2022-12-23 | 中国电力科学研究院有限公司 | Power grid main equipment fault tracing reasoning method, system, equipment and medium |
-
2023
- 2023-11-29 CN CN202311612438.0A patent/CN117593705A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2853972A2 (en) * | 2013-09-30 | 2015-04-01 | YPF Tecnologia S.A. | Device and method for detection and/or diagnosis of faults in a process, equipment and sensors |
| CN107633685A (en) * | 2016-07-19 | 2018-01-26 | 北京易华录信息技术股份有限公司 | A kind of transit equipment condition monitoring system and method |
| CN109768889A (en) * | 2019-01-16 | 2019-05-17 | 高正民 | A kind of visualization safety management wisdom operation platform |
| WO2022130789A1 (en) * | 2020-12-17 | 2022-06-23 | 株式会社日立パワーソリューションズ | Cause inference system and cause inference method |
| CN114518736A (en) * | 2022-02-22 | 2022-05-20 | 上海有间建筑科技有限公司 | Intelligent construction industry integrated management and control system |
| CN115508672A (en) * | 2022-11-22 | 2022-12-23 | 中国电力科学研究院有限公司 | Power grid main equipment fault tracing reasoning method, system, equipment and medium |
Non-Patent Citations (1)
| Title |
|---|
| 冀兆鹏: "人体运动视频图像目标局部特征快速提取仿真", 《计算机仿真》, 31 December 2019 (2019-12-31), pages 459 - 463 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101783970B (en) | Methods, devices and systems for automatically detecting and managing fault of camera | |
| CN111629181B (en) | Fire-fighting life passage monitoring system and method | |
| CN111047818A (en) | Forest fire early warning system based on video image | |
| CN113063611B (en) | Equipment monitoring management method and system | |
| CN102176758A (en) | Video quality diagnosis system and realization method thereof | |
| CN103260049A (en) | Intelligent skynet video quality diagnostic system | |
| CN104966304A (en) | Kalman filtering and nonparametric background model-based multi-target detection tracking method | |
| CN114021971A (en) | Comprehensive evaluation system, method and storage medium for expressway operation and maintenance management | |
| CN109509190A (en) | Video monitoring image screening technique, device, system and storage medium | |
| CN112363443A (en) | Automatic monitoring method and system for data center | |
| CN116055690B (en) | Method and equipment for processing machine room monitoring video | |
| CN114518736A (en) | Intelligent construction industry integrated management and control system | |
| CN111757096A (en) | Video operation and maintenance management system and method | |
| CN114143220A (en) | Real-time data visualization platform | |
| CN211184122U (en) | Intelligent video analysis system for linkage of railway operation safety prevention and control and large passenger flow early warning | |
| CN116385948B (en) | System and method for early warning railway side slope abnormality | |
| CN112348707A (en) | Holographic intelligent building energy-saving operation and maintenance management system based on BIM model | |
| CN103049365A (en) | Monitoring and evaluating method for information and application resource operating states | |
| CN110989042A (en) | Intelligent prediction method for highway fog-clustering risk | |
| CN116761049B (en) | Household intelligent security monitoring method and system | |
| CN117319609A (en) | Internet of things big data intelligent video monitoring system and method | |
| CN117593705A (en) | Intelligent operation and maintenance management system and method for vehicle | |
| CN110930707A (en) | Non-motor vehicle traffic violation supervision system and supervision method | |
| CN106101696B (en) | Video quality diagnosis system and video quality analysis algorithm | |
| CN114882589A (en) | Granary safety operation early warning system and method based on intelligent video analysis |
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 |