CN115017014B - Highway electromechanical monitoring system and method - Google Patents

Highway electromechanical monitoring system and method Download PDF

Info

Publication number
CN115017014B
CN115017014B CN202210807874.2A CN202210807874A CN115017014B CN 115017014 B CN115017014 B CN 115017014B CN 202210807874 A CN202210807874 A CN 202210807874A CN 115017014 B CN115017014 B CN 115017014B
Authority
CN
China
Prior art keywords
data
monitoring
monitoring system
network security
structured
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.)
Active
Application number
CN202210807874.2A
Other languages
Chinese (zh)
Other versions
CN115017014A (en
Inventor
龙开红
周玲
甘洁之
黄伟彪
陈佳
陈洽尧
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Litong Technology Investment Co ltd
Original Assignee
Guangdong Litong Technology Investment Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangdong Litong Technology Investment Co ltd filed Critical Guangdong Litong Technology Investment Co ltd
Priority to CN202210807874.2A priority Critical patent/CN115017014B/en
Publication of CN115017014A publication Critical patent/CN115017014A/en
Application granted granted Critical
Publication of CN115017014B publication Critical patent/CN115017014B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/30Monitoring
    • G06F11/3003Monitoring arrangements specially adapted to the computing system or computing system component being monitored
    • G06F11/302Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system component is a software system
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01RMEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/30Monitoring
    • G06F11/3003Monitoring arrangements specially adapted to the computing system or computing system component being monitored
    • G06F11/3006Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/30Monitoring
    • G06F11/3065Monitoring arrangements determined by the means or processing involved in reporting the monitored data
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/0002Inspection of images, e.g. flaw detection
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14Network analysis or design
    • H04L41/142Network analysis or design using statistical or mathematical methods
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00Network architectures or network communication protocols for network security
    • H04L63/14Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
    • H04L63/1408Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
    • H04L63/1425Traffic logging, e.g. anomaly detection
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00Network architectures or network communication protocols for network security
    • H04L63/20Network architectures or network communication protocols for network security for managing network security; network security policies in general
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/01Protocols
    • H04L67/12Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10016Video; Image sequence
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/30Subject of image; Context of image processing
    • G06T2207/30168Image quality inspection
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Computer Security & Cryptography (AREA)
  • Quality & Reliability (AREA)
  • Signal Processing (AREA)
  • Mathematical Physics (AREA)
  • Computer Hardware Design (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • Algebra (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Probability & Statistics with Applications (AREA)
  • Pure & Applied Mathematics (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Alarm Systems (AREA)

Abstract

The invention provides an electromechanical monitoring system for an expressway, which comprises: the system comprises a central monitoring server, a first monitoring system, a second monitoring system, a third monitoring system, a charging system, a monitoring system and a network safety system; the first monitoring system collects the original data of the charging system, processes the original data and sends the processed data to the central monitoring server; the second monitoring system collects the original data of the monitoring system, processes the original data and sends the processed data to the central monitoring server; the third monitoring system collects the original data of the network safety system, processes the original data and sends the processed data to the central monitoring server; and the central monitoring server determines the comprehensive health condition of the charging system, the monitoring system and the network security system based on the received and processed data of the charging system, the monitoring system and the network security system. The invention monitors the electromechanical system through a plurality of data dimensions, and is convenient for finding the fault of the system.

Description

Highway electromechanical monitoring system and method
Technical Field
The invention relates to the technical field of computer data processing, in particular to an electromechanical monitoring system and method for an expressway.
Background
At present, the highway electromechanical monitoring system generally realizes the basic monitoring and early warning function based on the running state of equipment and the like, the charging service monitoring does not form a uniform standard, the monitoring index is not comprehensive, the judgment logic is not rigorous, the service development requirement cannot be supported, the charging network is isolated from the monitoring network, and the monitoring function also forms a service dispersion situation. The monitoring system also lacks the combination with operation and maintenance data and flow in function, and the service expansibility is poor.
In the prior art, a statistical interval estimation method is applied to perform early warning, and when an index value exceeds the following interval, the early warning is performed:
Figure DEST_PATH_IMAGE001
a forward indicator;
Figure DEST_PATH_IMAGE002
reverse direction index;
since the section is judged only statistically whether the index is abnormal, it is difficult to accurately judge whether the equipment is abnormal.
In addition, in the prior art, fault evaluation is also performed by using a factor analysis method, but in the prior art, a factor analysis model determines the factor weight depending on the dispersion degree of each factor, which may cause some factors with lower dispersion degrees but have larger influence on actual services, resulting in inaccurate analysis results.
Disclosure of Invention
The present invention proposes the following technical solutions to address one or more technical defects in the prior art.
A highway electromechanical monitoring system, the system comprising: the system comprises a central monitoring server, a first monitoring system, a second monitoring system, a third monitoring system, a charging system, a monitoring system and a network safety system;
the first monitoring system collects the original data of the charging system, processes the original data and sends the processed data to the central monitoring server;
the second monitoring system collects original data of the monitoring system, processes the original data and sends the processed data to the central monitoring server;
the third monitoring system collects the original data of the network safety system, processes the original data and sends the processed data to the central monitoring server;
and the central monitoring server determines the comprehensive health condition of the charging system, the monitoring system and the network security system based on the received and processed data of the charging system, the monitoring system and the network security system.
Furthermore, the highway is divided into a plurality of sections according to the length, each section is provided with a first monitoring system, a second monitoring system and a third monitoring system, and the first monitoring system, the second monitoring system and the third monitoring system are respectively connected with the charging system, the monitoring system and the network safety system of the section.
Furthermore, the first monitoring system comprises a first edge computing device, a first structured data acquisition device and a first log analysis device, the original data of the charging system comprises transaction data, system performance data, device state data, system setting parameters and system log data, the first log analysis device carries out structured processing on the transaction data, the system performance data, the device state data, the system setting parameters and the system log data to obtain structured data of the charging system, and the first structured data acquisition device obtains the structured data of the charging system from the first log analysis device and then sends the structured data of the charging system to the first edge computing device through first heartbeat data to be subjected to preliminary screening, collection and analysis and then sends the data to the central monitoring server.
Furthermore, the second monitoring system comprises a second edge computing device, a second structured data acquisition device and an image AI diagnosis system, the original data of the monitoring system comprises video image data, device state data, system setting parameters and system log data, the image AI diagnosis system uses an AI algorithm to judge the sharpness value of a fixed line in an image, judge whether the comprehensive sharpness value of the image reaches a threshold value, judge whether the video quality reaches the standard, and generate the result of whether the video quality reaches the standard, the device state data, the system setting parameters and the system log data into the structured data of the monitoring system, and the second structured data acquisition device acquires the structured data of the monitoring system from the image AI diagnosis system, and then sends the structured data of the monitoring system to the second edge computing device for preliminary screening, collection and analysis through second heartbeat data and then sends the data to a central monitoring server.
Furthermore, the third monitoring system includes a third edge computing device, a third structured data collection device, and a third log analysis device, where the original data of the network security system includes security threat event data, network state data, device state data, and system log data, the third log analysis device performs structured processing on the security threat event data, the network state data, the device state data, and the system log data to obtain structured data of the network security system, and the third structured data collection device obtains the structured data of the network security system from the third log analysis device, and then sends the structured data of the network security system to the third edge computing device through the third heartbeat data, performs preliminary screening, aggregation, and analysis, and then sends the structured data to the central monitoring server.
Furthermore, the first edge computing device performs preliminary screening, collection and analysis on the structured data of the charging system and the structured data of the network security system by using an interval estimation early warning method, and then only sends abnormal data to the central monitoring server, wherein the interval estimation early warning method comprises the following steps:
Figure DEST_PATH_IMAGE003
forward direction index, fault occurs, but the index value does not exceed the early warning value;
Figure 477795DEST_PATH_IMAGE004
forward index, no fault occurs, but the index value exceeds the early warning value;
Figure DEST_PATH_IMAGE005
the reverse index is adopted, and the index value does not exceed the early warning value when a fault occurs;
Figure 332618DEST_PATH_IMAGE006
the index value exceeds the early warning value when the fault does not occur;
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE007
is the index sample mean, a is the confidence, u is the quantile at a/2 confidence,
Figure 689519DEST_PATH_IMAGE008
is the sample standard deviation, and n is the number of data.
Further, the image AI diagnostic system performs the operations of: extracting the gray value of an image shot by a monitoring camera; calculating the average gray value of the image:
Figure DEST_PATH_IMAGE009
wherein x and y are coordinate values of pixel points in the picture, and f (x, y) is a gray value of the pixel point (x, y); the variance of the mean gray value of the image is calculated by using a variance method:
Figure 756832DEST_PATH_IMAGE010
(ii) a Sampling a video static environment, avoiding influence of dynamic factors such as vehicles on a gray value, collecting gray value variances under different external environments to determine variance threshold values t under different external environments, and automatically adapting and monitoring the variance threshold values t under the external environments when the illuminance data of a meteorological sensor is accessed; because the variance of the gray value can be increased due to the dynamic factors of the vehicle, the system carries out snapshot for multiple times and takes the minimum value
Figure DEST_PATH_IMAGE011
When is coming into contact with
Figure 508888DEST_PATH_IMAGE012
Time, or when the environmental parameters are not changed obviously but the gray value variance-to-ring ratio is reduced obviously
Figure DEST_PATH_IMAGE013
The early warning is carried out, toll station and road surface monitoring video automatic monitoring are realized, wherein, k is dynamic environment influence parameter, confirms through the sampling, promptly: minimum grayscale variance in dynamic environment/minimum grayscale variance in static environment.
Furthermore, the manner of determining the comprehensive health condition of the charging system, the monitoring system and the network security system by the central monitoring server based on the received processed data of the charging system, the monitoring system and the network security system is as follows:
calculating the comprehensive health status value by adopting an optimized factor analysis method:
Figure 767568DEST_PATH_IMAGE014
wherein, w 1 、w 2 、w 2 Factor weights, f, for charging system, monitoring system and network security system, respectively 1 、f 2 、f 3 Actual failure rates of the charging system, the monitoring system and the network security system respectively, m is the total number of actual failures related to each factor, k 1 、k 2 、k 3 Are respectively and 1 、f 2 、f 3 the number of actual failures associated.
Further, f 1 、f 2 、f 3 And the central monitoring server calculates the abnormal data based on the received structured data of the charging system, the structured data of the monitoring system and the structured data of the network security system.
Furthermore, the central monitoring server is a cloud server.
The invention also provides an electromechanical monitoring method of the expressway electromechanical monitoring system based on any one of the above, which comprises the following steps:
a charging system acquisition step, wherein the first monitoring system acquires original data of the charging system, processes the original data and sends the processed data to the central monitoring server;
a monitoring system acquisition step, wherein the second monitoring system acquires original data of the monitoring system, processes the original data and sends the processed original data to the central monitoring server;
a network security system acquisition step, wherein the third monitoring system acquires original data of the network security system, processes the original data and sends the processed data to the central monitoring server;
and processing, namely determining the comprehensive health conditions of the charging system, the monitoring system and the network security system by the central monitoring server based on the received and processed data of the charging system, the monitoring system and the network security system.
Further, in the step of treating, the f 1 、f 2 、f 3 And the data are calculated by the central monitoring server based on the received abnormal data in the structured data of the charging system, the structured data of the monitoring system and the structured data of the network security system.
Furthermore, the central monitoring server is a cloud server.
The invention has the technical effects that: the invention relates to an electromechanical monitoring system for a highway, which comprises: the system comprises a central monitoring server, a first monitoring system, a second monitoring system, a third monitoring system, a charging system, a monitoring system and a network security system; the first monitoring system collects the original data of the charging system, processes the original data and sends the processed data to the central monitoring server; the second monitoring system collects the original data of the monitoring system, processes the original data and sends the processed data to the central monitoring server; the third monitoring system collects the original data of the network safety system, processes the original data and sends the processed data to the central monitoring server; and the central monitoring server determines the comprehensive health condition of the charging system, the monitoring system and the network security system based on the received and processed data of the charging system, the monitoring system and the network security system. In the invention, the terminal nodes such as charging/monitoring and the like perform self-monitoring based on-site service requirements, and edge calculation is performed according to service subsystem differentiation by taking road sections as sub-nodes, so that intelligent system monitoring at the road section level is realized; the central monitoring server carries out cloud deployment, extracts key monitoring and service data from each service subsystem of a road section, carries out three-dimensional monitoring on the whole-network full-service data, ensures monitoring accuracy and early warning timeliness, namely carries out monitoring on an electromechanical system through a plurality of data dimensions, and is convenient for finding out faults of the system; according to the invention, a charging system, a monitoring system and a network security system are respectively processed during data acquisition, a log analysis system is established, key information of service system operation in logs is extracted through strict logic analysis, preliminary statistics is carried out, unstructured data such as time and the like are structured, transmission and storage of original files are greatly reduced, efficient application of data is realized, an AI algorithm is used for judging the sharpness value of a fixed line in an image, and whether the comprehensive sharpness value of the image reaches a threshold value is judged, so that whether the video quality reaches the standard is judged, the data transmission quantity is reduced, and the system operation efficiency is improved; in the invention, the gray value of the video image is extracted, the AI algorithm is used for judging the sharpness value of the fixed line in the image, and whether the comprehensive sharpness value of the image reaches the threshold value is judged, so that whether the video quality reaches the standard is judged, and in the calculation process, the variance threshold value under the external environment is automatically adapted and monitored to perform early warning based on the real-time illumination data of the meteorological sensor, so that the automatic monitoring of the toll station and the road surface monitoring video is realized.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings.
FIG. 1 is a block diagram of a highway electromechanical monitoring system according to an embodiment of the present invention.
Fig. 2 is a flow chart of a highway electromechanical monitoring method according to an embodiment of the invention.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 shows a motorway electromechanical monitoring system of the invention, said system comprising: the system comprises a central monitoring server, a first monitoring system, a second monitoring system, a third monitoring system, a charging system, a monitoring system and a network safety system;
the first monitoring system collects the original data of the charging system, processes the original data and sends the processed data to the central monitoring server;
the second monitoring system collects original data of the monitoring system, processes the original data and sends the processed data to the central monitoring server;
the third monitoring system collects the original data of the network safety system, processes the original data and sends the processed data to the central monitoring server;
and the central monitoring server determines the comprehensive health condition of the charging system, the monitoring system and the network security system based on the received and processed data of the charging system, the monitoring system and the network security system.
In one embodiment, the highway is divided into a plurality of sections according to the length, and each section is provided with a first monitoring system, a second monitoring system and a third monitoring system which are respectively connected with the charging system, the monitoring system and the network security system of the section.
In the invention, the terminal nodes such as charging/monitoring and the like perform self-monitoring based on-site service requirements, and edge calculation is performed according to service subsystem differentiation by taking road sections as sub-nodes, so that intelligent system monitoring at the road section level is realized; the central monitoring server performs cloud deployment, extracts key monitoring and service data from each service subsystem of a road section, performs three-dimensional monitoring on the whole-network whole-service data, and ensures monitoring accuracy and early warning timeliness.
In one embodiment, the first monitoring system includes a first edge computing device, a first structured data collection device, and a first log analysis device, the raw data of the charging system includes transaction data, system performance data, device status data, system setting parameters, and system log data, the first log analysis device performs structured processing on the transaction data, the system performance data, the device status data, the system setting parameters, and the system log data to obtain structured data of the charging system, and the first structured data collection device obtains the structured data of the charging system from the first log analysis device, and then sends the structured data of the charging system to the first edge computing device through first heartbeat data to perform preliminary screening, collection, and analysis, and then sends the structured data to the central monitoring server.
In one embodiment, the second monitoring system includes a second edge computing device, a second structured data acquisition device, and an image AI diagnostic system, where the raw data of the monitoring system includes video image data, device status data, system setting parameters, and system log data, the image AI diagnostic system uses an AI algorithm to determine a sharpness value of a fixed line in an image, determine whether an image comprehensive sharpness value reaches a threshold value, determine whether video quality reaches a standard, and generate monitoring system structured data from a result of whether the image comprehensive sharpness value reaches the standard, the device status data, the system setting parameters, and the system log data, and the second structured data acquisition device acquires the monitoring system structured data from the image AI diagnostic system, and then sends the monitoring system structured data to the second edge computing device for preliminary screening, aggregation, and analysis, and then sends the data to a central monitoring server.
In one embodiment, the third monitoring system includes a third edge computing device, a third structured data collection device, and a third log analysis device, where the raw data of the network security system includes security threat event data, network state data, device state data, and system log data, the third log analysis device performs structured processing on the security threat event data, the network state data, the device state data, and the system log data to obtain structured data of the network security system, and the third structured data collection device obtains the structured data of the network security system from the third log analysis device, and then sends the structured data of the network security system to the third edge computing device through a third heartbeat data to perform preliminary screening, aggregation, and analysis, and then sends the structured data to the central monitoring server.
In the invention, a charging system, a monitoring system and a network security system are respectively processed during data acquisition, a log analysis system is established, key information of service system operation in logs is extracted through strict logic analysis, preliminary statistics is carried out, unstructured data such as time and the like are structured, transmission and storage of original files are greatly reduced, high-efficiency application of data is realized, an AI algorithm is used for judging the sharpness value of a fixed line in an image, and whether the comprehensive sharpness value of the image reaches a threshold value is judged, so that whether the video quality reaches the standard is judged, the data transmission quantity is reduced, and the system operation efficiency is improved.
In one embodiment, the first edge computing device performs preliminary screening, aggregation and analysis on the charging system structured data and the network security system structured data by using an interval estimation early warning method, and then sends only abnormal data to the central monitoring server, wherein the interval estimation early warning method is as follows:
Figure 237864DEST_PATH_IMAGE003
the forward index is failed, but the index value does not exceed the early warning value;
Figure 905606DEST_PATH_IMAGE004
forward direction index, no fault occurs, but the index value exceeds the early warning value;
Figure 43326DEST_PATH_IMAGE005
the reverse index is adopted, and the index value does not exceed the early warning value when a fault occurs;
Figure 771111DEST_PATH_IMAGE006
reverse direction index, no occurrence of failureFault, but index value exceeds the early warning value;
wherein the content of the first and second substances,
Figure 994282DEST_PATH_IMAGE007
is the index sample mean, a is the confidence, u is the quantile at a/2 confidence,
Figure 200135DEST_PATH_IMAGE008
is the sample standard deviation, and n is the number of data.
In the invention, the interval of the interval estimation method in the background technology is optimized by combining the production environment, and when the production environment fails and the related indexes do not exceed the interval range, the interval is shrunk by a fixed proportion; when the production environment is not in fault but the related indexes exceed the range of the interval, the interval is expanded by a fixed proportion. And the model is continuously trained by combining actual service data, and the early warning value of the index is optimized. Thereby improving the accuracy of the fault prediction, which is another important invention point of the invention.
In one embodiment, the image AI diagnostic system performs the operations of: extracting the gray value of an image shot by a monitoring camera; calculating the average gray value of the image:
Figure 192362DEST_PATH_IMAGE009
wherein x and y are coordinate values of pixel points in the picture, and f (x, y) is a gray value of the pixel point (x, y); the variance of the mean gray value of the image is calculated by using a variance method:
Figure 583723DEST_PATH_IMAGE010
(ii) a Sampling a video static environment, avoiding influence of dynamic factors such as vehicles on a gray value, collecting gray value variances under different external environments to determine variance threshold values t under different external environments, and automatically adapting and monitoring the variance threshold values t under the external environments when the illuminance data of a meteorological sensor is accessed; as the gray value variance can be increased due to vehicle dynamic factors, the system carries out snapshot for multiple times and takes the minimum value
Figure 559770DEST_PATH_IMAGE011
When is coming into contact with
Figure 303735DEST_PATH_IMAGE012
Time, or when the environmental parameters are not changed obviously but the gray value variance-to-ring ratio is reduced obviously
Figure 416047DEST_PATH_IMAGE013
The early warning will be carried out, toll station and road surface surveillance video automatic monitoring are realized, wherein, k is dynamic environmental impact parameter, confirms through the sampling, promptly: minimum gray variance in dynamic environment/minimum gray variance in static environment.
In the invention, the gray value of the video image is extracted, the AI algorithm is used for judging the sharpness value of the fixed line in the image, and whether the comprehensive sharpness value of the image reaches the threshold value is judged, so that whether the video quality reaches the standard is judged, and in the calculation process, the variance threshold value under the external environment is automatically adapted and monitored to perform early warning based on the real-time illumination data of the meteorological sensor, so that the automatic monitoring of the toll station and the road surface monitoring video is realized, which is another important invention point of the invention.
In one embodiment, the central monitoring server determines the comprehensive health condition of the charging system, the monitoring system and the network security system based on the received processed data of the charging system, the monitoring system and the network security system by:
calculating the comprehensive health status value by adopting an optimized factor analysis method:
Figure 220055DEST_PATH_IMAGE014
wherein, w 1 、w 2 、w 2 Factor weight f for charging system, monitoring system and network security system 1 、f 2 、f 3 Actual failure rates for charging systems, monitoring systems and network security systems, m being the total number of actual failures associated with each factor, k 1 、k 2 、k 3 Are respectively and 1 、f 2 、f 3 the number of actual failures associated.
In one embodiment, f 1 、f 2 、f 3 And the central monitoring server calculates the abnormal data based on the received structured data of the charging system, the structured data of the monitoring system and the structured data of the network security system. In one embodiment, the central monitoring server is a cloud server.
In the invention, because the traditional factor analysis model is dependent on the discrete degree of each factor when determining the factor weight, some factors with lower discrete degree but larger influence on actual service are probably caused, the invention combines the model with the actual fault occurrence rate and provides the optimized factor analysis method, namely, on the basis of the traditional factor analysis method, correction is carried out according to the number of various faults and the total number of the faults, so that the accuracy of the optimized factor analysis method is improved, which is another important invention point of the invention.
Fig. 2 shows an electromechanical monitoring method of an electromechanical highway monitoring system according to any one of the above embodiments, the method comprising:
a charging system acquisition step S201, wherein the first monitoring system acquires original data of the charging system, processes the original data and sends the processed data to the central monitoring server;
a monitoring system acquisition step S202, wherein the second monitoring system acquires original data of the monitoring system, processes the original data and sends the processed data to the central monitoring server;
a network security system acquisition step S203, wherein the third monitoring system acquires original data of the network security system, processes the original data and sends the processed data to the central monitoring server;
and a processing step S204, wherein the central monitoring server determines the comprehensive health condition of the charging system, the monitoring system and the network security system based on the received and processed data of the charging system, the monitoring system and the network security system.
In one embodiment, the highway is divided into a plurality of sections according to the length, and each section is provided with a first monitoring system, a second monitoring system and a third monitoring system which are respectively connected with the charging system, the monitoring system and the network security system of the section.
In the invention, the terminal nodes such as charging/monitoring and the like perform self-monitoring based on-site service requirements, and edge calculation is performed according to service subsystem differentiation by taking road sections as sub-nodes, so that intelligent system monitoring at the road section level is realized; the central monitoring server performs cloud deployment, extracts key monitoring and service data from each service subsystem of a road section, performs three-dimensional monitoring on the whole-network whole-service data, and ensures monitoring accuracy and early warning timeliness.
In one embodiment, the first monitoring system includes a first edge computing device, a first structured data collection device, and a first log analysis device, the raw data of the charging system includes transaction data, system performance data, device status data, system setting parameters, and system log data, the first log analysis device performs structured processing on the transaction data, the system performance data, the device status data, the system setting parameters, and the system log data to obtain structured data of the charging system, and the first structured data collection device obtains the structured data of the charging system from the first log analysis device, and then sends the structured data of the charging system to the first edge computing device through first heartbeat data to perform preliminary screening, collection, and analysis, and then sends the structured data to the central monitoring server.
In one embodiment, the second monitoring system includes a second edge computing device, a second structured data acquisition device, and an image AI diagnostic system, where the raw data of the monitoring system includes video image data, device status data, system setting parameters, and system log data, the image AI diagnostic system uses an AI algorithm to determine a sharpness value of a fixed line in an image, determine whether an image comprehensive sharpness value reaches a threshold value, determine whether video quality reaches a standard, and generate monitoring system structured data from a result of whether the image comprehensive sharpness value reaches the standard, the device status data, the system setting parameters, and the system log data, and the second structured data acquisition device acquires the monitoring system structured data from the image AI diagnostic system, and then sends the monitoring system structured data to the second edge computing device for preliminary screening, aggregation, and analysis, and then sends the data to a central monitoring server.
In one embodiment, the third monitoring system includes a third edge computing device, a third structured data collection device, and a third log analysis device, where the raw data of the network security system includes security threat event data, network state data, device state data, and system log data, the third log analysis device performs structured processing on the security threat event data, the network state data, the device state data, and the system log data to obtain structured data of the network security system, and the third structured data collection device obtains the structured data of the network security system from the third log analysis device, and then sends the structured data of the network security system to the third edge computing device through a third heartbeat data collection device for preliminary screening, aggregation, analysis, and then sends the structured data to the central monitoring server.
In the invention, a charging system, a monitoring system and a network security system are respectively processed during data acquisition, a log analysis system is established, key information of service system operation in logs is extracted through strict logic analysis, preliminary statistics is carried out, unstructured data such as time and the like are structured, transmission and storage of original files are greatly reduced, high-efficiency application of data is realized, an AI algorithm is used for judging the sharpness value of a fixed line in an image, and whether the comprehensive sharpness value of the image reaches a threshold value is judged, so that whether the video quality reaches the standard is judged, the data transmission quantity is reduced, and the system operation efficiency is improved.
In one embodiment, the first edge computing device performs preliminary screening, aggregation and analysis on the charging system structured data and the network security system structured data by using an interval estimation early warning method, and then sends only abnormal data to the central monitoring server, wherein the interval estimation early warning method is as follows:
Figure 355501DEST_PATH_IMAGE003
forward direction index, fault occurs, but the index value does not exceed the early warning value;
Figure 401693DEST_PATH_IMAGE004
forward index, no fault occurs, but the index value exceeds the early warning value;
Figure 368512DEST_PATH_IMAGE005
the reverse index is used for indicating that a fault occurs but the index value does not exceed the early warning value;
Figure 609000DEST_PATH_IMAGE006
the index value exceeds the early warning value when the fault does not occur;
wherein the content of the first and second substances,
Figure 28480DEST_PATH_IMAGE007
is the index sample mean, a is the confidence, u is the quantile at a/2 confidence,
Figure 379827DEST_PATH_IMAGE008
is the sample standard deviation, and n is the number of data.
In the invention, the interval of the interval estimation method in the background technology is optimized by combining the production environment, and when the production environment fails and the related indexes do not exceed the interval range, the interval is shrunk by a fixed proportion; when the production environment is not in fault but the related indexes exceed the range of the interval, the interval is expanded by a fixed proportion. And the model is continuously trained by combining actual service data, and the early warning value of the index is optimized. Thereby improving the accuracy of the fault prediction, which is another important invention point of the invention.
In one embodiment, the image AI diagnostic system performs the operations of: extraction monitoringGray values of images shot by the camera; calculating the average gray value of the image:
Figure 201153DEST_PATH_IMAGE009
wherein x and y are coordinate values of pixel points in the picture, and f (x, y) is a gray value of the pixel point (x, y); the variance of the mean gray value of the image is calculated by using a variance method:
Figure 878121DEST_PATH_IMAGE010
(ii) a Sampling a video static environment, avoiding influence of dynamic factors such as vehicles on a gray value, collecting gray value variances under different external environments to determine variance threshold values t under different external environments, and automatically adapting and monitoring the variance threshold values t under the external environments when the illuminance data of a meteorological sensor is accessed; as the gray value variance can be increased due to vehicle dynamic factors, the system carries out snapshot for multiple times and takes the minimum value
Figure 784898DEST_PATH_IMAGE011
When is coming into contact with
Figure 674356DEST_PATH_IMAGE012
Time, or when the environmental parameters are not changed obviously but the gray value variance-to-ring ratio is reduced obviously
Figure 114303DEST_PATH_IMAGE013
The early warning will be carried out, toll station and road surface surveillance video automatic monitoring are realized, wherein, k is dynamic environmental impact parameter, confirms through the sampling, promptly: minimum gray variance in dynamic environment/minimum gray variance in static environment.
In the invention, the gray value of the video image is extracted, the AI algorithm is used for judging the sharpness value of the fixed line in the image, and whether the comprehensive sharpness value of the image reaches the threshold value is judged, so that whether the video quality reaches the standard is judged, and in the calculation process, the variance threshold value under the external environment is automatically adapted and monitored to perform early warning based on the real-time illumination data of the meteorological sensor, so that the automatic monitoring of the toll station and the road surface monitoring video is realized, which is another important invention point of the invention.
In one embodiment, the central monitoring server determines the comprehensive health condition of the charging system, the monitoring system and the network security system based on the received processed data of the charging system, the monitoring system and the network security system by:
calculating the comprehensive health status value by adopting an optimized factor analysis method:
Figure 696594DEST_PATH_IMAGE014
wherein w 1 、w 2 、w 2 Factor weights for charging systems, monitoring systems and network security systems, f 1 、f 2 、f 3 Actual failure rates for charging systems, monitoring systems and network security systems, m being the total number of actual failures associated with each factor, k 1 、k 2 、k 3 Are respectively and 1 、f 2 、f 3 the number of actual failures associated.
In one embodiment, f 1 、f 2 、f 3 And the central monitoring server calculates the abnormal data based on the received structured data of the charging system, the structured data of the monitoring system and the structured data of the network security system. In one embodiment, the central monitoring server is a cloud server.
In the invention, because the traditional factor analysis model is dependent on the discrete degree of each factor when determining the factor weight, some factors with lower discrete degree but larger influence on actual service are probably caused, the invention combines the model with the actual fault occurrence rate and provides the optimized factor analysis method, namely, on the basis of the traditional factor analysis method, correction is carried out according to the number of various faults and the total number of the faults, so that the accuracy of the optimized factor analysis method is improved, which is another important invention point of the invention.
An embodiment of the present invention provides a computer storage medium, on which a computer program is stored, which when executed by a processor implements the above-mentioned method, and the computer storage medium can be a hard disk, a DVD, a CD, a flash memory, or the like.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
From the above description of the embodiments, it is clear to those skilled in the art that the present application can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the present application may be essentially implemented or the portions that contribute to the prior art may be embodied in the form of a software product, which may be stored in a storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the apparatuses described in the embodiments or some portions of the embodiments of the present application.
Finally, it should be noted that: although the present invention has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that: modifications and equivalents may be made thereto without departing from the spirit and scope of the invention and it is intended to cover in the claims the invention as defined in the appended claims.

Claims (5)

1. An electromechanical highway monitoring system, comprising: the system comprises a central monitoring server, a first monitoring system, a second monitoring system, a third monitoring system, a charging system, a monitoring system and a network safety system;
the first monitoring system collects the original data of the charging system, processes the original data and sends the processed data to the central monitoring server;
the second monitoring system collects the original data of the monitoring system, processes the original data and sends the processed data to the central monitoring server;
the third monitoring system collects the original data of the network safety system, processes the original data and sends the processed data to the central monitoring server;
the central monitoring server determines the comprehensive health condition of the charging system, the monitoring system and the network security system based on the received and processed data of the charging system, the monitoring system and the network security system;
the highway is divided into a plurality of sections according to the length, each section is provided with a first monitoring system, a second monitoring system and a third monitoring system, and the first monitoring system, the second monitoring system and the third monitoring system are respectively connected with a charging system, a monitoring system and a network safety system of the section;
the first monitoring system comprises first edge computing equipment, first structured data acquisition equipment and first log analysis equipment, original data of the charging system comprises transaction data, system performance data, equipment state data, system setting parameters and system log data, the first log analysis equipment carries out structured processing on the transaction data, the system performance data, the equipment state data, the system setting parameters and the system log data to obtain structured data of the charging system, and the first structured data acquisition equipment acquires the structured data of the charging system from the first log analysis equipment and then sends the structured data of the charging system to the first edge computing equipment through first heartbeat data to carry out primary screening, collection and analysis and then sends the data to a central monitoring server;
the second monitoring system comprises second edge computing equipment, second structured data acquisition equipment and an image AI diagnosis system, wherein the original data of the monitoring system comprises video image data, equipment state data, system setting parameters and system log data, the image AI diagnosis system judges the sharpness value of a fixed line in an image by using an AI algorithm, judges whether the comprehensive sharpness value of the image reaches a threshold value, judges whether the video quality reaches the standard, and generates monitoring system structured data by the result of whether the video quality reaches the standard, the equipment state data, the system setting parameters and the system log data, and the second structured data acquisition equipment acquires the monitoring system structured data from the image AI diagnosis system, and then sends the monitoring system structured data to the second edge computing equipment for preliminary screening, collection and analysis and then sends the data to a central monitoring server;
the third monitoring system comprises third edge computing equipment, third structured data acquisition equipment and third log analysis equipment, wherein the original data of the network security system comprises security threat event data, network state data, equipment state data and system log data, the third log analysis equipment carries out structured processing on the security threat event data, the network state data, the equipment state data and the system log data to obtain network security system structured data, and the third structured data acquisition equipment acquires the network security system structured data from the third log analysis equipment, then sends the network security system structured data to the third edge computing equipment through third heartbeat data, carries out preliminary screening, collection and analysis and then sends the network security system structured data to a central monitoring server;
wherein, the first edge computing device adopts an interval estimation early warning method to carry out structured data of the charging system, and the third edge computing device adopts an interval estimation early warning method to carry out preliminary screening, collection and analysis of the structured data of the network safety system and then only sends abnormal data to the central monitoring server,
wherein the image AI diagnostic system performs the operations of: extracting the gray value of an image shot by a monitoring camera; calculating the average gray value of the image:
Figure 850820DEST_PATH_IMAGE001
wherein x and y are coordinate values of pixel points in the picture, and f (x, y) is a gray value of the pixel point (x, y); the variance of the mean gray value of the image is calculated by using a variance method:
Figure 308346DEST_PATH_IMAGE002
(ii) a Sampling a video static environment, collecting gray value variances under different external environments to determine variance threshold values t under different external environments, and simultaneously accessing weather sensingAutomatically adapting and monitoring a variance threshold t under an external environment during illuminance data of the device; because the variance of the gray value is increased by the dynamic factors of the vehicle, the system carries out snapshot for multiple times and takes the minimum value
Figure 122718DEST_PATH_IMAGE003
When is coming into contact with
Figure 945181DEST_PATH_IMAGE004
Or when the environmental parameters do not change obviously but the gray value variance ring ratio is reduced obviously, namely: when the minimum gray value variance at the current moment is less than 80% of the minimum gray value variance at the previous moment, early warning is carried out, wherein k is a dynamic environment influence parameter and is determined by sampling, namely: k is equal to the minimum gray variance in the dynamic environment divided by the minimum gray variance in the static environment;
the method for determining the comprehensive health condition of the charging system, the monitoring system and the network security system by the central monitoring server based on the received and processed data of the charging system, the monitoring system and the network security system is as follows:
calculating the comprehensive health status value by adopting an optimized factor analysis method:
Figure 212214DEST_PATH_IMAGE005
wherein, w 1 、w 2 、w 2 Factor weights, f, for charging system, monitoring system and network security system, respectively 1 、f 2 、f 3 Actual failure rates of the charging system, the monitoring system and the network security system respectively, m is the total number of actual failures related to each factor, k 1 、k 2 、k 3 Are respectively and 1 、f 2 、f 3 the number of actual failures associated.
2. The system of claim 1, wherein the central monitoring server is a cloud server.
3. An electromechanical monitoring method based on the electromechanical monitoring system for the highway according to claim 1, characterized in that the method comprises:
a charging system acquisition step, wherein the first monitoring system acquires original data of the charging system, processes the original data and sends the processed data to the central monitoring server;
a monitoring system acquisition step, wherein the second monitoring system acquires original data of the monitoring system, processes the original data and sends the processed original data to the central monitoring server;
a network security system acquisition step, wherein the third monitoring system acquires original data of the network security system, processes the original data and sends the processed data to the central monitoring server;
and processing, namely determining the comprehensive health conditions of the charging system, the monitoring system and the network security system by the central monitoring server based on the received and processed data of the charging system, the monitoring system and the network security system.
4. The method of claim 3, wherein in the step of processing, the f 1 、f 2 、f 3 And the data are calculated by the central monitoring server based on the received abnormal data in the structured data of the charging system, the structured data of the monitoring system and the structured data of the network security system.
5. The method of claim 4, wherein the central monitoring server is a cloud server.
CN202210807874.2A 2022-07-11 2022-07-11 Highway electromechanical monitoring system and method Active CN115017014B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210807874.2A CN115017014B (en) 2022-07-11 2022-07-11 Highway electromechanical monitoring system and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210807874.2A CN115017014B (en) 2022-07-11 2022-07-11 Highway electromechanical monitoring system and method

Publications (2)

Publication Number Publication Date
CN115017014A CN115017014A (en) 2022-09-06
CN115017014B true CN115017014B (en) 2023-03-24

Family

ID=83080412

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210807874.2A Active CN115017014B (en) 2022-07-11 2022-07-11 Highway electromechanical monitoring system and method

Country Status (1)

Country Link
CN (1) CN115017014B (en)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113409179A (en) * 2021-01-26 2021-09-17 陕西交通电子工程科技有限公司 ETC portal operation state monitoring system for expressway

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111726252A (en) * 2020-06-17 2020-09-29 浪潮集团有限公司 Abnormal data reporting method and tool for industrial equipment
CN111901573A (en) * 2020-08-17 2020-11-06 泽达易盛(天津)科技股份有限公司 Fine granularity real-time supervision system based on edge calculation
CN114462897B (en) * 2022-04-12 2022-07-08 广东利通科技投资有限公司 Comprehensive performance evaluation method and device for highway electromechanical system and storage medium

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113409179A (en) * 2021-01-26 2021-09-17 陕西交通电子工程科技有限公司 ETC portal operation state monitoring system for expressway

Also Published As

Publication number Publication date
CN115017014A (en) 2022-09-06

Similar Documents

Publication Publication Date Title
CN107222780B (en) Method for comprehensive state perception and real-time content supervision of live broadcast platform
CN110084165B (en) Intelligent identification and early warning method for abnormal events in open scene of power field based on edge calculation
CN105788269A (en) Unmanned aerial vehicle-based abnormal traffic identification method
CN110912737A (en) Dynamic perception performance early warning method based on hybrid model
CN113269042B (en) Intelligent traffic management method and system based on driving vehicle violation identification
CN114781510A (en) Fault positioning method, device, system and storage medium
CN113221759A (en) Road scattering identification method and device based on anomaly detection model
CN115017014B (en) Highway electromechanical monitoring system and method
CN113032239A (en) Risk prompting method and device, electronic equipment and storage medium
CN110543827B (en) Multi-class vehicle detection method based on Gaussian mixture model and deep learning
CN116563809A (en) Road disease identification method and device, electronic equipment and storage medium
CN112261402B (en) Image detection method and system and camera shielding monitoring method and system
CN111553408B (en) Automatic test method for video recognition software
CN111258788B (en) Disk failure prediction method, device and computer readable storage medium
CN115408182A (en) Service system fault positioning method and device
CN111555917A (en) Alarm information processing method and device based on cloud platform
CN111209789A (en) Method for carrying out image acquisition and analysis on key item point occurrence moment
CN117437765B (en) Accident alarm method and system based on big data driving records
CN115830806A (en) Natural disaster condition analysis system based on high-resolution remote sensing
CN117523299B (en) Image recognition method, system and storage medium based on computer network
CN117354495B (en) Video monitoring quality diagnosis method and system based on deep learning
CN104168473B (en) A kind of detection method of shear wave interference of video image and device
CN112346985B (en) ACC function failure determination method, system, device and storage medium
CN117527523A (en) Cloud computing-based server security monitoring system
CN118230138A (en) Intelligent optimization method for network appointment vehicle image recognition system

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