CN117975713A - Intelligent traffic guiding management system for industrial upstairs - Google Patents
Intelligent traffic guiding management system for industrial upstairs Download PDFInfo
- Publication number
- CN117975713A CN117975713A CN202311759963.5A CN202311759963A CN117975713A CN 117975713 A CN117975713 A CN 117975713A CN 202311759963 A CN202311759963 A CN 202311759963A CN 117975713 A CN117975713 A CN 117975713A
- Authority
- CN
- China
- Prior art keywords
- module
- data
- sub
- traffic
- submodule
- 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
- 238000005457 optimization Methods 0.000 claims abstract description 94
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 82
- 238000013439 planning Methods 0.000 claims abstract description 66
- 238000012544 monitoring process Methods 0.000 claims abstract description 63
- 238000012545 processing Methods 0.000 claims abstract description 54
- 238000004891 communication Methods 0.000 claims abstract description 48
- 238000007726 management method Methods 0.000 claims abstract description 36
- 230000002265 prevention Effects 0.000 claims abstract description 27
- 238000000605 extraction Methods 0.000 claims abstract description 25
- 230000003993 interaction Effects 0.000 claims abstract description 23
- 238000007781 pre-processing Methods 0.000 claims abstract description 20
- 230000006855 networking Effects 0.000 claims abstract description 17
- 101001093748 Homo sapiens Phosphatidylinositol N-acetylglucosaminyltransferase subunit P Proteins 0.000 claims abstract description 15
- 230000002068 genetic effect Effects 0.000 claims abstract description 11
- 238000002922 simulated annealing Methods 0.000 claims abstract description 11
- 238000013135 deep learning Methods 0.000 claims abstract description 10
- 230000002787 reinforcement Effects 0.000 claims abstract description 7
- 230000008447 perception Effects 0.000 claims abstract 3
- 238000005516 engineering process Methods 0.000 claims description 31
- 238000004458 analytical method Methods 0.000 claims description 29
- 238000004364 calculation method Methods 0.000 claims description 29
- 238000013461 design Methods 0.000 claims description 27
- 230000004927 fusion Effects 0.000 claims description 27
- 230000002452 interceptive effect Effects 0.000 claims description 25
- 238000011084 recovery Methods 0.000 claims description 25
- 238000000034 method Methods 0.000 claims description 24
- 230000004044 response Effects 0.000 claims description 23
- 230000006870 function Effects 0.000 claims description 22
- 238000001514 detection method Methods 0.000 claims description 20
- 238000011217 control strategy Methods 0.000 claims description 19
- 230000003449 preventive effect Effects 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 14
- 238000013500 data storage Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 12
- 206010039203 Road traffic accident Diseases 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 10
- 238000004140 cleaning Methods 0.000 claims description 9
- 238000011161 development Methods 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 8
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 230000009471 action Effects 0.000 claims description 6
- 238000013079 data visualisation Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 6
- 206010000117 Abnormal behaviour Diseases 0.000 claims description 5
- 238000003066 decision tree Methods 0.000 claims description 5
- 238000010801 machine learning Methods 0.000 claims description 5
- 230000007246 mechanism Effects 0.000 claims description 5
- 238000013523 data management Methods 0.000 claims description 4
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 230000008451 emotion Effects 0.000 claims description 4
- 238000005265 energy consumption Methods 0.000 claims description 4
- 230000006872 improvement Effects 0.000 claims description 4
- 238000007637 random forest analysis Methods 0.000 claims description 4
- 238000012502 risk assessment Methods 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 238000013526 transfer learning Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 4
- 230000002829 reductive effect Effects 0.000 abstract description 4
- 230000018109 developmental process Effects 0.000 description 6
- 230000007613 environmental effect Effects 0.000 description 6
- 230000006399 behavior Effects 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 238000013480 data collection Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010223 real-time analysis Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002996 emotional effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/012—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from other sources than vehicle or roadside beacons, e.g. mobile networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/092—Reinforcement learning
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/096805—Systems involving transmission of navigation instructions to the vehicle where the transmitted instructions are used to compute a route
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/096833—Systems involving transmission of navigation instructions to the vehicle where different aspects are considered when computing the route
-
- Y—GENERAL 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Physiology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of intelligent traffic systems, in particular to an industrial upstairs intelligent traffic guiding management system which comprises a data acquisition module, a data processing module, a self-adaptive traffic signal control module, a vehicle networking optimization module, an intelligent scheduling path planning module, an environment perception module, an accident prevention module and a user interaction module. In the invention, traffic data is efficiently collected by using a traffic flow detector and a monitoring camera, the accuracy and the efficiency of data processing are improved by deep learning preprocessing and feature extraction, the refinement of traffic management is realized by a self-adaptive signal control module of deep reinforcement learning, the congestion is reduced, the traffic communication is promoted by a vehicle networking module by adopting DSRC or LTE-V2X, the route optimization is improved, the freight dispatching and the route planning are improved by an intelligent dispatching path planning module by combining a genetic algorithm and simulated annealing, and the accident rate is reduced by integrating a laser radar and an infrared camera by an environment perception and accident prevention module.
Description
Technical Field
The invention relates to the technical field of intelligent traffic systems, in particular to an intelligent traffic guiding management system for industrial upstairs.
Background
The intelligent traffic system is a traffic management system which comprehensively applies information technology, communication technology and control technology. The method aims at improving the transportation efficiency, reducing the traffic jam, improving the safety and providing a more convenient trip mode through real-time data acquisition, analysis and control. This field encompasses a wide range of traffic management and control technologies including intelligent traffic lights, intelligent public transportation, traffic monitoring and management systems, and the like.
An industrial building intelligent traffic dispersion management system is a specific application of an intelligent traffic system, and is focused on managing and dispersion of traffic flow in industrial areas, including vehicles and pedestrians. Such systems typically include sensors, cameras, real-time data analysis, intelligent signaling lights, and traffic control centers to coordinate and optimize traffic flow within an industrial area. This may include factories, warehouses, logistics centers, etc. where internal traffic flows need to be managed and optimized to ensure the efficiency of logistics operations. The system aims to improve the smoothness, safety and efficiency of traffic in an industrial area by means of sensors, monitoring equipment, real-time data analysis, intelligent signal control, communication technology and the like. The system can achieve the aims of reducing traffic jam, improving safety and efficiency, improving internal traffic flow and ensuring high efficiency of logistics operation through real-time monitoring, intelligent decision support and communication technology.
The existing intelligent traffic guiding management system has the defects in the aspects of data processing efficiency, accuracy and system intelligent degree. The traditional system does not fully utilize the internet of things technology, so that data collection is not real-time and comprehensive enough, and the real-time response capability of traffic management is affected. Existing systems rely on simpler algorithms for data processing, lack advanced analytical capabilities for deep learning and reinforcement learning, and are thus not accurate enough in prediction accuracy and signal optimization. In addition, traditional internet of vehicles communication technologies do not fully exploit their potential for optimizing routes and scheduling instructions. Environmental awareness and accident prevention measures fail to effectively predict and prevent potential risks in conventional systems, which increases the incidence of traffic accidents. Finally, the user interface design fails to fully consider the user experience, which results in insufficient user feedback and system update, and affects the overall use efficiency and user satisfaction of the system.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides an industrial upstairs intelligent traffic guiding management system.
In order to achieve the above purpose, the present invention adopts the following technical scheme: the intelligent traffic guiding management system for the industrial upstairs comprises a data acquisition module, a data processing module, a self-adaptive traffic signal control module, a vehicle networking optimization module, an intelligent scheduling path planning module, an environment sensing module, an accident prevention module and a user interaction module;
The data acquisition module is used for collecting road traffic data based on a traffic flow detector and a monitoring camera by adopting the internet of things technology and integrating the road traffic data into a real-time traffic data set;
the data processing module performs data preprocessing and feature extraction by using a deep learning algorithm based on a real-time traffic data set to generate processed traffic data;
the self-adaptive traffic signal control module adopts a deep reinforcement learning algorithm to carry out self-adaptive control on signals based on the processed traffic data, and generates a real-time signal control strategy;
The vehicle networking optimization module is used for carrying out data exchange and edge calculation by utilizing a vehicle-mounted communication system DSRC or LTE-V2X based on the processed traffic data to generate a route optimization scheme;
The intelligent scheduling path planning module performs optimal path planning and freight scheduling by adopting a genetic algorithm and a simulated annealing algorithm based on cargo attributes, vehicle positions and a route optimization scheme, and generates scheduling instructions and path planning results;
The environment sensing module is used for carrying out environment monitoring by utilizing laser radar and infrared camera equipment based on the processed traffic data and predicting abnormal behaviors or potential risks in the traffic environment to generate a risk early warning report;
the accident prevention module responds to the predicted occurrence risk by utilizing an automatic alarm system and a preventive control technology based on the risk early warning report to generate accident prevention measures;
The user interaction module designs and builds a user-friendly interface based on the scheduling instruction, the path planning result and the accident prevention measure, and generates a user interaction interface;
The real-time traffic data set comprises traffic flow, vehicle running speed, vehicle type and road condition, the real-time signal control strategy comprises a multi-intersection signal lamp on and off time sequence, the route optimization scheme comprises a running route, predicted running time and predicted traffic condition, the risk early warning report is specifically a predicted condition and countermeasure scheme for predicted traffic accidents and risks, and the accident prevention measures comprise alarm information and preventive control instructions.
As a further aspect of the invention: the data acquisition module comprises a video monitoring sub-module, a traffic flow detection sub-module, a V2X communication sub-module, an environment sensing sub-module and a database sub-module;
the data processing module comprises a data preprocessing sub-module, a data classifying sub-module, a data normalizing sub-module, a characteristic extracting sub-module and a data storing sub-module;
The self-adaptive traffic signal control module comprises a DRL training sub-module, a strategy selection sub-module, a signal control sub-module, a feedback learning sub-module and an optimization adjustment sub-module;
The vehicle networking optimization module comprises a vehicle-mounted communication sub-module, a data fusion sub-module, an edge calculation sub-module, a driving path optimization sub-module and an emergency response sub-module;
The intelligent scheduling path planning module comprises a path calculation sub-module, a freight scheduling sub-module, a multi-objective optimization sub-module, a path planning engine sub-module and a user interface sub-module;
the environment sensing module comprises a sensor data acquisition sub-module, a sensor data processing sub-module, an environment monitoring sub-module, a risk prediction sub-module and a risk reporting sub-module;
The accident prevention module comprises a risk identification sub-module, a system warning sub-module, a control intervention sub-module, a system backup sub-module and a system recovery sub-module;
the user interaction module comprises a data display sub-module, an interaction operation sub-module, an interface design sub-module, a user feedback sub-module and a system updating sub-module.
As a further aspect of the invention: the video monitoring submodule carries out real-time video stream analysis and vehicle identification by adopting a target detection algorithm, specifically a YOLO or SSD, based on a monitoring camera to generate a video monitoring data set;
the traffic flow detection sub-module is used for counting vehicles by adopting a lane line crossing detection method based on the video monitoring data set and comparing the vehicles with historical data to generate a traffic flow information data set;
the V2X communication sub-module is based on vehicle-mounted equipment and infrastructure, adopts a vehicle networking communication protocol specifically DSRC or C-V2X to exchange data, and is fused with a vehicle flow information data set to generate a V2X communication data set;
The environment sensing submodule is used for analyzing weather and road conditions based on an environment sensor by adopting Kalman filtering, integrating the weather and road conditions with a V2X communication data set and generating an environment sensing data set;
The database submodule adopts a MySQL database management system to perform data storage optimization based on the environment-aware data set, and performs query efficiency improvement to generate a comprehensive traffic database.
As a further aspect of the invention: the data preprocessing sub-module is used for filtering noise data by adopting a data cleaning algorithm comprising missing value processing and outlier removing based on the comprehensive traffic database, and unifying data formats to generate a preprocessed traffic data set;
the data classification submodule classifies data labels by adopting a support vector machine or a random forest based on the preprocessed traffic data set, evaluates the results and generates a classified traffic data set;
the data normalization submodule carries out characteristic scale adjustment by adopting a Z score or a minimum-maximum normalization algorithm based on the classified traffic data set, and carries out data equalization to generate a normalized traffic data set;
The feature extraction submodule is used for extracting key features based on the normalized traffic data set by adopting a feature layer of a convolutional neural network and performing feature optimization to generate a traffic data set after feature extraction;
and the data storage submodule adopts a NoSQL database to carry out large data storage management based on the traffic data set after feature extraction, and carries out data backup and recovery to generate a traffic data feature database.
As a further aspect of the invention: the DRL training submodule adopts a deep Q network or strategy gradient method to train a signal control strategy and optimize a model based on the processed traffic data, and generates a signal control decision model;
the strategy selection submodule adopts epsilon-greedy strategy to select signal strategies and analyze traffic flow adaptability based on the signal control decision model, and generates a signal strategy data set;
The signal control sub-module adopts a real-time dynamic control algorithm to adjust traffic signals in real time based on the signal strategy data set, and generates a real-time traffic signal control scheme;
the feedback learning submodule carries out real-time feedback and model updating by adopting an incremental learning algorithm based on a real-time traffic signal control scheme to generate a signal control model after feedback optimization;
and the optimization and adjustment submodule performs performance optimization and adjustment by adopting transfer learning or meta learning based on the signal control model after feedback optimization to generate an optimized and adjusted signal control strategy.
As a further aspect of the invention: the vehicle-mounted communication submodule is used for collecting and exchanging data by adopting a DSRC or LTE-V2X vehicle-mounted communication system based on the processed traffic data to generate a vehicle-mounted data exchange data set;
The data fusion submodule is used for carrying out data integration analysis by adopting a multi-source data fusion technology based on the vehicle-mounted data exchange data set to generate a data fusion analysis data set;
The edge computing sub-module analyzes the data set based on data fusion, adopts an edge computing framework to rapidly process the data, and generates an edge computing processing data set;
The driving path optimization sub-module is used for planning and optimizing a route by adopting a Dijkstra algorithm or an A-type algorithm based on an edge calculation processing data set to generate an optimized driving path scheme;
the emergency response submodule is used for adjusting and commanding a route under an emergency condition based on an optimized driving path scheme and a response mechanism and generating an emergency response scheduling scheme.
As a further aspect of the invention: the path calculation submodule performs path searching by adopting a genetic algorithm based on cargo attributes, vehicle positions and a route initial scheme, evaluates the path and generates a preliminary path calculation result;
the freight dispatching sub-module adopts a simulated annealing algorithm to optimally dispatch the matching of the vehicle and the freight based on the preliminary path calculation result, and generates a freight dispatching scheme;
The multi-objective optimization submodule generates an optimized dispatching path scheme by adopting a multi-objective optimization technology and referring to cost, time and energy consumption based on a freight dispatching scheme;
the path planning engine submodule adjusts path selection based on the optimized scheduling path scheme by using algorithms such as dynamic planning and the like to generate a final path planning result;
and the user interface sub-module adopts an interactive interface design based on the final path planning result, displays the path and the scheduling information, and generates a scheduling instruction and a path planning result.
As a further aspect of the invention: the sensor data acquisition submodule performs environment scanning by using a laser radar and an infrared camera, collects original data and generates an original sensor data set;
The sensor data processing sub-module performs data preprocessing by adopting a data cleaning and feature extraction algorithm based on an original sensor data set to generate processed sensor data;
The environment monitoring submodule carries out real-time environment monitoring by adopting a computer vision and machine learning method based on the processed sensor data to generate an environment monitoring report;
the risk prediction sub-module is used for predicting traffic risk by adopting a deep learning method based on the environment monitoring report, and generating a risk prediction result;
and the risk report sub-module generates a risk early warning report by adopting a risk analysis and evaluation method based on a risk prediction result.
As a further aspect of the invention: the risk identification sub-module is used for carrying out risk factor decomposition by adopting a decision tree analysis method based on the risk early warning report, carrying out risk grade assessment and generating a potential risk identification result;
The system warning submodule monitors abnormal modes by adopting a real-time monitoring algorithm based on the potential risk identification result, outputs early warning signals and generates an early warning signal triggering result;
the control intervention submodule adopts PID control logic to calculate risk response action based on the early warning signal triggering result, and issues a control command to generate preventive control measures;
the system backup submodule adopts a redundant data management strategy to backup key data based on preventive control measures, updates the system backup state and generates backup information;
The system recovery submodule adopts a state recovery technology to reconstruct system functions based on backup information and performs fault state coverage to generate a system recovery scheme.
As a further aspect of the invention: the data display submodule performs information integration display by adopting a data fusion technology based on a scheduling instruction, a path planning result and a system recovery scheme, and performs interactivity enhancement to generate a data visualization interface;
The interactive operation submodule carries out function option design by adopting a touch interactive design principle based on a data visual interface, and carries out user input processing to generate an interactive operation function;
the interface design submodule performs interface layout optimization by adopting a user experience optimization strategy based on the interactive operation function, performs interactive logic upgrading, and generates an optimized user interface;
the user feedback submodule analyzes user satisfaction degree by adopting an emotion analysis algorithm based on the optimized user interface, integrates feedback content and generates a user feedback report;
and the system updating submodule adopts an agile development framework to carry out functional iterative development based on a user feedback report, and carries out system performance optimization to generate a system upgrading scheme.
Compared with the prior art, the invention has the advantages and positive effects that:
In the invention, road traffic data is efficiently collected by using the traffic flow detector and the monitoring camera, and data preprocessing and feature extraction are performed by using deep learning, so that the accuracy and the efficiency of data processing are improved. The self-adaptive traffic signal control module adopts a deep reinforcement learning algorithm to optimize signal control, thereby realizing more refined traffic management and reducing traffic jam. The vehicle networking optimization module enhances communication and data sharing between vehicles through DSRC or LTE-V2X technology, and improves the efficiency of route optimization. The intelligent dispatching path planning module combines a genetic algorithm and a simulated annealing algorithm, so that the accuracy of freight dispatching and the optimization degree of route planning are effectively improved. The environment sensing module and the accident prevention module jointly use sensor equipment such as a laser radar, an infrared camera and the like, so that the prediction and prevention capability of potential risks is enhanced, and the traffic accident rate is effectively reduced. And finally, the friendly interface design of the user interaction module provides better interaction experience and information feedback channels for users, and the usability and acceptance of the system are further improved.
Drawings
FIG. 1 is a system flow diagram of the present invention;
FIG. 2 is a schematic diagram of a system framework of the present invention;
FIG. 3 is a flow chart of a data acquisition module according to the present invention;
FIG. 4 is a flow chart of a data processing module of the present invention;
FIG. 5 is a flow chart of an adaptive traffic signal control module of the present invention;
FIG. 6 is a flow chart of the Internet of vehicles optimization module of the present invention;
FIG. 7 is a flow chart of the intelligent scheduling path planning module of the present invention;
FIG. 8 is a flow chart of an environment awareness module according to the present invention;
FIG. 9 is a flow chart of an accident prevention module of the present invention;
Fig. 10 is a flowchart of a user interaction module according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In the description of the present invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientation or positional relationships shown in the drawings, merely to facilitate describing the present invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention. Furthermore, in the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Example 1
Referring to fig. 1, the industrial building intelligent traffic guiding management system includes a data acquisition module, a data processing module, a self-adaptive traffic signal control module, a car networking optimization module, an intelligent scheduling path planning module, an environment sensing module, an accident prevention module and a user interaction module;
The data acquisition module is used for collecting road traffic data based on a traffic flow detector and a monitoring camera by adopting the internet of things technology and integrating the road traffic data into a real-time traffic data set;
the data processing module performs data preprocessing and feature extraction by using a deep learning algorithm based on the real-time traffic data set to generate processed traffic data;
the self-adaptive traffic signal control module adopts a deep reinforcement learning algorithm to carry out self-adaptive control on signals based on the processed traffic data, and generates a real-time signal control strategy;
The vehicle networking optimization module is used for carrying out data exchange and edge calculation by utilizing a vehicle-mounted communication system DSRC or LTE-V2X based on the processed traffic data, and generating a route optimization scheme;
the intelligent dispatching path planning module performs optimal path planning and freight dispatching by adopting a genetic algorithm and a simulated annealing algorithm based on cargo attributes, vehicle positions and a route optimization scheme, and generates dispatching instructions and path planning results;
the environment sensing module is used for carrying out environment monitoring by utilizing laser radar and infrared camera equipment based on the processed traffic data and predicting abnormal behaviors or potential risks in the traffic environment to generate a risk early warning report;
The accident prevention module responds to the predicted occurrence risk by utilizing an automatic alarm system and a preventive control technology based on the risk early warning report to generate accident prevention measures;
The user interaction module designs and builds a user-friendly interface based on the scheduling instruction, the path planning result and the accident prevention measure, and generates a user interaction interface;
The real-time traffic data set comprises traffic flow, vehicle running speed, vehicle type and road condition, the real-time signal control strategy comprises the starting and closing time sequence of the multi-intersection signal lamp, the route optimization scheme comprises a running route, predicted running time and predicted traffic condition, the risk early warning report is specifically a predicted condition and countermeasure scheme for predicted traffic accidents and risks, and the accident precaution measure comprises alarm information and precaution control instructions.
Through the data acquisition module and the Internet of vehicles optimization module, the system can collect road traffic data in real time and analyze the road traffic data, so that an optimal route planning and signal control strategy are generated. This helps to reduce traffic congestion and queuing time, improve vehicle travel speed and road utilization, and further improve overall traffic efficiency.
The environment sensing module predicts abnormal behaviors or potential risks in the traffic environment by using laser radar and infrared camera equipment, and generates a risk early warning report. The accident prevention module takes corresponding preventive measures, such as an automatic alarm system and a preventive control technology, according to the risk early warning report. The measures can timely warn drivers and pedestrians, reduce the occurrence probability of traffic accidents and guarantee traffic safety.
And the intelligent scheduling path planning module adopts a genetic algorithm and a simulated annealing algorithm to carry out optimal path planning and freight scheduling based on the cargo attributes, the vehicle positions and the route optimization scheme. This helps reducing the empty rate and the travel distance of the truck, improving the cargo transportation efficiency, and reducing the logistics cost.
The user interaction module designs and builds a user-friendly interface, so that a user can conveniently check the scheduling instruction, the path planning result and the accident prevention measures. This improves the user experience and enhances the operability and practicality of the system.
Referring to fig. 2, the data acquisition module includes a video monitoring sub-module, a traffic flow detection sub-module, a V2X communication sub-module, an environment sensing sub-module, and a database sub-module;
The data processing module comprises a data preprocessing sub-module, a data classifying sub-module, a data normalizing sub-module, a characteristic extracting sub-module and a data storing sub-module;
the self-adaptive traffic signal control module comprises a DRL training sub-module, a strategy selection sub-module, a signal control sub-module, a feedback learning sub-module and an optimization adjustment sub-module;
The vehicle networking optimization module comprises a vehicle-mounted communication sub-module, a data fusion sub-module, an edge calculation sub-module, a driving path optimization sub-module and an emergency response sub-module;
the intelligent scheduling path planning module comprises a path calculation sub-module, a freight scheduling sub-module, a multi-objective optimization sub-module, a path planning engine sub-module and a user interface sub-module;
the environment sensing module comprises a sensor data acquisition sub-module, a sensor data processing sub-module, an environment monitoring sub-module, a risk prediction sub-module and a risk reporting sub-module;
The accident prevention module comprises a risk identification sub-module, a system warning sub-module, a control intervention sub-module, a system backup sub-module and a system recovery sub-module;
The user interaction module comprises a data display sub-module, an interaction operation sub-module, an interface design sub-module, a user feedback sub-module and a system updating sub-module.
In the data acquisition module, the video monitoring sub-module is responsible for collecting road traffic data through the monitoring camera, the traffic flow detection sub-module obtains real-time traffic flow data through the traffic flow detector, the V2X communication sub-module exchanges data through the vehicle-mounted communication system DSRC or LTE-V2X, the environment sensing sub-module uses the laser radar and the infrared camera equipment to conduct environment monitoring, and the database sub-module integrates the real-time traffic data set.
And in the data processing module, the data preprocessing sub-module performs data cleaning and preprocessing on the real-time traffic data set, the data classification sub-module performs classification processing according to the attribute of the traffic data, the data normalization sub-module converts the data with different scales into a unified standard, the feature extraction sub-module extracts key features from the processed traffic data, and the data storage sub-module stores the processed traffic data into a database.
In the self-adaptive traffic signal control module, a DRL training sub-module trains a signal control model by using a deep reinforcement learning algorithm, a strategy selection sub-module selects an optimal signal control strategy according to real-time traffic data, the signal control sub-module controls the opening and closing time sequence of the signal lamps of the multiple intersections according to the selected strategy, and a feedback learning sub-module performs feedback learning and optimization adjustment on the signal control strategy according to the actual effect.
In the vehicle networking optimization module, a vehicle-mounted communication sub-module performs data exchange and edge calculation by using a vehicle-mounted communication system DSRC or LTE-V2X, a data fusion sub-module fuses information such as vehicle position, running speed and the like with traffic data, an edge calculation sub-module performs real-time data processing and decision making on the edge of the vehicle, a running path optimization sub-module generates an optimal running route according to vehicle attributes and road conditions, and an emergency response sub-module responds and dispatches emergency situations such as traffic accidents and the like.
In the intelligent dispatching path planning module, a path calculation submodule calculates an optimal path according to the goods attribute, the vehicle position and the route optimization scheme, a goods dispatching submodule carries out goods dispatching and path planning according to the optimal path and the vehicle state, a multi-target optimization submodule considers a plurality of targets such as predicted running time, predicted traffic conditions and the like to carry out path planning and dispatching optimization, a path planning engine submodule realizes optimization algorithms such as a genetic algorithm, a simulated annealing algorithm and the like to generate an optimal path planning result, and a user interface submodule designs and constructs a user-friendly interface to display dispatching instructions and path planning results.
In the environment sensing module, a sensor data acquisition sub-module acquires sensor data by using a laser radar and an infrared camera device, a sensor data processing sub-module processes and analyzes the sensor data, environment information is extracted, an environment monitoring sub-module monitors abnormal behaviors or potential risks in a traffic environment, a risk prediction sub-module predicts occurrence probability of traffic accidents and risks based on the processed traffic data, and a risk reporting sub-module generates a detailed risk early warning report.
In the accident prevention module, the risk identification submodule identifies potential traffic accidents and risks according to the risk early warning report, the system warning submodule utilizes the automatic warning system to send warning information, the intervention submodule is controlled to take corresponding control measures to prevent accidents, the system backup submodule periodically backs up system data to prevent data loss, and the system recovery submodule recovers normal operation of the system after faults or accidents occur.
In the user interaction module, the data display sub-module displays the scheduling instruction, the path planning result and the accident prevention measure to the user in a visual mode, the interactive operation sub-module provides an operation interface for the user to interact with the system, the interface design sub-module designs a user-friendly interface layout and interaction mode, the user feedback sub-module receives feedback comments and suggestions of the user, and the system updating sub-module periodically updates system software to improve performance and functions.
Referring to fig. 3, the video monitoring sub-module performs real-time video stream analysis and vehicle identification by using a target detection algorithm, specifically YOLO or SSD, based on a monitoring camera to generate a video monitoring data set;
The traffic flow detection sub-module is used for counting vehicles by adopting a lane crossing detection method based on the video monitoring data set and comparing the vehicles with historical data to generate a traffic flow information data set;
The V2X communication sub-module is based on vehicle-mounted equipment and infrastructure, adopts a vehicle networking communication protocol specifically DSRC or C-V2X to exchange data, and is fused with a vehicle flow information data set to generate a V2X communication data set;
The environment sensing submodule is used for analyzing weather and road conditions based on an environment sensor by adopting Kalman filtering, integrating the weather and road conditions with the V2X communication data set and generating an environment sensing data set;
the database submodule adopts a MySQL database management system to optimize data storage based on the environment-aware data set and improves query efficiency to generate a comprehensive traffic database.
The video monitoring sub-module is based on a monitoring camera, and a YOLO or SSD destination detection algorithm is adopted to conduct real-time video stream analysis and vehicle identification. And preprocessing the video stream acquired by the monitoring camera, including operations such as image enhancement and denoising. And inputting the preprocessed video stream into a target detection algorithm, carrying out vehicle identification on each frame of image through a trained model, and generating a video monitoring data set.
The traffic flow detection sub-module is used for counting vehicles by adopting a lane line crossing detection method based on the video monitoring data set and comparing the traffic flow detection sub-module with historical data to generate a traffic flow information data set. And extracting the position information of the vehicles from the video monitoring data set, and determining the lane where each vehicle is positioned through a lane line detection algorithm. And counting the number of vehicles on each lane according to the positions of the lane lines and the position information of the vehicles. And comparing the statistical result with the historical data to generate a vehicle flow information data set.
The V2X communication sub-module is based on the vehicle-mounted equipment and the infrastructure, performs data exchange by adopting a DSRC or C-V2X vehicle networking communication protocol, and is fused with the vehicle flow information data set to generate a V2X communication data set. The connection is established through a communication interface between the vehicle-mounted device and the infrastructure. And sending the traffic flow information data set to other vehicles or traffic management centers to realize sharing and exchange of data. Data from other vehicles or traffic management centers is received and fused with the traffic flow information dataset.
The environment sensing submodule is based on an environment sensor, performs climate and road condition analysis by adopting Kalman filtering, and is integrated with the V2X communication data set to generate an environment sensing data set. Various environmental data, such as temperature, humidity, illumination intensity, etc., are collected by the environmental sensor. And processing and analyzing the environmental data by using a Kalman filtering algorithm to obtain accurate climate and road condition information. Integrating the processed environment data with the V2X communication data set to generate an environment sensing data set.
Based on the environment-aware data set, the database submodule adopts a MySQL database management system to conduct data storage optimization and query efficiency improvement, and a comprehensive traffic database is generated. Suitable database structures are designed to store the context-aware dataset and other relevant data. The MySQL database management system is used to store and manage data. In order to improve the query efficiency, operations such as index optimization, query optimization and the like can be performed on the database. And finally, using the optimized database as a comprehensive traffic database.
Referring to fig. 4, the data preprocessing sub-module performs noise data filtering and data format unification by adopting a data cleaning algorithm comprising missing value processing and outlier removal based on the comprehensive traffic database to generate a preprocessed traffic data set;
The data classification submodule classifies data labels by adopting a support vector machine or a random forest based on the preprocessed traffic data set, evaluates the results and generates a classified traffic data set;
The data normalization submodule carries out characteristic scale adjustment and data equalization by adopting a Z score or a minimum-maximum normalization algorithm based on the classified traffic data set to generate a normalized traffic data set;
the feature extraction submodule adopts a feature layer of a convolutional neural network to extract key features based on the normalized traffic data set, and performs feature optimization to generate a traffic data set after feature extraction;
the data storage submodule adopts a NoSQL database to carry out large data storage management based on the traffic data set after feature extraction, and carries out data backup and recovery to generate a traffic data feature database.
The data preprocessing sub-module is the first step in the overall process. Raw traffic data including vehicle speed, location, road conditions, etc. are obtained from a plurality of data sources. And carrying out missing value processing, outlier rejection and noise data filtering on the data through a data cleaning algorithm, so as to ensure the quality and accuracy of the data. And (3) unifying data formats, and ensuring that fields and structures of the data are consistent for subsequent processing. A preprocessed traffic data set is generated to provide a clean, consistent data base for subsequent operations.
The data classification sub-module builds on the data preprocessing. And extracting the characteristics, namely extracting key characteristics such as vehicle density, traffic flow and the like from the preprocessed data. And classifying the features by using a classification algorithm such as a support vector machine or a random forest, and marking the data with corresponding labels. Result evaluation is performed to ensure accuracy and performance of classification. A traffic data set containing classification labels is generated, providing for subsequent analysis and processing.
The data normalization submodule is based on the classified traffic data set. And adopting a Z score or a minimum-maximum standardization algorithm to scale the characteristics so as to ensure the consistent dimension of the data characteristics. And carrying out data equalization when needed so as to process unbalanced data distribution and ensure the accuracy of model training. A normalized traffic data set is generated, providing for feature extraction and modeling.
The feature extraction sub-module is a key step in the overall process. Based on the normalized traffic data set, a feature layer of a Convolutional Neural Network (CNN) is adopted to conduct key feature extraction, and key modes in traffic data, such as vehicle flow and congestion, are identified. After feature extraction, the extracted features are optimized to ensure their contribution and accuracy to the subsequent model. A set of traffic data characteristics is generated that includes CNN processing for modeling and analysis.
The data storage sub-module is responsible for effectively managing and storing the processed traffic data. The NoSQL database is used to store the feature extracted data therein for subsequent query and analysis. And establishing a data backup and recovery mechanism to ensure the safety of data. And constructing a traffic data feature library which contains various data after feature extraction and processing for subsequent traffic analysis and decision-making.
Referring to fig. 5, the drl training submodule performs training and model optimization of a signal control strategy by adopting a deep Q network or strategy gradient method based on the processed traffic data to generate a signal control decision model;
The strategy selection submodule carries out signal strategy selection and traffic flow adaptability analysis by adopting an epsilon-greedy strategy based on the signal control decision model to generate a signal strategy data set;
The signal control sub-module adopts a real-time dynamic control algorithm to adjust traffic signals in real time based on the signal strategy data set, and generates a real-time traffic signal control scheme;
the feedback learning submodule carries out real-time feedback and model updating by adopting an incremental learning algorithm based on a real-time traffic signal control scheme to generate a signal control model after feedback optimization;
The optimization and adjustment submodule performs performance optimization and adjustment by adopting transfer learning or meta learning based on the signal control model after feedback optimization, and generates a signal control strategy after optimization and adjustment.
In the whole system, the DRL training sub-module is responsible for training a signal control decision model. First, it receives processed traffic data including vehicle position, speed, road status, etc. These data will be used to train a deep Q network or a strategic gradient network model. Through continuous iteration, the sub-module will optimize the model to learn the optimal signal control strategy. The generated training model will be used for subsequent signal strategy selection and real-time control.
The policy selection submodule is based on a trained model. It uses an epsilon-greedy strategy to select a signal control strategy and evaluates the adaptability of the strategy by analyzing the current traffic flow situation. This process generates a signal policy dataset that includes performance evaluations of various signal policies and related traffic flow data.
The signal control sub-module adopts a real-time dynamic control algorithm to adjust traffic signals in real time based on the signal strategy data set and the real-time traffic data. According to the current traffic situation, it selects the optimal signal control strategy, including the adjustment of signal parameters such as green light time, red light time and yellow light time, etc. to generate a real-time traffic signal control scheme.
The feedback learning sub-module adopts an incremental learning algorithm to carry out real-time feedback based on an actual traffic signal control scheme and real-time traffic data. The decision model is controlled by continuously updating the signal to reflect the actual traffic conditions and performance. The process generates a feedback optimized signal control model so as to better adapt to the changed traffic condition.
The optimization and adjustment submodule performs performance optimization and adjustment by adopting a transfer learning or meta learning method based on the signal control model after feedback optimization. The migration learning can help the model adapt to a new traffic environment, and the meta learning can improve the adaptability and generalization of the model under different situations. Finally, the generated optimized and adjusted signal control strategy is used for actual traffic signal control.
Referring to fig. 6, the vehicle-mounted communication sub-module collects and exchanges data by using a DSRC or LTE-V2X vehicle-mounted communication system based on the processed traffic data, and generates a vehicle-mounted data exchange data set;
The data fusion submodule carries out data integration analysis by adopting a multi-source data fusion technology based on the vehicle-mounted data exchange data set to generate a data fusion analysis data set;
the edge computing sub-module analyzes the data set based on data fusion, adopts an edge computing framework to rapidly process the data, and generates an edge computing processing data set;
The driving path optimization sub-module is used for planning and optimizing a route by adopting a Dijkstra algorithm or an A-type algorithm based on an edge calculation processing data set to generate an optimized driving path scheme;
the emergency response submodule is used for adjusting and commanding a route under an emergency condition based on the optimized driving path scheme and the response mechanism, and generating an emergency response scheduling scheme.
The vehicle-mounted communication sub-module aims at establishing communication connection between vehicles and realizing data collection and exchange based on the processed traffic data. First, the system establishes communication with nearby vehicles using DSRC or LTE-V2X in-vehicle communication systems, requesting relevant data. Information about the position, speed and status of nearby vehicles is then collected and consolidated into an onboard data exchange data set for subsequent processing.
The data fusion submodule aims at integrating data from different vehicles and generating a data fusion analysis data set by using a multi-source data fusion technology. First, vehicle data is received from the in-vehicle communication sub-module, and data collection is performed. The data are then integrated into a unified data set using a multi-source data fusion technique. Finally, data analysis, including vehicle distribution, speed, road conditions, etc., is performed to generate a data fusion analysis dataset.
The edge computing submodule aims to analyze the data set based on data fusion, and the edge computing framework is utilized for rapidly processing the data to generate an edge computing processing data set. First, the data fusion analysis dataset is transmitted to an edge computing node, exploiting the computing power of the edge computing framework. And then, carrying out data processing on the edge computing nodes, including data filtering, data aggregation and real-time analysis, and generating an edge computing processing data set which comprises important information such as congestion conditions, traffic signal states and the like.
The travel path optimization submodule aims to calculate an optimal travel path based on the edge calculation processing data set by using a route planning algorithm (such as Dijkstra or A-type algorithm) and optimize a route. Firstly, calculating an optimal driving path by utilizing an edge calculation processing data set, and considering factors such as vehicle type, cargo attribute, real-time traffic condition and the like. An optimized travel path plan is then generated, including the proposed route, the predicted travel time, and the predicted traffic condition.
The emergency response submodule aims to take response measures according to emergency situations based on the optimized driving path scheme and generate an emergency response scheduling scheme. First, an emergency situation in the system, such as a traffic accident or road closure, is monitored. Then, based on the optimized driving path scheme, corresponding emergency measures such as route adjustment or intersection signal control are taken. Finally, an emergency response scheduling scheme is generated, including processing policies, route adjustment instructions, and alert information notifying relevant personnel.
Referring to fig. 7, the path calculation sub-module performs path search by adopting a genetic algorithm based on the cargo attribute, the vehicle position and the route initial scheme, and evaluates the path to generate a preliminary path calculation result;
the freight dispatching sub-module adopts a simulated annealing algorithm to optimally dispatch the matching of the vehicle and the freight based on the preliminary path calculation result, and generates a freight dispatching scheme;
The multi-objective optimization submodule generates an optimized dispatching path scheme by adopting a multi-objective optimization technology and referring to cost, time and energy consumption based on a freight dispatching scheme;
the path planning engine submodule adjusts path selection based on the optimized scheduling path scheme by using algorithms such as dynamic planning and the like to generate a final path planning result;
Based on the final path planning result, the user interface sub-module adopts an interactive interface design to display the path and the scheduling information and generate a scheduling instruction and a path planning result.
The path calculation submodule acquires the cargo attribute, the vehicle position and the route initial scheme, and uses a genetic algorithm to perform path search to generate a path. Next, the path is evaluated, including cost, time, etc. And finally, selecting an optimal path as a preliminary path calculation result according to the evaluation result.
And the freight dispatching sub-module acquires a preliminary path calculation result and uses a simulated annealing algorithm to optimally dispatch the matching of the vehicle and the freight. And then, generating a freight dispatching scheme according to the optimized dispatching result.
The multi-objective optimization submodule obtains a freight dispatching scheme, and the multi-objective optimization technology is used for considering factors such as cost, time and energy consumption. And finally, generating an optimized scheduling path scheme according to the multi-objective optimization result.
The path planning engine submodule acquires an optimized scheduling path scheme, and adjusts path selection by using algorithms such as dynamic planning and the like. And finally, generating a final path planning result according to the adjusted path selection.
The user interface sub-module obtains a final path planning result, designs an interactive interface and displays the path and scheduling information. And finally, generating a scheduling instruction and a path planning result according to the user demand.
Referring to fig. 8, the sensor data acquisition submodule performs environmental scanning by using a laser radar and an infrared camera, and collects raw data to generate a raw sensor data set;
The sensor data processing sub-module performs data preprocessing by adopting a data cleaning and feature extraction algorithm based on an original sensor data set to generate processed sensor data;
the environment monitoring submodule carries out real-time environment monitoring by adopting a computer vision and machine learning method based on the processed sensor data to generate an environment monitoring report;
The risk prediction sub-module adopts a deep learning method to predict traffic risk based on the environment monitoring report, and generates a risk prediction result;
and the risk report sub-module generates a risk early warning report by adopting a risk analysis and evaluation method based on a risk prediction result.
The sensor data acquisition submodule performs environment scanning by using a laser radar and an infrared camera, collects original data and generates an original sensor data set. The laser radar and the infrared camera are arranged at proper positions, so that the area needing to be monitored can be covered. And transmitting a laser beam through a laser radar, receiving the reflected signal, and acquiring the distance and position information of objects in the environment. An infrared camera acquires a thermal energy distribution image in the environment. These raw data are recorded to form a raw sensor dataset.
The sensor data processing sub-module performs data preprocessing by adopting a data cleaning and feature extraction algorithm based on the original sensor data set to generate processed sensor data. And performing quality inspection and outlier processing on the original sensor data, and removing invalid or erroneous data. And selecting a proper feature extraction algorithm according to requirements, and extracting useful feature information from the original data. For example, operations such as point cloud segmentation, ground segmentation and the like can be performed on the laser radar data; the infrared camera data can be subjected to operations such as target detection, background separation and the like. Finally, the processed data is saved as a processed sensor dataset.
The environment monitoring submodule carries out real-time environment monitoring by adopting a computer vision and machine learning method based on the processed sensor data, and generates an environment monitoring report. And analyzing and understanding the processed sensor data by using a computer vision algorithm, and identifying information such as target objects, obstacles and the like in the environment. The historical data is trained and learned in combination with machine learning algorithms, and models are built to predict future behavior and states. And generating an environment monitoring report according to the real-time analysis result, wherein the environment monitoring report comprises the information such as the position, the speed, the behavior and the like of the target object.
And the risk prediction sub-module is used for carrying out traffic risk prediction by adopting a deep learning method based on the environment monitoring report to generate a risk prediction result. Data in the environmental monitoring report is input into a deep learning model for training and learning. The deep learning model may be a convolutional neural network, a recurrent neural network, or other suitable model structure. In the training process, the model learns the rules and modes of traffic behavior according to the historical data. And predicting future traffic conditions by using the trained model to generate a risk prediction result. These results may include information such as the probability of a traffic accident, the degree of traffic congestion, etc.
And the risk report sub-module generates a risk early warning report by adopting a risk analysis and evaluation method based on the risk prediction result. And analyzing and evaluating the risk prediction result, and determining the standards and thresholds of different risk levels. The prediction results are classified into different risk classes, such as low risk, medium risk, and high risk classes, according to criteria and thresholds. And arranging the risk level and the corresponding prediction result into a risk early warning report for providing decision support and risk management advice for related personnel.
Referring to fig. 9, the risk recognition sub-module performs risk factor decomposition by adopting a decision tree analysis method based on the risk early warning report, performs risk level evaluation, and generates a potential risk recognition result;
based on the potential risk identification result, the system warning submodule adopts a real-time monitoring algorithm to monitor an abnormal mode, outputs a warning signal and generates a warning signal triggering result;
The control intervention submodule adopts PID control logic to calculate risk response action based on the early warning signal triggering result, and issues control commands to generate preventive control measures;
The system backup submodule adopts a redundant data management strategy to carry out key data backup based on preventive control measures, and carries out system backup state update to generate backup information;
the system recovery submodule adopts a state recovery technology to reconstruct the system function based on the backup information and performs fault state coverage to generate a system recovery scheme.
And the risk identification sub-module is used for carrying out risk factor decomposition by adopting a decision tree analysis method based on the risk early warning report, carrying out risk grade assessment and generating a potential risk identification result. And constructing a decision tree model according to the information and the data provided in the risk early warning report. The risk factors are used as root nodes and are divided into different child nodes according to different characteristics and conditions. Then, the risk level of each child node is determined by calculating the risk probability and the influence degree of the child node. And summarizing the risk levels of all the child nodes to generate a potential risk identification result.
Based on the potential risk recognition result, the system warning submodule adopts a real-time monitoring algorithm to monitor an abnormal mode, outputs a warning signal and generates a warning signal triggering result. And determining key indexes and parameters to be monitored according to the potential risk identification result. A suitable real-time monitoring algorithm is designed to detect the occurrence of abnormal patterns. When an abnormal mode is detected, the system sends out a corresponding early warning signal, and records the event as an early warning signal triggering result.
And the control intervention submodule adopts PID control logic to calculate risk response action based on the early warning signal triggering result, and issues a control command to generate a preventive control measure. And determining control measures and target values to be adopted according to the triggering result of the early warning signal. PID control logic is used to calculate the amount of control action required. And issuing the calculated control command to a corresponding executing mechanism or equipment. The performed control actions are recorded as preventive control measures.
And the system backup submodule adopts a redundant data management strategy to backup key data based on preventive control measures, updates the system backup state and generates backup information. The critical data and storage media that need to be backed up are determined. And carrying out redundancy backup on the key data to ensure the reliability and the integrity of the data. And simultaneously, recording information such as backup time, backup position and backup state. And updating the backup state information of the system to generate backup information.
The system recovery submodule adopts a state recovery technology to reconstruct the system function based on the backup information and performs fault state coverage to generate a system recovery scheme. And determining the system functions and data to be restored according to the backup information. State restoration techniques are used to reconstruct the functionality and configuration of the system. During the reconstruction process, the fault state can be subjected to covering treatment so as to ensure the normal operation of the system. And recording the recovered system functions and data as a system recovery scheme.
Referring to fig. 10, the data display sub-module performs information integration display by adopting a data fusion technology based on a scheduling instruction, a path planning result and a system recovery scheme, and performs interactivity enhancement to generate a data visualization interface;
The interactive operation submodule carries out function option design by adopting a touch interactive design principle based on a data visual interface, carries out user input processing and generates an interactive operation function;
the interface design submodule performs interface layout optimization by adopting a user experience optimization strategy based on the interactive operation function, performs interactive logic upgrading, and generates an optimized user interface;
the user feedback sub-module is used for carrying out user satisfaction analysis by adopting an emotion analysis algorithm based on the optimized user interface, integrating feedback contents and generating a user feedback report;
the system updating sub-module adopts an agile development framework to carry out function iterative development based on a user feedback report, and carries out system performance optimization to generate a system upgrading scheme.
The task of the data presentation sub-module is to integrate the data of the scheduling instructions, the path planning results and the system recovery scheme into one unified data model. This requires the application of data fusion techniques to ensure consistency and accuracy of the data source. Then, an appropriate data visualization is selected so that the user can intuitively understand the information. In addition, interactivity is added so that users can interact with the data, with in-depth knowledge of the details. Finally, a data visualization interface is generated through the sub-module, so that the data can be clearly presented.
The interactive operation sub-module is established on the basis of the data visualization interface and aims at providing function options and ensuring a user-friendly interface. The touch interaction design principle is adopted, so that a user can easily interact with the interface to trigger the required functions. At the heart of this sub-module is user input processing, including clicking, dragging, zooming, etc., so that the user can explore the data, perform tasks, and achieve their goals. Finally, the interactive operation sub-module generates an interactive operation function, so that a user can interact with the data.
The interface design sub-module is constructed on the basis of the interactive operation function, and the key point is the optimization of the interface layout, so that the ordered arrangement of information is ensured, and the cognitive burden is reduced. This sub-module also applies user experience optimization policies, including response time, consistency, and ease of use, to provide a high quality user experience. Meanwhile, interactive logic is upgraded to ensure that the user can easily use the interface. Finally, an optimized user interface is generated by this sub-module, emphasizing aesthetics and functionality.
The user feedback submodule is constructed on the basis of the optimized user interface and aims to collect user feedback and analyze user satisfaction. This sub-module uses an emotion analysis algorithm to quantify the emotional tendency of the user. The user feedback content is integrated into a user feedback report including questions and suggestions. This process helps to understand the needs of the user, improves the system, and increases user satisfaction.
System update sub-module: the system updating sub-module adopts an agile development framework to carry out functional iterative development based on the user feedback report. This means that a function update plan is formulated, improvements are implemented, and system performance optimization, including performance testing and code optimization, is performed. Finally, a system upgrading scheme is generated, so that the system is ensured to keep competitive power, and the continuously-changing requirements are met.
The present invention is not limited to the above embodiments, and any equivalent embodiments which can be changed or modified by the technical disclosure described above can be applied to other fields, but any simple modification, equivalent changes and modification made to the above embodiments according to the technical matter of the present invention will still fall within the scope of the technical disclosure.
Claims (10)
1. An industrial building intelligent traffic guiding management system is characterized in that: the intelligent traffic guiding management system for the industrial upstairs comprises a data acquisition module, a data processing module, a self-adaptive traffic signal control module, a vehicle networking optimization module, an intelligent scheduling path planning module, an environment perception module, an accident prevention module and a user interaction module;
The data acquisition module is used for collecting road traffic data based on a traffic flow detector and a monitoring camera by adopting the internet of things technology and integrating the road traffic data into a real-time traffic data set;
the data processing module performs data preprocessing and feature extraction by using a deep learning algorithm based on a real-time traffic data set to generate processed traffic data;
the self-adaptive traffic signal control module adopts a deep reinforcement learning algorithm to carry out self-adaptive control on signals based on the processed traffic data, and generates a real-time signal control strategy;
The vehicle networking optimization module is used for carrying out data exchange and edge calculation by utilizing a vehicle-mounted communication system DSRC or LTE-V2X based on the processed traffic data to generate a route optimization scheme;
The intelligent scheduling path planning module performs optimal path planning and freight scheduling by adopting a genetic algorithm and a simulated annealing algorithm based on cargo attributes, vehicle positions and a route optimization scheme, and generates scheduling instructions and path planning results;
The environment sensing module is used for carrying out environment monitoring by utilizing laser radar and infrared camera equipment based on the processed traffic data and predicting abnormal behaviors or potential risks in the traffic environment to generate a risk early warning report;
the accident prevention module responds to the predicted occurrence risk by utilizing an automatic alarm system and a preventive control technology based on the risk early warning report to generate accident prevention measures;
The user interaction module designs and builds a user-friendly interface based on the scheduling instruction, the path planning result and the accident prevention measure, and generates a user interaction interface;
The real-time traffic data set comprises traffic flow, vehicle running speed, vehicle type and road condition, the real-time signal control strategy comprises a multi-intersection signal lamp on and off time sequence, the route optimization scheme comprises a running route, predicted running time and predicted traffic condition, the risk early warning report is specifically a predicted condition and countermeasure scheme for predicted traffic accidents and risks, and the accident prevention measures comprise alarm information and preventive control instructions.
2. The industrial upstairs intelligent traffic-guiding management system of claim 1, wherein: the data acquisition module comprises a video monitoring sub-module, a traffic flow detection sub-module, a V2X communication sub-module, an environment sensing sub-module and a database sub-module;
the data processing module comprises a data preprocessing sub-module, a data classifying sub-module, a data normalizing sub-module, a characteristic extracting sub-module and a data storing sub-module;
The self-adaptive traffic signal control module comprises a DRL training sub-module, a strategy selection sub-module, a signal control sub-module, a feedback learning sub-module and an optimization adjustment sub-module;
The vehicle networking optimization module comprises a vehicle-mounted communication sub-module, a data fusion sub-module, an edge calculation sub-module, a driving path optimization sub-module and an emergency response sub-module;
The intelligent scheduling path planning module comprises a path calculation sub-module, a freight scheduling sub-module, a multi-objective optimization sub-module, a path planning engine sub-module and a user interface sub-module;
the environment sensing module comprises a sensor data acquisition sub-module, a sensor data processing sub-module, an environment monitoring sub-module, a risk prediction sub-module and a risk reporting sub-module;
The accident prevention module comprises a risk identification sub-module, a system warning sub-module, a control intervention sub-module, a system backup sub-module and a system recovery sub-module;
the user interaction module comprises a data display sub-module, an interaction operation sub-module, an interface design sub-module, a user feedback sub-module and a system updating sub-module.
3. The industrial upstairs intelligent traffic-guiding management system of claim 2, wherein: the video monitoring submodule carries out real-time video stream analysis and vehicle identification by adopting a target detection algorithm, specifically a YOLO or SSD, based on a monitoring camera to generate a video monitoring data set;
the traffic flow detection sub-module is used for counting vehicles by adopting a lane line crossing detection method based on the video monitoring data set and comparing the vehicles with historical data to generate a traffic flow information data set;
the V2X communication sub-module is based on vehicle-mounted equipment and infrastructure, adopts a vehicle networking communication protocol specifically DSRC or C-V2X to exchange data, and is fused with a vehicle flow information data set to generate a V2X communication data set;
The environment sensing submodule is used for analyzing weather and road conditions based on an environment sensor by adopting Kalman filtering, integrating the weather and road conditions with a V2X communication data set and generating an environment sensing data set;
The database submodule adopts a MySQL database management system to perform data storage optimization based on the environment-aware data set, and performs query efficiency improvement to generate a comprehensive traffic database.
4. The industrial upstairs intelligent traffic-guiding management system of claim 2, wherein: the data preprocessing sub-module is used for filtering noise data by adopting a data cleaning algorithm comprising missing value processing and outlier removing based on the comprehensive traffic database, and unifying data formats to generate a preprocessed traffic data set;
the data classification submodule classifies data labels by adopting a support vector machine or a random forest based on the preprocessed traffic data set, evaluates the results and generates a classified traffic data set;
the data normalization submodule carries out characteristic scale adjustment by adopting a Z score or a minimum-maximum normalization algorithm based on the classified traffic data set, and carries out data equalization to generate a normalized traffic data set;
The feature extraction submodule is used for extracting key features based on the normalized traffic data set by adopting a feature layer of a convolutional neural network and performing feature optimization to generate a traffic data set after feature extraction;
and the data storage submodule adopts a NoSQL database to carry out large data storage management based on the traffic data set after feature extraction, and carries out data backup and recovery to generate a traffic data feature database.
5. The industrial upstairs intelligent traffic-guiding management system of claim 2, wherein: the DRL training submodule adopts a deep Q network or strategy gradient method to train a signal control strategy and optimize a model based on the processed traffic data, and generates a signal control decision model;
the strategy selection submodule adopts epsilon-greedy strategy to select signal strategies and analyze traffic flow adaptability based on the signal control decision model, and generates a signal strategy data set;
The signal control sub-module adopts a real-time dynamic control algorithm to adjust traffic signals in real time based on the signal strategy data set, and generates a real-time traffic signal control scheme;
the feedback learning submodule carries out real-time feedback and model updating by adopting an incremental learning algorithm based on a real-time traffic signal control scheme to generate a signal control model after feedback optimization;
and the optimization and adjustment submodule performs performance optimization and adjustment by adopting transfer learning or meta learning based on the signal control model after feedback optimization to generate an optimized and adjusted signal control strategy.
6. The industrial upstairs intelligent traffic-guiding management system of claim 2, wherein: the vehicle-mounted communication submodule is used for collecting and exchanging data by adopting a DSRC or LTE-V2X vehicle-mounted communication system based on the processed traffic data to generate a vehicle-mounted data exchange data set;
The data fusion submodule is used for carrying out data integration analysis by adopting a multi-source data fusion technology based on the vehicle-mounted data exchange data set to generate a data fusion analysis data set;
The edge computing sub-module analyzes the data set based on data fusion, adopts an edge computing framework to rapidly process the data, and generates an edge computing processing data set;
The driving path optimization sub-module is used for planning and optimizing a route by adopting a Dijkstra algorithm or an A-type algorithm based on an edge calculation processing data set to generate an optimized driving path scheme;
the emergency response submodule is used for adjusting and commanding a route under an emergency condition based on an optimized driving path scheme and a response mechanism and generating an emergency response scheduling scheme.
7. The industrial upstairs intelligent traffic-guiding management system of claim 2, wherein: the path calculation submodule performs path searching by adopting a genetic algorithm based on cargo attributes, vehicle positions and a route initial scheme, evaluates the path and generates a preliminary path calculation result;
the freight dispatching sub-module adopts a simulated annealing algorithm to optimally dispatch the matching of the vehicle and the freight based on the preliminary path calculation result, and generates a freight dispatching scheme;
The multi-objective optimization submodule generates an optimized dispatching path scheme by adopting a multi-objective optimization technology and referring to cost, time and energy consumption based on a freight dispatching scheme;
the path planning engine submodule adjusts path selection based on the optimized scheduling path scheme by using algorithms such as dynamic planning and the like to generate a final path planning result;
and the user interface sub-module adopts an interactive interface design based on the final path planning result, displays the path and the scheduling information, and generates a scheduling instruction and a path planning result.
8. The industrial upstairs intelligent traffic-guiding management system of claim 2, wherein: the sensor data acquisition submodule performs environment scanning by using a laser radar and an infrared camera, collects original data and generates an original sensor data set;
The sensor data processing sub-module performs data preprocessing by adopting a data cleaning and feature extraction algorithm based on an original sensor data set to generate processed sensor data;
The environment monitoring submodule carries out real-time environment monitoring by adopting a computer vision and machine learning method based on the processed sensor data to generate an environment monitoring report;
the risk prediction sub-module is used for predicting traffic risk by adopting a deep learning method based on the environment monitoring report, and generating a risk prediction result;
and the risk report sub-module generates a risk early warning report by adopting a risk analysis and evaluation method based on a risk prediction result.
9. The industrial upstairs intelligent traffic-guiding management system of claim 2, wherein: the risk identification sub-module is used for carrying out risk factor decomposition by adopting a decision tree analysis method based on the risk early warning report, carrying out risk grade assessment and generating a potential risk identification result;
The system warning submodule monitors abnormal modes by adopting a real-time monitoring algorithm based on the potential risk identification result, outputs early warning signals and generates an early warning signal triggering result;
the control intervention submodule adopts PID control logic to calculate risk response action based on the early warning signal triggering result, and issues a control command to generate preventive control measures;
the system backup submodule adopts a redundant data management strategy to backup key data based on preventive control measures, updates the system backup state and generates backup information;
The system recovery submodule adopts a state recovery technology to reconstruct system functions based on backup information and performs fault state coverage to generate a system recovery scheme.
10. The industrial upstairs intelligent traffic-guiding management system of claim 2, wherein: the data display submodule performs information integration display by adopting a data fusion technology based on a scheduling instruction, a path planning result and a system recovery scheme, and performs interactivity enhancement to generate a data visualization interface;
The interactive operation submodule carries out function option design by adopting a touch interactive design principle based on a data visual interface, and carries out user input processing to generate an interactive operation function;
the interface design submodule performs interface layout optimization by adopting a user experience optimization strategy based on the interactive operation function, performs interactive logic upgrading, and generates an optimized user interface;
the user feedback submodule analyzes user satisfaction degree by adopting an emotion analysis algorithm based on the optimized user interface, integrates feedback content and generates a user feedback report;
and the system updating submodule adopts an agile development framework to carry out functional iterative development based on a user feedback report, and carries out system performance optimization to generate a system upgrading scheme.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311759963.5A CN117975713A (en) | 2023-12-19 | 2023-12-19 | Intelligent traffic guiding management system for industrial upstairs |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311759963.5A CN117975713A (en) | 2023-12-19 | 2023-12-19 | Intelligent traffic guiding management system for industrial upstairs |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117975713A true CN117975713A (en) | 2024-05-03 |
Family
ID=90844913
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311759963.5A Pending CN117975713A (en) | 2023-12-19 | 2023-12-19 | Intelligent traffic guiding management system for industrial upstairs |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117975713A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118134209A (en) * | 2024-05-06 | 2024-06-04 | 江苏大块头智驾科技有限公司 | Intelligent harbor mine integrated management, control and scheduling system and method |
| CN118313632A (en) * | 2024-06-07 | 2024-07-09 | 鱼快创领智能科技(南京)有限公司 | Large-scale urban distribution logistics capacity scheduling system and method with scalable calculation capacity |
-
2023
- 2023-12-19 CN CN202311759963.5A patent/CN117975713A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118134209A (en) * | 2024-05-06 | 2024-06-04 | 江苏大块头智驾科技有限公司 | Intelligent harbor mine integrated management, control and scheduling system and method |
| CN118134209B (en) * | 2024-05-06 | 2024-07-05 | 江苏大块头智驾科技有限公司 | Intelligent harbor mine integrated management, control and scheduling system and method |
| CN118313632A (en) * | 2024-06-07 | 2024-07-09 | 鱼快创领智能科技(南京)有限公司 | Large-scale urban distribution logistics capacity scheduling system and method with scalable calculation capacity |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117975713A (en) | Intelligent traffic guiding management system for industrial upstairs | |
| CN112686090B (en) | Intelligent monitoring system for abnormal behavior in bus | |
| GB2573738A (en) | Driving monitoring | |
| CN109544985A (en) | Detection system for the vehicles | |
| CN116308960B (en) | Intelligent park property prevention and control management system based on data analysis and implementation method thereof | |
| CN106448267B (en) | Road traffic accident chain based on car networking blocks system | |
| CN112633057B (en) | Intelligent monitoring method for abnormal behavior in bus | |
| WO2021257429A2 (en) | Label-free performance evaluator for traffic light classifier system | |
| CN117275235A (en) | Vehicle monitoring method and system | |
| CN117236930A (en) | 5G and artificial intelligence based highway bridge comprehensive monitoring system | |
| CN113761728A (en) | Airport electric special vehicle fault early warning method based on Internet of vehicles platform | |
| CN118038674A (en) | Monitoring system real-time dynamic analysis warning system based on big data | |
| Kumar et al. | Moving Vehicles Detection and Tracking on Highways and Transportation System for Smart Cities | |
| CN108364471B (en) | Freight planning management method and system based on intelligent traffic light OD information inspection | |
| CN116324926A (en) | Method for generating road shoulder opening permit by means of monitoring system and monitoring system | |
| Mohammad et al. | New Ontology structure for intelligent controlling of traffic signals | |
| Huang | SVM‐Based Real‐Time Identification Model of Dangerous Traffic Stream State | |
| CN113628461B (en) | Traffic supervision device and method | |
| Emmanuel et al. | Enhancing Traffic Management in Urban Areas through UAV-Assisted Intelligent Mobile Systems | |
| Das et al. | Vehicular Propagation Velocity Forecasting Using Open CV | |
| CN118071040B (en) | Safety inspection evaluation method and system for highway construction | |
| CN117429419B (en) | Automatic driving method applied to port and driving vehicle | |
| Bayen | Machine Learning for Autonomous Vehicle Real-time Traffic Monitoring and Analysis | |
| CN117558134B (en) | Operation and maintenance management system, method, equipment and medium for rail transit vehicle | |
| CN118274846B (en) | Unmanned aerial vehicle group collaborative path planning method and system for road hidden trouble investigation |
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 |