Foggy day smart city management system based on digital twinborn technology

Abstract

The invention relates to a foggy day smart city management system based on a digital twinborn technology, and the system comprises a real-time monitoring and data collection module which is used for collecting and preprocessing environment data and operation data of a target city; the digital twin module is used for constructing a digital twin model of the target city; the foggy day simulation module is used for constructing a foggy day scene based on a digital twinborn model and carrying out simulation on the city operation state of the target city in the foggy day scene according to the preprocessed environment data and operation data; and the decision support module is used for generating decision support information according to the analogue simulation result. According to the invention, real-time monitoring and prediction of the urban operation state can be realized, and especially intelligent management of traffic, environment and the like under foggy weather extreme weather conditions can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of smart city management, and in particular to a foggy smart city management system based on digital twin technology. Background Art

[0002] With the deepening of smart city construction, digital twin technology, as one of its core technologies, has been widely used in urban planning, traffic management, environmental protection and other fields. However, in extreme weather conditions such as foggy days, the operation and management of cities face many challenges, such as traffic congestion, low environmental visibility, and increased safety hazards. In the existing foggy smart city management and optimization system, although the Internet of Things, big data and artificial intelligence technologies have been applied, in actual operation, there are still problems such as massive data connections between urban departments on the edge side, diverse types of heterogeneous devices on the edge side, high real-time response requirements, unpredictable burst loads, and incompatible interfaces, which make data integration and sharing difficult; when simulating foggy environments, existing systems often only consider single factors such as atmospheric scattering and particle systems, which leads to inaccurate simulation results; when predicting the impact of foggy days on urban traffic and environment, they can only be based on traditional statistical models or empirical formulas, resulting in limited prediction and decision-making capabilities. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a foggy smart city management system based on digital twin technology, which can realize real-time monitoring and prediction of the city's operating status, especially intelligent management of traffic, environment and other aspects under extreme weather conditions in foggy days.

[0004] The technical solution adopted by the present invention to solve the technical problem is: to provide a foggy smart city management system based on digital twin technology, which is characterized by comprising:

[0005] Real-time monitoring and data collection module, used to collect and pre-process environmental and operational data of the target city;

[0006] Digital twin module, used to build a digital twin model of the target city;

[0007] The foggy weather simulation module is used to construct foggy weather scenarios based on the digital twin model, and simulate the urban operation status of the target city under the foggy weather scenario according to the preprocessed environmental data and operation data;

[0008] The decision support module is used to generate decision support information based on simulation results.

[0009] Furthermore, the foggy weather simulation module includes:

[0010] Meteorological data fusion module, used to predict the probability and duration of foggy days and perform meteorological data fusion based on pre-processed environmental data and operational data;

[0011] The foggy day scenario construction module is used to build foggy day scenarios based on the digital twin model, and simulate the urban operation status of the target city under the foggy day scenario according to the results of meteorological data fusion.

[0012] Furthermore, the meteorological data fusion is expressed as:

[0013] mathbfx used =x model +K(x obs -Hx model )

[0014] Among them, x used is the fused meteorological state vector, x model is the predicted meteorological state vector, x obs is the observed meteorological state vector, H is the observation operator, and K is the Kalman gain matrix.

[0015] Furthermore, the foggy weather simulation module further includes:

[0016] The numerical calculation module is used to simulate the movement and interaction of airflow in a foggy environment using fluid mechanics numerical calculation methods, and further optimize the digital twin model based on the calculation results.

[0017] Furthermore, the foggy scene construction module is implemented by building a physical model based on Mie scattering and particle dynamic behavior to simulate the propagation and scattering process of light in a foggy scene.

[0018] Furthermore, the scattering intensity I of Mie scattering is expressed as:

[0019]

[0020] Where I0 is the incident light intensity, g is the asymmetry factor of the scattered light, θ is the scattering angle, λ is the wavelength of the light, and r is the distance between the scatterer and the observer. is the contribution of scatterers of different sizes to the scattering intensity, n(r') is the number density distribution of scatterers (such as droplets), and σ(r') is the scattering cross section;

[0021] The dynamic behavior of particles is expressed as:

[0022]

[0023] Here, x is the position of the particle, v is the velocity of the particle, and a is the acceleration of the particle.

[0024] Furthermore, the real-time monitoring and data acquisition module includes:

[0025] Data collection module, used to collect environmental data and operation data of the target city;

[0026] The data cleaning module includes a data integration module and a data standardization module. The data integration module is used to integrate data from different sources and in different formats into a unified format, and the data standardization module is used to normalize the integrated data.

[0027] Furthermore, the digital twin module includes:

[0028] The initial model building module is used to build a digital twin model of a set type;

[0029] The data-driven modeling module is used to update the status information of the constructed digital twin model based on the collected environmental data and operation data.

[0030] Furthermore, the digital twin model of the set type includes a geospatial model, which is used to describe the geospatial structure and layout of the city.

[0031] Beneficial Effects

[0032] Due to the adoption of the above-mentioned technical scheme, the present invention has the following advantages and positive effects compared with the prior art: the system of the present invention realizes seamless connection and efficient sharing of data among various urban departments by adopting a unified data format and interface, forming a comprehensive and real-time urban management information system, and can also share data and work collaboratively with other urban management systems to improve the overall efficiency and level of urban management; the present invention comprehensively considers various factors such as atmospheric scattering, particle systems, meteorological data fusion and numerical calculation methods, and realizes high-precision simulation of foggy environments; the present invention uses deep learning to analyze, learn and integrate a large amount of historical data and real-time data, thereby realizing accurate prediction and intelligent decision-making of changes in urban traffic, environment, etc. under foggy environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a schematic diagram of a flow chart of an implementation mode of the present invention. DETAILED DESCRIPTION

[0034] The present invention will be further described below in conjunction with specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention. In addition, it should be understood that after reading the content taught by the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms fall within the scope limited by the appended claims of the application equally.

[0035] An embodiment of the present invention relates to a foggy smart city management and optimization system based on digital twin technology, including a real-time monitoring and data acquisition module, a digital twin modeling module, a foggy simulation module, a decision support module and a user interaction module.

[0036] The real-time monitoring and data acquisition module collects key information such as the city's traffic flow, air quality, and meteorological data in real time through IoT devices and sensors, and performs preprocessing and integration to form a unified data format. Specifically, the real-time monitoring and data acquisition module uses two modules: data acquisition and data cleaning. The data acquisition module uses IoT devices and sensors to collect the city's traffic flow, air quality, meteorological data, etc. in real time. IoT devices include but are not limited to traffic cameras, air quality monitoring stations, weather radars, etc. The data cleaning module includes two sub-modules: data integration and data standardization, which verify, remove duplicates, and process outliers on the collected raw data. The data integration module integrates data from different sources and formats into a unified format to facilitate subsequent analysis. The data standardization module normalizes the data to make it comparable.

[0037] The digital twin modeling module uses big data and artificial intelligence technology to build a virtual digital twin model that is highly consistent with the physical city. The model reflects the physical space, social space and information space of the city, providing a basis for simulation and decision support. Specifically, the digital twin module mainly uses technologies such as deep learning and machine learning, and includes two modules: modeling process and model type. The modeling process includes three sub-modules: initial model construction, data-driven modeling and AI optimization. The initial model construction is based on high-precision maps and GIS technology to build a geographic spatial model of the city. Data-driven modeling continuously updates the status information of the digital twin model through IoT data and real-time monitoring data. For example, data from traffic cameras can be used to update the traffic flow status of roads, and data from air quality monitoring stations can update the air quality status. The AI ​​optimization module uses AI algorithms to dynamically optimize and predict the model. For example, the changing trend of traffic flow is predicted through deep learning algorithms, so as to adjust the duration of traffic lights in advance. The model types include three sub-models: geographic space model, traffic flow model and air quality model. The geospatial model describes the city’s geospatial structure and layout, the traffic flow model simulates and analyzes the changing patterns and trends of traffic flow, and the air quality model predicts and evaluates changes in air quality and pollution trends.

[0038] The foggy weather simulation module is based on the digital twin model, combined with meteorological data and real-time monitoring data, to simulate the city's operating status under severe weather conditions of foggy days. By simulating changes in traffic flow, air quality, etc. under different weather conditions, it provides a scientific basis for the decision support module. The foggy weather simulation module mainly uses AI technologies such as simulation and prediction models. Among them, the simulation technology evaluates the effects of different management strategies under foggy conditions through simulation, and includes two sub-modules: meteorological data fusion and foggy weather scene construction. Meteorological data fusion is used to combine real-time meteorological data and historical data to predict the probability and duration of foggy days. Foggy weather scene construction actually builds foggy weather scenes based on the digital twin model to simulate the impact of foggy days on urban traffic, environment, etc. The prediction model includes two sub-modules: a prediction model based on time series and a prediction model based on regression analysis. The prediction model based on time series uses LSTM (long short-term memory network) technology to predict the changing trend of traffic flow. The prediction model based on regression analysis uses linear regression, decision tree regression and other technologies to predict the changing trend of air quality.

[0039] The prediction and decision support module is based on simulation results and combines urban planning, traffic management, environmental protection and other fields to provide scientific and accurate decision support for the user interface and interaction modules.

[0040] The user interaction module uses 3D rendering and virtual reality technology to present the simulation results in a graphical form, providing a friendly user interface and interactive mode, making it convenient for city managers and the public to understand the city’s operating status and decision-making support information in real time.

[0041] The application effect of the present invention is further illustrated below in conjunction with the accompanying drawings and specific embodiments.

[0042] Example 1: Traffic management in foggy weather.

[0043] like Figure 1As shown in the figure, the foggy smart city management and optimization system based on digital twin technology includes real-time monitoring and data acquisition module, data processing and analysis module, digital twin modeling module, foggy simulation module, prediction and decision support module and user interaction module. The data acquisition module collects key information such as traffic flow, air quality, and meteorological data of the city in real time through IoT devices and sensors. The data processing module preprocesses and integrates the collected data to form a unified data format and stores it in the data warehouse. The digital twin modeling module uses big data, artificial intelligence and other technical means to build a virtual digital twin model that is highly consistent with the physical city. The foggy simulation module simulates the city operation status under severe weather conditions such as foggy days based on the digital twin model and meteorological data. The prediction and decision support module provides scientific and accurate decision support for city managers based on the simulation results. At the same time, through the user interface and interactive methods, it is convenient for city managers and the public to understand the city's operation status and decision support information in real time.

[0044] The real-time monitoring and data collection module includes two parts: traffic cameras and sensors and meteorological data access. Traffic cameras and sensors deployed at key intersections and sections collect data such as traffic flow, vehicle speed, and vehicle spacing in real time. Meteorological data access obtains real-time meteorological data through meteorological stations or relevant meteorological departments, including temperature, humidity, visibility, wind speed, etc., especially visibility data related to foggy days.

[0045] The data processing and analysis module includes data integration, data cleaning and data analysis. Data integration integrates traffic data and meteorological data to form a unified database to ensure the accuracy and consistency of the data. Data cleaning cleans the collected data, removes outliers and duplicate data, and ensures the accuracy of subsequent analysis. Data analysis uses AI algorithms to analyze the integrated data, evaluate the impact of fog on traffic, and predict the changing trend of traffic flow.

[0046] The digital twin modeling module builds a city's geospatial model based on high-precision maps and GIS technology. Through IoT data and real-time monitoring data, the data from traffic cameras is used to update the traffic flow status of roads. The changing trend of traffic flow is predicted through deep learning algorithms, so that the duration of traffic lights can be adjusted in advance.

[0047] The foggy weather simulation module includes physical model construction, meteorological data fusion and numerical calculation. The three steps are explained in detail using the example of foggy weather traffic management.

[0048] Physical model construction is the basis of fog simulation, which mainly includes atmospheric scattering model and particle system simulation. The atmospheric scattering model is used to describe the propagation and scattering process of light in the atmosphere. In a foggy environment, light is mainly affected by Mie scattering. The scattering intensity I of Mie scattering can be expressed by the following formula:

[0049]

[0050] Among them, I0 is the incident light intensity, g is the asymmetry factor of the scattered light, θ is the scattering angle, λ is the wavelength of light, r is the distance between the scatterer and the observer, r' as an integral variable describes the contribution of scatterers of different sizes to the scattering intensity, n(r′) is the number density distribution of scatterers (such as droplets), and σ(r′) is the scattering cross section.

[0051] Since the position and velocity of particles can be generated by random processes, particle system simulation is used to generate and render tiny particles such as fog droplets to simulate the natural distribution and movement of fog droplets in the air. The dynamic behavior of particles can be described by the following differential equations:

[0052]

[0053] Among them, x is the position of the particle, v is the velocity of the particle, and a is the acceleration of the particle. The acceleration a may be affected by gravity, air resistance, etc.

[0054] Meteorological data fusion measures and assimilates real-time meteorological parameters such as temperature, humidity, wind speed, wind direction, etc., integrates the data into the simulation model, and simulates the traffic conditions under different foggy conditions. The mathematical model of meteorological data fusion can be expressed as:

[0055] mathbfx used =x model +K(x obs -Hx model )

[0056] Among them, x used is the fused meteorological state vector, x model is the predicted meteorological state vector, x obs is the observed meteorological state vector, H is the observation operator, and K is the Kalman gain matrix.

[0057] Numerical calculation utilizes computational fluid dynamics (CFD) numerical calculation method. CFD method includes mass conservation equation, momentum conservation equation and energy conservation equation, which can simulate the movement and interaction of airflow in foggy environment and further optimize the simulation model.

[0058] Through scientific and rigorous physical models and mathematical formulas, combined with the detailed meteorological data obtained by accessing, cleaning and integrating the above-mentioned traffic cameras and sensors, and mapping them to the digital twin modeling module, we can build an accurate traffic simulation model in foggy environments, providing strong support for traffic management and planning.

[0059] The decision support module includes traffic flow prediction and intelligent control. Traffic flow prediction is based on historical data and real-time data, and uses deep learning algorithms to predict the trend of traffic flow changes under foggy conditions. Intelligent control includes traffic light optimization and traffic guidance information release. Traffic light optimization automatically adjusts the duration of traffic lights and optimizes traffic flow lines based on prediction results and real-time traffic conditions. Traffic guidance information release releases fog warning information and speed limit and distance increase instructions through variable message boards (CMS) and variable speed limit signs (CSLS) to guide drivers to drive safely.

[0060] Implement corresponding traffic control measures, such as speed limit and diversion, based on the prediction and decision support results. Monitor road conditions in real time through visibility detectors and other equipment, keep in touch with the meteorological department, and obtain fog information in a timely manner. At the same time, continuously collect and analyze traffic data under foggy conditions, such as collecting patrol feedback from traffic police and road maintenance personnel and real-time information from drivers, evaluate the effectiveness of traffic control measures, provide reference for subsequent decision-making, form a data collection and feedback cycle, and continuously optimize simulation models and prediction algorithms based on feedback data to improve the accuracy and reliability of decision-making.

[0061] Through the above process, the foggy weather traffic management system can realize real-time monitoring, prediction and optimal management of traffic conditions under foggy weather conditions, provide scientific and effective decision-making support for urban managers, and reduce the impact of foggy weather on traffic safety and efficiency.

[0062] Embodiment 2: Monitoring and early warning of foggy environment.

[0063] On foggy days, the air quality in cities tends to decline, posing a threat to the health of residents. Through the foggy smart city management and optimization system of the present invention, the air quality of the city can be monitored and warned in real time. When the system detects that the air quality index in a certain area exceeds the preset threshold, the system will automatically start the emergency plan, such as shutting down some pollution sources, increasing the operation of air purification equipment, etc., to improve the air quality. At the same time, the system will also predict the development trend of foggy days based on meteorological data and real-time monitoring data. If it is predicted that the air quality will continue to deteriorate in the future, the system will issue early warning information to residents in advance and give corresponding protective measures, such as reducing outdoor activities, wearing masks, etc. After the preliminary preparation, it mainly includes real-time monitoring and data acquisition modules, data analysis and prediction modules, early warning release, continuous monitoring and feedback, and system optimization and upgrading.

[0064] In the early stage, haze monitoring stations were deployed in key areas such as main roads, industrial areas, and residential areas in the city. These stations are equipped with sensors that can monitor key meteorological and environmental parameters such as PM2.5, PM10, temperature, and humidity in real time. The monitoring data of each station is transmitted to the central data processing center via wired or wireless means. The data processing center uses the efficient data transmission protocol DTU200 to ensure the real-time and accuracy of the data. At the same time, the level standards for haze warnings are formulated according to national standards and regional actual conditions.

[0065] The real-time monitoring and data collection module includes two parts: data collection and data verification. For data collection, the sensors at each haze monitoring station collect environmental data in real time and transmit it to the data processing center through the network. For data verification, after receiving the data, the data processing center first verifies and screens the data to ensure the accuracy and completeness of the data.

[0066] The data analysis and prediction module first uses deep learning AI algorithms to analyze the collected environmental data and identify the development trend and change pattern of haze. Then, it combines historical data and real-time data to build a foggy day prediction model. These models can predict the concentration and duration of haze in the future, providing a scientific basis for early warning.

[0067] The warning issuance includes the judgment of the warning level and the issuance of warning information. According to the forecast results and warning standards, it is judged whether the current haze situation has reached the warning level and the warning level is determined. Once the warning level is reached, the warning information is issued to the public through various channels such as radio, television, and text messages to remind the public to take corresponding protective measures.

[0068] During the entire warning period, the data in the warning process is analyzed, the warning model and algorithm are optimized, the changes in haze are continuously monitored, and the warning level is adjusted in a timely manner based on real-time data and public feedback to ensure the accuracy and timeliness of the warning information. At the same time, the system is upgraded and improved according to technological development and application needs to improve the stability and scalability of the system.

[0069] Through the above process, the foggy environment monitoring and early warning system can realize real-time monitoring, prediction and early warning of haze, provide timely and accurate information support to the government and the public, and promote the protection and improvement of the ecological environment.

[0070] The foggy smart city management and optimization system of the present invention integrates technologies such as the Internet of Things, big data, and artificial intelligence to monitor, predict, and optimize the operation status of cities under foggy conditions in real time. Specific technical means include digital twins, physical model construction, meteorological data fusion, numerical calculation methods, and artificial intelligence technology. The comprehensive application of these technical means can make the foggy simulation model more accurate and practical. The system can not only provide scientific and accurate decision-making support for urban managers, but also effectively alleviate the impact of foggy days on traffic and the environment, and improve the livability and sustainable development capabilities of the city.

Claims

1. A foggy smart city management system based on digital twin technology, characterized in that: include: Real-time monitoring and data collection module, used to collect and pre-process environmental and operational data of the target city; Digital twin module, used to build a digital twin model of the target city; The foggy weather simulation module is used to construct foggy weather scenarios based on the digital twin model, and simulate the urban operation status of the target city under the foggy weather scenario according to the preprocessed environmental data and operation data; The decision support module is used to generate decision support information based on simulation results.

2. The system according to claim 1, characterized in that The foggy weather simulation module comprises: Meteorological data fusion module, used to predict the probability and duration of foggy days and perform meteorological data fusion based on pre-processed environmental data and operational data; The foggy day scenario construction module is used to build foggy day scenarios based on the digital twin model, and simulate the urban operation status of the target city under the foggy day scenario according to the results of meteorological data fusion.

3. The system according to claim 2, characterized in that Meteorological data fusion is expressed as: mathbfx used =x model +K(x obs -Hx model ) Among them, x used is the fused meteorological state vector, x model is the predicted meteorological state vector, x obs is the observed meteorological state vector, H is the observation operator, and K is the Kalman gain matrix.

4. The system according to claim 2, characterized in that The foggy weather simulation module also includes: The numerical calculation module is used to simulate the movement and interaction of airflow in a foggy environment using fluid mechanics numerical calculation methods, and further optimize the digital twin model based on the calculation results.

5. The system according to claim 2, characterized in that The foggy scene construction module is realized by building a physical model based on Mie scattering and particle dynamic behavior to simulate the propagation and scattering process of light in a foggy scene.

6. The system according to claim 5, characterized in that The scattering intensity I of Mie scattering is expressed as: Where I0 is the incident light intensity, g is the asymmetry factor of the scattered light, θ is the scattering angle, λ is the wavelength of the light, and r is the distance between the scatterer and the observer. is the contribution of scatterers of different sizes to the scattering intensity, n(r′) is the number density distribution of scatterers (such as droplets), and σ(r′) is the scattering cross section; The dynamic behavior of particles is expressed as: Here, x is the position of the particle, v is the velocity of the particle, and a is the acceleration of the particle.

7. The system according to claim 1, characterized in that The real-time monitoring and data acquisition module includes: Data collection module, used to collect environmental data and operation data of the target city; The data cleaning module includes a data integration module and a data standardization module. The data integration module is used to integrate data from different sources and in different formats into a unified format, and the data standardization module is used to normalize the integrated data.

8. The system according to claim 1, characterized in that The digital twin module includes: The initial model building module is used to build a digital twin model of a set type; The data-driven modeling module is used to update the status information of the constructed digital twin model based on the collected environmental data and operation data.

9. The system according to claim 8, characterized in that The digital twin model of the set type includes a geospatial model, which is used to describe the geospatial structure and layout of the city.

Images