Infrastructure carbon emission dynamic monitoring and predicting system based on digital twinning

Abstract

The invention relates to an infrastructure carbon emission dynamic monitoring and prediction system based on a digital twinborn technology, and aims to realize dynamic monitoring, trend prediction and optimal management of infrastructure full life cycle carbon emission through a virtual-real combined digital twinborn model. The system comprises a data acquisition module, a digital twinborn model module, a carbon emission evaluation module, a carbon emission prediction module, an optimization decision module and an interaction and visualization module. Compared with the prior art, the digital twinborn technology is applied to dynamic monitoring and prediction of infrastructure carbon emission, and the method has the characteristics of real-time monitoring, accurate prediction, scene simulation and dynamic optimization, is suitable for the infrastructure fields of roads, waterways, buildings and the like, and provides scientific support and an efficient solution for realizing a low-carbon target.

Description

Technical Field

[0001] The present invention relates to the field of infrastructure carbon emissions, and in particular to a dynamic monitoring and prediction system for infrastructure carbon emissions based on digital twin. Background Art

[0002] With the increasingly severe global climate change, carbon emission management in the field of infrastructure construction and operation has become an important topic for achieving low-carbon goals. Traditional carbon emission assessment methods mainly rely on life cycle assessment (LCA) technology to estimate emissions at different stages through fixed data and carbon emission factors. Although this method can provide a basic assessment, it lacks sensitivity to dynamic changes and is difficult to capture the immediate impacts of construction equipment energy consumption fluctuations, traffic flow changes, and environmental conditions on emissions in real time. At the same time, existing methods mostly focus on a certain stage and ignore the systematic analysis of carbon emissions throughout the life cycle.

[0003] In addition, carbon emission management relies on multi-source data, including material use, equipment energy consumption, traffic operation, and environmental conditions. However, the current data collection and integration efficiency is low, and there is a lack of dynamic association between data, resulting in the lack of comprehensiveness and accuracy of assessment results. At the same time, existing optimization strategies are often formulated based on experience, unable to quantify the emission reduction potential of different scenarios, and lacking the ability to accurately predict future carbon emission trends and simulate scenarios.

[0004] Digital twin technology can provide a new breakthrough for carbon emission management by constructing a virtual model of a physical object and realizing dynamic mapping and feedback regulation in combination with real-time data. However, there are still obvious deficiencies in the application of existing digital twin technology in the field of infrastructure carbon emissions: First, existing digital twin models mostly focus on structural performance and function simulation, lacking accurate mapping of carbon emission characteristics; Second, existing digital twin applications mainly focus on data collection and analysis in a single stage (such as the operation stage) and are difficult to achieve integrated monitoring throughout the life cycle; Third, existing digital twin systems lack calculation models and optimization algorithms specifically for carbon emissions and are difficult to support accurate carbon emission prediction and optimization. In addition, the application of digital twin in the field of infrastructure carbon emissions still faces challenges such as complex modeling, insufficient accuracy of real-time data-driven, and high requirements for simulation calculation efficiency.

[0005] Chinese Patent Application Publication No. CN113435054A discloses a carbon emission assessment method and system based on a digital twin model. Through the carbon emission assessment method and system based on the digital twin model, it solves the problems of carbon emission data budgeting before construction and design scheme optimization, realizes the refined calculation and real-time monitoring of carbon emissions throughout the life cycle, improves the accounting efficiency and accuracy, and provides assessment and optimization guidance for carbon emissions for enterprises. The above application realizes the carbon emission assessment combined with digital twins. However, the combination of carbon emission monitoring methods and digital twin technology faces three key technical problems: First, how to construct a high-fidelity digital twin model that can accurately reflect the carbon emission characteristics of infrastructure; second, how to achieve real-time data two-way mapping and closed-loop feedback between physical infrastructure and virtual models; third, how to achieve multi-scenario carbon emission simulation and accurate prediction in the digital twin environment. The present invention successfully solves the above technical problems through an innovative design of the digital twin model construction process, real-time data mapping mechanism, and multi-algorithm fusion prediction method, and realizes the technical leap of infrastructure carbon emission monitoring from static assessment to dynamic monitoring and prediction.

[0006] In summary, there is currently a lack of a digital twin-based dynamic monitoring method for infrastructure carbon emissions to solve or partially solve the aforementioned problems. Summary of the Invention

[0007] The purpose of the present invention is to overcome the defects of the above-mentioned existing technologies and provide a digital twin technology-based dynamic monitoring and prediction system for infrastructure carbon emissions. By collecting carbon emission-related data in real time, constructing a dynamically updated digital twin model, dynamically monitoring, finely evaluating, and trend predicting the carbon emissions throughout the life cycle of infrastructure, and combining with the simulation of optimization schemes to provide scientific low-carbon decision-making support.

[0008] The purpose of the present invention can be achieved through the following technical solutions:

[0009] The present invention provides a digital twin-based dynamic monitoring and prediction system for infrastructure carbon emissions. By constructing a digital twin model and combining real-time data and historical data, it realizes the dynamic monitoring, fine evaluation, trend prediction, and optimization decision-making of carbon emissions. The system includes:

[0010] A data acquisition module for collecting carbon emission-related data of infrastructure in the design, construction, and operation and maintenance stages in real time through a sensor network and monitoring devices, including material usage data, construction energy consumption data, traffic flow data, equipment energy consumption data, and environmental condition data;

[0011] A digital twin model module for constructing a virtual digital twin model of infrastructure through three-dimensional modeling, driving the dynamic update of carbon emission status through real-time data streams, and realizing two-way mapping between physical objects and virtual models;

[0012] A carbon emission assessment module, which is used to utilize the digital twin model and life cycle assessment to conduct refined assessment of the carbon emissions throughout the life cycle of infrastructure and generate a phased carbon emission quantification report;

[0013] A carbon emission prediction module, which is used to conduct real-time prediction of the future change trend of carbon emissions through machine learning and dynamic simulation data of the digital twin model, and evaluate the emission reduction potential of optimization schemes;

[0014] An optimization decision-making module, which is used to simulate the carbon emission impacts of different design, construction and operation optimization schemes based on the carbon emission assessment and prediction results, and generate low-carbon optimization suggestions;

[0015] An interaction and visualization module, which is used to display the carbon emission status of infrastructure with a three-dimensional digital twin model as the core, provide dynamic visualization results of assessment, prediction and optimization schemes, and obtain the parameters input by users through interaction to achieve real-time adjustment and feedback.

[0016] As a preferred technical solution, the parameters input by users include design stage parameters, construction stage parameters, operation and maintenance stage parameters, assessment parameters, prediction parameters and optimization parameters, among which,

[0017] Design stage parameters: material type selection, material usage, structural design scheme, energy type selection;

[0018] Construction stage parameters: construction equipment type, construction progress, transportation route, construction time arrangement;

[0019] Operation and maintenance stage parameters: traffic flow control strategy, equipment operation parameters, maintenance plan, energy usage plan;

[0020] Assessment parameters: carbon emission calculation period, assessment index weight, warning threshold setting;

[0021] Prediction parameters: prediction time range, prediction model selection, scenario parameter setting;

[0022] Optimization parameters: optimization target weight, constraint condition setting, optimization scheme selection.

[0023] As a preferred technical solution, the digital twin model module includes:

[0024] A high-precision modeling unit, which is used to construct a three-dimensional geometric model of infrastructure and completely map the structural characteristics and functional status of physical objects;

[0025] A real-time data mapping unit, which is used to map the dynamic data collected by sensors to the virtual model and update the carbon emission status in real time;

[0026] A simulation unit for dynamically simulating and predicting multiple links of carbon emissions based on real-time data and historical data, where the multiple links include material use, traffic operation, and equipment energy consumption.

[0027] As a preferred technical solution, the simulation unit is also used to achieve multi-scenario prediction, dynamically switch design solutions, construction strategies, and operation modes according to user instructions, and evaluate the long-term impact of each scenario on carbon emissions.

[0028] As a preferred technical solution, the carbon emission assessment module conducts phased assessments of carbon emissions in the design, construction, and operation and maintenance stages through the dynamic data flow in the digital twin model, combined with the LCA method, and outputs a total carbon emission report for the entire life cycle.

[0029] As a preferred technical solution, the carbon emission prediction module uses machine learning algorithms combined with the real-time simulation results of the digital twin model to accurately predict the carbon emission trend and simulate the implementation effect of the optimization plan. Among them, the machine learning algorithm is a convolutional neural network CNN or a long short-term memory network LSTM.

[0030] As a preferred technical solution, the optimization decision-making module simulates the emission reduction effects of different low-carbon plans through the digital twin model, including:

[0031] In the design stage, simulate the impact of the application of low-carbon materials on carbon emissions;

[0032] In the construction stage, simulate the effects of optimizing the use of construction equipment and adjusting transportation routes;

[0033] In the operation and maintenance stage, simulate the potential for improving long-term carbon emissions through intelligent traffic management and energy substitution.

[0034] As a preferred technical solution, the interaction and visualization module displays the dynamic carbon emission status of the infrastructure and the simulation results of the optimization plan through a three-dimensional digital twin model, and shows the carbon emission changes and the feasibility of optimization suggestions in the form of heat maps and trend charts.

[0035] As a preferred technical solution, the digital twin model module is also used to achieve real-time feedback, realize the reaction of the carbon emission prediction result to the optimization of the physical system through bidirectional mapping, and simulate the implementation process and potential benefits of the optimization measures in the virtual model.

[0036] As a preferred technical solution, when the carbon emission trend is abnormal or exceeds the warning threshold, the carbon emission prediction module uses the digital twin model for accurate traceability and provides repair and optimization suggestions in combination with real-time simulation.

[0037] As a preferred technical solution, the optimization decision-making module is used to achieve automatic optimization based on the digital twin model, adjust parameters by combining evaluation and prediction results, simulate the emission reduction effect of optimization measures in real time, and achieve efficient low-carbon management.

[0038] Compared with the prior art, the present invention has at least one of the following beneficial effects:

[0039] (1) Dynamic monitoring and real-time update: The present invention constructs a virtual digital twin model of infrastructure through 3D modeling in the digital twin model module, uses real-time data streams to drive dynamic updates of the carbon emission status, and uses machine learning and dynamic simulation data of the digital twin model in the carbon emission prediction module to predict the future change trend of carbon emissions in real time, and evaluate the emission reduction potential of optimization schemes, realizing the two-way mapping between physical objects and virtual models, and the digital twin model and real-time data drive, achieving dynamic monitoring and instant update of infrastructure carbon emissions, and accurately reflecting the carbon emission changes throughout the life cycle.

[0040] (2) Trend prediction and scenario simulation: The present invention sets up a carbon emission prediction module, uses machine learning and dynamic simulation data of the digital twin model to predict the future change trend of carbon emissions in real time, and evaluate the emission reduction potential of optimization schemes, combines machine learning algorithms and digital twin technologies to accurately predict future carbon emission trends, and quantifies the emission reduction potential of optimization schemes through multi-scenario simulation.

[0041] (3) Full life cycle coverage: In the carbon emission assessment module of the present invention, the digital twin model and life cycle assessment are used to conduct refined assessment of the carbon emissions throughout the life cycle of infrastructure, generate phased carbon emission quantification reports covering the design, construction, and operation and maintenance stages, and support refined management of carbon emissions throughout the life cycle.

[0042] (4) Decision support and feedback optimization: Provide targeted low-carbon optimization schemes, and simulate the implementation effects of optimization measures through the digital twin model to provide scientific support for low-carbon management.

[0043] (5) 3D visualization and user interaction: Display the carbon emission assessment results and optimization suggestions in an intuitive 3D interface, support real-time adjustment and dynamic update of the results, and improve the user decision-making efficiency. Description of the Drawings

[0044] Figure 1 It is a schematic diagram of the dynamic monitoring and prediction system for infrastructure carbon emissions based on digital twins in the embodiment. Detailed Embodiment

[0045] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0046] See Figure 1 , this embodiment provides a dynamic monitoring and prediction system for infrastructure carbon emissions based on digital twins. Taking highway infrastructure as the object, a carbon emission dynamic monitoring and prediction system is constructed based on digital twin technology to realize refined management and optimization of carbon emissions from the design, construction to operation and maintenance stages.

[0047] The system mainly includes the following parts:

[0048] 1. Data acquisition module.

[0049] Real-time carbon emission data at each stage of design, construction, and operation and maintenance are collected through a sensor network, including dynamic data such as material usage, construction equipment energy consumption, traffic flow, and environmental conditions, and a complete carbon emission dataset is formed in combination with historical data.

[0050] 2. Digital twin model module.

[0051] A digital twin model consistent with the physical object of the infrastructure is constructed, and the real-time data is used to drive the dynamic update of the carbon emission status to realize the two-way mapping between the physical facility and the virtual model. The model supports multi-scenario simulation, including carbon emission simulation of different design schemes, construction strategies, and operation modes.

[0052] 3. Carbon emission assessment module.

[0053] Based on the digital twin model and the life cycle assessment (LCA) method, the total carbon emissions at each stage of design, construction, and operation and maintenance are calculated, a phased quantitative report is generated, and the key sources of carbon emissions are identified.

[0054] 4. Carbon emission prediction module.

[0055] Using machine learning algorithms (such as long short-term memory network LSTM or convolutional neural network CNN) combined with the dynamic data stream of the digital twin model, the future carbon emission change trend is accurately predicted, and the emission reduction potential of different optimization measures is evaluated.

[0056] 5. Optimization decision-making module.

[0057] Simulate the impact of different design, construction, and operation optimization schemes on carbon emissions, and generate low-carbon optimization suggestions, such as: suggesting the use of low-carbon materials, optimizing the construction process, promoting new energy equipment, or intelligent traffic management.

[0058] 6. Interaction and Visualization Module.

[0059] The digital twin model and carbon emission status are displayed through a 3D visualization interface, supporting users to adjust parameters in real time (such as design schemes or operation strategies), and dynamically updating the evaluation, prediction, and optimization results.

[0060] The process of using the system for carbon emission monitoring and prediction includes the following steps:

[0061] Step 1: Data collection.

[0062] Carbon emission-related data in the design, construction, and operation and maintenance stages are obtained through a sensor network and a data collection system:

[0063] Design stage: Record the types, quantities, and carbon emission factors of building materials (such as cement, steel bars, asphalt); collect resource requirements and energy consumption involved in the road design scheme.

[0064] Construction stage: Monitor the fuel consumption, operation duration, and energy efficiency of construction equipment; collect the driving mileage, fuel consumption, and transportation frequency of vehicles during material transportation; record the impact of construction environmental factors (such as temperature and humidity) on energy consumption.

[0065] Operation and maintenance stage: Collect traffic flow data, including vehicle types (fuel vehicles, electric vehicles, etc.), speed distribution, and travel time; record the energy consumption of daily maintenance equipment; monitor the impact of external environmental conditions (such as air humidity and temperature) on traffic operation and equipment energy efficiency.

[0066] Step 2: Digital twin model construction.

[0067] High-precision modeling: Use 3D modeling tools to construct a digital twin model consistent with the physical structure of the road, mapping the geometric and physical characteristics of the roadbed, pavement, and supporting facilities; establish virtual mapping relationships for key carbon emission links in each stage of the model (such as material production, construction equipment, vehicle operation, etc.).

[0068] Dynamic data mapping: Bind real-time data to the digital twin model and establish a data flow-driven dynamic update mechanism; ensure that the dynamic changes in carbon emissions (such as traffic flow changes, construction energy consumption fluctuations) can be reflected in the virtual model in real time.

[0069] Multi-scenario simulation: Support carbon emission simulations for different design schemes (such as the application of low-carbon materials), construction strategies (such as equipment energy efficiency optimization), and operation modes (such as intelligent traffic management);

[0070] Step 3: Carbon emission assessment.

[0071] Design phase assessment: Calculate the total carbon emissions from material production and transportation based on the LCA method; Analyze the impact of different design schemes on carbon emissions in combination with the digital twin model.

[0072] Construction phase assessment: Calculate the total carbon emissions during the construction phase through real-time monitored energy consumption data of construction equipment and material transportation data; Use the digital twin model to dynamically simulate the impact of construction progress and equipment usage changes on carbon emissions.

[0073] Operation and maintenance phase assessment: Quantify the carbon emissions during vehicle operation in combination with traffic flow, vehicle types, and operating energy efficiency; Evaluate the carbon emissions generated by daily maintenance through the energy consumption data of maintenance equipment.

[0074] Step Four: Dynamic carbon emission prediction.

[0075] Machine learning model: Use the Long Short-Term Memory (LSTM) model, combine the real-time dynamic data and historical data in the digital twin model to predict the future carbon emission trend; Identify the key driving factors of carbon emissions (such as traffic peaks, vehicle emission factors).

[0076] Trend analysis: Predict the carbon emission changes in different future stages (such as the emission differences between peak and trough hours); Simulate the long-term impact of traffic flow changes or the introduction of new technologies (such as the popularization of electric vehicles) on carbon emissions;

[0077] Step Five: Generation of optimization solutions.

[0078] Design phase optimization: Simulate the impact of the application of low-carbon materials (such as green concrete, high-strength steel) on carbon emissions and recommend the optimal design scheme.

[0079] Construction phase optimization: Analyze the construction equipment scheduling and usage efficiency through the digital twin model, propose energy efficiency optimization strategies; Recommend optimizing the material transportation route to reduce carbon emissions.

[0080] Operation and maintenance phase optimization: Simulate the emission reduction effect of intelligent traffic management systems (such as traffic flow guidance, dynamic speed limit); Propose strategies for promoting new energy vehicles and suggestions for energy-saving transformation of maintenance equipment.

[0081] Step Six: Interaction and visualization.

[0082] Three-dimensional digital twin display: Display the dynamic carbon emission status of the road in a virtual interface, including the emission distribution and change trend in each stage; Support heat map display of high-emission areas and key emission sources.

[0083] Real-time parameter adjustment: Users can adjust the design scheme, construction strategy, or operation mode to view the emission reduction effects of different optimization measures; The digital twin model dynamically updates the evaluation and prediction results, intuitively quantifying the benefits of optimization measures;

[0084] In summary, this embodiment provides an infrastructure carbon emission dynamic monitoring and prediction system based on digital twin technology, aiming to achieve dynamic monitoring, trend prediction, and optimization management of carbon emissions throughout the life cycle of infrastructure through a digital twin model that combines virtual and real elements. The system includes a data collection module, a digital twin model module, a carbon emission assessment module, a carbon emission prediction module, an optimization decision-making module, and an interaction and visualization module.

[0085] The system obtains carbon emission-related data in the design, construction, and operation and maintenance stages through the data collection module, including material usage data, construction equipment energy consumption data, traffic flow data, and environmental condition data. The digital twin model module combines real-time data and historical data to build a virtual digital model consistent with the physical infrastructure, dynamically updates the carbon emission status, and supports multi-scenario simulation. The carbon emission assessment module quantifies the carbon emissions in each stage of the life cycle based on the life cycle assessment (LCA) method. The carbon emission prediction module accurately predicts future carbon emission trends through machine learning algorithms and the dynamic simulation data of the digital twin model, and evaluates the emission reduction potential of different optimization solutions. The optimization decision-making module combines the assessment and prediction results to provide low-carbon optimization suggestions for design optimization, construction adjustment, and operation management. The interaction and visualization module takes the three-dimensional digital twin model as the core, displays the carbon emission monitoring, assessment, and prediction results, and supports users to adjust the plan and update the model in real time.

[0086] The present invention applies digital twin technology to the dynamic monitoring and prediction of infrastructure carbon emissions, featuring real-time monitoring, accurate prediction, scenario simulation, and dynamic optimization. It is applicable to infrastructure fields such as highways, waterways, and buildings, providing scientific support and efficient solutions for achieving low-carbon goals.

[0087] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A digital twin-based dynamic monitoring and prediction system for infrastructure carbon emissions, characterized in that, By constructing a digital twin model and combining real-time data and historical data, dynamic monitoring, refined assessment, trend prediction and optimization decision-making of carbon emissions are realized. The system includes: A data collection module for collecting real-time carbon emission-related data of infrastructure during the design, construction and operation and maintenance phases through a sensor network and monitoring devices, including material usage data, construction energy consumption data, traffic flow data, equipment energy consumption data and environmental condition data; A digital twin model module for constructing a virtual digital twin model of infrastructure through 3D modeling, driving dynamic updates of carbon emission status through real-time data streams, and realizing bidirectional mapping between physical objects and virtual models; A carbon emission assessment module for using the digital twin model and life cycle assessment to conduct refined assessment of carbon emissions throughout the life cycle of infrastructure and generate phased carbon emission quantification reports; A carbon emission prediction module for using machine learning and dynamic simulation data of the digital twin model to conduct real-time prediction of future changes in carbon emissions and evaluate the emission reduction potential of optimization plans; An optimization decision-making module for simulating the carbon emission impacts of different design, construction and operation optimization plans based on the carbon emission assessment and prediction results and generating low-carbon optimization suggestions; An interaction and visualization module for displaying the carbon emission status of infrastructure with a 3D digital twin model as the core, providing dynamic visualization results of assessment, prediction and optimization plans, and obtaining parameters input by users through interaction to achieve real-time adjustment and feedback.

2. The dynamic monitoring and prediction system for infrastructure carbon emissions based on digital twin according to claim 1, characterized in that, The digital twin model module includes: A high-precision modeling unit for constructing a 3D geometric model of infrastructure and completely mapping the structural characteristics and functional status of physical objects; A real-time data mapping unit for mapping dynamic data collected by sensors to the virtual model and updating the carbon emission status in real time; A simulation and prediction unit for dynamically simulating and predicting multiple links of carbon emissions based on real-time data and historical data, where the multiple links include material usage, traffic operation and equipment energy consumption.

3. The infrastructure carbon emission dynamic monitoring and prediction system based on digital twin according to claim 2, wherein The simulation and prediction unit is also used to realize multi-scenario prediction, dynamically switch design plans, construction strategies and operation modes according to user instructions, and evaluate the long-term impacts of each scenario on carbon emissions.

4. A dynamic monitoring and prediction system for infrastructure carbon emissions based on digital twins according to claim 1, characterized in that, The carbon emission assessment module conducts phased assessment of carbon emissions in the design, construction and operation and maintenance phases through the dynamic data stream in the digital twin model, combined with the LCA method, and outputs a total life cycle carbon emission report.

5. A dynamic carbon emission monitoring and prediction system for infrastructure based on digital twin according to claim 1, characterized in that, The carbon emission prediction module conducts high-precision prediction of carbon emission trends through machine learning algorithms combined with real-time simulation results of the digital twin model, and simulates the implementation effects of optimization plans, where the machine learning algorithm is a convolutional neural network CNN or a long short-term memory network LSTM.

6. The dynamic carbon emission monitoring and prediction system for infrastructure based on digital twin according to claim 1, characterized in that, The optimization decision-making module simulates the emission reduction effects of different low-carbon plans through the digital twin model, including: In the design phase, simulating the impact of the application of low-carbon materials on carbon emissions; In the construction phase, simulating the effects of optimizing the use of construction equipment and adjusting transportation routes; In the operation and maintenance phase, simulating the improvement potential of intelligent traffic management and energy substitution on long-term carbon emissions.

7. A dynamic carbon emission monitoring and prediction system for infrastructure based on digital twin according to claim 1, characterized in that, The described interaction and visualization module displays the dynamic carbon emission status of the infrastructure and the simulation results of the optimization plan through a three-dimensional digital twin model, and shows the carbon emission changes and the feasibility of optimization suggestions in the form of heat maps and trend charts.

8. The dynamic carbon emission monitoring and prediction system for infrastructure based on digital twin according to claim 1, characterized in that, The described digital twin model module is also used to achieve real-time feedback, realize the reaction of the carbon emission prediction result to the physical system optimization through bidirectional mapping, and simulate the implementation process and potential benefits of the optimization measures in the virtual model.

9. The dynamic carbon emission monitoring and prediction system for infrastructure based on digital twin according to claim 1, characterized in that, The described carbon emission prediction module is also used to accurately trace the source through the digital twin model when the carbon emission trend is abnormal or exceeds the warning threshold, and provide repair and optimization suggestions in combination with real-time simulation.

10. A dynamic monitoring and prediction system for infrastructure carbon emissions based on digital twin according to claim 1, characterized in that, The described optimization decision-making module is used to achieve automatic optimization based on the digital twin model, adjust parameters in combination with the evaluation and prediction results, and simulate the emission reduction effect of the optimization measures in real time to achieve efficient low-carbon management.

Images