Park carbon emission supervision method, system and device and storage medium

Abstract

The invention discloses a park carbon emission supervision method, system and device and a storage medium, and the method comprises the steps: determining a park carbon emission target and a park carbon neutralization target through employing a dual-carbon target planning model based on the historical carbon emission data of an enterprise; according to the enterprise historical carbon emission data and the enterprise live-action space digital twinborn model, constructing a carbon emission model of the enterprises in the park, further constructing a park carbon emission model, and generating park carbon emission data and park carbon neutralization data; according to the park carbon emission data and a park carbon emission target, a first neural network model is adopted to generate a park carbon emission target completion degree; according to the park carbon emission target completion degree, the park carbon neutralization data and the park carbon neutralization target, a second neural network model is adopted to generate the park carbon neutralization target completion degree; and according to the park carbon emission target completion degree and the park carbon neutralization target completion degree, determining a regulation and control strategy of carbon emission and carbon neutralization. According to the invention, accurate management of park carbon emission can be realized.

Description

Technical Field

[0001] This invention relates to the field of carbon emission technology, and in particular to a method, system, equipment and storage medium for monitoring carbon emissions in industrial parks based on dual carbon targets. Background Technology

[0002] To achieve carbon peaking and carbon neutrality goals, some industrial parks have successively planned their own timelines and roadmaps for achieving carbon neutrality, accelerating their transition to low-carbon or even zero-carbon targets. To better formulate carbon reduction plans, it is necessary to account for and manage the carbon emissions of these parks in a refined manner. However, current traditional methods are vague about the current carbon emission status and complex carbon neutrality characteristics, only able to analyze a portion of the carbon footprint of a particular system. The accuracy and comprehensiveness of these carbon analysis results are low, hindering the formulation of carbon reduction plans for industrial parks, preventing the development of accurate low-carbon development strategies, and failing to meet the requirements of refined carbon emission management in the new era. Summary of the Invention

[0003] To address the above technical issues, this invention provides a method, system, equipment, and storage medium for monitoring carbon emissions in industrial parks, which improves the comprehensiveness and accuracy of carbon emission and carbon neutrality analysis and monitoring in industrial parks, enabling precise management of carbon emissions in industrial parks.

[0004] This invention provides a method for monitoring carbon emissions in industrial parks, comprising:

[0005] Obtain historical carbon emission data and a digital twin model of the enterprise's physical space;

[0006] Based on the historical carbon emission data of the enterprises, a pre-set dual-carbon target planning model is used to determine the carbon emission target and the carbon neutrality target of the park; the dual-carbon target planning model is a combination model of Transformer and Long Short-Term Memory Network.

[0007] Based on the historical carbon emission data of the enterprises and the digital twin model of the enterprises' real-world space, a carbon emission model of the enterprises in the park is constructed, and a carbon emission model of the park is constructed based on the carbon emission model of the enterprises in the park; carbon emission data and carbon neutrality data of the park are generated based on the carbon emission model of the park.

[0008] Based on the carbon emission data and carbon emission targets of the park, a preset first neural network model is used to generate the completion rate of the park's carbon emission targets; based on the completion rate of the park's carbon emission targets, the carbon neutrality data and carbon neutrality targets of the park, a preset second neural network model is used to generate the completion rate of the park's carbon neutrality targets.

[0009] Based on the achievement rates of the park's carbon emission targets and carbon neutrality targets, control strategies for carbon emissions and carbon neutrality are determined.

[0010] As an improvement to the above scheme, the step of determining the park's carbon emission target and carbon neutrality target based on the enterprise's historical carbon emission data and using a preset dual-carbon target planning model includes:

[0011] Obtain the preset dual-carbon target data for the industrial park;

[0012] Input the historical carbon emission data of the enterprise into the dual-carbon target planning model labeled with the dual-carbon target data of the park, and obtain the initial carbon emission target and the initial carbon neutrality target of the park output by the model.

[0013] Based on the enterprise's historical carbon emission data, the park's initial carbon emission target, and the park's initial carbon neutrality target, a preset support vector machine is used to determine the enterprise's dual carbon targets, and the determination result is obtained.

[0014] If the determination result is normal, then the initial carbon emission target of the park is determined as the park's carbon emission target, and the initial carbon neutrality target of the park is determined as the park's carbon neutrality target.

[0015] As an improvement to the above scheme, the dual-carbon target programming model includes a converter network, an attention module, a long short-term memory network, and a conditional random field layer.

[0016] The converter network is used to perform preliminary feature extraction and dependency analysis on the enterprise's historical carbon emission data and the park's dual-carbon target data; the converter network is constructed by stacking a multi-head self-attention layer, a masked multi-head self-attention layer, an encoder-decoder attention layer, and a feedforward neural network.

[0017] The attention module is used to optimize the output of the converter network;

[0018] The long short-term memory network is used to predict future carbon emission data and carbon neutrality data;

[0019] The conditional random field layer is used to optimize the prediction results of carbon emission targets and carbon neutrality targets, and outputs the initial carbon emission targets and the initial carbon neutrality targets of the park.

[0020] As an improvement to the above scheme, the generation of carbon emission data and carbon neutrality data of the park based on the park's carbon emission model includes:

[0021] Based on the carbon emission model of the park, calculate the carbon emission data of the park operation and the carbon emission data of enterprises in the park, and generate the park carbon emission data, which includes the amount and distribution of greenhouse gas emissions in the park.

[0022] Based on the carbon emission model of the park, calculate the carbon neutrality data of the park's operation and the carbon neutrality data of enterprises within the park, and combine the carbon emission data of the park to generate park carbon neutrality data. The park carbon neutrality data includes the carbon sink, carbon emission reduction, carbon sink distribution and carbon emission reduction distribution generated by carbon neutrality measures within the park.

[0023] The carbon emission data for park operation includes operational energy emission data and operational maintenance carbon emission data; the carbon emission data of enterprises within the park includes enterprise energy carbon emission data and enterprise production carbon emission data; the carbon neutrality data for park operation includes operational energy storage data, operational carbon sequestration data, and operational green electricity data; and the carbon neutrality data of enterprises within the park includes enterprise energy storage data, enterprise carbon sequestration data, and enterprise green electricity data.

[0024] As an improvement to the above scheme, the expression for the carbon emission model of the park is as follows:

[0025] M C =[X 3D E R ]

[0026]

[0027] In the formula, M C For the carbon emission model of the park, X 3D E is a digital twin model of the park's real-world space. R E is a carbon emission model for companies within the park. r For the carbon emission model of the r-th enterprise, This represents the actual carbon emissions from the power grid. This represents the actual carbon emissions from a gas-fired boiler. This represents the actual carbon emissions of a combined cooling, heating, and power (CCHP) unit. This represents the actual carbon emissions from heat. This represents the actual carbon emissions from natural gas. This refers to the conversion rate of the electro-gas conversion equipment.

[0028] As an improvement to the above scheme, the formula for calculating the carbon emission data of enterprises within the park is as follows:

[0029]

[0030] In the formula, For carbon emission data of enterprises within the park, N C J represents the number of firms. i Let m be the number of fuel types for the i-th enterprise. i,j Let be the mass of the j-th type of fuel consumed by the i-th enterprise. Let η be the fuel-standard coal carbon emission conversion factor for the j-th fuel of the i-th enterprise, A be the correction ratio factor, and η be the standard coal emission conversion factor.i,j Let e ​​be the combustion efficiency of the j-th fuel for the i-th enterprise, T be the total number of time periods for electricity consumption for the i-th enterprise, and e be the combustion efficiency of the j-th fuel for the i-th enterprise. i,t Let be the electricity consumption of the i-th enterprise in the t-th time period. ψ is the conversion factor for carbon emissions from electricity to standard coal equivalent. t Let K be the correction factor for electricity carbon emissions in the t-th time period. i p represents the total number of production activity categories for the i-th enterprise. i,k Let be the output value of the k-th production activity category of the i-th enterprise. The output value minus the standard coal carbon emission conversion factor for the k-th production activity category of the i-th enterprise;

[0031] The formula for calculating the carbon emission data of the park operation is as follows:

[0032]

[0033] In the formula, This refers to carbon emission data for the park's operations, where H represents the quantity of different fuel types used in the park's operations, and m represents the total carbon emissions. h The consumption quality of the h-th type of fuel for park operations. η is the fuel-standard coal carbon emission conversion factor for the h-th fuel, B is the correction ratio factor, and η is the standard coal emission conversion factor. h Let e ​​be the combustion efficiency of the h-th fuel, T be the total number of electricity consumption periods during park operation, and e be the combustion efficiency of the h-th fuel. τ For the electricity consumption in the τth time period, ψ is the conversion factor for carbon emissions from electricity to standard coal equivalent. τ Let q be the correction factor for electricity carbon emissions in the τth time period, X be the total number of date categories for park operation and maintenance, and q be the total number of dates for operation and maintenance. χ For the carbon emissions of the χth date category for the operation and maintenance of the park, μ χ The total number of dates for the x-th date category in the park's operation and maintenance;

[0034] The formula for calculating the carbon neutrality data of enterprises within the park is as follows:

[0035]

[0036] In the formula, E Cop-CZ For corporate carbon neutrality data, S i Let E be the number of different types of energy storage devices for the i-th enterprise. i,s Let be the energy stored in the s-th type of energy storage device of the i-th enterprise. η is the energy storage-standard coal carbon emission conversion factor for the s-th type of energy storage equipment of the i-th enterprise, C is the correction ratio factor, and η is the standard coal emission conversion factor. i,s Let P be the energy storage efficiency of the s-th type of energy storage device of the i-th enterprise. iLet E be the total number of green energy generation devices for the i-th enterprise. i,ρ Let ρ be the amount of green electricity generated by the i-th enterprise. Let ρ be the conversion factor between the electricity and standard coal equivalent of the ρth type of green electricity, D be the correction ratio factor, and θ be the standard coal equivalent. ρ For the utilization rate of the ρth type of green electricity, G i C represents the total number of carbon capture categories for the i-th enterprise. g Let g be the carbon sequestration value of the g-th carbon capture method for the i-th enterprise;

[0037] The formula for calculating the carbon neutrality data of the park's operation is as follows:

[0038]

[0039] In the formula, E P-CZ For carbon neutrality data of the park's operation, W represents the type and quantity of energy storage devices in the park, and E represents the carbon neutrality data of the park's operation. w The energy stored in the wth type of energy storage device in the park. η is the energy storage-standard coal carbon emission conversion factor for the w-th type of energy storage equipment in the park, F is the correction ratio factor, and η is the standard coal emission conversion factor. w Let E be the energy storage efficiency of the w-th type of energy storage device in the park, Ω be the total number of green electricity generation devices in the park, and E be the energy storage efficiency of the w-th type of energy storage device in the park. ω Let ω be the amount of green electricity generated in the park. Let ω be the conversion factor between the electricity and standard coal equivalent of the ωth type of green electricity, I be the correction ratio factor, and θ be the standard coal equivalent. ω Let Z be the utilization rate of the ωth type of green electricity, Z be the total number of carbon capture categories in the park, and C be the utilization rate of the ωth type of green electricity. ζ The carbon sequestration value is the result of the ζth carbon capture method in the park.

[0040] As an improvement to the above scheme, the first neural network model includes a first convolutional module, a second convolutional module, and a first fully connected layer connected in sequence; the input of the first convolutional module is the carbon emission data of the park and the carbon emission target of the park, and the output of the first fully connected layer is the completion degree of the carbon emission target of the park;

[0041] The second neural network model includes a third convolutional module, a second fully connected layer, a fourth convolutional module, and a third fully connected layer connected in sequence; the input of the third convolutional module is the carbon neutrality data of the park and the carbon neutrality target of the park, the input of the second fully connected layer is the output of the third convolutional module and the first fully connected layer, and the output of the third fully connected layer is the completion rate of the park's carbon emission target.

[0042] This invention also provides a carbon emission monitoring system for industrial parks, comprising:

[0043] The data acquisition module is used to acquire historical carbon emission data of enterprises and digital twin models of the enterprise's real-world space;

[0044] The target planning module is used to determine the park's carbon emission target and carbon neutrality target based on the enterprise's historical carbon emission data and using a preset dual-carbon target planning model; the dual-carbon target planning model is a combination model of Transformer and Long Short-Term Memory Network.

[0045] The model calculation module is used to construct carbon emission models of enterprises within the park based on the historical carbon emission data of the enterprises and the digital twin model of the enterprise's real-world space, and to construct the carbon emission model of the park based on the carbon emission models of the enterprises within the park; and to generate park carbon emission data and park carbon neutrality data based on the park's carbon emission model.

[0046] The target completion module is used to generate the park carbon emission target completion rate using a preset first neural network model based on the park carbon emission data and the park carbon emission target; and to generate the park carbon neutrality target completion rate using a preset second neural network model based on the park carbon emission target completion rate, the park carbon neutrality data and the park carbon neutrality target.

[0047] The regulation strategy module is used to determine the regulation strategy for carbon emissions and carbon neutrality based on the completion rate of the carbon emission target and the completion rate of the carbon neutrality target of the park.

[0048] The present invention also provides a computer device, including a processor and a memory, wherein the memory stores a computer program and the computer program is configured to be executed by the processor, wherein the processor executes the computer program to implement the park carbon emission monitoring method described in any of the preceding claims.

[0049] The present invention also provides a computer-readable storage medium storing a computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the carbon emission monitoring method for industrial parks described above.

[0050] Compared with existing technologies, the beneficial effects of the carbon emission monitoring method, system, equipment, and storage medium provided by this invention are as follows:

[0051] By using a dual-carbon target programming model composed of a converter and a long short-term memory network, based on historical carbon emission data of enterprises, the carbon emission targets and carbon neutrality targets of the industrial park are determined. This enables accurate and effective dual-carbon target programming, which is conducive to precise monitoring of carbon emissions in the park. A carbon emission model of enterprises within the park is constructed based on historical carbon emission data and a digital twin model of the enterprises' real-world spatial environment. Based on this model, a carbon emission model of the entire park is then built. This model accurately and comprehensively reflects the carbon emission characteristics of each enterprise and the park as a whole, achieving precise quantification and dynamic monitoring of carbon emissions, and providing a precise framework for subsequent carbon data calculation and analysis. Furthermore, based on the park's carbon emission model... The system generates carbon emission data and carbon neutrality data for the industrial park. Based on the carbon emission data and carbon emission targets, a pre-set first neural network model is used to generate the completion rate of the carbon emission targets. Based on the completion rate of the carbon emission targets, carbon neutrality data, and carbon neutrality targets, a pre-set second neural network model is used to generate the completion rate of the carbon neutrality targets. Finally, based on the completion rates of the carbon emission targets and carbon neutrality targets, control strategies for carbon emissions and carbon neutrality are determined. This system can monitor the completion status of carbon emissions and carbon neutrality targets in the park in real time, achieve precise supervision of carbon emissions in the park, and provide a more scientific and effective decision-making basis and solution for the park's dual-carbon management. Attached Figure Description

[0052] Figure 1 This is a schematic flowchart of a carbon emission monitoring method for industrial parks provided in an embodiment of the present invention;

[0053] Figure 2 This is a schematic diagram illustrating the application environment of a carbon emission monitoring method for industrial parks provided in an embodiment of the present invention;

[0054] Figure 3 This is a schematic diagram of the structure of a dual-carbon target programming model provided in an embodiment of the present invention;

[0055] Figure 4 This is a schematic diagram of the structure of the first neural network model and the second neural network model provided in the embodiments of the present invention;

[0056] Figure 5 This is a schematic diagram of the structure of a carbon emission monitoring system for a park provided in an embodiment of the present invention;

[0057] Figure 6 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present invention. Detailed Implementation

[0058] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0059] Please see Figure 1 , Figure 1 This is a schematic flowchart of a carbon emission monitoring method for industrial parks provided by an embodiment of the present invention. The carbon emission monitoring method for industrial parks includes:

[0060] S1: Obtain historical carbon emission data and a digital twin model of the enterprise's real-world space;

[0061] S2: Based on the historical carbon emission data of the enterprise, a preset dual-carbon target planning model is used to determine the carbon emission target and the carbon neutrality target of the park; the dual-carbon target planning model is a combination model of Transformer and Long Short-Term Memory Network.

[0062] S3: Based on the historical carbon emission data of the enterprises and the digital twin model of the enterprises' real-world space, construct a carbon emission model of the enterprises in the park, and construct a carbon emission model of the park based on the carbon emission model of the enterprises in the park; generate park carbon emission data and park carbon neutrality data based on the park's carbon emission model;

[0063] S4: Based on the carbon emission data of the park and the carbon emission target of the park, a preset first neural network model is used to generate the completion rate of the park's carbon emission target; based on the completion rate of the park's carbon emission target, the carbon neutrality data of the park and the carbon neutrality target of the park, a preset second neural network model is used to generate the completion rate of the park's carbon neutrality target.

[0064] S5: Determine the control strategies for carbon emissions and carbon neutrality based on the achievement rates of the carbon emission targets and carbon neutrality targets of the park.

[0065] Specifically, the carbon emission monitoring method for industrial parks in this embodiment can be applied to, for example... Figure 2In the application environment shown, the carbon emission monitoring method for the industrial park is implemented by a computing control platform 101. The computing control platform 101 communicates with a carbon footprint sensor 102 and a carbon emission model display device 103 via a communication channel. The carbon footprint sensor 102 collects carbon footprint data and transmits it to the computing control platform 101 for data processing. The carbon emission model display device 103 displays the data processing results from the computing control platform 101. The computing control platform 101 can generate a digital twin model of carbon emissions based on the carbon footprint data collected by the carbon footprint sensor 102. The computing control platform 101 includes, but is not limited to, at least one of a server, a high-performance computing cluster, an edge computing platform, and a hybrid computing platform, wherein the server can be implemented using a standalone server or a server cluster composed of multiple servers. The carbon footprint sensor 102 includes, but is not limited to, at least one of a smart meter, a smart gas flow sensor, a smart heat meter, a greenhouse gas sensor, a production material sensor, an equipment operating status sensor, a waste emission sensor, and a carbon capture sensor.

[0066] In step S1, carbon emission monitoring metadata for enterprises in the industrial park is obtained through carbon footprint sensing devices and the park's enterprise carbon emission monitoring database. This metadata includes: historical carbon emission data and a digital twin model of the enterprise's physical space. Historical carbon emission data includes: enterprise carbon rating data and historical carbon footprint data. Specifically, the enterprise carbon rating data is used to assess the enterprise's carbon emission intensity, energy efficiency, and emission reduction potential, while the historical carbon footprint data is used to analyze historical trends in enterprise carbon emissions and evaluate the effectiveness of emission reduction measures.

[0067] In step S2, the historical carbon emission data of enterprises is first preprocessed and converted into tensors for easier calculation. Tensors represent quantities with multiple dimensions and sizes in mathematical operations. The preprocessed historical carbon emission data is then input into a dual-carbon target programming model composed of a Transformer and a Long Short-Term Memory network for target programming, resulting in initial carbon emission targets and initial carbon neutrality targets for the industrial park. Both the initial carbon emission targets and the initial carbon neutrality targets output by the model are tensors.

[0068] As one optional embodiment, the step of determining the park's carbon emission target and carbon neutrality target based on the enterprise's historical carbon emission data using a preset dual-carbon target planning model includes:

[0069] Obtain the preset dual-carbon target data for the industrial park;

[0070] Input the historical carbon emission data of the enterprise into the dual-carbon target planning model labeled with the dual-carbon target data of the park, and obtain the initial carbon emission target and the initial carbon neutrality target of the park output by the model.

[0071] Based on the enterprise's historical carbon emission data, the park's initial carbon emission target, and the park's initial carbon neutrality target, a preset support vector machine is used to determine the enterprise's dual carbon targets, and the determination result is obtained.

[0072] If the determination result is normal, then the initial carbon emission target of the park is determined as the park's carbon emission target, and the initial carbon neutrality target of the park is determined as the park's carbon neutrality target.

[0073] Specifically, in step S2, preset dual-carbon target data for the industrial park is acquired as a label. This dual-carbon target data, along with historical carbon emission data of enterprises, is input into the dual-carbon target planning model to obtain the initial carbon emission target and the initial carbon neutrality target for the industrial park. This provides a preliminary plan for the carbon emission and carbon neutrality targets within the industrial park. The dual-carbon target data for the industrial park includes, but is not limited to, at least one of the following: time, emission reduction amount, cost, and emission reduction plan.

[0074] Furthermore, the initial carbon emission targets and carbon neutrality targets for the industrial park are evaluated. Specifically, a trained support vector machine (SVM) is used to discriminate the dual carbon targets of enterprises to obtain the results. The SVM can evaluate the rationality of enterprises' dual carbon targets from multiple dimensions based on their historical carbon emission data, the initial carbon emission targets of the industrial park, and the initial carbon neutrality targets. It can find the optimal classification hyperplane in high-dimensional space to determine whether the enterprises' dual carbon targets are consistent with the overall dual carbon target planning of the industrial park and the enterprises' own historical carbon emission situation.

[0075] The support vector machine outputs a judgment result indicating whether the enterprise's dual-carbon targets are normal or abnormal. If the judgment result indicates that the enterprise's dual-carbon targets are normal, the initial carbon emission target of the park is determined as the park's carbon emission target, and the initial carbon neutrality target of the park is determined as the park's carbon neutrality target. This simplifies the target setting process and improves management efficiency. If the judgment result indicates that the enterprise's dual-carbon targets are abnormal, the abnormal components in the initial carbon emission target and the initial carbon neutrality target of the park are identified, and a list of enterprises with abnormal dual-carbon targets within the park is obtained based on the abnormal components. Optionally, the list of enterprises with abnormal dual-carbon targets within the park can be used to identify enterprises with abnormal dual-carbon targets within the park. This allows for the development of differentiated dual-carbon target control strategies based on the park's carbon emission model for these enterprises. By developing personalized solutions based on the list of enterprises with abnormal dual-carbon targets within the park, it helps improve the efficiency and success rate of the park in achieving its overall dual-carbon targets.

[0076] For example, if the predicted carbon peak time and carbon neutrality time of a company based on its actual carbon emission data are significantly later than the predicted carbon peak time and carbon neutrality time corresponding to the company's dual carbon targets, it will be judged as abnormal. If the error between the predicted carbon peak time and carbon neutrality time of a company based on its actual carbon emission data and the predicted carbon peak time and carbon neutrality time corresponding to the company's dual carbon targets is less than a preset threshold, it will be judged as normal.

[0077] As one optional embodiment, the dual-carbon goal programming model includes a converter network, an attention module, a long short-term memory network, and a conditional random field layer;

[0078] The converter network is used to perform preliminary feature extraction and dependency analysis on the enterprise's historical carbon emission data and the park's dual-carbon target data; the converter network is constructed by stacking a multi-head self-attention layer, a masked multi-head self-attention layer, an encoder-decoder attention layer, and a feedforward neural network.

[0079] The attention module is used to optimize the output of the converter network;

[0080] The long short-term memory network is used to predict future carbon emission data and carbon neutrality data;

[0081] The conditional random field layer is used to optimize the prediction results of carbon emission targets and carbon neutrality targets, and outputs the initial carbon emission targets and the initial carbon neutrality targets of the park.

[0082] Specifically, please refer to Figure 3 , Figure 3 This is a schematic diagram of a dual-carbon target planning model provided in an embodiment of the present invention. Historical carbon emission data of enterprises and dual-carbon target data of industrial parks are input into the dual-carbon target planning model, which sequentially passes through several Transformer network modules, an attention module, a Long Short-Term Memory (LSTM) network, and a Conditional Random Field layer to obtain the initial carbon emission target and the initial carbon neutrality target of the industrial park. The initial carbon emission target and the initial carbon neutrality target represent the preliminary carbon emission target and preliminary carbon neutrality target that can be set based on historical data and current targets, respectively.

[0083] The Transformer network module is constructed by stacking multi-head self-attention layers, masked multi-head self-attention layers (Masked MHSA), encoder-decoder attention layers (Enc-Dec Attention), and feedforward neural networks (FFN). It is capable of performing preliminary feature extraction and dependency analysis on historical carbon emission data of enterprises and dual-carbon target data of industrial parks input into the dual-carbon target planning model. The attention module optimizes the output of the Transformer to meet the input requirements of the Long Short-Term Memory (LSTM) network and increases the weight of key feature data. The LSTM network consists of multiple LSTM layers and is used to model and predict future carbon emission and carbon neutrality data. Conditional Random Field (CRF) layers are used to optimize the prediction results of carbon emission and carbon neutrality targets, ensuring the consistency and reasonableness of the predicted data over time.

[0084] Further, in step S3, the enterprise's real-world spatial digital twin model and historical carbon emission data are input into the enterprise's standard carbon emission model to construct a carbon emission model for the enterprises within the park. Specifically, the computing control platform 101 inputs the enterprise's real-world spatial digital twin model into the enterprise's standard carbon emission model to initialize the real-world spatial digital twin sub-model of the carbon emission model for the enterprises within the park. Then, it inputs the enterprise's historical carbon emission data into the carbon emission model for the enterprises within the park after initializing the real-world spatial digital twin sub-model, thus obtaining the carbon emission model for the enterprises within the park. Subsequently, based on the enterprises included in the park, a carbon emission model for the park is constructed based on the carbon emission models of the enterprises within the park.

[0085] This embodiment focuses on achieving carbon peaking and carbon neutrality goals, targeting properties and enterprises within the industrial park. Based on real-scene 3D and digital twin information technologies, it studies and constructs a dual-carbon monitoring platform for the park. This platform enables the collection and calculation of carbon emission data, facilitating more precise carbon emission management and providing data support and basis for urban green and low-carbon development planning. Specifically, by acquiring digital twin models of enterprise real-scene spaces and combining them with carbon rating and historical carbon footprint data from the enterprise's historical carbon emission data, a comprehensive understanding of the enterprise's past carbon emission performance can be obtained. This platform can also intuitively reflect the actual situation of the enterprise's physical spatial layout and equipment operation. Constructing enterprise carbon emission models based on standard enterprise carbon emission models can accurately simulate and predict enterprise carbon emissions, helping park managers clearly grasp the overall carbon emission status of the park and providing strong support for enterprises and the park to deeply analyze carbon emission sources and assess emission reduction potential.

[0086] As one optional embodiment, the expression for the carbon emission model of the park is:

[0087] M C =[X 3D E R ]

[0088]

[0089] In the formula, M C For the carbon emission model of the park, X 3D E is a digital twin model of the park's real-world space. R E is a carbon emission model for companies within the park. r For the carbon emission model of the r-th enterprise, This represents the actual carbon emissions from the power grid. This represents the actual carbon emissions from a gas-fired boiler. This represents the actual carbon emissions of a combined cooling, heating, and power (CCHP) unit. This represents the actual carbon emissions from heat. This represents the actual carbon emissions from natural gas. This refers to the conversion rate of the electro-gas conversion equipment.

[0090] As one optional embodiment, the generation of park carbon emission data and park carbon neutrality data based on the park's carbon emission model includes:

[0091] Based on the carbon emission model of the park, calculate the carbon emission data of the park operation and the carbon emission data of enterprises in the park, and generate the park carbon emission data, which includes the amount and distribution of greenhouse gas emissions in the park.

[0092] Based on the carbon emission model of the park, calculate the carbon neutrality data of the park's operation and the carbon neutrality data of enterprises within the park, and combine the carbon emission data of the park to generate park carbon neutrality data. The park carbon neutrality data includes the carbon sink, carbon emission reduction, carbon sink distribution and carbon emission reduction distribution generated by carbon neutrality measures within the park.

[0093] The carbon emission data for park operation includes operational energy emission data and operational maintenance carbon emission data; the carbon emission data of enterprises within the park includes enterprise energy carbon emission data and enterprise production carbon emission data; the carbon neutrality data for park operation includes operational energy storage data, operational carbon sequestration data, and operational green electricity data; and the carbon neutrality data of enterprises within the park includes enterprise energy storage data, enterprise carbon sequestration data, and enterprise green electricity data.

[0094] Optionally, enterprise energy carbon emission data may include enterprise fuel carbon emission data and enterprise electricity consumption carbon emission data; carbon emission data of enterprises within the park may also include enterprise carbon emission benefit data, which is the production output value corresponding to unit carbon emission. Carbon neutrality data of enterprises within the park and carbon neutrality data of park operation may also include carbon neutrality cost data, including but not limited to wind and solar curtailment penalty cost data, energy conversion equipment operating cost data, energy storage equipment operating cost data, equipment depreciation cost data, carbon capture and carbon sequestration cost data, and carbon trading cost data, wherein carbon trading cost data includes but is not limited to free carbon quota data and carbon trading tiered price data.

[0095] Specifically, based on the park's carbon emission model, the park's operational carbon emission data, enterprise carbon emission data, operational carbon neutrality data, and enterprise carbon neutrality data are calculated and summarized. Park carbon emission data is generated based on the operational carbon emission data and enterprise carbon emission data, and then park carbon neutrality data is generated based on these data. The park's carbon emission data comprehensively characterizes the amount and distribution of greenhouse gas emissions within the park. The park carbon neutrality data includes the carbon sink, carbon reduction, carbon sink distribution, and carbon reduction distribution resulting from carbon neutrality measures within the park, comprehensively characterizing the effectiveness of these measures. Compared to existing technologies, the park carbon emission data in this embodiment includes not only enterprise carbon emission data but also operational carbon emission data generated by the park's public facilities and equipment.

[0096] This embodiment establishes an information-based carbon data collection mechanism, develops a carbon emission data collection template suitable for the park level, and establishes a standardized and routine carbon emission data collection mechanism. This improves the accuracy and coverage of carbon emission data, enabling the spatial cleaning, matching, and fusion of multi-source heterogeneous data such as land use, buildings, energy consumption, and enterprise operations. This results in the spatial statistics and presentation of the park's dual carbon data on a single map. Specifically, by constructing enterprise and park carbon emission models, precise quantification and dynamic monitoring of carbon emissions are achieved. This accurately reflects the carbon emission characteristics of each enterprise and the park as a whole, providing a precise framework for subsequent carbon data calculation and analysis. The carbon emission data generated by aggregating carbon emission data from park operations and enterprises based on the park's carbon emission model can clearly characterize the amount and distribution of greenhouse gas emissions within the park. By aggregating carbon neutrality data from park operations and enterprises and combining it with the park's carbon emission data, park carbon neutrality data that characterizes carbon sink volume, carbon emission reduction volume, carbon sink distribution, and carbon emission reduction distribution can be obtained. This can demonstrate the actual effects of various carbon neutrality measures within the park, help assess the contribution of different measures to carbon neutrality, and thus optimize resource allocation within the park, promoting the park to achieve its carbon neutrality goals more effectively.

[0097] As one optional embodiment, the formula for calculating the carbon emission data of enterprises within the park is as follows:

[0098]

[0099] In the formula, For carbon emission data of enterprises within the park, N C J represents the number of firms. i Let m be the number of fuel types for the i-th enterprise. i,j Let be the mass of the j-th type of fuel consumed by the i-th enterprise. Let η be the fuel-standard coal carbon emission conversion factor for the j-th fuel of the i-th enterprise, A be the correction ratio factor, and η be the standard coal emission conversion factor. i,j Let e ​​be the combustion efficiency of the j-th fuel for the i-th enterprise, T be the total number of time periods for electricity consumption for the i-th enterprise, and e be the combustion efficiency of the j-th fuel for the i-th enterprise. i,t Let be the electricity consumption of the i-th enterprise in the t-th time period. ψ is the conversion factor for carbon emissions from electricity to standard coal equivalent. t Let K be the correction factor for electricity carbon emissions in the t-th time period. i p represents the total number of production activity categories for the i-th enterprise. i,k Let be the output value of the k-th production activity category of the i-th enterprise. The output value minus the standard coal carbon emission conversion factor for the k-th production activity category of the i-th enterprise;

[0100] The formula for calculating the carbon emission data of the park operation is as follows:

[0101]

[0102] In the formula, This refers to carbon emission data for the park's operations, where H represents the quantity of different fuel types used in the park's operations, and m represents the total carbon emissions. h The consumption quality of the h-th type of fuel for park operations. η is the fuel-standard coal carbon emission conversion factor for the h-th fuel, B is the correction ratio factor, and η is the standard coal emission conversion factor. h Let e ​​be the combustion efficiency of the h-th fuel, T be the total number of electricity consumption periods during park operation, and e be the combustion efficiency of the h-th fuel. τ For the electricity consumption in the τth time period, ψ is the conversion factor for carbon emissions from electricity to standard coal equivalent. τ Let q be the correction factor for electricity carbon emissions in the τth time period, X be the total number of date categories for park operation and maintenance, and q be the total number of dates for operation and maintenance. χ For the carbon emissions of the χth date category for the operation and maintenance of the park, μ χ The total number of dates for the x-th date category in the park's operation and maintenance;

[0103] The formula for calculating the carbon neutrality data of enterprises within the park is as follows:

[0104]

[0105] In the formula, E Cop-CZ For corporate carbon neutrality data, S i Let E be the number of different types of energy storage devices for the i-th enterprise. i,s Let be the energy stored in the s-th type of energy storage device of the i-th enterprise. η is the energy storage-standard coal carbon emission conversion factor for the s-th type of energy storage equipment of the i-th enterprise, C is the correction ratio factor, and η is the standard coal emission conversion factor. i,s Let P be the energy storage efficiency of the s-th type of energy storage device of the i-th enterprise. i Let E be the total number of green energy generation devices for the i-th enterprise. i,ρ Let ρ be the amount of green electricity generated by the i-th enterprise. Let ρ be the conversion factor between the electricity and standard coal equivalent of the ρth type of green electricity, D be the correction ratio factor, and θ be the standard coal equivalent. ρ For the utilization rate of the ρth type of green electricity, G o C represents the total number of carbon capture categories for the i-th enterprise. g Let g be the carbon sequestration value of the g-th carbon capture method for the i-th enterprise;

[0106] The formula for calculating the carbon neutrality data of the park's operation is as follows:

[0107]

[0108] In the formula, E P-CZ For carbon neutrality data of the park's operation, W represents the type and quantity of energy storage devices in the park, and E represents the carbon neutrality data of the park's operation. w The energy stored in the wth type of energy storage device in the park. η is the energy storage-standard coal carbon emission conversion factor for the w-th type of energy storage equipment in the park, F is the correction ratio factor, and η is the standard coal emission conversion factor. w Let E be the energy storage efficiency of the w-th type of energy storage device in the park, Ω be the total number of green electricity generation devices in the park, and E be the energy storage efficiency of the w-th type of energy storage device in the park. ω Let ω be the amount of green electricity generated in the park. Let ω be the conversion factor between the electricity and standard coal equivalent of the ωth type of green electricity, I be the correction ratio factor, and θ be the standard coal equivalent. ω Let Z be the utilization rate of the ωth type of green electricity, Z be the total number of carbon capture categories in the park, and C be the utilization rate of the ωth type of green electricity. ζ The carbon sequestration value is the result of the ζth carbon capture method in the park.

[0109] Further, in step S4, the park's carbon emission data and carbon emission targets are input into the first neural network model to identify the completion rate of the park's carbon emission targets, generating a park carbon emission target completion rate. The park carbon emission target completion rate is used to monitor the completion status of the park's carbon emission targets in real time, evaluate the implementation effect of the park's carbon emission policies, and dynamically adjust the carbon quota allocation for enterprises within the park.

[0110] Then, the carbon emission target completion rate of the park, the carbon neutrality data of the park, and the carbon neutrality target of the park are input into the second neural network model to identify the carbon neutrality target completion rate of the park and generate the carbon neutrality target completion rate of the park.

[0111] As one optional embodiment, the first neural network model includes a first convolutional module, a second convolutional module, and a first fully connected layer connected in sequence; the input of the first convolutional module is the carbon emission data of the park and the carbon emission target of the park, and the output of the first fully connected layer is the completion degree of the carbon emission target of the park;

[0112] The second neural network model includes a third convolutional module, a second fully connected layer, a fourth convolutional module, and a third fully connected layer connected in sequence; the input of the third convolutional module is the carbon neutrality data of the park and the carbon neutrality target of the park, the input of the second fully connected layer is the output of the third convolutional module and the first fully connected layer, and the output of the third fully connected layer is the completion rate of the park's carbon emission target.

[0113] Specifically, please refer to Figure 4 The first neural network model comprises a first convolutional module, a second convolutional module, and a first fully connected layer connected in sequence. The carbon emission data and carbon emission targets of the industrial park are input to the first neural network model, passing through the first and second convolutional modules before entering the first fully connected layer. The first fully connected layer generates the completion rate of the carbon emission targets as the output of the first neural network model.

[0114] The second neural network model includes a third convolutional module, a second fully connected layer, a fourth convolutional module, and a third fully connected layer. The input to the third convolutional module is the carbon neutrality data and the carbon neutrality target of the park. The input to the second fully connected layer is the output of the third convolutional module and the carbon emission target completion rate of the park output by the first fully connected layer. The input to the fourth convolutional module is the output of the second fully connected layer. The input to the third fully connected layer is the output of the fourth convolutional module. Finally, the carbon neutrality target completion rate of the park is generated by the third fully connected layer as the output of the second neural network model.

[0115] The first, second, third, and fourth convolutional modules consist of, but are not limited to, convolutional layers, activation layers, and pooling layers.

[0116] This embodiment, through the combination of multiple convolutional modules and fully connected layers, can model the complex nonlinear relationship between carbon emissions and carbon neutrality data in the park, thereby more accurately reflecting the actual situation of carbon emissions and carbon neutrality in the park, and thus improving the accuracy of the assessment of the completion of carbon emission targets and carbon neutrality targets in the park; by utilizing the powerful data analysis and pattern recognition capabilities of neural networks, the completion rate of carbon emission targets in the park can be accurately calculated.

[0117] Furthermore, both the first and second neural network models specifically employ backpropagation (BP) neural networks. The specific training steps for the first and second neural network models include:

[0118] The carbon emission data, carbon emission targets, carbon neutrality data, and carbon neutrality targets of the park are normalized.

[0119] Initialize the neural network topology parameters of the first fully connected layer, the second fully connected layer, and the third fully connected layer;

[0120] The initial location of the sparrow population is generated using a sparrow search algorithm, the fitness of each individual sparrow in the population is calculated, and the location of the individual sparrows is updated based on the fitness.

[0121] Determine whether the sparrow search termination condition is met. If the sparrow search termination condition is met, output the optimal weight and the optimal threshold, and train the first neural network model and the second neural network model based on the optimal weight and the optimal threshold.

[0122] Specifically, the min-max normalization method is used to map the park's carbon emission data, carbon emission targets, carbon neutrality data, and carbon neutrality targets to the interval [a, b], thus achieving normalization. The specific formula for normalization is:

[0123]

[0124] In the formula, X scaled For the normalized result, X max X is the maximum value in a set of data. min Let be the minimum value in a set of data, 'a' be the lower normalization bound, and 'b' be the upper normalization bound.

[0125] Furthermore, based on the preset topology parameters of the BP neural network, the number of nodes in each layer is determined, the weight matrix is ​​initialized, the bias is initialized to a random value close to zero, and a suitable activation function is selected, thereby initializing the topology parameters of the BP neural networks in the first, second, and third fully connected layers. The topology parameters include the number of nodes in the input, hidden, and output layers of the BP neural network.

[0126] Furthermore, a sparrow search algorithm is used for parameter optimization. First, the initial location of the sparrow population is generated. Then, the fitness of each individual sparrow in the population is calculated, and the location of the individual sparrows is updated based on the fitness. Specifically, the fitness formula for the sparrow population and the location update formula for the sparrows belonging to the discoverer are as follows:

[0127]

[0128] In the formula, F X Let f([x] be the fitness matrix of the sparrow population. v,1 x v,2 …x v,d [x] represents the fitness value of a single sparrow. v,1 x v,2 …x v,d Let d represent the coordinates of a single sparrow in the search space, d be the dimension of the search space, and n be the number of sparrows. Let α be the position of the i-th sparrow belonging to the discoverer in the j-th dimension search space after t updates, where α is a random parameter. max Let be the maximum number of iterations, ST be the foraging safety threshold, Q be the normal random parameter, and L be a column vector with all elements equal to 1.

[0129] When the sparrow search meets the termination condition, the optimal weights and thresholds are output, and the BP neural network is trained based on these optimal weights and thresholds to obtain the trained first and second neural network models. This embodiment optimizes the training process of the BP neural network through the sparrow search algorithm, which can increase the breadth of the BP neural network's training parameter space and help find better initial solutions for BP neural network training. This improves the performance of the neural networks for identifying the completion of carbon emission targets and the completion of carbon neutrality targets in the industrial park, thereby providing a more scientific and effective decision-making basis and solution for the park's dual-carbon management.

[0130] Further, in step S5, a control strategy oriented towards the carbon emission target of the park is generated based on the completion rate of the park's carbon emission target, and a control strategy oriented towards the carbon neutrality target of the park is generated based on the completion rate of the park's carbon neutrality target. For example, if the target completion rate is lower than a preset value, the entry of enterprises with a carbon rating of high-carbon industries into the park will be restricted, and the park service content and prices for different enterprises will be adjusted according to their carbon ratings.

[0131] Optionally, the carbon emission target-oriented regulation strategy of the park includes, but is not limited to, restricting the access standards for enterprises with carbon ratings of high-carbon industries, and restricting and eliminating enterprises with high energy consumption, high pollution, and high carbon emissions; the carbon neutrality target-oriented regulation strategy of the park includes, but is not limited to, restricting the access standards for enterprises with carbon ratings of high-carbon industries, lowering the carbon emission baseline for enterprises with carbon ratings of high-carbon industries, increasing the carbon sink trading costs for enterprises in the park, optimizing the utilization rate of green electricity in the park, urging enterprises in the park to upgrade their production equipment, increasing the park's investment in energy storage equipment, and increasing the park's investment in carbon capture equipment.

[0132] This embodiment develops targeted control strategies based on the achievement of carbon emission targets in the park, closely focusing on the carbon emission targets and driving the park towards them. By generating control strategies based on the achievement of carbon neutrality targets in the park, the park can better balance the relationship between economic development and environmental protection, gradually achieving a green and low-carbon sustainable development model, thereby improving the scientific nature and accuracy of carbon emission management in the park.

[0133] Compared with existing technologies, this invention, through its embodiment, determines the carbon emission target and carbon neutrality target of the industrial park by using a dual-carbon target planning model composed of a converter and a long short-term memory network based on historical carbon emission data of enterprises. This enables accurate and effective dual-carbon target planning, which is beneficial for precise monitoring of carbon emissions in the park. Furthermore, it constructs carbon emission models for enterprises within the park based on historical carbon emission data and digital twin models of their real-world spatial locations, and then constructs a carbon emission model for the entire park based on these enterprise carbon emission models. This accurately and comprehensively reflects the carbon emission characteristics of each enterprise and the park as a whole, achieving precise quantification and dynamic monitoring of carbon emissions, and providing a precise framework for subsequent carbon data calculation and analysis. Moreover, based on… The park's carbon emission model generates carbon emission data and carbon neutrality data. Based on the park's carbon emission data and carbon emission targets, a pre-set first neural network model is used to generate the park's carbon emission target completion rate. Based on the park's carbon emission target completion rate, carbon neutrality data, and carbon neutrality targets, a pre-set second neural network model is used to generate the park's carbon neutrality target completion rate. Finally, based on the park's carbon emission target completion rate and carbon neutrality target completion rate, carbon emission and carbon neutrality control strategies are determined. This allows for real-time monitoring of the park's carbon emission and carbon neutrality target completion status, enabling precise supervision of park carbon emissions and providing a more scientific and effective decision-making basis and solution for the park's dual-carbon management.

[0134] Accordingly, the present invention also provides a park carbon emission monitoring system, which can realize all the processes of the park carbon emission monitoring method in the above embodiments.

[0135] Please see Figure 5 , Figure 5 This is a schematic diagram of a carbon emission monitoring system for a park provided by an embodiment of the present invention. The park carbon emission monitoring system includes:

[0136] Data acquisition module 501 is used to acquire historical carbon emission data of enterprises and digital twin models of enterprise real-world space;

[0137] The target planning module 502 is used to determine the park's carbon emission target and carbon neutrality target based on the enterprise's historical carbon emission data and using a preset dual-carbon target planning model; the dual-carbon target planning model is a combination model of Transformer and Long Short-Term Memory Network.

[0138] The model calculation module 503 is used to construct a carbon emission model of enterprises in the park based on the historical carbon emission data of the enterprises and the digital twin model of the enterprise's real-world space, and to construct a carbon emission model of the park based on the carbon emission model of the enterprises in the park; and to generate park carbon emission data and park carbon neutrality data based on the park's carbon emission model.

[0139] The target completion module 504 is used to generate the park carbon emission target completion rate using a preset first neural network model based on the park carbon emission data and the park carbon emission target; and to generate the park carbon neutrality target completion rate using a preset second neural network model based on the park carbon emission target completion rate, the park carbon neutrality data and the park carbon neutrality target.

[0140] The regulation strategy module 505 is used to determine the regulation strategy for carbon emissions and carbon neutrality based on the completion rate of the carbon emission target and the completion rate of the carbon neutrality target of the park.

[0141] Preferably, the step of determining the park's carbon emission target and carbon neutrality target based on the enterprise's historical carbon emission data using a preset dual-carbon target planning model includes:

[0142] Obtain the preset dual-carbon target data for the industrial park;

[0143] Input the historical carbon emission data of the enterprise into the dual-carbon target planning model labeled with the dual-carbon target data of the park, and obtain the initial carbon emission target and the initial carbon neutrality target of the park output by the model.

[0144] Based on the enterprise's historical carbon emission data, the park's initial carbon emission target, and the park's initial carbon neutrality target, a preset support vector machine is used to determine the enterprise's dual carbon targets, and the determination result is obtained.

[0145] If the determination result is normal, then the initial carbon emission target of the park is determined as the park's carbon emission target, and the initial carbon neutrality target of the park is determined as the park's carbon neutrality target.

[0146] Preferably, the dual-carbon goal programming model includes a converter network, an attention module, a long short-term memory network, and a conditional random field layer;

[0147] The converter network is used to perform preliminary feature extraction and dependency analysis on the enterprise's historical carbon emission data and the park's dual-carbon target data; the converter network is constructed by stacking a multi-head self-attention layer, a masked multi-head self-attention layer, an encoder-decoder attention layer, and a feedforward neural network.

[0148] The attention module is used to optimize the output of the converter network;

[0149] The long short-term memory network is used to predict future carbon emission data and carbon neutrality data;

[0150] The conditional random field layer is used to optimize the prediction results of carbon emission targets and carbon neutrality targets, and outputs the initial carbon emission targets and the initial carbon neutrality targets of the park.

[0151] Preferably, the generation of carbon emission data and carbon neutrality data of the park based on the park's carbon emission model includes:

[0152] Based on the carbon emission model of the park, calculate the carbon emission data of the park operation and the carbon emission data of enterprises in the park, and generate the park carbon emission data, which includes the amount and distribution of greenhouse gas emissions in the park.

[0153] Based on the carbon emission model of the park, calculate the carbon neutrality data of the park's operation and the carbon neutrality data of enterprises within the park, and combine the carbon emission data of the park to generate park carbon neutrality data. The park carbon neutrality data includes the carbon sink, carbon emission reduction, carbon sink distribution and carbon emission reduction distribution generated by carbon neutrality measures within the park.

[0154] The carbon emission data for park operation includes operational energy emission data and operational maintenance carbon emission data; the carbon emission data of enterprises within the park includes enterprise energy carbon emission data and enterprise production carbon emission data; the carbon neutrality data for park operation includes operational energy storage data, operational carbon sequestration data, and operational green electricity data; and the carbon neutrality data of enterprises within the park includes enterprise energy storage data, enterprise carbon sequestration data, and enterprise green electricity data.

[0155] Preferably, the expression for the carbon emission model of the park is:

[0156] M C =[X 3D E R ]

[0157]

[0158] In the formula, M C For the carbon emission model of the park, X 3D E is a digital twin sub-model of the park's real-world space. R E is a carbon emission model for companies within the park. r For the carbon emission model of the r-th enterprise, This represents the actual carbon emissions from the power grid. This represents the actual carbon emissions from a gas-fired boiler. This represents the actual carbon emissions of a combined cooling, heating, and power (CCHP) unit. This represents the actual carbon emissions from heat. This represents the actual carbon emissions from natural gas. This refers to the conversion rate of the electro-gas conversion equipment.

[0159] Preferably, the formula for calculating the carbon emission data of enterprises within the park is as follows:

[0160]

[0161] In the formula, For carbon emission data of enterprises within the park, N C J represents the number of firms. i Let m be the number of fuel types for the i-th enterprise. i,j Let be the mass of the j-th type of fuel consumed by the i-th enterprise. Let η be the fuel-standard coal carbon emission conversion factor for the j-th fuel of the i-th enterprise, A be the correction ratio factor, and η be the standard coal emission conversion factor. i,j Let e ​​be the combustion efficiency of the j-th fuel for the i-th enterprise, T be the total number of time periods for electricity consumption for the i-th enterprise, and e be the combustion efficiency of the j-th fuel for the i-th enterprise. i,t Let be the electricity consumption of the i-th enterprise in the t-th time period. ψ is the conversion factor for carbon emissions from electricity to standard coal equivalent. t Let K be the correction factor for electricity carbon emissions in the t-th time period. i p represents the total number of production activity categories for the i-th enterprise. i,k Let be the output value of the k-th production activity category of the i-th enterprise. The output value minus the standard coal carbon emission conversion factor for the k-th production activity category of the i-th enterprise;

[0162] The formula for calculating the carbon emission data of the park operation is as follows:

[0163]

[0164] In the formula, This refers to carbon emission data for the park's operations, where H represents the quantity of different fuel types used in the park's operations, and m represents the total carbon emissions. h The consumption quality of the h-th type of fuel for park operations. η is the fuel-standard coal carbon emission conversion factor for the h-th fuel, B is the correction ratio factor, and η is the standard coal emission conversion factor. h Let e ​​be the combustion efficiency of the h-th fuel, T be the total number of electricity consumption periods during park operation, and e be the combustion efficiency of the h-th fuel. τ For the electricity consumption in the τth time period, ψ is the conversion factor for carbon emissions from electricity to standard coal equivalent. τ Let q be the correction factor for electricity carbon emissions in the τth time period, X be the total number of date categories for park operation and maintenance, and q be the total number of dates for operation and maintenance. χ For the carbon emissions of the χth date category for the operation and maintenance of the park, μ χ The total number of dates for the x-th date category in the park's operation and maintenance;

[0165] The formula for calculating the carbon neutrality data of enterprises within the park is as follows:

[0166]

[0167] In the formula, E Cop-CZ For corporate carbon neutrality data, S iLet E be the number of different types of energy storage devices for the i-th enterprise. i,s Let be the energy stored in the s-th type of energy storage device of the i-th enterprise. η is the energy storage-standard coal carbon emission conversion factor for the s-th type of energy storage equipment of the i-th enterprise, C is the correction ratio factor, and η is the standard coal emission conversion factor. i,s Let P be the energy storage efficiency of the s-th type of energy storage device of the i-th enterprise. i Let E be the total number of green energy generation devices for the i-th enterprise. i,ρ Let ρ be the amount of green electricity generated by the i-th enterprise. Let ρ be the conversion factor between the electricity and standard coal equivalent of the ρth type of green electricity, D be the correction ratio factor, and θ be the standard coal equivalent. ρ For the utilization rate of the ρth type of green electricity, G o C represents the total number of carbon capture categories for the i-th enterprise. g Let g be the carbon sequestration value of the g-th carbon capture method for the i-th enterprise;

[0168] The formula for calculating the carbon neutrality data of the park's operation is as follows:

[0169]

[0170] In the formula, E P-CZ For carbon neutrality data of the park's operation, W represents the type and quantity of energy storage devices in the park, and E represents the carbon neutrality data of the park's operation. w The energy stored in the wth type of energy storage device in the park. η is the energy storage-standard coal carbon emission conversion factor for the w-th type of energy storage equipment in the park, F is the correction ratio factor, and η is the standard coal emission conversion factor. w Let E be the energy storage efficiency of the w-th type of energy storage device in the park, Ω be the total number of green electricity generation devices in the park, and E be the energy storage efficiency of the w-th type of energy storage device in the park. ω Let ω be the amount of green electricity generated in the park. Let ω be the conversion factor between the electricity and standard coal equivalent of the ωth type of green electricity, I be the correction ratio factor, and θ be the standard coal equivalent. ω Let Z be the utilization rate of the ωth type of green electricity, Z be the total number of carbon capture categories in the park, and C be the utilization rate of the ωth type of green electricity. ζ The carbon sequestration value is the result of the ζth carbon capture method in the park.

[0171] Preferably, the first neural network model includes a first convolutional module, a second convolutional module, and a first fully connected layer connected in sequence; the input of the first convolutional module is the carbon emission data of the park and the carbon emission target of the park, and the output of the first fully connected layer is the completion degree of the carbon emission target of the park;

[0172] The second neural network model includes a third convolutional module, a second fully connected layer, a fourth convolutional module, and a third fully connected layer connected in sequence; the input of the third convolutional module is the carbon neutrality data of the park and the carbon neutrality target of the park, the input of the second fully connected layer is the output of the third convolutional module and the first fully connected layer, and the output of the third fully connected layer is the completion rate of the park's carbon emission target.

[0173] In specific implementation, the working principle, control process and technical effects of the park carbon emission monitoring system provided in this embodiment of the invention are the same as those of the park carbon emission monitoring method in the above embodiments, and will not be repeated here.

[0174] See Figure 6 , Figure 6 This is a structural block diagram of a computer device provided in an embodiment of the present invention. The computer device includes: a processor 601, a memory 602, and a computer program stored in the memory 602 and executable on the processor 601. When the processor 601 executes the computer program, it implements the steps in the above-described embodiments of the park carbon emission monitoring method. Alternatively, when the processor 601 executes the computer program, it implements the functions of each module / unit in the above-described system embodiments.

[0175] For example, the computer program may be divided into one or more modules / units, which are stored in the memory 602 and executed by the processor 601 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the computer device.

[0176] The computer device may include, but is not limited to, a processor 601 and a memory 602. Those skilled in the art will understand that the schematic diagram is merely an example of a computer device and does not constitute a limitation on the computer device. It may include more or fewer components than illustrated, or combine certain components, or different components. For example, the computer device may also include input / output devices, network access devices, buses, etc.

[0177] The processor 601 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor 601 is the control center of the computer device, connecting various parts of the entire computer device through various interfaces and lines.

[0178] The memory 602 can be used to store the computer programs and / or modules. The processor 601 implements various functions of the computer device by running or executing the computer programs and / or modules stored in the memory 602 and calling the data stored in the memory 602. The memory 602 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 602 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital card (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0179] Wherein, if the modules / units integrated into the computer device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor 601, it can implement the steps of the various method embodiments described above. Wherein, the computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or system capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0180] This invention also provides a computer-readable storage medium, which includes a stored computer program, wherein the computer program, when running, controls the device where the computer-readable storage medium is located to execute the park carbon emission monitoring method described in any of the above embodiments.

[0181] This invention provides a method, system, equipment, and storage medium for monitoring carbon emissions in industrial parks. Its advantages include: determining the park's carbon emission targets and carbon neutrality targets using a dual-carbon target programming model composed of a converter and a long short-term memory network, based on historical carbon emission data of enterprises. This enables accurate and effective dual-carbon target programming, facilitating precise monitoring of carbon emissions in the park. Furthermore, it constructs carbon emission models for enterprises within the park based on historical carbon emission data and digital twin models of their real-world spatial locations, and then constructs a carbon emission model for the entire park based on these enterprise carbon emission models. This accurately and comprehensively reflects the carbon emission characteristics of each enterprise and the park as a whole, achieving precise quantification and dynamic monitoring of carbon emissions, and providing a basis for subsequent carbon data calculation and analysis. The system provides a precise framework; subsequently, it generates carbon emission data and carbon neutrality data for the park based on the park's carbon emission model; according to the park's carbon emission data and carbon emission targets, it uses a preset first neural network model to generate the park's carbon emission target completion rate, and according to the park's carbon emission target completion rate, carbon neutrality data, and carbon neutrality targets, it uses a preset second neural network model to generate the park's carbon neutrality target completion rate; finally, based on the park's carbon emission target completion rate and carbon neutrality target completion rate, it determines the carbon emission and carbon neutrality control strategies, enabling real-time monitoring of the park's carbon emission and carbon neutrality target completion status, achieving precise supervision of park carbon emissions, and providing a more scientific and effective decision-making basis and solution for the park's dual-carbon management.

[0182] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for monitoring carbon emissions in an industrial park, characterized in that, include: Obtain historical carbon emission data and a digital twin model of the enterprise's physical space; Based on the historical carbon emission data of the enterprises, a pre-set dual-carbon target planning model is used to determine the carbon emission target and the carbon neutrality target of the park; the dual-carbon target planning model is a combination model of Transformer and Long Short-Term Memory Network. Based on the historical carbon emission data of the enterprises and the digital twin model of the enterprises' real-world space, a carbon emission model of the enterprises in the park is constructed, and a carbon emission model of the park is constructed based on the carbon emission model of the enterprises in the park; carbon emission data and carbon neutrality data of the park are generated based on the carbon emission model of the park. Based on the carbon emission data and carbon emission targets of the park, a preset first neural network model is used to generate the completion rate of the park's carbon emission targets; based on the completion rate of the park's carbon emission targets, the carbon neutrality data and carbon neutrality targets of the park, a preset second neural network model is used to generate the completion rate of the park's carbon neutrality targets. Based on the achievement rates of the park's carbon emission targets and carbon neutrality targets, control strategies for carbon emissions and carbon neutrality are determined.

2. The carbon emission monitoring method for industrial parks as described in claim 1, characterized in that, Based on the enterprise's historical carbon emission data, a pre-set dual-carbon target planning model is used to determine the park's carbon emission target and carbon neutrality target, including: Obtain the preset dual-carbon target data for the industrial park; Input the historical carbon emission data of the enterprise into the dual-carbon target planning model labeled with the dual-carbon target data of the park, and obtain the initial carbon emission target and the initial carbon neutrality target of the park output by the model. Based on the enterprise's historical carbon emission data, the park's initial carbon emission target, and the park's initial carbon neutrality target, a preset support vector machine is used to determine the enterprise's dual carbon targets, and the determination result is obtained. If the determination result is normal, then the initial carbon emission target of the park is determined as the park's carbon emission target, and the initial carbon neutrality target of the park is determined as the park's carbon neutrality target.

3. The method for monitoring carbon emissions in industrial parks as described in claim 2, characterized in that, The dual-carbon target programming model includes a converter network, an attention module, a long short-term memory network, and a conditional random field layer; The converter network is used to perform preliminary feature extraction and dependency analysis on the enterprise's historical carbon emission data and the park's dual-carbon target data; the converter network is constructed by stacking a multi-head self-attention layer, a masked multi-head self-attention layer, an encoder-decoder attention layer, and a feedforward neural network. The attention module is used to optimize the output of the converter network; The long short-term memory network is used to predict future carbon emission data and carbon neutrality data; The conditional random field layer is used to optimize the prediction results of carbon emission targets and carbon neutrality targets, and outputs the initial carbon emission targets and the initial carbon neutrality targets of the park.

4. The method for monitoring carbon emissions in industrial parks as described in claim 1, characterized in that, The generation of carbon emission data and carbon neutrality data for the park based on the park's carbon emission model includes: Based on the carbon emission model of the park, calculate the carbon emission data of the park operation and the carbon emission data of enterprises in the park, and generate the park carbon emission data, which includes the amount and distribution of greenhouse gas emissions in the park. Based on the carbon emission model of the park, calculate the carbon neutrality data of the park's operation and the carbon neutrality data of enterprises within the park, and combine the carbon emission data of the park to generate park carbon neutrality data. The park carbon neutrality data includes the carbon sink, carbon emission reduction, carbon sink distribution and carbon emission reduction distribution generated by carbon neutrality measures within the park. The carbon emission data for park operation includes operational energy emission data and operational maintenance carbon emission data; the carbon emission data of enterprises within the park includes enterprise energy carbon emission data and enterprise production carbon emission data; the carbon neutrality data for park operation includes operational energy storage data, operational carbon sequestration data, and operational green electricity data; and the carbon neutrality data of enterprises within the park includes enterprise energy storage data, enterprise carbon sequestration data, and enterprise green electricity data.

5. The carbon emission monitoring method for industrial parks as described in claim 4, characterized in that, The expression for the carbon emission model of the park is as follows: M C =[X 3D E R ] In the formula, M C For the carbon emission model of the park, X 3D E is a digital twin model of the park's real-world space. R E is a carbon emission model for companies within the park. r For the carbon emission model of the r-th enterprise, This represents the actual carbon emissions from the power grid. This represents the actual carbon emissions from a gas-fired boiler. This represents the actual carbon emissions of a combined cooling, heating, and power (CCHP) unit. This represents the actual carbon emissions from heat. This represents the actual carbon emissions from natural gas. This refers to the conversion rate of the electro-gas conversion equipment.

6. The carbon emission monitoring method for industrial parks as described in claim 4, characterized in that, The formula for calculating the carbon emission data of enterprises within the park is as follows: In the formula, For carbon emission data of enterprises within the park, N C J represents the number of firms. i Let m be the number of fuel types for the i-th enterprise. i,j Let be the mass of the j-th type of fuel consumed by the i-th enterprise. Let η be the fuel-standard coal carbon emission conversion factor for the j-th fuel of the i-th enterprise, A be the correction ratio factor, and η be the standard coal emission conversion factor. i,j Let e ​​be the combustion efficiency of the j-th fuel for the i-th enterprise, T be the total number of time periods for electricity consumption for the i-th enterprise, and e be the combustion efficiency of the j-th fuel for the i-th enterprise. i,t Let be the electricity consumption of the i-th enterprise in the t-th time period. ψ is the conversion factor for carbon emissions from electricity to standard coal equivalent. t Let K be the correction factor for electricity carbon emissions in the t-th time period. i p represents the total number of production activity categories for the i-th enterprise. i,k Let be the output value of the k-th production activity category of the i-th enterprise. The output value minus the standard coal carbon emission conversion factor for the k-th production activity category of the i-th enterprise; The formula for calculating the carbon emission data of the park operation is as follows: In the formula, This refers to carbon emission data for the park's operations, where H represents the quantity of different fuel types used in the park's operations, and m represents the total carbon emissions. h The consumption quality of the h-th type of fuel for park operations. η is the fuel-standard coal carbon emission conversion factor for the h-th fuel, B is the correction ratio factor, and η is the standard coal emission conversion factor. h Let e ​​be the combustion efficiency of the h-th fuel, T be the total number of electricity consumption periods during park operation, and e be the combustion efficiency of the h-th fuel. τ For the electricity consumption in the τth time period, ψ is the conversion factor for carbon emissions from electricity to standard coal equivalent. τ Let q be the correction factor for electricity carbon emissions in the τth time period, X be the total number of date categories for park operation and maintenance, and q be the total number of dates for operation and maintenance. χ For the carbon emissions of the χth date category for the operation and maintenance of the park, μ χ The total number of dates for the x-th date category in the park's operation and maintenance; The formula for calculating the carbon neutrality data of enterprises within the park is as follows: In the formula, E Cop-CZ For corporate carbon neutrality data, S i Let E be the number of different types of energy storage devices for the i-th enterprise. i,s Let be the energy stored in the s-th type of energy storage device of the i-th enterprise. η is the energy storage-standard coal carbon emission conversion factor for the s-th type of energy storage equipment of the i-th enterprise, C is the correction ratio factor, and η is the standard coal emission conversion factor. i,s Let P be the energy storage efficiency of the s-th type of energy storage device of the i-th enterprise. e Let E be the total number of green energy generation devices for the i-th enterprise. j,ρ Let ρ be the amount of green electricity generated by the i-th enterprise. Let ρ be the conversion factor between the electricity and standard coal equivalent of the ρth type of green electricity, D be the correction ratio factor, and θ be the standard coal equivalent. ρ For the utilization rate of the ρth type of green electricity, G i C represents the total number of carbon capture categories for the i-th enterprise. g Let g be the carbon sequestration value of the g-th carbon capture method for the i-th enterprise; The formula for calculating the carbon neutrality data of the park's operation is as follows: In the formula, E P-CZ For carbon neutrality data of the park's operation, W represents the type and quantity of energy storage devices in the park, and E represents the carbon neutrality data of the park's operation. w The energy stored in the wth type of energy storage device in the park. η is the energy storage-standard coal carbon emission conversion factor for the w-th type of energy storage equipment in the park, F is the correction ratio factor, and η is the standard coal emission conversion factor. w Let E be the energy storage efficiency of the w-th type of energy storage device in the park, Ω be the total number of green electricity generation devices in the park, and E be the energy storage efficiency of the w-th type of energy storage device in the park. ω Let ω be the amount of green electricity generated in the park. Let ω be the conversion factor between the electricity and standard coal equivalent of the ωth type of green electricity, I be the correction ratio factor, and θ be the standard coal equivalent. ω Let Z be the utilization rate of the ωth type of green electricity, Z be the total number of carbon capture categories in the park, and C be the utilization rate of the ωth type of green electricity. ζ The carbon sequestration value is the result of the ζth carbon capture method in the park.

7. The carbon emission monitoring method for industrial parks as described in claim 1, characterized in that, The first neural network model includes a first convolutional module, a second convolutional module, and a first fully connected layer connected in sequence; the input of the first convolutional module is the carbon emission data of the park and the carbon emission target of the park, and the output of the first fully connected layer is the completion degree of the carbon emission target of the park; The second neural network model includes a third convolutional module, a second fully connected layer, a fourth convolutional module, and a third fully connected layer connected in sequence; the input of the third convolutional module is the carbon neutrality data of the park and the carbon neutrality target of the park, the input of the second fully connected layer is the output of the third convolutional module and the first fully connected layer, and the output of the third fully connected layer is the completion rate of the park's carbon emission target.

8. A carbon emission monitoring system for industrial parks, characterized in that, include: The data acquisition module is used to acquire historical carbon emission data of enterprises and digital twin models of the enterprise's real-world space; The target planning module is used to determine the park's carbon emission target and carbon neutrality target based on the enterprise's historical carbon emission data and using a preset dual-carbon target planning model; the dual-carbon target planning model is a combination model of Transformer and Long Short-Term Memory Network. The model calculation module is used to construct carbon emission models of enterprises within the park based on the historical carbon emission data of the enterprises and the digital twin model of the enterprise's real-world space, and to construct the carbon emission model of the park based on the carbon emission models of the enterprises within the park; and to generate park carbon emission data and park carbon neutrality data based on the park's carbon emission model. The target completion module is used to generate the park carbon emission target completion rate using a preset first neural network model based on the park carbon emission data and the park carbon emission target; and to generate the park carbon neutrality target completion rate using a preset second neural network model based on the park carbon emission target completion rate, the park carbon neutrality data and the park carbon neutrality target. The regulation strategy module is used to determine the regulation strategy for carbon emissions and carbon neutrality based on the completion rate of the carbon emission target and the completion rate of the carbon neutrality target of the park.

9. A computer device, characterized in that, It includes a processor and a memory, the memory storing a computer program configured to be executed by the processor, the processor executing the computer program to implement the park carbon emission monitoring method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the device containing the computer-readable storage medium executes the computer program, it implements the park carbon emission monitoring method as described in any one of claims 1 to 7.

Images