An AI-based carbon neutrality grid evaluation system

Abstract

The present invention discloses a carbon neutrality grid evaluation system based on artificial intelligence, which relates to the technical field of carbon neutrality. The system combines multiple data sources to further achieve high-resolution monitoring of CO2 emission concentration and low-altitude imaging, thereby providing a more accurate electronic map of CO2 distribution. In the electronic map of CO2 distribution, the CO2 emission conditions, carbon capture data, and offset data at different geographical locations are distinguished, and real-time monitoring is carried out to summarize and establish them, providing a comprehensive carbon status data set; by using deep machine learning technology, the relationship between environmental factor Hjyz, capture coefficient Bzxs, and offset coefficient Dxxs can be better understood in multi-dimensional data information, thereby providing a more accurate neutralization evaluation index Zhpg. Through the threshold evaluation module, the ability to analyze historical data and calculate the average evaluation threshold Q is provided, further determining the accuracy of decision-making.

Description

Technical Field

[0001] The present invention relates to the technical field of carbon neutralization, and specifically to a carbon neutralization grid evaluation system based on artificial intelligence. Background Art

[0002] With the continuous intensification of climate change problems, carbon neutralization has become one of the key strategies to address the global challenge of greenhouse gas emissions. Scientists and enterprises are actively seeking innovative methods to reduce carbon emissions and achieve carbon neutralization. At the same time, the application of artificial intelligence technology in the field of carbon neutralization has become increasingly important. Artificial intelligence technology can help monitor emissions in real time, optimize carbon capture and offset strategies, and provide intelligent decision-making support.

[0003] Although carbon neutralization can offset and store carbon dioxide in the air, to accurately evaluate the carbon neutralization index, not only the emission concentration of carbon dioxide in the air, the quantity of adsorbents, and the density of vegetation need to be considered, but also various factors such as the changes in the surrounding environment during the adsorbent regeneration process and the growth cycle of vegetation need to be considered. Moreover, the distribution of carbon dioxide is not regionally divided, and it is impossible to further evaluate carbon neutralization in different geographical locations, resulting in uncertainty in decision-making and inefficiency of carbon neutralization plans. Summary of the Invention

[0004] Aiming at the deficiencies of the prior art, the present invention provides a carbon neutralization grid evaluation system based on artificial intelligence, which solves the problems mentioned in the above background art.

[0005] To achieve the above objectives, the present invention is realized through the following technical solutions: A carbon neutralization grid evaluation system based on artificial intelligence includes a regional division module, a data collection module, a data processing module, a carbon neutralization analysis module, and a threshold evaluation module;

[0006] The regional division module is used to monitor the CO 2 emission concentration Pfd in different geographical locations by using a gas analyzer, and at the same time use a drone to patrol the geographical locations of CO 2 emissions and conduct low-altitude imaging, and simulate and obtain a CO 2 distribution electronic map based on artificial intelligence technology. According to the range of CO 2 emissions, the CO 2 distribution electronic map is segmented into several grid-like regions, and the nearby vegetation coverage area Zbfg is determined;

[0007] The data collection module is used to monitor the CO 2 emission status, carbon capture status, and carbon offset status in different geographical locations in real time, and sequentially generate CO 2Status data, carbon capture data, and carbon offset data are summarized and established into a carbon status dataset;

[0008] The data processing module is used to clean and extract features from relevant data information in the carbon status dataset, and standardize the processed data information according to the dimensionless processing technology to unify the units;

[0009] The carbon neutralization analysis module is used to adsorb CO 2 , and analyze the surrounding environmental impact during the regeneration process of the adsorbent to obtain the environmental factor Hjyz, and associate the environmental factor Hjyz with the CO 2 emission concentration Pfd to obtain the capture coefficient Bzxs, analyze and calculate the vegetation coverage area Zbfg and the vegetation growth status to generate the offset coefficient Dxxs, and use artificial intelligence technology for in-depth machine learning analysis to obtain the neutralization evaluation index Zhpg. The neutralization evaluation index Zhpg is obtained through the following formula:

[0010] ;

[0011] In the formula, Jyl represents the CO 2 trading volume, , and respectively represent the weight values of the offset coefficient Dxxs, the CO 2 trading volume Jyl, and the capture coefficient Bzxs. Among them, , , , and , R represents a constant correction coefficient;

[0012] The threshold evaluation module is used to extract relevant data information in the carbon status dataset on a weekly, monthly, or quarterly basis within the historical time axis to obtain historical data and calculate the average value to obtain the average evaluation threshold Q, and compare and analyze the neutralization evaluation index Zhpg with the average evaluation threshold Q to obtain a warning evaluation report.

[0013] Preferably, several grid-like regions are marked as region i1, region i2,..., region in, and the corresponding vegetation coverage areas Zbfg of several mesh regions are sequentially transmitted to the carbon status dataset to analyze and calculate the corresponding neutralization evaluation indexes Zhpg of region i1, region i2,..., region in.

[0014] Preferably, the data acquisition module will collect the CO 2 status data, carbon capture data, and carbon offset data in region i1, region i2,..., region in in real time, including a carbon capture unit and a carbon offset unit;

[0015] The carbon capture unit is used to capture in real time the emission sources of CO in regions i1, i2, ..., in by using adsorbents in carbon capture and storage technology, and during thermal desorption, collect and record in real time the data information of the surrounding temperature difference Wdc, adsorption saturation Xfbh, and pressure difference Ylc; 2

[0016] The carbon offset unit is used to collect and record the data information on the growth status of vegetation in regions i1, i2, ..., in, including the growth cycle Szsd, vegetation density, geographical location, plant type, soil quality, and seasonal changes of the vegetation.

[0017] Preferably, the data processing module includes a data preprocessing unit and a standardization unit;

[0018] The data preprocessing unit is used to frequently calibrate the data information in the carbon status data set, monitor and process the missing values therein, and use signal processing technology to remove the high-frequency noise in the data information;

[0019] The standardization unit is used to convert one or both of the carbon status data sets into the same unit by using dimensionless processing technology, and unify the data values generated by different sensors or acquisition devices within the same range value.

[0020] Preferably, based on artificial intelligence technology, an algorithm model is established, and the environmental factor Hjyz, capture coefficient Bzxs, and offset coefficient Dxxs are obtained through feature extraction and analysis calculation, and the capture coefficient Bzxs and the offset coefficient Dxxs are correlated to obtain the neutralization evaluation index Zhpg.

[0021] Preferably, the temperature difference Wdc and the pressure difference Ylc are correlated, and after dimensionless processing, the environmental factor Hjyz is obtained through the following formula:

[0022] ;

[0023] In the formula, represents the weight value of the temperature difference Wdc, represents the weight value of the pressure difference Ylc, where, and represents the constant correction coefficient.

[0024] Preferably, the environmental factor Hjyz is correlated with the CO 2 emission concentration Pfd, and after dimensionless processing, the capture coefficient Bzxs is obtained through the following formula: ​​​

[0025] ;

[0026] In the formula, Xfbh represents the adsorption saturation degree, represents the weight value of the environmental factor Hjyz, represents the weight value of the sum of the CO 2 emission concentration Pfd and the adsorption saturation degree Xfbh. Among them, , , and , represents the constant correction coefficient.

[0027] Preferably, the growth period Szsd is associated with the vegetation coverage area Zbfg, and after dimensionless processing, the cancellation coefficient Dxxs is obtained through the following formula:

[0028] ;

[0029] In the formula, Scz represents the duration, represents the weight value of the vegetation coverage area Zbfg, represents the weight value of the sum of the growth period Szsd and the duration Scz. Among them, , , and , represents the constant correction coefficient.

[0030] Preferably, the threshold evaluation module includes a historical evaluation unit and a warning evaluation report unit;

[0031] The historical evaluation unit is used to extract the historical relevant data information in regions i1, i2,..., in respectively, and calculate to obtain the corresponding average evaluation threshold Q. The average evaluation threshold Q includes a first evaluation threshold Q1 and a second evaluation threshold Q2. Among them, the first evaluation threshold Q1 is greater than the average evaluation threshold Q, and the second evaluation threshold Q2 is less than the average evaluation threshold Q.

[0032] Preferably, the warning evaluation report unit is used to compare and analyze the neutralization evaluation index Zhpg with the corresponding average evaluation threshold Q to obtain a warning evaluation report:

[0033] When the neutralization evaluation index Zhpg ≤ the second evaluation threshold Q2, that is, Zhpg ≤ Q2, a first-level warning is obtained, indicating that the current carbon neutral state exceeds the safe range of 50%. At this time, the use of renewable energy needs to be increased;

[0034] When the second evaluation threshold Q2 < the neutralization evaluation index Zhpg ≤ the average evaluation threshold Q, a secondary warning is obtained, that is, Zhpg ≤ Q2, indicating that the current carbon neutral state exceeds the safe range of 30%. At this time, large-scale afforestation is required;

[0035] When the average evaluation threshold Q < the neutralization evaluation index Zhpg ≤ the first evaluation threshold Q1, that is, Zhpg ≤ Q2, a tertiary warning is obtained, indicating that the current carbon neutral state is already within the safe range. At this time, data collection and monitoring will be continuously strengthened.

[0036] The present invention provides an artificial intelligence-based carbon neutrality grid evaluation system, which has the following beneficial effects:

[0037] (1) The artificial intelligence-based carbon neutrality grid evaluation system combines multiple data sources, including gas analyzers, drone inspections, artificial intelligence simulations, etc., and further realizes high-resolution monitoring of CO 2 emission concentration and low-altitude imaging, thereby providing a more accurate CO 2 distribution electronic map, and dividing the CO 2 distribution electronic map into regions to distinguish the CO 2 emission situation, carbon capture data and offset data at different geographical locations, and conducting real-time monitoring and summarizing them to establish a comprehensive carbon status data set, providing a reliable basis for decision-making; by using deep machine learning technology, it is possible to better understand the relationship between environmental factors Hjyz, capture coefficient Bzxs and offset coefficient Dxxs in multi-dimensional data information, thereby providing a more accurate neutralization evaluation index Zhpg. Through the threshold evaluation module, the ability to analyze historical data and calculate the average evaluation threshold Q is provided, further determining the accuracy of decision-making;

[0038] (2) The artificial intelligence-based carbon neutrality grid evaluation system divides different geographical locations into several grid-like regions and marks them. The system can more accurately analyze the CO 2 emission, vegetation coverage and carbon neutrality situation of each region, which takes into account the differences in geographical locations and helps to formulate more targeted carbon neutrality strategies;

[0039] (3) The artificial intelligence-based carbon neutrality grid evaluation system extracts historical data information to obtain the average evaluation threshold Q. It is based on the average level of the past carbon neutral state, provides a benchmark for subsequent evaluations, compares and analyzes the neutralization evaluation index Zhpg with the average evaluation threshold Q, and provides warning reports at different levels, enabling decision-makers to better understand the status and trends of carbon neutrality and take appropriate actions according to different situations to achieve more sustainable carbon neutrality goals. Brief Description of the Drawings

[0040] Figure 1 This is a block diagram of a carbon neutrality grid assessment system based on artificial intelligence according to the present invention. Detailed Embodiments

[0041] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0042] With the continuous intensification of climate change issues, carbon neutrality has become one of the key strategies to address the global challenge of greenhouse gas emissions. Scientists and enterprises are actively seeking innovative methods to reduce carbon emissions and achieve carbon neutrality. At the same time, the application of artificial intelligence technology in the field of carbon neutrality has become increasingly important. Artificial intelligence technology can help monitor emissions in real time, optimize carbon capture and offset strategies, and provide intelligent decision-making support.

[0043] Although carbon neutrality can offset and store carbon dioxide in the air, to accurately evaluate the carbon neutrality index, not only the emission concentration of carbon dioxide in the air, the quantity of adsorbents, and the density of vegetation need to be considered, but also various factors such as the changes in the surrounding environment during the adsorbent regeneration process and the growth cycle of vegetation need to be considered. Moreover, the distribution of carbon dioxide is not regionally divided, and it is impossible to further evaluate the carbon neutrality of different geographical locations, resulting in uncertainty in decision-making and inefficiency of carbon neutrality plans.

[0044] Embodiment 1: Please refer to Figure 1 , the present invention provides a carbon neutrality grid assessment system based on artificial intelligence, including a regional division module, a data acquisition module, a data processing module, a carbon neutrality analysis module, and a threshold evaluation module;

[0045] The regional division module is used to monitor the CO 2 emission concentration Pfd at different geographical locations by using a gas analyzer, and at the same time use a drone to inspect the geographical locations of CO 2 emissions and perform low-altitude imaging, and simulate and obtain an electronic map of CO 2 distribution based on artificial intelligence technology. According to the range of CO 2 emissions, the electronic map of CO 2 distribution is segmented into several grid-like regions, and the nearby vegetation coverage area Zbfg is determined; The gas analyzer can be installed at positions such as industrial emission sources, combustion equipment, power plants, factories, and transportation vehicles to measure CO2 Emission levels.

[0046] The data acquisition module is used to monitor the CO emissions in real time at different geographical locations. 2 Status, carbon capture, and carbon offset situations, and generate CO status data, carbon capture data, and carbon offset data in sequence, and summarize and establish a carbon status dataset. 2 The data processing module is used to clean and extract feature information from the relevant data in the carbon status dataset, and standardize the processed data information according to the dimensionless processing technology to unify the units.

[0047] The carbon neutralization analysis module is used to adsorb CO with an adsorbent, analyze the surrounding environmental impacts during the regeneration process of the adsorbent, obtain the environmental factor Hjyz, associate the environmental factor Hjyz with the CO emission concentration Pfd, obtain the capture coefficient Bzxs, analyze and calculate the vegetation coverage area Zbfg and the vegetation growth status to generate the offset coefficient Dxxs, and use artificial intelligence technology for in-depth machine learning analysis to obtain the neutralization evaluation index Zhpg. The neutralization evaluation index Zhpg is obtained through the following formula:

[0048] 2 ; during the regeneration process of the adsorbent, analyze the surrounding environmental impacts, obtain the environmental factor Hjyz, and associate the environmental factor Hjyz with the CO emission concentration Pfd to obtain the capture coefficient Bzxs. Analyze and calculate the vegetation coverage area Zbfg and the vegetation growth status to generate the offset coefficient Dxxs, and use artificial intelligence technology for in-depth machine learning analysis to obtain the neutralization evaluation index Zhpg. The neutralization evaluation index Zhpg is obtained through the following formula: 2 In the formula, Jyl represents the CO trading volume,

[0049] ;

[0050] In the formula, Jyl represents the CO trading volume, 2 trading volume, , and respectively represent the weight values of the offset coefficient Dxxs, the CO trading volume Jyl, and the capture coefficient Bzxs. Among them, 2 trading volume Jyl and the capture coefficient Bzxs, where, , , , and , R represents a constant correction coefficient;

[0051] The threshold evaluation module is used to extract relevant data information from the carbon status dataset on a weekly, monthly, or quarterly basis within the historical time axis to obtain historical data and calculate the average value, obtain the average evaluation threshold Q, and compare and analyze the neutralization evaluation index Zhpg with the average evaluation threshold Q to obtain a warning evaluation report.

[0052] During the operation of this system, the system combines multiple data sources, including gas analyzers, drone inspections, artificial intelligence simulations, etc., to further provide highly accurate carbon neutralization evaluations, helping decision-makers better understand and master the CO emission status at different geographical locations. 2 Emission status; the system can monitor CO in real time.2 Emission, carbon capture, and carbon offset situations are monitored, and a warning assessment report is generated. This means that when problems occur or the carbon neutrality goal is threatened, timely actions can be taken to ensure the smooth implementation of the carbon emission reduction plan. By leveraging deep machine learning techniques, it is possible to better understand the relationships among environmental factor Hjyz, capture coefficient Bzxs, and offset coefficient Dxxs in multi-dimensional data information, thereby providing a more accurate neutralization assessment index Zhpg. Through the threshold assessment module, the ability to analyze historical data and calculate the average assessment threshold Q is provided, which helps to improve the carbon neutrality strategy in combination with long-term trends.

[0053] Example 2: Refer to Figure 1 , specifically: Mark several grid-like regions, denoted as region i1, region i2,..., region in, and sequentially transmit the corresponding vegetation coverage areas Zbfg of several mesh regions to the carbon status dataset, and analyze and calculate the corresponding neutralization assessment indices Zhpg of region i1, region i2,..., region in.

[0054] The data acquisition module will collect in real time the CO 2 status data, carbon capture data, and carbon offset data in region i1, region i2,..., region in, including a carbon capture unit and a carbon offset unit;

[0055] The carbon capture unit is used to utilize the adsorbent in carbon capture and storage technology to capture in real time the CO 2 emission sources in region i1, region i2,..., region in, and during thermal desorption, collect and record in real time the data information of the surrounding temperature difference Wdc, adsorption saturation Xfbh, and pressure difference Ylc;

[0056] The carbon offset unit is used to collect and record the data information on the growth status of vegetation in region i1, region i2,..., region in, including the growth cycle Szsd of vegetation, vegetation density, geographical location, plant type, soil quality, and seasonal changes.

[0057] The data processing module includes a data preprocessing unit and a standardization unit;

[0058] The data preprocessing unit is used to frequently calibrate the data information in the carbon status dataset, monitor and process the missing values therein, and use signal processing techniques to remove the high-frequency noise in the data information;

[0059] The standardization unit is used to convert one or two in the carbon status dataset into the same unit using dimensionless processing techniques and unify the data values generated by different sensors or acquisition devices within the same range.

[0060] In this embodiment, by dividing different geographical locations into several grid-like regions and marking them, the system can more accurately analyze the CO emissions, vegetation cover, and carbon neutrality situation in each region, taking into account the geographical location differences and helping to formulate more targeted carbon neutrality strategies. The carbon offset unit collects and records the growth status data of vegetation, including information such as the growth cycle Szsd, density, type, etc., to further understand the impact and changes of vegetation in multiple aspects for better evaluating the effect of carbon offset. The data preprocessing unit is responsible for operations such as calibrating the carbon status data set, handling missing values, and removing noise, ensuring the quality and reliability of the data and reducing the impact of misleading data on the analysis results. The standardization unit uniformly converts the data into the same unit and range, making the information from different data sources comparable, which helps to better integrate the data for cross-regional or cross-device comparison and analysis. 2 Emissions, vegetation cover, and carbon neutrality conditions, which allows for the consideration of geographical location differences and helps in formulating more targeted carbon neutrality strategies. The carbon offset unit collects and records data on the growth status of vegetation, including information such as the growth cycle Szsd, density, type, etc., to further understand the impact and changes of vegetation in multiple aspects for better evaluating the effect of carbon offset. The data preprocessing unit is responsible for operations such as calibrating the carbon status data set, handling missing values, and removing noise, ensuring the quality and reliability of the data and reducing the impact of misleading data on the analysis results. The standardization unit uniformly converts the data into the same unit and range, making the information from different data sources comparable, which helps to better integrate the data for cross-regional or cross-device comparison and analysis.

[0061] Example 3: Please refer to Figure 1 , specifically: Based on artificial intelligence technology, an algorithm model is established, and through feature extraction and analysis and calculation, the environmental factor Hjyz, capture coefficient Bzxs, and offset coefficient Dxxs are obtained, and the capture coefficient Bzxs is associated with the offset coefficient Dxxs to obtain the neutralization evaluation index Zhpg.

[0062] The temperature difference Wdc is associated with the pressure difference Ylc, and after dimensionless processing, the environmental factor Hjyz is obtained through the following formula:

[0063] ;

[0064] In the formula, represents the weight value of the temperature difference Wdc, represents the weight value of the pressure difference Ylc, where , , and , represents the constant correction coefficient.

[0065] The above temperature difference Wdc is obtained by collecting through a temperature sensor;

[0066] The pressure difference Ylc is obtained by monitoring through a differential pressure sensor;

[0067] The environmental factor Hjyz is associated with the CO 2 emission concentration Pfd, and after dimensionless processing, the capture coefficient Bzxs is obtained through the following formula:

[0068] ;

[0069] In the formula, Xfbh represents the adsorption saturation degree, It is expressed as the weight value of the environmental factor Hjyz. It is expressed as the weight value of the sum of the CO 2 emission concentration Pfd and the adsorption saturation Xfbh. Among them, , , and , It is expressed as a constant correction coefficient.

[0070] The above-mentioned adsorption saturation Xfbh refers to the ratio of the CO 2 molecules adsorbed on the adsorbent to its maximum adsorption capacity, and is obtained by monitoring with a mass difference sensor. Measure the mass difference of the adsorbent before and after adsorbing CO 2 , calculate the adsorption amount of CO 2 on the adsorbent, and thus determine the adsorption saturation.

[0071] CO 2 The emission concentration Pfd refers to the concentration of carbon dioxide in the air within a certain grid-like area, and is obtained by monitoring with a gas analyzer.

[0072] Associate the growth cycle Szsd with the vegetation coverage area Zbfg, and after dimensionless processing, the cancellation coefficient Dxxs is obtained through the following formula:

[0073] ;

[0074] In the formula, Scz represents the duration, It is expressed as the weight value of the vegetation coverage area Zbfg. It is expressed as the weight value of the sum of the growth cycle Szsd and the duration Scz. Among them, , , and , It is expressed as a constant correction coefficient.

[0075] The above-mentioned duration Scz refers to the duration for which the carbon offset means lasts, and is obtained by regularly recording using a data logger;

[0076] The vegetation coverage area Zbfg refers to the coverage area of vegetation within a certain grid-like area, and is collected by high-altitude inspection with a drone;

[0077] The growth cycle Szsd observes the growth rate of vegetation by recording the timestamps of vegetation growth.

[0078] In this embodiment, by obtaining the environmental factor Hjyz, it is convenient to understand and optimize CO 2The capture process ensures optimal environmental conditions. By evaluating the capture coefficient Bzxs, the efficiency of carbon capture can be understood in real time. At the same time, through in-depth calculations, the offset coefficient Dxxs can be obtained to determine the impact of vegetation in different geographical locations on carbon dioxide in the corresponding areas.

[0079] Example 4: Please refer to Figure 1 , specifically: The threshold evaluation module includes a historical evaluation unit and a warning evaluation report unit;

[0080] The historical evaluation unit is used to separately extract historical relevant data information in regions i1, i2,..., in, and calculate to obtain the corresponding average evaluation threshold Q. The average evaluation threshold Q includes a first evaluation threshold Q1 and a second evaluation threshold Q2. Among them, the first evaluation threshold Q1 is greater than the average evaluation threshold Q, and the second evaluation threshold Q2 is less than the average evaluation threshold Q.

[0081] The warning evaluation report unit is used to compare and analyze the neutralization evaluation index Zhpg with the corresponding average evaluation threshold Q to obtain a warning evaluation report:

[0082] When the neutralization evaluation index Zhpg ≤ the second evaluation threshold Q2, that is, Zhpg ≤ Q2, a first-level warning is obtained, indicating that the current carbon neutral state exceeds the 50% safety range. At this time, the use of renewable energy sources such as solar energy and wind energy needs to be increased to reduce the factory's dependence on fossil fuels;

[0083] When the second evaluation threshold Q2 < the neutralization evaluation index Zhpg ≤ the average evaluation threshold Q, a second-level warning is obtained, that is, Zhpg ≤ Q2, indicating that the current carbon neutral state exceeds the 30% safety range. At this time, large-scale afforestation needs to be carried out;

[0084] When the average evaluation threshold Q < the neutralization evaluation index Zhpg ≤ the first evaluation threshold Q1, that is, Zhpg ≤ Q2, a third-level warning is obtained, indicating that the current carbon neutral state is already within the safety range. At this time, data collection and monitoring will be continuously strengthened to more accurately understand the progress of carbon neutrality and timely adjust strategies.

[0085] In this embodiment, by analyzing historical data, the system can calculate the average evaluation threshold Q, including the first evaluation threshold Q1 and the second evaluation threshold Q2, both based on the average level of the past carbon neutral state, providing a benchmark for subsequent evaluations. Comparing and analyzing the neutralization evaluation index Zhpg with the average evaluation threshold Q and providing warning reports at different levels enable decision-makers to better understand the status and trends of carbon neutrality and take appropriate actions according to different situations.

[0086] Example: A certain factory has introduced an artificial intelligence-based carbon neutrality grid evaluation system. The following is an example for the certain factory:

[0087] Data collection: The temperature difference Wdc is 15; the pressure difference Ylc is 20; is 0.50; is 0.60; is 2; the adsorption saturation Xfbh is 62%; CO 2 The emission concentration Pfd is 85; is 0.62; is 0.52; is 3; the duration Scz is 152; the vegetation coverage area Zbfg is 264; the growth cycle Szsd is 8; is 0.38; is 0.75; is 3; CO 2 The trading volume Jyl is 152; is 0.55; is 0.22; is 0.68; R is 5;

[0088] Based on the above data, the following calculations can be performed:

[0089] Environmental factor ;

[0090] Capture coefficient ;

[0091] Offset coefficient ;

[0092] Neutralization evaluation index ;

[0093] If the average evaluation threshold Q is 150, the first evaluation threshold Q1 is 180, and the second evaluation threshold Q2 is 140, then at this time the neutralization evaluation index Zhpg ≤ the second evaluation threshold Q2, obtaining a first-level warning, indicating that the current carbon neutral state exceeds the safe range of 50%. At this time, it is necessary to increase the use of renewable energy such as solar energy and wind energy to reduce the factory's dependence on fossil fuels.

[0094] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A carbon neutrality grid assessment system based on artificial intelligence, characterized by: It includes regional division module, data collection module, data processing module, carbon neutrality analysis module and threshold assessment module; The regional division module is used to monitor the CO2 emission concentration Pfd in different geographical locations using a gas analyzer, and at the same time use drones to inspect the geographical locations of CO2 emissions and perform low-altitude imaging, and simulate and obtain the CO2 distribution electronic map based on artificial intelligence technology, divide the CO2 distribution electronic map into several grid-like areas according to the range of CO2 emissions, and determine the nearby vegetation coverage area Zbfg; Mark several grid-shaped areas, record them as area i1, area i2, ..., area in, and transmit the corresponding vegetation coverage areas Zbfg of several grid-shaped areas to the carbon state data set in sequence, and analyze and calculate the corresponding neutralization evaluation index Zhpg of area i1, area i2, ..., area in; The data acquisition module is used to monitor the status of CO2 emitted in different geographical locations, carbon capture status and carbon offset status in real time, and generate CO2 status data, carbon capture data and carbon offset data in turn, and summarize them into a carbon status data set; The data acquisition module will collect CO2 status data, carbon capture data and carbon offset data in area i1, area i2, ..., area in in real time, including carbon capture units and carbon offset units; The carbon capture unit is used to use the adsorbent in the carbon capture and storage technology to capture the emission sources of CO2 in areas i1, i2, ..., and in real time, and to collect and record the ambient temperature difference Wdc, adsorption saturation Xfbh, and pressure difference Ylc data information in real time during thermal desorption; The carbon offset unit is used to collect and record the growth status data information of the vegetation in the area i1, area i2, ..., area in, including the growth cycle Szsd of the vegetation, vegetation density, geographical location, plant type, soil quality and seasonal changes; The data processing module is used to perform data cleaning and feature extraction on the relevant data information in the carbon state data set, and standardize the processed data information according to the dimensionless processing technology to unify the units; The carbon neutrality analysis module is used to use an adsorbent to adsorb CO2, analyze the impact of the surrounding environment during the adsorbent regeneration process, obtain the environmental factor Hjyz, and associate the environmental factor Hjyz with the CO2 emission concentration Pfd to obtain the capture coefficient Bzxs, analyze and calculate the vegetation coverage area Zbfg and the vegetation growth state to generate the offset coefficient Dxxs, use artificial intelligence technology to perform deep machine learning analysis, and obtain the neutralization evaluation index Zhpg. The neutralization evaluation index Zhpg is obtained by the following formula: ； In the formula, Jyl represents the CO2 trading volume, , and They are respectively expressed as the weight values ​​of the offset coefficient Dxxs, CO2 trading volume Jyl and capture coefficient Bzxs, where: , , ,and , R represents the constant correction coefficient; ； In the formula, Expressed as the weight value of the temperature difference Wdc, Expressed as the weight value of the pressure difference Ylc, where , ,and , Expressed as a constant correction factor; The environmental factor Hjyz is associated with the CO2 emission concentration Pfd and after dimensionless processing, the capture coefficient Bzxs is obtained by the following formula: ； In the formula, Xfbh represents the adsorption saturation, Expressed as the weight value of the environmental factor Hjyz, It is expressed as the weight value of the sum of CO2 emission concentration Pfd and adsorption saturation Xfbh, where: , ,and , Expressed as a constant correction factor; The growth period Szsd is associated with the vegetation coverage area Zbfg, and after dimensionless processing, the offset coefficient Dxxs is obtained by the following formula: ； In the formula, Scz represents the duration, Expressed as the weight value of vegetation coverage area Zbfg, It is expressed as the weight value of the sum of the growth period Szsd and the duration Scz, where: , ,and , Expressed as a constant correction factor; The threshold assessment module is used to extract relevant data information from the weekly, monthly or quarterly carbon status data set within the historical timeline to obtain historical data and calculate the average value, obtain the average assessment threshold Q, and compare and analyze the neutralization assessment index Zhpg with the average assessment threshold Q to obtain an early warning assessment report.

2. According to the carbon neutrality grid assessment system based on artificial intelligence in claim 1, it is characterized by: The data processing module includes a data preprocessing unit and a standardization unit; The data preprocessing unit is used to frequently calibrate the data information in the carbon state data set, monitor and process the missing values ​​therein, and use signal processing technology to remove high-frequency noise in the data information; The standardized unit is used to convert one or both of the carbon state data sets into the same unit using dimensionless processing technology, and to unify the data values ​​generated by different sensors or acquisition devices within the same range of values.

3. According to the carbon neutrality grid assessment system based on artificial intelligence in claim 1, it is characterized by: According to artificial intelligence technology, an algorithm model is established, and features are extracted and analyzed to obtain: environmental factor Hjyz, capture coefficient Bzxs and offset coefficient Dxxs, and the capture coefficient Bzxs is associated with the offset coefficient Dxxs to obtain the neutralization evaluation index Zhpg.

4. The carbon neutrality grid assessment system based on artificial intelligence according to claim 1 is characterized by: The threshold assessment module includes a historical assessment unit and an early warning assessment reporting unit; The historical evaluation unit is used to extract historical related data information from area i1, area i2, ..., area in respectively, and calculate to obtain the corresponding average evaluation threshold Q, wherein the average evaluation threshold Q includes a first evaluation threshold Q1 and a second evaluation threshold Q2, wherein the first evaluation threshold Q1 is greater than the average evaluation threshold Q, and the second evaluation threshold Q2 is less than the average evaluation threshold Q.

5. The carbon neutrality grid assessment system based on artificial intelligence according to claim 4 is characterized by: The early warning assessment reporting unit is used to compare and analyze the neutralization assessment index Zhpg with the corresponding average assessment threshold Q to obtain an early warning assessment report: When the neutralization evaluation index Zhpg≤the second evaluation threshold Q2, that is, Zhpg≤Q2, a first-level warning is obtained, indicating that the current carbon neutrality status exceeds the safety range of 50%, and the use of renewable energy needs to be increased; When the second assessment threshold Q2<the neutralization assessment index Zhpg≤the average assessment threshold Q, a second-level warning is obtained, i.e., Q2<Zhpg≤Q, indicating that the current carbon neutrality status exceeds the safety range of 30%, and large-scale afforestation is required at this time; When the average assessment threshold Q is less than the neutralization assessment index Zhpg≤the first assessment threshold Q1, that is, Q<Zhpg≤Q1, a third-level warning is obtained, indicating that the current carbon neutrality status is within a safe range. At this time, data collection and monitoring will be continuously strengthened.

Images