Urban agglomeration carbon emission spatial multi-dimensional data analysis method and system based on artificial intelligence

Abstract

The invention relates to the technical field of industrial carbon emission processing, in particular to an urban agglomeration carbon emission space multi-dimensional data analysis method and system based on artificial intelligence, and the method comprises the steps: dividing a city in an urban agglomeration into a plurality of carbon emission spaces according to a geographic distribution region; multi-dimensional data of the industrial production industry in each carbon emission space in an urban agglomeration are collected, multi-dimensional data of different industrial types in each carbon emission space are analyzed, an energy influence value, a traffic influence value and an economic influence value are determined, and then the energy influence value, the traffic influence value and the economic influence value are subjected to comprehensive operation to obtain a comprehensive calculation result. According to the method, the comprehensive carbon emission coefficient of each industrial type in the urban agglomeration in different carbon emission spaces is determined, and the industrial types are sequentially arranged in each carbon emission space according to the comprehensive carbon emission coefficient to obtain an industrial production sequence, so that a more comprehensive carbon emission analysis view is provided for the industrial carbon emission reduction policy of the urban agglomeration.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial carbon emission processing, and in particular to an artificial intelligence-based urban agglomeration carbon emission spatial multidimensional data analysis method and system. Background Art

[0002] As the main place for human activities, cities account for a considerable proportion of carbon emissions. Each city in the urban agglomeration has close economic ties, industrial division of labor and cooperation, as well as mutually influential transportation and social life systems. Therefore, effective monitoring and management of carbon emissions in urban agglomerations is of great significance to achieving carbon reduction goals.

[0003] Prior art CN116663921A discloses a method for analyzing the characteristics of carbon emissions from urban agglomeration transportation, including pre-analyzing the spatial total amount and spatial intensity of urban agglomeration carbon emissions, summarizing the general law of urban agglomeration carbon emissions in recent years, analyzing the carbon emission network and spatial structure of regional urban agglomerations using gravity models, social network analysis methods, and other methods, and using QAP regression analysis to explore the influencing factors of regional transportation carbon emissions correlation. The present invention constructs a spatial correlation network of urban agglomeration transportation carbon emissions, analyzes the structural form of the spatial correlation network of transportation carbon emissions, and can provide a reference for the path of urban agglomeration transportation carbon emission reduction.

[0004] However, due to the differences in cities’ geographical locations, economic development and their own advantages, the energy consumption structure and carbon emission intensity are different in the production process of each industry. When making carbon emission decisions for industrial activities in urban agglomerations, traditional data forms may still have certain limitations. Summary of the invention

[0005] The purpose of the present invention is to solve the problems in the background technology and to propose an artificial intelligence-based urban agglomeration carbon emission spatial multidimensional data analysis method and system.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A spatial multidimensional data analysis method for urban agglomeration carbon emissions based on artificial intelligence, the method specifically comprises the following steps:

[0008] Step 1: Select the target city cluster, delineate the carbon emission space according to the geographical distribution of the city, and collect the historical carbon emission values ​​and the city standard load value FC in the carbon emission space;

[0009] Step 2: Collect industrial distribution information in the carbon emission space and operational data of industrial production companies. Industrial distribution information includes industrial types, and operational data includes energy consumption, industrial production and transportation, and industrial economic level.

[0010] Step 3: Use artificial intelligence technology to analyze the comprehensive carbon emission coefficient of industrial types in each city, where the comprehensive carbon emission coefficient is composed of energy impact value, traffic impact value and economic impact value;

[0011] Energy impact value refers to obtaining the energy structure and historical energy consumption values ​​of the target industry, and determining the energy representative value of each energy structure based on the historical energy consumption values ​​of the target industry, and combining the energy representative value with the corresponding carbon emission factor to obtain the result;

[0012] Traffic impact value refers to the result obtained by determining the target industry's transportation mode and inertial transportation value based on the target industry's logistics and transportation records, combining the inertial transportation value with the carbon emission factor of the transportation mode, and further calculating it;

[0013] The economic impact value refers to the result obtained after calculating the industrial economic value of the target industry and the overall economic value of the city;

[0014] Step 4: Arrange the industrial types of all cities in the urban agglomeration in ascending order according to the comprehensive carbon emission coefficient to obtain the industrial production sequence, and then transmit the industrial production sequence to relevant departments.

[0015] As a further solution of the present invention, a method for calculating the comprehensive carbon emission coefficient includes:

[0016] Select any city in the target urban agglomeration, and choose an industrial type in this city as the target industry, obtain the energy impact value YN, traffic impact value YT and economic impact value YE of the target industry, and use the formula ZC=(YN+YT)×YE×λ to get the comprehensive carbon emission coefficient ZC, where λ is the correction factor.

[0017] As a further solution of the present invention, a method for calculating the energy impact value YN includes:

[0018] S01: Collect the energy structure of the target industry, and use the current time as the time node to collect the corresponding energy consumption value per unit time in the historical time;

[0019] The energy structure includes electricity, natural gas, oil and diesel, the unit time is set to 1 month, and the historical time is set to 36 months;

[0020] S02: Obtain the energy structure and the energy consumption value of the energy structure in the historical time, and use the mean processing method to calculate the energy representative value ENm corresponding to each energy structure, where m represents the number of different energy structures;

[0021] S03: Obtain the carbon emission factor Am for each energy structure and use the formula The energy carbon emission value CL of the target industry is obtained, and b1 represents the total amount of energy types in the energy structure;

[0022] S04: Obtain the city corresponding to the target industry and the city standard load value FC, based on the formula The energy impact value YN is obtained, δ1 is the energy constant, and the value of δ1 is 0.0153.

[0023] As a further solution of the present invention, when calculating the energy representative value, it is necessary to identify and delete the abnormal data in each energy structure. The specific method for identifying the abnormal data is:

[0024] Using the formula Calculate the data deviation value Um of energy structure m, where i represents the number of different unit time, i∈[1,I], I represents the total amount of selected unit time, further, I takes the value of 36, E m-i It represents the energy consumption value generated by energy structure m in the i-th unit time, and Ea is the energy consumption value E m-i The mean of

[0025] The data deviation value Um and the standard deviation value U b-m For comparison, if Um≤U b-m , it means that the energy consumption values ​​of energy structure m are normal data. On the contrary, if Um>U b-m , get |E m-i -Ea|, and then |E m-i The values ​​of -Ea| are arranged in descending order and deleted in the calculation of the data deviation value Um in order. The remaining data are recalculated until the data deviation value Um≤U b-m , then obtain the deleted data in the data deviation value Um, and in the energy consumption value E m-i A control query is performed in the query, and finally the query result data is marked as abnormal data.

[0026] As a further solution of the present invention, a method for calculating the traffic impact value includes:

[0027] According to the logistics and transportation records of the target industry, identify the transportation methods of the target industry, including road transportation, railway transportation, water transportation and air transportation;

[0028] Obtain the transportation distance in the logistics transportation record, take the average of the transportation distance as the inertial transportation value of the target industry, multiply the inertial transportation value of the target industry by the carbon emission factor of the transportation mode, and obtain the transportation carbon emission value TT of the target industry;

[0029] Based on the formula The traffic impact value YT is obtained, δ2 is the traffic constant, and the value of δ2 is 0.0094.

[0030] As a further solution of the present invention, the method for calculating the economic impact value includes:

[0031] Take quarter as time unit to obtain the industrial economic value SR of the target industry and the overall economic value SR of the city.

[0032] Economic value SZ, using the formula The economic impact value YE is obtained, CC represents the total carbon emissions of the target industry per unit time, δ3 is the correlation index, and the value of δ3 is 0.0212.

[0033] An artificial intelligence-based multidimensional data analysis system for urban agglomeration carbon emissions space, which includes an information collection module, a city division module, a carbon emissions analysis module, and a comprehensive output module;

[0034] The city division module is used to divide the cities in the urban agglomeration into several carbon emission spaces according to the geographical distribution areas of the cities. At the same time, there is a one-way communication connection between the city division module and the information collection module;

[0035] The information collection module is used to collect historical carbon emission values ​​and urban standard load values, industrial distribution information, and operating data of industrial production companies in each carbon emission space, and transmit them to the carbon emission analysis module, where industrial distribution information refers to industrial types, and operating data includes energy consumption, industrial production and transportation, and industrial economic level;

[0036] The carbon emission analysis module is used to calculate according to the operation data in each carbon emission space, determine the energy impact value, traffic impact value and economic impact value, and then perform comprehensive calculations on the energy impact value, traffic impact value and economic impact value to determine the comprehensive carbon emission coefficient of each industrial type. After that, the carbon emission analysis module transmits the comprehensive carbon emission coefficient in the carbon emission space to the comprehensive output module;

[0037] The comprehensive output module is used to arrange the industrial types of all cities in the urban agglomeration in ascending order according to the comprehensive carbon emission coefficient, obtain the industrial production sequence, and output the industrial production sequence as data on the terminal device.

[0038] Compared with the prior art, the advantages of the present invention are:

[0039] 1. By collecting multidimensional data of industrial production industries in urban agglomerations and analyzing the multidimensional data of different industrial types in each city, the comprehensive carbon emission coefficient of each industrial type in different cities in the urban agglomeration is determined, thereby providing a more comprehensive carbon emission analysis perspective for the industrial carbon emission reduction policy of the urban agglomeration;

[0040] 2. Calculate the energy impact value, traffic impact value and economic impact value of different industrial types in each city in the urban agglomeration respectively, and then calculate the energy impact value, traffic impact value and economic impact value to determine the comprehensive carbon emission coefficient, thereby providing data support for policy decisions such as urban planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic diagram of the structure of the method of the present invention;

[0042] Figure 2 It is a schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0044] Example 1: Reference Figure 1 , a spatial multidimensional data analysis method for urban agglomeration carbon emissions based on artificial intelligence, the method specifically includes the following steps:

[0045] Step 1: Select the target city cluster and obtain all the cities in the target city cluster. At the same time, define the carbon emission space according to the geographical distribution area of ​​the city. Furthermore, each city in the target city cluster is set up with a corresponding carbon emission space, and then the historical carbon emission value and the city standard load value FC in each carbon emission space are obtained. Among them, the city standard load value refers to the maximum value of carbon emissions that a city can carry out. The specific city standard load value is set by technical personnel in related fields according to the level of urban development. If the carbon emissions of a city exceed the city standard load value, it is necessary to offset the excess carbon emissions based on the carbon trading mechanism;

[0046] In this embodiment, the time unit of the carbon emission value is set to 1 month, and the historical time in the acquired historical carbon emission value is set to 36 months;

[0047] Step 2: Collect industrial distribution information in each carbon emission space, where the industrial distribution information includes industrial types. Further, industrial types include industrial sectors in light industry and heavy industry. For example, light industry includes food processing, tobacco processing, and textile industry, and heavy industry includes steel industry, metallurgical industry, and machinery manufacturing;

[0048] Then, the operational data of each industrial production company in the carbon emission space is collected, and the industrial production companies are classified according to industrial types. The operational data includes energy consumption, industrial production transportation, and industrial economic level.

[0049] Step 3: Randomly select a city in the target city cluster and select an industrial type in this city as the target industry. Taking the target industry as an example, use artificial intelligence technology to analyze the comprehensive carbon emission coefficient of the target industry;

[0050] The analysis methods for comprehensive carbon emission coefficients in specific target industries include:

[0051] Extract the operation data of the target industry, and obtain the corresponding carbon emission value based on the operation data. Combine the operation data with the carbon emission value for analysis to determine the carbon emission linear value. Furthermore, the carbon emission linear value includes the energy impact value, traffic impact value, and economic impact value.

[0052] Among them, the energy impact value refers to the relationship between energy consumption and carbon emissions in the target industry, the traffic impact value refers to the relationship between industrial production and transportation and carbon emissions in the target industry, and the economic impact value refers to the relationship between the industrial economic level and carbon emissions of the target industry;

[0053] The calculation methods of energy impact value include:

[0054] S01: Collect the energy structure of the target industry, and use the current time as the time node to collect the energy consumption value corresponding to each unit time in the historical time, where the energy structure includes but is not limited to electricity, natural gas, oil and diesel. The unit time is set to 1 month in this embodiment, and the historical time is set to 36 months;

[0055] S02: Obtain the energy structure and the energy consumption value of the energy structure in the historical time, and use the mean processing method to calculate the energy representative value ENm corresponding to each energy structure, where m represents the number of different energy structures;

[0056] Among them, when using the mean processing method, it is necessary to delete the abnormal data in each energy structure, and then calculate the mean of the remaining data. The specific method for identifying abnormal data is:

[0057] Using the formula Calculate the data deviation value Um of energy structure m, where i represents the number of different unit time, i∈[1,I], I represents the total amount of selected unit time, further, I takes the value of 36, E m-i It represents the energy consumption value generated by energy structure m in the i-th unit time, and Ea is the energy consumption value E m-i The mean of

[0058] The data deviation value Um and the standard deviation value U b-m For comparison, if Um≤U b-m, it means that the energy consumption values ​​of energy structure m are all normal data. On the contrary, if Um>U b-m When |E m-i -Ea|, and then |E m-i The values ​​of -Ea| are arranged in descending order and deleted in the calculation of the data deviation value Um. The remaining data are recalculated until the data deviation value Um≤U b-m , then obtain the deleted data in the data deviation value Um, and in the energy consumption value E m-i The query result data is marked as abnormal data, where the standard deviation value U b-m Obtained by technicians in this field after big data calculation;

[0059] S03: Obtain the carbon emission factor Am corresponding to each energy structure, and use the formula Obtain the energy carbon emission value CL of the target industry, b1 represents the total amount of energy types in the energy structure, and the carbon emission factor Am is obtained by technicians in this field based on big data network query;

[0060] S04: Obtain the city corresponding to the target industry and the city standard load value FC, based on the formula The energy impact value YN is obtained, δ1 is the energy constant, and the specific value of δ1 is obtained by technicians in this field after big data calculation. In this embodiment, the value of δ1 is 0.0153;

[0061] The calculation methods of traffic impact value include:

[0062] According to the logistics and transportation records of the target industry, first identify the transportation mode of the target industry. Specifically, the transportation mode includes road transportation, railway transportation, water transportation and air transportation, etc.;

[0063] Then, the transportation distance in the logistics transportation record is obtained, and the mean value of the transportation distance is taken as the inertial transportation value of the target industry. The inertial transportation value of the target industry is multiplied by the carbon emission factor of the transportation mode to obtain the transportation carbon emission value TT of the target industry;

[0064] Based on the formula The traffic impact value YT is obtained, δ2 is a traffic constant, and the specific value of δ2 is obtained by those skilled in the art after big data calculation. In this embodiment, the value of δ2 is 0.0094;

[0065] The calculation method of economic impact value includes:

[0066] Taking quarter as the time unit, obtain the industrial economic value SR of the target industry and the overall economic value SZ of the city respectively, and use the formula The economic impact value YE is obtained, CC represents the total carbon emissions of the target industry per unit time, δ3 is a correlation index, and the specific δ3 value is obtained by technicians in this field after big data calculation. In this embodiment, the value of δ3 is 0.0212;

[0067] The calculation method of comprehensive carbon emission coefficient includes:

[0068] Obtain the energy impact value YN, the traffic impact value YT and the economic impact value YE, and use the formula ZC = (YN + YT) × YE × λ to obtain the comprehensive carbon emission coefficient ZC, where λ is a correction factor, and the specific value of λ is obtained by technicians in this field after big data calculation;

[0069] Take all industrial types as target industries in turn and calculate the comprehensive carbon emission coefficient according to the method in step 3 above;

[0070] Step 4: Based on the comprehensive carbon emission coefficient, arrange the industrial types of all cities in the urban agglomeration in ascending order according to the comprehensive carbon emission coefficient, and obtain the industrial production sequence;

[0071] Then, based on the industrial production sequence of each city in the urban agglomeration, the city with the smallest comprehensive carbon emission coefficient for each industrial type in the urban agglomeration is obtained respectively, and transmitted to the terminal equipment of relevant departments at the same time as the industrial production sequence, so as to provide relevant data support for industrial production policies.

[0072] Example 2: Reference Figure 2 , an artificial intelligence-based urban agglomeration carbon emission spatial multidimensional data analysis system, including information collection module, city division module, carbon emission analysis module and comprehensive output module;

[0073] The city division module is used to divide the cities in the urban agglomeration into several carbon emission spaces according to the geographical distribution areas of the cities. At the same time, there is a one-way communication connection between the city division module and the information collection module;

[0074] The information collection module is used to collect historical carbon emission values ​​and urban standard load values, industrial distribution information, and operating data of industrial production companies in each carbon emission space, and transmit them to the carbon emission analysis module, where industrial distribution information refers to industrial types, and operating data includes energy consumption, industrial production and transportation, and industrial economic level;

[0075] The carbon emission analysis module is used to calculate according to the operation data in each carbon emission space, determine the energy impact value, traffic impact value and economic impact value, and then perform comprehensive calculations on the energy impact value, traffic impact value and economic impact value to determine the comprehensive carbon emission coefficient of each industrial type. After that, the carbon emission analysis module transmits the comprehensive carbon emission coefficient in the carbon emission space to the comprehensive output module;

[0076] The comprehensive output module is used to arrange the industrial types of all cities in the urban agglomeration in ascending order according to the comprehensive carbon emission coefficient to obtain the industrial production sequence. At the same time, based on the industrial production sequence of each city, the city with the smallest comprehensive carbon emission value for each industrial type in the urban agglomeration is obtained and transmitted to the terminal device simultaneously with the industrial production sequence.

[0077] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An artificial intelligence-based spatial multidimensional data analysis method for urban agglomeration carbon emissions, characterized in that: The method specifically comprises the following steps: Step 1: Select the target city cluster, delineate the carbon emission space according to the geographical distribution of the city, and collect the historical carbon emission values ​​and the city standard load value FC in the carbon emission space; Step 2: Collect industrial distribution information in the carbon emission space and operational data of industrial production companies. Industrial distribution information includes industrial types, and operational data includes energy consumption, industrial production and transportation, and industrial economic level. Step 3: Use artificial intelligence technology to analyze the comprehensive carbon emission coefficient of industrial types in each city, where the comprehensive carbon emission coefficient is composed of energy impact value, traffic impact value and economic impact value; Energy impact value refers to obtaining the energy structure and historical energy consumption values ​​of the target industry, and determining the energy representative value of each energy structure based on the historical energy consumption values ​​of the target industry, and combining the energy representative value with the corresponding carbon emission factor to obtain the result; Traffic impact value refers to the result obtained by determining the target industry's transportation mode and inertial transportation value based on the target industry's logistics and transportation records, combining the inertial transportation value with the carbon emission factor of the transportation mode, and further calculating it; The economic impact value refers to the result obtained after calculating the industrial economic value of the target industry and the overall economic value of the city; Step 4: Arrange the industrial types of all cities in the urban agglomeration in ascending order according to the comprehensive carbon emission coefficient to obtain the industrial production sequence, and then transmit the industrial production sequence to relevant departments.

2. The method for analyzing urban agglomeration carbon emission spatial multidimensional data based on artificial intelligence according to claim 1 is characterized in that: The calculation method of comprehensive carbon emission coefficient includes: Select any city in the target urban agglomeration, and choose an industrial type in this city as the target industry, obtain the energy impact value YN, traffic impact value YT and economic impact value YE of the target industry, and use the formula ZC=(YN+YT)×YE×λ to get the comprehensive carbon emission coefficient ZC, where λ is the correction factor.

3. The method for analyzing urban agglomeration carbon emission spatial multidimensional data based on artificial intelligence according to claim 2 is characterized in that: The calculation method of energy impact value YN includes: S01: Collect the energy structure of the target industry, and use the current time as the time node to collect the corresponding energy consumption value per unit time in the historical time; The energy structure includes electricity, natural gas, oil and diesel, the unit time is set to 1 month, and the historical time is set to 36 months; S02: Obtain the energy structure and the energy consumption value of the energy structure in the historical time, and use the mean processing method to calculate the energy representative value ENm corresponding to each energy structure, where m represents the number of different energy structures; S03: Obtain the carbon emission factor Am for each energy structure and use the formula The energy carbon emission value CL of the target industry is obtained, and b1 represents the total amount of energy types in the energy structure; S04: Obtain the city corresponding to the target industry and the city standard load value FC, based on the formula The energy impact value YN is obtained, δ1 is the energy constant, and the value of δ1 is 0.0153.

4. The method for analyzing spatial multidimensional data of carbon emissions of urban agglomerations based on artificial intelligence according to claim 3 is characterized in that: When calculating the energy representative value, it is necessary to identify and delete abnormal data in each energy structure. The specific method for identifying abnormal data is as follows: Using the formula Calculate the data deviation value Um of energy structure m, where i represents the number of different unit time, i∈[1,I], I represents the total amount of selected unit time, further, I takes the value of 36, E m-i It represents the energy consumption value generated by energy structure m in the i-th unit time, and Ea is the energy consumption value E m-i The mean of The data deviation value Um and the standard deviation value U b-m For comparison, if Um≤U b-m , it means that the energy consumption values ​​of energy structure m are normal data. On the contrary, if Um>U b-m , get |E m-i -Ea|, and then |E m-i The values ​​of -Ea| are arranged in descending order and deleted in the calculation of the data deviation value Um in order. The remaining data are recalculated until the data deviation value Um≤U b-m , then obtain the deleted data in the data deviation value Um, and in the energy consumption value E m-i A control query is performed in the query, and finally the query result data is marked as abnormal data.

5. The method for analyzing spatial multidimensional data of urban agglomeration carbon emissions based on artificial intelligence according to claim 2 is characterized in that: The calculation methods of traffic impact value include: According to the logistics and transportation records of the target industry, identify the transportation methods of the target industry, including road transportation, railway transportation, water transportation and air transportation; Obtain the transportation distance in the logistics transportation record, take the average of the transportation distance as the inertial transportation value of the target industry, multiply the inertial transportation value of the target industry by the carbon emission factor of the transportation mode, and obtain the transportation carbon emission value TT of the target industry; Based on the formula The traffic impact value YT is obtained, δ2 is the traffic constant, and the value of δ2 is 0.0094.

6. The method for analyzing spatial multidimensional data of urban agglomeration carbon emissions based on artificial intelligence according to claim 2 is characterized in that: The calculation method of economic impact value includes: Taking quarter as the time unit, obtain the industrial economic value SR of the target industry and the overall economic value SZ of the city respectively, and use the formula The economic impact value YE is obtained, CC represents the total carbon emissions of the target industry per unit time, δ3 is the correlation index, and the value of δ3 is 0.0212.

7. The urban agglomeration carbon emission spatial multidimensional data analysis system based on artificial intelligence is characterized by: The multidimensional data analysis system includes an information collection module, a city division module, a carbon emission analysis module and a comprehensive output module; The city division module is used to divide the cities in the urban agglomeration into several carbon emission spaces according to the geographical distribution areas of the cities. At the same time, there is a one-way communication connection between the city division module and the information collection module; The information collection module is used to collect historical carbon emission values ​​and urban standard load values, industrial distribution information, and operating data of industrial production companies in each carbon emission space, and transmit them to the carbon emission analysis module, where industrial distribution information refers to industrial types, and operating data includes energy consumption, industrial production and transportation, and industrial economic level; The carbon emission analysis module is used to calculate according to the operation data in each carbon emission space, determine the energy impact value, traffic impact value and economic impact value, and then perform comprehensive calculations on the energy impact value, traffic impact value and economic impact value to determine the comprehensive carbon emission coefficient of each industrial type. After that, the carbon emission analysis module transmits the comprehensive carbon emission coefficient in the carbon emission space to the comprehensive output module; The comprehensive output module is used to arrange the industrial types of all cities in the urban agglomeration in ascending order according to the comprehensive carbon emission coefficient, obtain the industrial production sequence, and output the industrial production sequence as data on the terminal device.

Images