Intelligent Analysis Method and System for Carbon Emission Data

Abstract

The embodiments of this specification provide an intelligent analysis method and system for carbon emission data. The intelligent analysis method for carbon emission data includes: obtaining initial carbon emission data, performing verification based on the initial carbon emission data to determine the verified carbon emission data, and detecting abnormal data based on the verified carbon emission data; establishing a carbon emission prediction model, and performing carbon emission-related predictions based on carbon emission-related data and the carbon emission prediction model to determine carbon emission prediction data; establishing a unit energy consumption calculation model, and calculating the unit carbon emissions and production energy consumption data based on the relevant data of the production conditions and the unit energy consumption calculation model; establishing a carbon emission knowledge and technical document library, obtaining the problem data of the user, and the carbon Q&A assistant module answering the problem data based on the carbon emission knowledge and technical document library. Connecting to the carbon inventory data, carbon verification data, and power plant real-time operation data to realize functions such as data verification, automatic report generation, real-time prediction, multi-dimensional analysis, and intelligent Q&A.

Description

Technical Field

[0001] The embodiments of this specification relate to the technical field of carbon emissions, and particularly to an intelligent analysis method for carbon emission data. Background Art

[0002] In July 2021, the carbon emission trading market was launched for trading. The power generation industry was the first to be included. By collecting reports and statements of key indicator parameters such as the consumption of fossil fuels in the furnace, elemental carbon content, and electricity generated and fed into the grid of emission control enterprises, and through on-site confirmation, the material balance method was used to verify the CO2 emissions and emission intensity. There are generally problems such as non-compliance with procedures, failure to perform duties, errors in parameter selection and statistical calculation in emission control enterprises, and prominent data quality problems. Since the continuous monitoring technology for CO2 emissions from thermal power plant flue gas is not yet mature, at present, it is urgent to use information technology means to standardize the whole process of carbon accounting management, and carry out work such as calibration and verification of monitoring equipment, direct collection of original data, supervision of the performance of inventory check personnel, and standardized management of the accounting process, so as to avoid artificial interference with data and ensure the authenticity, integrity, and accuracy of carbon emission data.

[0003] Currently, the nuclear accounting method is used in the carbon emission trading market, which requires regulated enterprises to declare data on the national carbon market management platform for monthly certification and annual verification. Currently, there is generally a lack of refined monthly management, and the control system mainly completes the verification and confirmation of "post-event" carbon emission data: for example, to know the carbon emissions of an enterprise in 2023, general personnel need to collect, sort out, and confirm the annual materials provided by the enterprise in January 2024. The accuracy review and verification of carbon emission data, including the full-scale visualization display and comparative analysis of the historical carbon emission indicators of the unit, to avoid the superposition of errors and increase the compliance cost, also belong to the important content of carbon emission work. Therefore, a better solution is urgently needed. Summary of the Invention

[0004] In view of this, the embodiments of this specification provide an intelligent analysis method for carbon emission data. One or more embodiments of this specification simultaneously relate to an intelligent analysis system for carbon emission data, a computing device, a computer-readable storage medium, and a computer program to solve the technical defects existing in the prior art.

[0005] According to the first aspect of the embodiments of this specification, an intelligent analysis method for carbon emission data is provided, including:

[0006] Obtain initial carbon emission data, verify based on the initial carbon emission data to determine verified carbon emission data, detect abnormal data based on the verified carbon emission data to determine the abnormal data detection result, and generate a carbon emission report based on the abnormal data detection result and the verified carbon emission data;

[0007] Obtain coal quality test data, and determine the carbon content data of furnace coal elements based on the coal quality test data; establish a carbon emission prediction model, and conduct carbon emission-related predictions based on carbon emission-related data and the carbon emission prediction model to determine carbon emission prediction data;

[0008] Establish a unit energy consumption calculation model, calculate the carbon emissions and production energy consumption data of the unit based on the relevant data of the production conditions and the unit energy consumption calculation model, and compare and analyze the carbon emissions and production energy consumption data of the unit with the carbon emissions data and energy consumption data in the carbon inventory digital management and control system and the carbon asset trading operation platform system to determine the data difference;

[0009] Based on the carbon market policies and interpretations, the carbon market Q&A knowledge base, and the carbon market quotations, establish a carbon emission knowledge and technology document library, create a carbon Q&A assistant module based on the carbon emission knowledge and technology document library, obtain the question data of users, and the carbon Q&A assistant module answers the question data based on the carbon emission knowledge and technology document library.

[0010] In a possible implementation manner, conduct verification based on the initial carbon emission data to determine the verified carbon emission data, including:

[0011] Obtain the historical data of the power plant, and conduct verification on the initial carbon emission data based on the confidence interval and the historical data to determine the verified carbon emission data;

[0012] Obtain the real-time data of the power plant, establish a carbon emission data index prediction model, and conduct verification based on the real-time data and the carbon emission data index prediction model to determine the verified carbon emission data.

[0013] In a possible implementation manner, conduct abnormal data detection based on the verified carbon emission data to determine the abnormal data detection result, including:

[0014] Conduct abnormal data detection based on the verified carbon emission data and the abnormal threshold to determine the abnormal data detection result; among them, the abnormal data detection result includes an alarm result, a concern result, and a normal result.

[0015] In a possible implementation manner, obtain coal quality test data, and determine the carbon content data of furnace coal elements based on the coal quality test data, including:

[0016] Obtain the data related to elemental carbon; among them, the data related to elemental carbon includes air-dried basis ash, air-dried basis sulfur, air-dried basis volatile matter, air-dried basis moisture, total moisture, and air-dried basis low calorific value, and use the correlation coefficient model and the linear regression analysis model to verify the correlation between the data related to elemental carbon and elemental carbon;

[0017] Conduct coal quality data fitting through historical coal quality test data and daily test data, and determine the carbon content data of furnace coal elements in combination with the correlation.

[0018] In a possible implementation, it further includes:

[0019] Obtain the real-time data of the unit, and generate a performance monitoring chart based on the real-time data of the unit and the process flow chart of a typical thermal power enterprise;

[0020] Conduct trend analysis and index statistics based on the performance monitoring chart.

[0021] In a possible implementation, it further includes:

[0022] Conduct carbon emission intensity analysis based on power generation, heat supply, heat supply ratio, and carbon emission data, determine the emission intensity analysis result, and display the historical trend change based on the emission intensity analysis result.

[0023] In a possible implementation, create a carbon Q&A assistant module based on the carbon emission knowledge and technology file library, obtain the question data of the user, and the carbon Q&A assistant module answers the question data based on the carbon emission knowledge and technology file library, including:

[0024] Create a carbon Q&A assistant module based on the carbon emission knowledge and technology file library through a large language model;

[0025] Obtain the question data of the user, and the carbon Q&A assistant module answers the question data based on the carbon emission knowledge and technology file library by optimizing the question classification and answer retrieval algorithms.

[0026] According to the second aspect of the embodiments of the present specification, a carbon emission data intelligent analysis system is provided, including:

[0027] A data verification module, configured to obtain initial carbon emission data, verify based on the initial carbon emission data to determine the verified carbon emission data, detect abnormal data based on the verified carbon emission data to determine the abnormal data detection result, and generate a carbon emission report based on the abnormal data detection result and the verified carbon emission data;

[0028] A data prediction module, configured to obtain coal quality analysis data, determine the carbon content data of furnace coal elements based on the coal quality analysis data; establish a carbon emission prediction model, and conduct carbon emission-related predictions based on carbon emission-related data and the carbon emission prediction model to determine the carbon emission prediction data;

[0029] A data analysis module, configured to establish a unit energy consumption calculation model, calculate the unit carbon emissions and production energy consumption data based on the relevant data of the production condition and the unit energy consumption calculation model, and compare and analyze the unit carbon emissions and production energy consumption data with the carbon emissions data and energy consumption data in the carbon inventory digital management and control system and the carbon asset trading operation platform system to determine the data difference;

[0030] The knowledge Q&A module is configured to establish a carbon emission knowledge and technology document library based on carbon market policies and interpretations, the carbon market Q&A knowledge base, and the carbon market quotations, create a carbon Q&A assistant module based on the carbon emission knowledge and technology document library, obtain the question data of users, and the carbon Q&A assistant module answers the question data based on the carbon emission knowledge and technology document library.

[0031] According to the third aspect of the embodiments of this specification, a computing device is provided, including:

[0032] A memory and a processor;

[0033] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the above-mentioned intelligent analysis method for carbon emission data are implemented.

[0034] According to the fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions. When the instructions are executed by the processor, the steps of the above-mentioned intelligent analysis method for carbon emission data are implemented.

[0035] According to the fifth aspect of the embodiments of this specification, a computer program is provided. When the computer program is executed on a computer, the computer is made to execute the steps of the above-mentioned intelligent analysis method for carbon emission data.

[0036] The embodiments of this specification provide an intelligent analysis method and system for carbon emission data. The intelligent analysis method for carbon emission data includes: obtaining initial carbon emission data, performing verification based on the initial carbon emission data to determine the verified carbon emission data, and detecting abnormal data based on the verified carbon emission data; establishing a carbon emission prediction model, and performing carbon emission-related predictions based on carbon emission-related data and the carbon emission prediction model to determine carbon emission prediction data; establishing a unit energy consumption calculation model, and calculating the unit carbon emissions and production energy consumption data based on the relevant data of the production conditions and the unit energy consumption calculation model; establishing a carbon emission knowledge and technology document library, obtaining the question data of users, and the carbon Q&A assistant module answers the question data based on the carbon emission knowledge and technology document library. Connecting to carbon inventory data, carbon verification data, and power plant real-time operation data to implement functions such as data verification, automatic report generation, real-time prediction, multi-dimensional analysis, and intelligent Q&A. Description of the Drawings

[0037] Figure 1 is a flowchart of an intelligent analysis method for carbon emission data provided by an embodiment of this specification;

[0038] Figure 2 is a schematic diagram of the classification of abnormal data levels of an intelligent analysis method for carbon emission data provided by an embodiment of this specification;

[0039] Figure 3 It is a schematic diagram of a report template for an intelligent analysis method of carbon emission data provided by an embodiment of this specification;

[0040] Figure 4 It is a schematic diagram of the association of enterprise basic information data for an intelligent analysis method of carbon emission data provided by an embodiment of this specification;

[0041] Figure 5 It is a schematic diagram of low - level heat data analysis for an intelligent analysis method of carbon emission data provided by an embodiment of this specification;

[0042] Figure 6 It is a schematic diagram of production data upload for an intelligent analysis method of carbon emission data provided by an embodiment of this specification;

[0043] Figure 7 It is a schematic diagram of index trend analysis for an intelligent analysis method of carbon emission data provided by an embodiment of this specification;

[0044] Figure 8 It is a dot - line graph of carbon emission intensity and carbon emissions for an intelligent analysis method of carbon emission data provided by an embodiment of this specification;

[0045] Figure 9 It is a schematic diagram of the trend of carbon emission intensity for an intelligent analysis method of carbon emission data provided by an embodiment of this specification;

[0046] Figure 10 It is a schematic diagram of unit comparison analysis for an intelligent analysis method of carbon emission data provided by an embodiment of this specification;

[0047] Figure 11 It is a schematic diagram of the structure of an intelligent analysis system for carbon emission data provided by an embodiment of this specification;

[0048] Figure 12 It is a structural block diagram of a computing device provided by an embodiment of this specification. Specific embodiments

[0049] In the following description, many specific details are set forth in order to provide a thorough understanding of this specification. However, this specification can be implemented in many other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the connotation of this specification. Therefore, this specification is not limited by the specific embodiments disclosed below.

[0050] The terms used in one or more embodiments of this specification are for the purpose of describing specific embodiments only and are not intended to limit one or more embodiments of this specification. The singular forms "a" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include the plural forms unless the context clearly dictates otherwise. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0051] It should be understood that although the terms first, second, etc. may be used in one or more embodiments of this specification to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to determining".

[0052] In this specification, a method for intelligent analysis of carbon emission data is provided. This specification also relates to an intelligent analysis system for carbon emission data, a computing device, and a computer-readable storage medium, which will be described in detail one by one in the following embodiments.

[0053] See Figure 1 , Figure 1 shows a flowchart of a method for intelligent analysis of carbon emission data provided according to an embodiment of this specification, which specifically includes the following steps.

[0054] Step 101: Obtain initial carbon emission data, determine verified carbon emission data based on the initial carbon emission data, detect abnormal data based on the verified carbon emission data, determine the abnormal data detection result, and generate a carbon emission report based on the abnormal data detection result and the verified carbon emission data.

[0055] Among them, the initial carbon emission data is the data transmitted through the carbon emission control system. For example, the carbon emission control system within an enterprise. The verified carbon emission data refers to the data after verifying the initial carbon emission data through verification rules.

[0056] In practical applications, when establishing carbon emission data verification rules, the verification methods to be established include threshold verification, historical data verification, real-time carbon emission measurement verification, and intelligent data verification. For abnormal data, the system automatically gives an early warning to promptly detect possible data quality problems and monitor the data quality management situation. The data of each power plant is used for learning and training in the dimension of an independent unit to form a verification ability customized for each plant. This solution supports the administrator to customize the configuration of data verification rules, such as modifying the parameter range of verification rules, warning reminder methods, etc. Finally, the reasons for errors in the filled data are statistically tracked, and a deviation analysis of the filled data is formed.

[0057] In a possible implementation manner, based on the initial carbon emission data for verification to determine the verified carbon emission data, it includes: obtaining the historical data of the power plant, and verifying the initial carbon emission data based on the confidence interval and historical data to determine the verified carbon emission data; obtaining the real-time data of the power plant, establishing a carbon emission data index prediction model, and verifying the initial carbon emission data based on the real-time data and the carbon emission data index prediction model to determine the verified carbon emission data.

[0058] In practical applications, this solution should support multiple verification mechanisms, including but not limited to threshold verification, historical data verification, real-time carbon emission measurement verification, intelligent data verification, etc.

[0059] Data is checked according to the preset threshold. When the data filled in the control system is not within the threshold range, an error prompt is given, and the detailed information on the required range of the filled data is pointed out. At the same time, an abnormal data filling instruction is designed for the inventory personnel to record or clarify data problems. The relevant explanations are entered for the first time in the description item, and can be automatically brought out as alternative items when the same threshold problem appears subsequently. The threshold range defaults to the threshold settings built into the system, and supports the system administrator to manually adjust the personalization at the group level and unit level.

[0060] The threshold verification of 13 types of group-wide carbon emission parameters is shown in the following table:

[0061] Table 1

[0062]

[0063] For the unit-level data thresholds of the lower calorific value of the coal as fired, total moisture of the coal as fired, inherent moisture, total sulfur on an air-dried basis, carbon content on an as-received basis in the composite sample, hydrogen on an air-dried basis, inherent moisture, and total sulfur on an air-dried basis, historical data (optional, the previous year, two years, three years, four years, five years) are collected and the maximum and minimum values are found, and a certain proportion (the proportion is adjustable) % is enlarged and reduced respectively as the verification range of the key index parameters of a single unit.

[0064] For example, based on the element carbon content analysis index in No. 2 in Table 1, the specific judgment formula is as follows: ) / measurement of air-dry basis high heat -1|<10%;

[0065] Among them, Cad refers to the elemental carbon content of the integrated sample on an air-dry basis; NCVgr,ad: refers to the high calorific value on an air-dry basis; the measured high calorific value on an air-dry basis refers to the high calorific value on an air-dry basis of the integrated sample; C ad is the amount of carbon, H ad is the amount of hydrogen. The coefficients of carbon and hydrogen as well as the constant 0.0335 are obtained through a large number of fittings of previous data.

[0066] During the verification process, the high calorific value on an air-dry basis can be judged based on the above formula to determine whether it is within the normal range.

[0067] Furthermore, combined with the historical data of the power plant (optional, the previous year, two years, three years, four years, five years), the confidence interval is introduced as the rationality range of the reported data, so as to dynamically adjust the data verification range according to the historical data and form the one-plant-one-policy capability of data verification on the power plant side. The confidence level evaluation index is used as the basis for judging the accuracy of the reported data, and the administrator can adjust the confidence level.

[0068] ① Set the confidence level. The system provides three confidence levels: 68%, 95%, and 99.7%. The default is 95%. ② Calculate the confidence interval. The confidence interval = [Historical data mean - t*SE, historical data mean + t*SE]. The historical data mean uses the verified monthly production and emission data in the carbon report. t is obtained by querying the t distribution table in combination with the sample quantity. SE is the sample standard error. ③ Support unified configuration of confidence levels, generate confidence intervals by unit and indicator, and remind when the reported data is outside the interval.

[0069] Furthermore, real-time data is used to calculate and verify carbon emissions. The real-time data of the company's data center is connected, and based on the big data model, a prediction model for carbon emission data indicators such as emissions, quotas, power generation coal consumption, and heating coal consumption is established to form monthly carbon emission forecast data, which is compared with the monthly carbon emission data of the reported data to give a carbon emission difference value. If the deviation exceeds a certain ratio (the ratio is adjustable), an alarm will be issued.

[0070] It can also include carbon emission data verification: including but not limited to providing emission and quota calculation methods according to the latest accounting guidelines, providing inventory data, real-time calculation data, forecast data, threshold verification, historical value verification and other data cross-checking solutions, forming historical data comparison for the same unit, detecting data deviations from the same coal source, analyzing emission differences of similar units, and multi-source mutual verification.

[0071] Furthermore, the administrator can enable, disable, modify, or configure data verification rules according to actual needs: for threshold verification, the administrator can adjust the threshold verification range of each indicator; for historical data verification, the administrator can adjust the confidence interval and the selected range of historical data; for real-time carbon emission measurement verification, the administrator can adjust the abnormal reminder value range; for fitting prediction data verification, the administrator can make personalized adjustments to the data anomaly reminder range for the entire group and power plants.

[0072] In a possible implementation, abnormal data detection is performed based on the verified carbon emission data to determine the abnormal data detection result, including: performing abnormal data detection based on the verified carbon emission data and the abnormal threshold to determine the abnormal data detection result; wherein, the abnormal data detection result includes an alarm result, a concern result, and a normal result.

[0073] In practical applications, refer to Figure 2 , this solution has the function of automatically detecting abnormal data and issuing early warnings. The abnormal data levels are divided into three categories: alarm (red label), concern (yellow label), and normal (green label). The number of abnormal data can be statistically counted by category / level / overall abnormal situation. The system supports generating a "List of Abnormal Data" after abnormal data appears, and supports functions such as downloading, forwarding, and sharing of file lists.

[0074] Furthermore, the system can count all abnormal data and the reasons for the anomalies, can generate abnormal data records, and display the problem data to users in the form of reports or graphics to help improve data quality, and supports exporting in the form of PDF, word, etc. The summary of abnormal data refers to forming an initial problem list and recording the processing results each time.

[0075] This solution can also generate carbon emission reports, compile templates that meet the standards of the group company, and ensure the security and compliance of documents through permission control and version management. The system supports the configuration of data indicators associated with the indicator library, realizes the generation of reports with unified formats and accurate content through indicator data extraction, and has a periodic automatic generation and push function to improve the efficiency of report compilation.

[0076] Refer to Figure 3 , in this solution, templates that meet the standards of the group company are established, carbon emission indicators are collected from the data center and the carbon asset trading operation platform system to form a complete carbon emission report. At the same time, the administrator can create, update, and customize report templates according to specific needs. This solution controls the operations on the templates according to user roles and permissions. Specific permissions are required for operations such as creating, changing, deleting, and upgrading templates to ensure the security and compliance of documents.

[0077] Refer to Figure 4, support data index configuration associated with the index library, realize the generation of reports with unified format and accurate content by fetching data through indexes, and have the function of automatically generating and pushing periodically to improve the report compilation efficiency.

[0078] Furthermore, this solution can customize the report generation cycle according to the provided template, and generate the annual emission analysis report of emission control enterprises, the annual total reports of subsidiaries and the group company on schedule. It can count the power plants for which reports have been generated and the power plants that have not carried out the report submission work in real time, display the number of enterprises that have (not) completed the report submission, and the specific enterprise list can be viewed by clicking. For reports that have not been submitted overdue, this solution has a reminder function to assist in understanding the generation situation of the carbon emission reports of power plants and mastering the progress of uploading data for reports.

[0079] Step 102: Obtain the coal quality test data, determine the carbon content data of furnace coal based on the coal quality test data; establish a carbon emission prediction model, and conduct carbon emission related predictions based on the carbon emission related data and the carbon emission prediction model to determine the carbon emission prediction data.

[0080] Among them, the coal quality test data are the relevant data obtained after testing the coal, which can be obtained through calorific value measurement or proximate analysis. There can be multiple carbon emission prediction models, which are used to predict different types of data. The carbon emission related data can be determined according to the corresponding carbon emission prediction model. For example, for the carbon emission prediction model used to predict carbon emissions, the corresponding carbon emission related data can be the amount of coal input to the furnace and the lower calorific value of the coal input to the furnace. Correspondingly, the carbon emission related prediction and the carbon emission prediction data are the predictions and data corresponding to the carbon emission prediction model.

[0081] In practical applications, build a unified general carbon emission prediction model on the platform to ensure the consistency and authority of the model. According to the specific characteristics of different units, apply and optimize the carbon emission prediction model, and bind these parameters to the actual data acquisition point codes of each power plant and each unit in the data middle platform to realize real-time substitution, calculation and analysis of data. Combine the data filled in the carbon inventory digital management and control system, and give timely warnings for situations beyond the prediction range, and analyze the reasons for the overlimit.

[0082] Furthermore, the overall technical path of this solution: use the basic carbon emission data and the production plan data provided by emission control enterprises to predict indicators such as unit emissions / quota amounts, carbon element content, power generation / heating coal consumption, and power generation / heating carbon emission intensity.

[0083] In a possible implementation, coal quality test data is obtained, and the carbon content data of furnace coal is determined based on the coal quality test data, including: obtaining data related to elemental carbon; wherein, the data related to elemental carbon includes air-dried basis ash, air-dried basis sulfur, air-dried basis volatile matter, air-dried basis moisture, total moisture, and air-dried basis net calorific value. The correlation between the data related to elemental carbon and elemental carbon is verified using a correlation coefficient model and a linear regression analysis model; the coal quality data is fitted through historical coal quality test data and daily test data, and the carbon content data of furnace coal is determined in combination with the correlation.

[0084] In practical applications, referring to Figure 5 , the industrial analysis of the power plant can obtain coal quality data such as air-dried basis ash, air-dried basis sulfur, air-dried basis volatile matter, air-dried basis moisture, total moisture, and air-dried basis net calorific value every day. The correlation coefficient model and the linear regression analysis model are used to verify the correlation between the above parameters and elemental carbon. The coal quality parameters are affected by coal types and blending combustion. The coal quality data is fitted through historical coal quality test data and daily test data to predict the carbon content data of the coal entering the furnace.

[0085] Furthermore, referring to Figure 6 , relying on machine learning technology, the enterprise emission data is predicted based on the coal consumption and net calorific value of the coal entering the furnace, or according to the production data provided by the enterprise, the predicted data is fitted to form the carbon emission / quota prediction data. This solution needs to have the functions of batch import and export.

[0086] Specifically, in this solution, 8 models are set to predict different data, as described in detail below. Among them, the input parameters are the data related to carbon emissions, and the predicted parameters are the carbon emission prediction data.

[0087] (1) Prediction model for carbon emissions (coal 1):

[0088] Predicted parameter: Carbon emissions (coal 1);

[0089] Input parameters:

[0090] Coal quantity entering the furnace (unit: ton);

[0091] Net calorific value of coal entering the furnace (unit: GJ / t);

[0092] (2) Prediction model for carbon emissions (coal 2):

[0093] Predicted parameter: Carbon emissions (coal 2);

[0094] Input parameters:

[0095] Power generation (unit: MWh);

[0096] Heat supply (unit: GJ);

[0097] Unit capacity (unit: MW);

[0098] Operating hours (unit: hours);

[0099] (3) Power generation emission intensity prediction model:

[0100] Prediction parameter: Power generation emission intensity;

[0101] Input parameters:

[0102] Heat supply ratio (unit: %);

[0103] Unit capacity (unit: MW);

[0104] Unit type;

[0105] Load (output) factor (unit: %);

[0106] (4) Power generation coal consumption prediction model:

[0107] Prediction parameter: Power generation coal consumption;

[0108] Input parameters:

[0109] Heat supply ratio (unit: %);

[0110] Unit capacity (unit: MW);

[0111] Unit type;

[0112] Load (output) factor (unit: %);

[0113] (5) Prediction model for carbon content of received basis elements in the comprehensive sample:

[0114] Prediction parameter: Carbon content of received basis elements in the comprehensive sample;

[0115] Input parameters:

[0116] Lower calorific value of as-received coal for furnace entry (unit: GJ / t);

[0117] Air-dried basis moisture of as-received coal for furnace entry (unit: %);

[0118] Sulfur content of as-received coal for furnace entry (unit: %);

[0119] (6) Prediction model for carbon content of air-dried basis elements in the comprehensive sample:

[0120] Prediction parameter: Carbon content of air-dried basis elements in the comprehensive sample;

[0121] Input parameters:

[0122] Volatile matter of air-dried basis in the comprehensive sample (unit: %);

[0123] Composite sample air-dried basis ash content (unit: %);

[0124] Composite sample air-dried basis moisture content (unit: %);

[0125] Composite sample air-dried basis gross calorific value (unit: GJ / t);

[0126] Composite sample air-dried basis total sulfur (unit: %);

[0127] (7) Carbon emission (gas) prediction model:

[0128] Prediction parameter: Carbon emission (gas);

[0129] Input parameters:

[0130] Gas consumption (unit: 10,000 m³);

[0131] Lower calorific value of gas (unit: GJ / t);

[0132] (8) Power generation gas consumption prediction model:

[0133] Prediction parameter: Power generation gas consumption;

[0134] Input parameters:

[0135] Load factor (unit: %);

[0136] Heat supply ratio (unit: %);

[0137] Unit capacity (unit: MW);

[0138] Unit type;

[0139] In the above prediction models, the key steps to optimize the carbon emission prediction model include data preprocessing, feature engineering, and model fusion. Data preprocessing improves data quality through methods such as cleaning and normalization; feature engineering enhances model sensitivity by extracting and selecting features; model fusion combines multiple models such as random forest and gradient boosting to improve prediction performance by integrating the advantages of different models. In the model training stage, historical data and pre-set algorithms are used to adjust model parameters to optimize prediction performance. After training, the model needs to be tested using a validation dataset to evaluate the accuracy and reliability of its predictions. Commonly used validation methods include cross-validation and leave-one-out validation to ensure that the model has good generalization ability.

[0140] In this solution, the neural network can be used to estimate the time entropy (NNetEn). By training the neural network, features reflecting its internal structure and dynamic characteristics can be extracted from the time series, thereby estimating the time entropy. This method can effectively process non-linear and non-stationary time series data, providing a new perspective to understand and analyze the complexity of time series. When implementing the neural network to estimate the time entropy, an appropriate time series dataset needs to be prepared first. Then, a suitable neural network structure, such as a multi-layer perceptron or a recurrent neural network, is selected and trained so that the network can learn the patterns and features of the time series. During the training process, the network parameters are adjusted and the loss function is optimized to minimize the prediction error and improve the generalization ability of the model. Finally, the trained network is used to estimate the entropy value of the time series.

[0141] Furthermore, during the process of using the neural network for prediction, it is necessary to first perform fuzzy clustering on the input data, and use the initial clustering conditions of the fuzzy clustering algorithm improved by the genetic algorithm in the clustering algorithm to solve the problem of local convergence.

[0142] It should be noted that other models can also be used for prediction, such as singular spectrum decomposition (SSD), variational mode decomposition (VMD), kernel extreme learning machine (KELM), least squares support vector machine (LSSVM), etc. The prediction accuracy is improved through error correction and induced ordered weighted averaging (IOWA) operators. This method is particularly suitable for processing highly complex carbon emission data.

[0143] In a possible implementation, it also includes: obtaining the real-time data of the unit, generating a performance monitoring view based on the real-time data of the unit and the process flow chart of a typical thermal power enterprise; performing trend analysis and index statistics based on the performance monitoring view.

[0144] In practical applications, the system can view real-time data such as the power generation / heat supply coal consumption of the unit, and the positive / negative balance efficiency of the boiler. The system needs to include the process flow chart of a typical thermal power enterprise, on which real-time data of indicators such as the coal consumption of the coal fed into the furnace, the operating hours, and the load rate of the thermal system, boiler performance, and turbine performance connected to the system can be viewed. On the process flow chart, the indicator data is displayed in three lines from top to bottom. The top line is the real-time data, the middle line is the data calculated from carbon emissions, and the bottom line is the design data of the thermal system. The three lines of data are marked with different colors. See Figure 7 , the system supports trend analysis of indicators. Click on the data in the above figure to enter the data bar history record, and the time period selection is supported to query the indicator data for different time periods. The start time and end time can also be selected to query the indicator statistical values for different time periods.

[0145] Step 103: Establish a unit energy consumption calculation model, calculate the unit carbon emissions and production energy consumption data based on the relevant data of the production conditions and the unit energy consumption calculation model, and compare and analyze the unit carbon emissions and production energy consumption data with the carbon emissions data and energy consumption data in the carbon inventory digital management and control system and the carbon asset trading operation platform system to determine the data difference.

[0146] In practical applications, taking the unit as the dimension, display the analysis of energy consumption indicators, emission intensity indicators, unit boiler efficiency, carbon content per unit calorific value of coal, etc. of each unit of the enterprise in multiple time dimensions in the form of charts, form rankings and comparisons of units or companies, and display the maximum and minimum values of indicators under a fixed time scale. Support the analysis between carbon emissions and energy consumption at the unit level, the analysis of carbon emission intensity, and the analysis of carbon emission trends, etc.

[0147] Establish a unit energy consumption calculation model. The system can obtain the relevant data of the production conditions from the data middle platform or the carbon asset trading operation platform system, calculate the unit carbon emissions and production energy consumption data in combination with the power generation data, and compare and analyze the carbon emissions data and energy consumption data in the carbon inventory digital management and control system and the carbon asset trading operation platform system to find out the data difference. Support data drilling and in-depth mining, and conduct mining analysis on the changes of key parameters such as load rate, standard coal consumption for power generation, low calorific value of fossil fuels, heat supply ratio, carbon oxidation rate, and carbon content per unit calorific value to find out the reasons for the data difference.

[0148] For carbon emission indicators, set monthly year-on-year and month-on-month analysis from aspects such as unit type, cooling method, fuel type, etc., and 1-12 months can be selected; quarterly year-on-year and month-on-month analysis, and the first quarter, second quarter, third quarter, and fourth quarter can be selected; annual year-on-year and month-on-month analysis, and the year can be selected. The analysis results can be displayed in different forms (such as graphs, tables, a combination of graphs and tables).

[0149] In a possible implementation manner, it further includes: performing carbon emission intensity analysis based on the power generation, heat supply, heat supply ratio, and carbon emissions data to determine the emission intensity analysis results, and displaying the historical trend changes based on the emission intensity analysis results.

[0150] In practical applications, refer to Figure 8 and Figure 9 , calculate the power generation / heat supply carbon emission intensity analysis according to the power generation, heat supply, heat supply ratio, and carbon emissions data, and display the historical trend changes. Display the carbon emission intensity parameters in real time, and visually display the healthy interval band of the carbon emission intensity in combination with the quota value to facilitate the auxiliary analysis of the carbon emission status of the unit.

[0151] Furthermore, there are monthly year-on-year and month-on-month analysis, which can be selected from January to December; quarterly year-on-year and month-on-month analysis, which can be selected from the first quarter, second quarter, third quarter, and fourth quarter; annual year-on-year and month-on-month analysis, which can be selected from the year. The analysis results can be displayed in different forms (combination of graphs, tables, and icons).

[0152] Furthermore, the unit load rate data is obtained to generate the coal consumption, carbon emission intensity and unit load rate fluctuation operation curve. The unit load rate fluctuation is tracked, and trend analysis is performed on each unit according to a certain period. The operation safety status of each unit is monitored to see if it deteriorates or changes, and the rationality of load changes, operation duration and carbon emission changes is verified.

[0153] See also Figure 10 , visualize the carbon emission source data. According to the emission source trend analysis, the total carbon emissions of enterprises are divided into specific emission sources, and the time series change analysis is carried out according to the emission sources, such as fossil fuel combustion, external electricity emission trends, power generation, heating carbon emission trends, etc.

[0154] Step 104: Based on carbon market policies and interpretations, the carbon market Q&A knowledge base and carbon market trends, a carbon emission knowledge and technology document library is established, and a carbon Q&A assistant module is created based on the carbon emission knowledge and technology document library to obtain user question data. The carbon Q&A assistant module answers the question data based on the carbon emission knowledge and technology document library.

[0155] In actual application, we collect carbon market policies and interpretations, carbon market Q&A knowledge base, carbon market trends and other contents, establish a carbon emission knowledge and technology document library, upload all materials to the knowledge platform, and create a carbon Q&A assistant module. In the form of Q&A / voice interaction, users input questions, and the system module can answer them in a targeted manner based on the built-in knowledge and technology document library, making it convenient for practitioners to quickly obtain the specific requirements of industry standards and technical indicators, understand industry trends and interpret policies and regulations. We have added years of work experience of carbon asset companies, such as common carbon emission indicator thresholds, post-dispute handling methods, and other unique modules to effectively provide knowledge to carbon inventory business personnel quickly and accurately.

[0156] In one possible implementation, a carbon question and answer assistant module is created based on the carbon emission knowledge and technology document library to obtain user question data, and the carbon question and answer assistant module answers the question data based on the carbon emission knowledge and technology document library, including: creating a carbon question and answer assistant module based on the carbon emission knowledge and technology document library through a language big model; obtaining user question data, and the carbon question and answer assistant module answers the question data based on the carbon emission knowledge and technology document library by optimizing question classification and answer retrieval algorithms.

[0157] In practical applications, data augmentation techniques are utilized to improve the performance of the retrieval engine when processing the knowledge base, enabling deeper information mining and knowledge discovery. A large language model is introduced, which has the ability of natural language processing, including semantic understanding, sentiment analysis, etc., to enhance the system's accurate parsing ability for user queries. By optimizing the question classification and answer retrieval algorithms, the system can quickly and accurately respond to user questions and provide real-time and accurate information feedback. Dialogue management is implemented to maintain the dialogue state, understand the context, and provide a smooth multi-turn dialogue experience.

[0158] Furthermore, a historical dialogue storage and retrieval mechanism is designed to enable users to review and utilize previous dialogue content. A background management tool is provided, allowing administrators to customize the sensitive word list and data desensitization rules, implementing a sensitive content detection and filtering mechanism to ensure the compliance of dialogue content and protect user privacy. A permission control mechanism can also be designed to set the access scope of the knowledge base according to different positions and roles. And users can independently decide to use the Internet-based Q&A or the knowledge base-based Q&A mode.

[0159] The embodiments of this specification provide a method and system for intelligent analysis of carbon emission data. The method for intelligent analysis of carbon emission data includes: obtaining initial carbon emission data, verifying to determine the verified carbon emission data based on the initial carbon emission data, and detecting abnormal data based on the verified carbon emission data; establishing a carbon emission prediction model, and making carbon emission-related predictions based on carbon emission-related data and the carbon emission prediction model to determine carbon emission prediction data; establishing a unit energy consumption calculation model, and calculating the unit carbon emissions and production energy consumption data based on the relevant data of the production conditions and the unit energy consumption calculation model; establishing a carbon emission knowledge and technology document library, obtaining the question data of users, and the carbon Q&A assistant module answers the question data based on the carbon emission knowledge and technology document library. Connecting to carbon inventory data, carbon verification data, and power plant real-time operation data to implement functions such as data verification, automatic report generation, real-time prediction, multi-dimensional analysis, and intelligent Q&A.

[0160] Corresponding to the above method embodiments, this specification also provides embodiments of a system for intelligent analysis of carbon emission data. Figure 11 The structural schematic diagram of a system for intelligent analysis of carbon emission data provided by an embodiment of this specification is shown. As Figure 11 shown, the device includes:

[0161] A data verification module 1101, configured to obtain initial carbon emission data, verify to determine the verified carbon emission data based on the initial carbon emission data, detect abnormal data based on the verified carbon emission data to determine the abnormal data detection result, and generate a carbon emission report based on the abnormal data detection result and the verified carbon emission data;

[0162] The data prediction module 1102 is configured to obtain coal quality test data, determine the carbon content data of furnace coal elements based on the coal quality test data; establish a carbon emission prediction model, and perform carbon emission related predictions based on the carbon emission related data and the carbon emission prediction model to determine the carbon emission prediction data;

[0163] The data analysis module 1103 is configured to establish a unit energy consumption calculation model, calculate the unit carbon emissions and production energy consumption data based on the relevant data of the production conditions and the unit energy consumption calculation model, and compare and analyze the unit carbon emissions and production energy consumption data with the carbon emissions data and energy consumption data in the carbon inventory digital management and control system and the carbon asset trading operation platform system to determine the data difference;

[0164] The knowledge Q&A module 1104 is configured to establish a carbon emission knowledge and technology document library based on the carbon market policies and interpretations, the carbon market Q&A knowledge base and the carbon market quotations, create a carbon Q&A assistant module based on the carbon emission knowledge and technology document library, obtain the question data of the user, and the carbon Q&A assistant module answers the question data based on the carbon emission knowledge and technology document library.

[0165] In a possible implementation manner, verifying and determining the verified carbon emission data based on the initial carbon emission data includes:

[0166] Obtain the historical data of the power plant, and verify and determine the verified carbon emission data based on the confidence interval and the historical data;

[0167] Obtain the real-time data of the power plant, establish a carbon emission data index prediction model, and verify and determine the verified carbon emission data based on the real-time data and the carbon emission data index prediction model.

[0168] In a possible implementation manner, detecting abnormal data based on the verified carbon emission data to determine the abnormal data detection result includes:

[0169] Detect abnormal data based on the verified carbon emission data and the abnormal threshold to determine the abnormal data detection result; wherein, the abnormal data detection result includes an alarm result, a concern result and a normal result.

[0170] In a possible implementation manner, obtaining the coal quality test data and determining the carbon content data of furnace coal elements based on the coal quality test data includes:

[0171] Obtain the data related to elemental carbon; wherein, the data related to elemental carbon includes air-dried basis ash, air-dried basis sulfur, air-dried basis volatile matter, air-dried basis moisture, total moisture and air-dried basis low calorific value, and verify the correlation between the data related to elemental carbon and elemental carbon by using the correlation coefficient model and the linear regression analysis model;

[0172] Perform coal quality data fitting through historical coal quality test data and daily test data, and determine the carbon content data of furnace coal elements in combination with the correlation.

[0173] In a possible implementation, it further includes:

[0174] Obtain the real-time data of the unit, and generate a performance monitoring view based on the real-time data of the unit and the process flow chart of a typical thermal power enterprise;

[0175] Perform trend analysis and index statistics based on the performance monitoring view.

[0176] In a possible implementation, it further includes:

[0177] Conduct carbon emission intensity analysis based on power generation, heat supply, heat supply ratio, and carbon emission data, determine the analysis result of emission intensity, and display the historical trend change based on the analysis result of emission intensity.

[0178] In a possible implementation, create a carbon Q&A assistant module based on the carbon emission knowledge and technology file library, obtain the question data of the user, and the carbon Q&A assistant module answers the question data based on the carbon emission knowledge and technology file library, including:

[0179] Create a carbon Q&A assistant module based on the carbon emission knowledge and technology file library through a language large model;

[0180] Obtain the question data of the user, and the carbon Q&A assistant module answers the question data based on the carbon emission knowledge and technology file library by optimizing the question classification and answer retrieval algorithms.

[0181] The embodiments of this specification provide a carbon emission data intelligent analysis method and system. The carbon emission data intelligent analysis system includes: obtaining initial carbon emission data, performing verification based on the initial carbon emission data to determine the verified carbon emission data, and performing abnormal data detection based on the verified carbon emission data; establishing a carbon emission prediction model, and performing carbon emission-related predictions based on the carbon emission-related data and the carbon emission prediction model to determine the carbon emission prediction data; establishing a unit energy consumption calculation model, and calculating the unit carbon emissions and production energy consumption data based on the relevant data of the production conditions and the unit energy consumption calculation model; establishing a carbon emission knowledge and technology file library, obtaining the question data of the user, and the carbon Q&A assistant module answers the question data based on the carbon emission knowledge and technology file library. Connecting to the carbon inventory data, carbon verification data, and the real-time operation data of the power plant to realize functions such as data verification, automatic report generation, real-time prediction, multi-dimensional analysis, and intelligent Q&A.

[0182] The above is a schematic solution of an intelligent carbon emission data analysis system according to this embodiment. It should be noted that the technical solution of this intelligent carbon emission data analysis system and the technical solution of the above intelligent carbon emission data analysis method belong to the same concept. For the details not described in the technical solution of the intelligent carbon emission data analysis system, reference can be made to the description of the technical solution of the above intelligent carbon emission data analysis method.

[0183] Figure 12 FIG. shows a structural block diagram of a computing device 1200 according to an embodiment of this specification. The components of the computing device 1200 include but are not limited to a memory 1210 and a processor 1220. The processor 1220 is connected to the memory 1210 through a bus 1230, and a database 1250 is used to store data.

[0184] The computing device 1200 further includes an access device 1240, which enables the computing device 1200 to communicate via one or more networks 1260. Examples of these networks include the Public Switched Telephone Network (PSTN), Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), or a combination of communication networks such as the Internet. The access device 1240 may include one or more of any type of wired or wireless network interface (e.g., a network interface card (NIC)), such as an IEEE802.11 Wireless Local Area Network (WLAN) wireless interface, a Worldwide Interoperability for Microwave Access (Wi-MAX) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, a Near Field Communication (NFC).

[0185] In an embodiment of this specification, the above components of the computing device 1200 and Figure 12 other components not shown in the figure may also be connected to each other, for example, through a bus. It should be understood that Figure 12 the shown structural block diagram of the computing device is only for illustrative purposes and is not a limitation on the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0186] The computing device 1200 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smart phones), wearable computing devices (e.g., smart watches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or personal computers (PCs). The computing device 1200 can also be a mobile or stationary server.

[0187] Among them, the processor 1220 is used to execute the following computer-executable instructions, and when the computer-executable instructions are executed by the processor, the steps of the above-mentioned intelligent analysis method for carbon emission data are implemented. The above is a schematic solution of a computing device in this embodiment. It should be noted that the technical solution of this computing device and the technical solution of the above-mentioned intelligent analysis method for carbon emission data belong to the same concept. For the details not described in detail in the technical solution of the computing device, reference can be made to the description of the technical solution of the above-mentioned intelligent analysis method for carbon emission data.

[0188] An embodiment of this specification also provides a computer-readable storage medium, which stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the steps of the above-mentioned intelligent analysis method for carbon emission data are implemented.

[0189] The above is a schematic solution of a computer-readable storage medium in this embodiment. It should be noted that the technical solution of this storage medium and the technical solution of the above-mentioned intelligent analysis method for carbon emission data belong to the same concept. For the details not described in detail in the technical solution of the storage medium, reference can be made to the description of the technical solution of the above-mentioned intelligent analysis method for carbon emission data.

[0190] An embodiment of this specification also provides a computer program, wherein when the computer program is executed on a computer, the computer is made to execute the steps of the above-mentioned intelligent analysis method for carbon emission data.

[0191] The above is a schematic solution of a computer program in this embodiment. It should be noted that the technical solution of this computer program and the technical solution of the above-mentioned intelligent analysis method for carbon emission data belong to the same concept. For the details not described in detail in the technical solution of the computer program, reference can be made to the description of the technical solution of the above-mentioned intelligent analysis method for carbon emission data.

[0192] The above describes specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require the particular order or sequential order shown to achieve the desired result. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0193] The computer instructions include computer program code, which may be in source code form, object code form, executable file, or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0194] It should be noted that for the foregoing method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the embodiments of this specification are not limited by the described order of actions, because according to the embodiments of this specification, certain steps may be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments of this specification.

[0195] In the above embodiments, the descriptions of the various embodiments have their own focuses. For the parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0196] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The alternative embodiments do not elaborate on all the details and do not limit the invention to only the specific embodiments described. Obviously, many modifications and variations can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the embodiments of this specification, so that those skilled in the art can well understand and utilize this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A carbon emission data intelligent analysis method, characterized in that: include: Acquire initial carbon emission data, perform verification based on the initial carbon emission data to determine verified carbon emission data, perform abnormal data detection based on the verified carbon emission data to determine abnormal data detection results, and generate a carbon emission report based on the abnormal data detection results and the verified carbon emission data; Acquire coal quality test data, and determine the elemental carbon content data of the incoming coal based on the coal quality test data; Establishing a carbon emission prediction model, performing carbon emission related prediction based on carbon emission related data and the carbon emission prediction model, and determining carbon emission prediction data; Establish a unit energy consumption calculation model, calculate the unit carbon emissions and production energy consumption data based on relevant data of production conditions and the unit energy consumption calculation model, compare and analyze the unit carbon emissions and production energy consumption data with the carbon emission data and energy consumption data in the carbon inventory digital management and control system and the carbon asset trading operation platform system, and determine the data difference; Based on carbon market policies and interpretations, the carbon market Q&A knowledge base and carbon market trends, a carbon emission knowledge and technology document library is established, and a carbon Q&A assistant module is created based on the carbon emission knowledge and technology document library to obtain user question data. The carbon Q&A assistant module answers the question data based on the carbon emission knowledge and technology document library; The step of verifying and determining verified carbon emission data based on the initial carbon emission data includes: Acquire historical data of the power plant, and calibrate the initial carbon emission data based on the confidence interval and the historical data to determine the calibrated carbon emission data; Acquire real-time data of the power plant, establish a carbon emission data indicator prediction model, and verify and determine the verified carbon emission data based on the real-time data and the carbon emission data indicator prediction model; The step of obtaining coal quality test data and determining the carbon content of incoming coal based on the coal quality test data includes: Obtaining element carbon related data; wherein the element carbon related data includes air-dried basis ash, air-dried basis sulfur, air-dried basis volatile matter, air-dried basis moisture, total moisture and air-dried basis lower calorific value, and using a correlation coefficient model and a linear regression analysis model to verify the correlation between the element carbon related data and the element carbon; Fitting coal quality data through historical coal quality test data and daily test data, and determining the carbon content data of the coal entering the furnace in combination with the correlation; The step of creating a carbon question and answer assistant module based on the carbon emission knowledge and technology document library, obtaining user question data, and the carbon question and answer assistant module answering the question data based on the carbon emission knowledge and technology document library includes: Based on the carbon emission knowledge and technical document library, a carbon question-answering assistant module is created through a language macro model; Obtaining user's question data, the carbon question-answering assistant module answers the question data based on the carbon emission knowledge and technical document library by optimizing question classification and answer retrieval algorithms; The knowledge and technology document library includes carbon market policies and interpretations, a carbon market Q&A knowledge base and carbon market trends.

2. The method according to claim 1, characterized in that The abnormal data detection is performed based on the verified carbon emission data to determine the abnormal data detection result, including: Abnormal data detection is performed based on the verified carbon emission data and the abnormal threshold value to determine the abnormal data detection result; wherein the abnormal data detection result includes an alarm result, a concern result and a normal result.

3. The method according to claim 1, characterized in that Also includes: Acquire real-time data of the unit, and generate a performance monitoring diagram based on the real-time data of the unit and a process flow diagram of a typical thermal power enterprise; Trend analysis and indicator statistics are performed based on the performance monitoring graph.

4. The method according to claim 1, characterized in that Also includes: Carbon emission intensity analysis is performed based on power generation, heat supply, heat supply ratio, and carbon emission data to determine emission intensity analysis results, and historical trend changes are displayed based on the emission intensity analysis results.

5. A carbon emission data intelligent analysis system, characterized in that: The steps for implementing the carbon emission data intelligent analysis method according to any one of claims 1 to 4 include: a data verification module configured to obtain initial carbon emission data, verify and determine verified carbon emission data based on the initial carbon emission data, perform abnormal data detection based on the verified carbon emission data, determine abnormal data detection results, and generate a carbon emission report based on the abnormal data detection results and the verified carbon emission data; The data prediction module is configured to obtain coal quality test data, determine the carbon content data of the coal entering the furnace based on the coal quality test data; establish a carbon emission prediction model, perform carbon emission related prediction based on the carbon emission related data and the carbon emission prediction model, and determine the carbon emission prediction data; The data analysis module is configured to establish a unit energy consumption calculation model, calculate the unit carbon emissions and production energy consumption data based on relevant data of production conditions and the unit energy consumption calculation model, compare and analyze the unit carbon emissions and production energy consumption data with the carbon emission data and energy consumption data in the carbon inventory digital management and control system and the carbon asset trading operation platform system, and determine the data difference; The knowledge question and answer module is configured to establish a carbon emission knowledge and technology document library based on carbon market policies and interpretations, a carbon market Q&A knowledge base and carbon market trends, create a carbon question and answer assistant module based on the carbon emission knowledge and technology document library, obtain user question data, and the carbon question and answer assistant module answers the question data based on the carbon emission knowledge and technology document library.

6. A computing device, characterized in that include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the carbon emission data intelligent analysis method described in any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the carbon emission data intelligent analysis method described in any one of claims 1 to 4.

Images