Carbon inspection coal quality analysis data verification method

Abstract

The invention relates to the technical field of environmental protection in the power industry, in particular to a carbon inspection coal quality analysis data verification method, which comprises the following steps: extracting initial coal quality analysis data from a coal sample by using coal quality analysis parameters; segmenting on the basis of the received basis volatile data to obtain coal quality analysis interval data meeting different interval conditions; modeling through regression analysis to obtain an initial coal quality regression analysis model; based on output values of different initial coal quality regression analysis models, screening corresponding coal quality analysis interval data to obtain final coal quality analysis interval data, and determining a final coal quality regression analysis model; and generating a first checking result during carbon checking by using the final coal quality regression analysis model. Therefore, the problems of insufficient model fitting degree, relatively low prediction precision, lack of robustness, incapability of determining contribution degrees of different parameters according to different volatile component intervals, relatively low reliability and the like due to neglect of the influence of coal quality parameters on the low calorific value in related technologies are solved.

Description

Technical Field

[0001] This application relates to the technical field of environmental protection in the power industry, and particularly relates to a method for verifying coal quality analysis data for carbon verification. Background Art

[0002] With the increasingly severe global climate change problem, reducing greenhouse gas emissions has become the focus of attention of governments and industrial sectors around the world. Coal-fired power plants are one of the main sources of carbon dioxide emissions. Therefore, how to accurately measure the carbon dioxide emissions of coal-fired power plants and optimize the emission reduction management of power plants is a key technical link to achieve the carbon emission reduction goal.

[0003] In related technologies, the carbon emissions can be calculated by measuring and calculating coal quality analysis data such as the carbon content and net calorific value of fossil fuels; or by establishing preliminary multiple linear regression models for the elemental carbon content and net calorific value respectively, and conducting significance tests, and then finally establishing an optimal prediction regression model for the net calorific value and elemental carbon content, so as to assist third-party verification agencies in differentiating carbon data.

[0004] However, in related technologies, a single regression model is used to process all coal sample data, which easily ignores the influence of coal quality parameters (such as volatile matter and ash) on the net calorific value, resulting in insufficient model fitting degree and low prediction accuracy. In addition, the single model lacks robustness in dealing with extreme values and cannot clarify the contribution degrees of different parameters according to different volatile matter intervals, seriously affecting the reliability of the verification results and urgently needing improvement. Summary of the Invention

[0005] This application provides a method for verifying coal quality analysis data for carbon verification to solve the problems in related technologies, such as using a single regression model for processing, ignoring the influence of coal quality parameters on the net calorific value, resulting in insufficient model fitting degree and low prediction accuracy. In addition, it lacks robustness in dealing with extreme values and cannot clarify the contribution degrees of different parameters according to different volatile matter intervals, seriously affecting the reliability of the verification results.

[0006] The first aspect of the embodiments of the present application provides a method for verifying coal quality analysis data for carbon verification, which is applied from the perspective of proximate analysis. Among them, the method includes the following steps: extracting initial coal quality analysis data from coal samples using at least one coal quality analysis parameter; segmenting the initial coal quality analysis data based on the volatile matter on as-received basis to obtain coal quality analysis interval data that meets different interval conditions; modeling the coal quality analysis interval data through regression analysis to obtain at least one initial coal quality regression analysis model; screening the corresponding coal quality analysis interval data based on the output values of different initial coal quality regression analysis models to obtain the final coal quality analysis interval data, and determining the final coal quality regression analysis model based on the final coal quality analysis interval data; using the final coal quality regression analysis model to generate the first verification result during carbon verification.

[0007] Through the above technical solution, initial coal quality analysis data can be extracted from coal samples using coal quality analysis parameters and segmented, and then coal quality analysis interval data that meets different interval conditions can be obtained. By modeling, an initial coal quality regression analysis model can be obtained, screening the corresponding coal quality analysis interval data to obtain the final coal quality analysis interval data, determining the final coal quality regression analysis model, and then using the final coal quality regression analysis model to generate the first verification result during carbon verification. Through segmented modeling, the deviation caused by data heterogeneity in the global model is avoided, making the prediction result of the model more in line with the actual data distribution. By comparing the output values of different interval models, abnormal data can be identified, improving the reliability of the verification report, and then accurately calculating the carbon emissions of coal-fired power plants, thereby optimizing the emission reduction management and optimization strategies of the power plants.

[0008] Optionally, in an embodiment of the present application, the determining the final coal quality regression analysis model based on the final coal quality analysis interval data includes: obtaining the first final coal quality regression analysis model when the volatile matter on as-received basis in the final coal quality analysis interval data is in the first interval condition; obtaining the second final coal quality regression analysis model when the volatile matter on as-received basis in the final coal quality analysis interval data is in the second interval condition; obtaining the third final coal quality regression analysis model when the volatile matter on as-received basis in the final coal quality analysis interval data is in the third interval condition; obtaining the fourth final coal quality regression analysis model when the volatile matter on as-received basis in the final coal quality analysis interval data is in the fourth interval condition.

[0009] Through the above technical solution, corresponding final coal quality regression analysis models can be established respectively according to different intervals of the volatile matter on as-received basis, and then better capture the relationship between coal quality characteristics and carbon emissions in different intervals, reduce the impact of data heterogeneity on the model, thereby improving prediction accuracy, more flexibly adapting to different coal quality characteristics corresponding to different intervals, enhancing the generalization ability of the model, and then formulating more refined procurement, combustion, and emission strategies for coal in different intervals.

[0010] Optionally, in an embodiment of the present application,

[0011] The expression of the first final coal quality regression analysis model may but is not limited to:

[0012] Q gr,ad = 41.106 - 0.478M t - 0.418A ad - 0.251V ad - 0.363S t,ad ,

[0013] wherein, Q gr,ad represents the calorific value at constant volume on an air-dried basis, unit MJ / kg, M t represents the total moisture, A ad represents the ash content, V ad represents the volatile matter, S t,ad represents the sulfur content;

[0014] The expression of the second final coal quality regression analysis model may but is not limited to:

[0015] Q gr,ad = 39.797 - 0.465M t - 0.414A ad - 0.205V ad - 0.144S t,ad ,

[0016] wherein, Q gr,ad represents the calorific value at constant volume on an air-dried basis, unit MJ / kg, M t represents the total moisture, A ad represents the ash content, V ad represents the volatile matter, S t,ad represents the sulfur content;

[0017] The expression of the third final coal quality regression analysis model may but is not limited to:

[0018] Q gr,ad = 32.884 - 0.391M t - 0.373A ad + 0.001V ad - 0.358S t,ad ,

[0019] wherein, Q gr,ad represents the calorific value at constant volume on an air-dried basis, unit MJ / kg, M t represents the total moisture, A ad represents the ash content, V ad represents the volatile matter, S t,ad represents the sulfur content;

[0020] The expression of the fourth final coal quality regression analysis model can be, but is not limited to:

[0021] Q gr,ad = 31.816 - 0.388M t - 0.362A ad + 0.033V ad - 0.365S t,ad ,

[0022] wherein, Q gr,ad represents the net calorific value at air-dry basis, with the unit of MJ / kg, M t represents the total moisture, A ad represents the ash content, V ad represents the volatile matter, S t,ad represents the sulfur content.

[0023] Through the above technical solution, the net calorific value at air-dry basis can be used as the dependent variable, and the total moisture, ash content, volatile matter and sulfur content can be used as independent variables to construct the final coal quality regression analysis model. The influence degree of coal quality parameters in different intervals on the prediction target is determined through different coefficients and constant terms, so that each model focuses on a specific volatile matter interval, reduces the influence of data heterogeneity on the model, thereby improving the prediction accuracy, enhancing the model adaptability, and supporting fine decision-making.

[0024] Optionally, in an embodiment of the present application, screening the corresponding coal quality analysis interval data based on the output values of different initial coal quality regression analysis models to obtain the final coal quality analysis interval data includes: obtaining at least one evaluation index corresponding to the different initial coal quality regression analysis models; determining the abnormal data that meet the preset abnormal conditions in the corresponding coal quality analysis interval data based on the at least one evaluation index and the output values; screening the coal quality analysis interval data based on the abnormal data to obtain the final coal quality analysis interval data.

[0025] Through the above technical solution, the abnormal data that meet the preset abnormal conditions can be determined through different evaluation indexes and the output values of different initial coal quality regression analysis models, and the coal quality analysis interval data can be screened by using the abnormal data. Furthermore, the final coal quality analysis interval data can be obtained. The deviation between the model output and the measured value is quantified through the evaluation index, the abnormal data is accurately located and removed, and the overfitting or underfitting of the model caused by the abnormal data is reduced, providing a reliable basis for subsequent modeling and decision-making and maintaining the prediction stability.

[0026] In the second aspect of the embodiments of the present application, a method for verifying coal quality analysis data for carbon verification is provided, which is applied from the perspective of elemental analysis. Among them, the method includes the following steps: obtaining initial coal quality analysis data; determining the net calorific value at air dry basis in the initial coal quality analysis data; modeling the initial coal quality analysis data based on the net calorific value at air dry basis and regression analysis to obtain at least one initial coal quality regression analysis model; screening the corresponding initial coal quality analysis data based on the output values of different initial coal quality regression analysis models to obtain the final coal quality analysis data, and determining the final coal quality regression analysis model based on the final coal quality analysis data; using the final coal quality regression analysis model to generate the second verification result during carbon verification.

[0027] Through the above technical solution, the initial coal quality analysis data can be modeled by determining the net calorific value at air dry basis in the initial coal quality analysis data, and then the initial coal quality regression analysis model can be obtained. After screening the corresponding initial coal quality analysis data, the final coal quality regression analysis model is determined, and then the second verification result during carbon verification is generated. By establishing a regression model using the net calorific value at air dry basis and coal quality parameters, the internal relationship between coal quality characteristics and calorific value can be more accurately reflected, the prediction accuracy can be improved, the data is screened based on the output values of different initial coal quality regression analysis models, ensuring that the final coal quality regression analysis model can cover the entire volatile matter range, reducing model deviation caused by data heterogeneity, being more flexible to adapt to changes in parameters such as volatile matter, and maintaining prediction stability.

[0028] Optionally, in an embodiment of the present application, the expression of the final coal quality regression analysis model can be, but is not limited to:

[0029] Q gr,ad =-0.795 - 0.01*M t +0.348*C ad +0.786*H ad +0.096*S t,ad ,

[0030] where Q gr,ad represents the net calorific value at air dry basis, with the unit MJ / kg, M t represents the moisture at air dry basis, C ad represents the carbon at air dry basis, H ad represents the hydrogen at air dry basis, S t,ad represents the sulfur at air dry basis.

[0031] Through the above technical solution, the final coal quality regression analysis model can be established by comprehensively considering multiple coal quality parameters, thus more comprehensively reflecting the influence of coal quality characteristics on calorific value, more accurately predicting the calorific value of different coals, improving the prediction accuracy, adapting to changes in different coal quality characteristics, reducing deviations caused by abnormal data, and enhancing the robustness of the model.

[0032] Optionally, in an embodiment of the present application, screening the corresponding initial coal quality analysis data based on the output values of different initial coal quality regression analysis models to obtain the final coal quality analysis data includes: obtaining at least one evaluation index corresponding to the different initial coal quality regression analysis models; determining, based on the at least one evaluation index and the output values, the abnormal data in the corresponding initial coal quality analysis data that meet the preset abnormal conditions; and screening the initial coal quality analysis data based on the abnormal data to obtain the final coal quality analysis data.

[0033] Through the above technical solution, the abnormal data that meet the preset abnormal conditions can be determined according to the evaluation indexes and output values corresponding to different initial coal quality regression analysis models, and then the initial coal quality analysis data can be screened, so as to obtain the final coal quality analysis data. The abnormal data can be accurately located through the evaluation indexes, and data cleaning can be carried out, providing a reliable basis for subsequent modeling and decision-making, and further enhancing the robustness and generalization ability of the model.

[0034] An embodiment of the third aspect of the present application provides a carbon verification coal quality analysis data verification device, which is applied from the perspective of industrial analysis. The device includes: an extraction module for extracting initial coal quality analysis data from a coal sample by using at least one coal quality analysis parameter; a first generation module for segmenting the initial coal quality analysis data based on the received basis volatile matter to obtain coal quality analysis interval data that meet different interval conditions; a first construction module for modeling the coal quality analysis interval data through regression analysis to obtain at least one initial coal quality regression analysis model; a first determination module for screening the corresponding coal quality analysis interval data based on the output values of different initial coal quality regression analysis models to obtain the final coal quality analysis interval data, and determining the final coal quality regression analysis model based on the final coal quality analysis interval data; and a second generation module for generating a first verification result during carbon verification by using the final coal quality regression analysis model.

[0035] Through the above technical solution, the initial coal quality analysis data can be extracted from the coal sample by using the coal quality analysis parameter and segmented, and then the coal quality analysis interval data that meet different interval conditions can be obtained. The initial coal quality regression analysis model can be obtained through modeling, the corresponding coal quality analysis interval data can be screened to obtain the final coal quality analysis interval data, and the final coal quality regression analysis model can be determined. Furthermore, the first verification result during carbon verification can be generated by using the final coal quality regression analysis model. Through segmented modeling, the deviation caused by data heterogeneity in the global model is avoided, making the prediction result of the model more consistent with the actual data distribution. By comparing the output values of different interval models, abnormal data can be identified, the reliability of the verification report can be improved, and the carbon emissions of coal-fired power plants can be accurately calculated, thereby optimizing the emission reduction management and optimization strategy of the power plant.

[0036] Optionally, in an embodiment of the present application, the first determination module includes: a first generation unit configured to obtain a first final coal quality regression analysis model when the received basis volatile matter in the final coal quality analysis interval data is within the first interval condition; a second generation unit configured to obtain a second final coal quality regression analysis model when the received basis volatile matter in the final coal quality analysis interval data is within the second interval condition; a third generation unit configured to obtain a third final coal quality regression analysis model when the received basis volatile matter in the final coal quality analysis interval data is within the third interval condition; a fourth generation unit configured to obtain a fourth final coal quality regression analysis model when the received basis volatile matter in the final coal quality analysis interval data is within the fourth interval condition.

[0037] Through the above technical solutions, corresponding final coal quality regression analysis models can be established respectively according to different intervals of the received basis volatile matter, thereby better capturing the relationship between coal quality characteristics and carbon emissions within different intervals, reducing the impact of data heterogeneity on the model, improving prediction accuracy, more flexibly adapting to different coal quality characteristics corresponding to different intervals, enhancing the generalization ability of the model, and then formulating more refined procurement, combustion, and emission strategies for coals in different intervals.

[0038] Optionally, in an embodiment of the present application, wherein,

[0039] The expression of the first final coal quality regression analysis model may but is not limited to:

[0040] Q gr,ad = 41.106 - 0.478M t - 0.418A ad - 0.251V ad - 0.363S t,ad ,

[0041] wherein, Q gr,ad represents the air-dried basis lower calorific value, with the unit of MJ / kg, M t represents the total moisture, a ad represents the ash content, V ad represents the volatile matter, S t,ad represents the sulfur content;

[0042] The expression of the second final coal quality regression analysis model may but is not limited to:

[0043] Q gr,ad = 39.797 - 0.465M t - 0.414A ad - 0.205V ad - 0.144S t,ad ,

[0044] wherein, Qgr,ad represents the air-dried basis net calorific value, unit MJ / kg, M t represents the total moisture, A ad represents the ash content, V ad represents the volatile matter, S t,ad represents the sulfur content;

[0045] The expression of the third final coal quality regression analysis model can be but is not limited to:

[0046] Q gr,ad = 32.884 - 0.391M t - 0.373A ad + 0.001V ad - 0.358S t,ad ,

[0047] wherein, Q gr,ad represents the air-dried basis net calorific value, unit MJ / kg, M t represents the total moisture, A ad represents the ash content, V ad represents the volatile matter, S t,ad represents the sulfur content;

[0048] The expression of the fourth final coal quality regression analysis model can be but is not limited to:

[0049] Q gr,ad = 31.816 - 0.388M t - 0.362A ad + 0.033V ad - 0.365S t,ad ,

[0050] wherein, Q gr,ad represents the air-dried basis net calorific value, unit MJ / kg, M t represents the total moisture, A ad represents the ash content, V ad represents the volatile matter, S t,ad represents the sulfur content.

[0051] Through the above technical solution, the air-dried basis net calorific value can be used as the dependent variable, and the total moisture, ash content, volatile matter and sulfur content can be used as independent variables to construct the final coal quality regression analysis model. The influence degree of coal quality parameters on the prediction target in different intervals is determined through different coefficients and constant terms, so that each model focuses on a specific volatile matter interval, reduces the influence of data heterogeneity on the model, thereby improving the prediction accuracy, enhancing the model adaptability and supporting fine decision-making.

[0052] Optionally, in an embodiment of the present application, the first determination module includes: a first acquisition unit configured to acquire at least one evaluation index corresponding to the different initial coal quality regression analysis models; a first determination unit configured to determine, based on the at least one evaluation index and the output value, abnormal data in the corresponding coal quality analysis interval data that satisfies a preset abnormal condition; and a first screening unit configured to screen the coal quality analysis interval data based on the abnormal data to obtain the final coal quality analysis interval data.

[0053] Through the above technical solution, abnormal data that satisfies the preset abnormal condition can be determined by different evaluation indexes and the output values of different initial coal quality regression analysis models, and the coal quality analysis interval data can be screened by using the abnormal data, so as to obtain the final coal quality analysis interval data. The deviation between the model output and the measured value is quantified by the evaluation index, the abnormal data is accurately located and removed, reducing the overfitting or underfitting of the model that may be caused by the abnormal data, providing a reliable basis for subsequent modeling and decision-making, and maintaining the prediction stability.

[0054] An embodiment of the fourth aspect of the present application provides a carbon verification coal quality analysis data verification device, which is applied from the perspective of elemental analysis. The device includes: an acquisition module configured to acquire initial coal quality analysis data; a second determination module configured to determine the air-dried basis lower calorific value in the initial coal quality analysis data; a second construction module configured to perform modeling on the initial coal quality analysis data based on the air-dried basis lower calorific value and regression analysis to obtain at least one initial coal quality regression analysis model; a third determination module configured to screen the corresponding initial coal quality analysis data based on the output values of different initial coal quality regression analysis models to obtain the final coal quality analysis data, and determine the final coal quality regression analysis model based on the final coal quality analysis data; and a third generation module configured to generate a second verification result during carbon verification by using the final coal quality regression analysis model.

[0055] Through the above technical solution, the initial coal quality analysis data can be modeled by determining the air-dried basis lower calorific value in the initial coal quality analysis data, so as to obtain the initial coal quality regression analysis model, and the final coal quality regression analysis model can be determined after screening the corresponding initial coal quality analysis data, and then the second verification result during carbon verification can be generated. By establishing a regression model using the air-dried basis lower calorific value and coal quality parameters, the internal relationship between coal quality characteristics and calorific value can be more accurately reflected, improving the prediction accuracy. Screening data based on the output values of different initial coal quality regression analysis models ensures that the final coal quality regression analysis model can cover the entire volatile matter interval, reducing the model deviation caused by data heterogeneity, being more flexible in adapting to changes in parameters such as volatile matter, and maintaining the prediction stability.

[0056] Optionally, in an embodiment of the present application, the expression of the final coal quality regression analysis model may but is not limited to:

[0057] Q gr,ad = -0.795 - 0.01 * M t + 0.348 * C ad + 0.786 * H ad + 0.096 * S t,ad ,

[0058] Wherein, Q gr,ad represents the net calorific value at air-dried basis, unit MJ / kg, M t represents the moisture at air-dried basis, C ad represents the carbon at air-dried basis, H ad represents the hydrogen at air-dried basis, S t,ad represents the sulfur at air-dried basis.

[0059] Through the above technical solution, multiple coal quality parameters can be comprehensively considered to establish a final coal quality regression analysis model, so as to more comprehensively reflect the influence of coal quality characteristics on calorific value, more accurately predict the calorific value of different coal qualities, improve the prediction accuracy, adapt to the changes of different coal quality characteristics, reduce the deviation caused by abnormal data, and enhance the robustness of the model.

[0060] Optionally, in an embodiment of the present application, the third determination module includes: a second acquisition unit, configured to acquire at least one evaluation index corresponding to the different initial coal quality regression analysis models; a second determination unit, configured to determine, based on the at least one evaluation index and the output value, abnormal data in the corresponding initial coal quality analysis data that meet a preset abnormal condition; and a second screening unit, configured to screen the initial coal quality analysis data based on the abnormal data to obtain the final coal quality analysis data.

[0061] Through the above technical solution, abnormal data that meet the preset abnormal condition can be determined according to the evaluation indexes and output values corresponding to different initial coal quality regression analysis models, and then the initial coal quality analysis data can be screened to obtain the final coal quality analysis data. The abnormal data are accurately located through the evaluation indexes, and data cleaning is performed, providing a reliable basis for subsequent modeling and decision-making, and further enhancing the robustness and generalization ability of the model.

[0062] An embodiment of the fifth aspect of the present application provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the carbon verification coal quality analysis data verification method as described in the above embodiment.

[0063] An embodiment of the sixth aspect of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the program is executed by a processor, it implements the carbon verification coal quality analysis data verification method as described above.

[0064] An embodiment of the seventh aspect of the present application provides a computer program product, including a computer program, which when executed implements the above coal quality analysis data verification method for carbon verification.

[0065] Embodiments of the present application can extract initial coal quality analysis data from coal samples using coal quality analysis parameters, segment them, and then obtain coal quality analysis interval data that meets different interval conditions. By building a model, an initial coal quality regression analysis model is obtained, the corresponding coal quality analysis interval data is screened to obtain the final coal quality analysis interval data, and the final coal quality regression analysis model is determined. Then, the first verification result during carbon verification is generated using the final coal quality regression analysis model. Through segmented modeling, the deviation caused by data heterogeneity in the global model is avoided, making the prediction result of the model more consistent with the actual data distribution. By comparing the output values of different interval models, abnormal data is identified, the reliability of the verification report is improved, and then the carbon emissions of coal-fired power plants are accurately calculated, thereby optimizing the emission reduction management and optimization strategies of the power plants. Thus, the problems in the related art are solved, such as using a single regression model for processing, ignoring the influence of coal quality parameters on the low calorific value, resulting in insufficient model fitting degree and low prediction accuracy. In addition, the processing of extreme values lacks robustness, and the contribution degrees of different parameters cannot be clarified according to different volatile matter intervals, seriously affecting the reliability of the verification results.

[0066] The additional aspects and advantages of the present application will be partially given in the following description, partially become obvious from the following description, or be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] The above and / or additional aspects and advantages of the present application will become obvious and easy to understand from the following description of the embodiments in conjunction with the drawings, where:

[0068] Figure 1 is a flowchart of a method for verifying coal quality analysis data for carbon verification according to an embodiment of the present application;

[0069] Figure 2 is a schematic diagram of the working principle of a method for verifying coal quality analysis data for carbon verification according to an embodiment of the present application;

[0070] Figure 3 is a block diagram of a device for verifying coal quality analysis data for carbon verification according to an embodiment of the present application;

[0071] Figure 4 is a flowchart of a method for verifying coal quality analysis data for carbon verification according to another embodiment of the present application;

[0072] Figure 5 is a flowchart of the working principle of a method for verifying coal quality analysis data for carbon verification according to an embodiment of the present application;

[0073] Figure 6 A block diagram of a carbon verification coal quality analysis data verification device provided according to another embodiment of the present application;

[0074] Figure 7 A schematic structural diagram of an electronic device provided according to an embodiment of the present application.

[0075] Reference numerals:

[0076] Among them, 30 - carbon verification coal quality analysis data verification device; 301 - extraction module, 302 - first generation module, 303 - first construction module, 304 - first determination module, 305 - second generation module; 60 - carbon verification coal quality analysis data verification device; 601 - acquisition module, 602 - second determination module, 603 - second construction module, 604 - third determination module, 605 - third generation module; 701 - memory, 702 - processor, 703 - communication interface. Detailed implementation manners

[0077] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application and should not be construed as limiting the present application.

[0078] The method for verifying coal quality analysis data in carbon verification according to the embodiments of the present application will be described below with reference to the accompanying drawings. In view of the problem in the above-mentioned background art that a single regression model is used for processing, ignoring the influence of coal quality parameters on the low calorific value, resulting in insufficient model fitting degree and low prediction accuracy. In addition, the processing of extreme values lacks robustness, and the contribution degrees of different parameters cannot be clarified according to different volatile matter intervals, seriously affecting the reliability of the verification results. The present application provides a method for verifying coal quality analysis data in carbon verification. In this method, initial coal quality analysis data can be extracted from coal samples using coal quality analysis parameters, and segmented to obtain coal quality analysis interval data that meet different interval conditions. An initial coal quality regression analysis model is obtained through modeling, the corresponding coal quality analysis interval data is screened to obtain the final coal quality analysis interval data, and the final coal quality regression analysis model is determined. Then, the first verification result during carbon verification is generated using the final coal quality regression analysis model. Through segmented modeling, the deviation caused by data heterogeneity in the global model is avoided, making the prediction result of the model more in line with the actual data distribution. By comparing the output values of models in different intervals, abnormal data is identified, improving the reliability of the verification report, and then accurately calculating the carbon emissions of coal-fired power plants, thereby optimizing the emission reduction management and optimization strategies of the power plants. Thus, the problems in the related art, such as using a single regression model for processing, ignoring the influence of coal quality parameters on the low calorific value, resulting in insufficient model fitting degree and low prediction accuracy. In addition, the processing of extreme values lacks robustness, and the contribution degrees of different parameters cannot be clarified according to different volatile matter intervals, seriously affecting the reliability of the verification results, are solved.

[0079] Specifically, Figure 1 FIG. is a flowchart of a method for verifying coal quality analysis data in carbon verification according to an embodiment of the present application.

[0080] As Figure 1 shown, the method for verifying coal quality analysis data in carbon verification is applied from the perspective of proximate analysis. Among them, the method includes the following steps:

[0081] In step S101, initial coal quality analysis data is extracted from coal samples using at least one coal quality analysis parameter.

[0082] It can be understood that at least one coal quality analysis parameter in the embodiments of the present application can include, but is not limited to, received basis volatile matter, total moisture, ash, volatile matter, sulfur content, etc. The present application does not make specific limitations; and coal samples can be obtained by using vehicle sampling, coal pile sampling or coal stream sampling according to the national standard GB475.

[0083] As a possible implementation manner, in the embodiments of the present application, corresponding initial coal quality analysis data can be extracted from coal samples according to different coal quality analysis parameters.

[0084] Exemplarily, in the embodiments of the present application, 1200 groups of initial coal quality analysis data can be extracted from coal samples using total moisture, ash, volatile matter, sulfur content, etc.

[0085] In step S102, the initial coal quality analysis data is segmented based on the received basis volatile matter to obtain coal quality analysis interval data that meets different interval conditions.

[0086] It can be understood that in the embodiments of the present application, the volatile matter characteristics are different corresponding to different received basis volatile matter contents. Therefore, in the embodiments of the present application, based on the received basis volatile matter, denoted as V ar , content, the natural distribution breakpoints of the volatile matter are determined through K-means clustering analysis to ensure the balance between data that meets different interval conditions and high homogeneity of physical and chemical properties.

[0087] In the actual execution process, the embodiments of the present application can segment the initial coal quality analysis data to obtain coal quality analysis interval data with the received basis volatile matter in different intervals.

[0088] Exemplarily, in the embodiments of the present application, when 15.54% ≤ V ar < 22.49% on the received basis, the initial coal quality analysis data is divided into coal quality analysis interval data corresponding to low volatile coal; when 22.49% ≤ V ar < 25% on the received basis, the initial coal quality analysis data is divided into coal quality analysis interval data corresponding to medium-low volatile coal; when 25% ≤ V ar < 26.61% on the received basis, the initial coal quality analysis data is divided into coal quality analysis interval data corresponding to medium-high volatile coal; when 26.61% ≤ V ar ≤ 34.32% on the received basis, the initial coal quality analysis data is divided into coal quality analysis interval data corresponding to high volatile coal.

[0089] In step S103, regression analysis is performed on the coal quality analysis interval data to obtain at least one initial coal quality regression analysis model.

[0090] In some embodiments, the embodiments of the present application can use the least squares method to solve the regression coefficients for each coal quality analysis interval data, and then obtain the corresponding initial coal quality regression analysis model. The main content is as follows:

[0091] First, construct a data matrix.

[0092] Among them, in the embodiments of the present application, the dependent variable Y can be set as the air-dried basis net calorific value, and the independent variables can include but are not limited to total moisture, ash, volatile matter, sulfur content, etc., and the present application does not make specific limitations. Further, the embodiments of the present application can design the data matrix X and the response vector Y, and their expressions can include but are not limited to the following respectively:

[0093]

[0094] wherein, represents the net dry basis lower calorific value, with the unit of MJ / kg, represents the total moisture, represents the ash content, represents the volatile matter, represents the sulfur content, i = 1,..., n, where n is the number of samples in the interval, and the first column of the data matrix X is the constant term 1, which is used to estimate the intercept term β0.

[0095] Next, calculate the regression coefficients.

[0096] wherein, in the embodiments of the present application, the regression coefficients β can be solved through matrix operations based on the data matrix X and the response vector Y, and its expression can be but is not limited to:

[0097] β = (X T X) -1 X T Y,

[0098] wherein, in the embodiments of the present application, the physical meaning of β is that each element in β corresponds to the coefficient of the independent variable, indicating the marginal effect on the lower calorific value when the independent variable increases by 1 unit while keeping other variables unchanged. For example, in high-volatile coal, the sulfur content coefficient is -0.365, indicating that when the sulfur content increases by 1%, the lower calorific value decreases by 0.365 MJ / kg.

[0099] Finally, construct the initial coal quality regression analysis model.

[0100] wherein, in the embodiments of the present application, the initial coal quality regression analysis model can be constructed through the regression coefficients.

[0101] Exemplarily, in the embodiments of the present application, when the received basis volatile matter 26.61% ≤ V ar ≤ 34.32%, construct the initial coal quality regression analysis model, and the specific content can be:

[0102] First, select the first 5 groups of sample data to construct a data matrix.

[0103] wherein, in the embodiments of the present application, the expressions of the data matrix X and the response vector Y can be but are not limited to:

[0104]

[0105] Next, calculate the regression coefficients.

[0106] wherein, the expression of the regression coefficients in the embodiments of the present application can be but is not limited to:

[0107]

[0108] Finally, an initial coal quality regression analysis model is constructed.

[0109] Among them, the expression of the initial coal quality regression analysis model constructed in the embodiment of the present application can be, but is not limited to:

[0110] Q gr,ad = 31.816 - 0.388M t - 0.362A ad + 0.033V ad - 0.365S t,ad ,

[0111] Among them, Q gr,ad represents the net calorific value at air-dry basis, with the unit of MJ / kg, M t represents the total moisture, a ad represents the ash content, V ad represents the volatile matter, S t,ad represents the sulfur content.

[0112] In step S104, based on the output values of different initial coal quality regression analysis models, the corresponding coal quality analysis interval data is screened to obtain the final coal quality analysis interval data, and the final coal quality regression analysis model is determined based on the final coal quality analysis interval data.

[0113] Through the above analysis, it can be seen that the embodiment of the present application can construct the corresponding initial coal quality regression analysis model according to different coal quality analysis interval data. Therefore, in order to comprehensively evaluate the internal consistency of coal quality data, timely identify the outliers in the data, and correct these outliers to ensure the credibility and reliability of the data, the embodiment of the present application can screen the data through the output values of different initial coal quality regression analysis models.

[0114] In some embodiments, the embodiment of the present application can screen the corresponding coal quality analysis interval data through the output values of different initial coal quality regression analysis models, and then obtain the final coal quality analysis interval data, thereby determining the final coal quality regression analysis model.

[0115] Optionally, in an embodiment of the present application, screening the corresponding coal quality analysis interval data based on the output values of different initial coal quality regression analysis models to obtain the final coal quality analysis interval data includes: obtaining at least one evaluation index corresponding to different initial coal quality regression analysis models; determining the abnormal data that meets the preset abnormal conditions in the corresponding coal quality analysis interval data based on the at least one evaluation index and the output value; screening the coal quality analysis interval data based on the abnormal data to obtain the final coal quality analysis interval data.

[0116] It is understandable that the embodiment of the present application can determine the coefficient R 2 And root mean square error RMSE are used as the evaluation indicators corresponding to the initial coal quality regression analysis model.

[0117] Among them, R 2 As a measure of the proportion of the model's explained variation in the variables, the R 2 About 0.94, and after segmentation it increases to 0.96-0.97, proving that the segmentation strategy proposed in the embodiment of the present application can effectively capture local data features; further, in the embodiment of the present application, R 2 The expression can be, but is not limited to:

[0118]

[0119] Among them, y i represents the true value of the low calorific value of the i-th sample (MJ / kg), represents the low calorific value model prediction value of the i-th sample (MJ / kg), It represents the mean of the true value of the lower calorific value of all samples (MJ / kg), and n represents the total number of samples.

[0120] RMSE can reflect the average deviation between the predicted value and the true value. After the segmentation strategy is implemented in the embodiment of the present application, the RMSE is reduced from 0.46MJ / kg to 0.22-0.40MJ / kg, and the accuracy is improved by 52.1%-33.3%. Further, in the embodiment of the present application, the expression of RMSE can be but is not limited to:

[0121]

[0122] Among them, y i represents the true value of the low calorific value of the i-th sample (MJ / kg), represents the low calorific value model prediction value of the i-th sample (MJ / kg), and n represents the total number of samples

[0123] As a possible implementation method, the embodiment of the present application can be based on R 2 The coal quality analysis interval data is further optimized by using the RMSE, and then the abnormal data that meets the preset abnormal conditions are eliminated, so as to obtain the final coal quality analysis interval data. Among them, the preset abnormal conditions can be set by technicians in this field according to actual conditions, and this application does not make specific restrictions.

[0124] Furthermore, the embodiment of the present application can further optimize the coal quality analysis interval data of each interval by using M estimation robust regression, wherein the weight function expression of the Huber function can be but is not limited to:

[0125]

[0126] Among them, r i represents the standardized residual, k represents the adjustment parameter, and k = 1.345 is taken.

[0127] And the iterative reweighted least squares method is adopted, and the coefficients are stabilized through 3 - 5 iterations, so as to reduce the influence of outliers, and the influence degree can be reduced by 60% - 75%.

[0128] Optionally, in an embodiment of the present application, determining the final coal quality regression analysis model based on the final coal quality analysis interval data includes: when the received - basis volatile matter in the final coal quality analysis interval data is in the first interval, obtaining the first final coal quality regression analysis model; when the received - basis volatile matter in the final coal quality analysis interval data is in the second interval, obtaining the second final coal quality regression analysis model; when the received - basis volatile matter in the final coal quality analysis interval data is in the third interval, obtaining the third final coal quality regression analysis model; when the received - basis volatile matter in the final coal quality analysis interval data is in the fourth interval, obtaining the fourth final coal quality regression analysis model. Among them, the expression of the first final coal quality regression analysis model can be but is not limited to:

[0129] Q gr,ad = 41.106 - 0.478M t - 0.418A ad - 0.251V ad - 0.363S t,ad ,

[0130] Among them, Q gr,ad represents the air - dried basis low - calorific value, with the unit of MJ / kg, M t represents the total moisture, A ad represents the ash content, V ad represents the volatile matter, S t,ad represents the sulfur content;

[0131] The expression of the second final coal quality regression analysis model can be but is not limited to:

[0132] Q gr,ad = 39.797 - 0.465M t - 0.414A ad - 0.205V ad - 0.144S t,ad ,

[0133] Among them, Q gr,ad represents the air - dried basis low - calorific value, with the unit of MJ / kg, M t represents the total moisture, A ad represents the ash content, V adIndicates volatile matter, S t,ad Indicates sulfur content;

[0134] The expression of the third final coal quality regression analysis model can be but is not limited to:

[0135] Q gr,ad = 32.884 - 0.391M t - 0.373A ad + 0.001V ad - 0.358S t,ad ,

[0136] wherein, Q gr,ad Indicates the net calorific value at air-dried basis, unit MJ / kg, M t Indicates total moisture, A ad Indicates ash content, V ad Indicates volatile matter, S t,ad Indicates sulfur content;

[0137] The expression of the fourth final coal quality regression analysis model can be but is not limited to:

[0138] Q gr,ad = 31.816 - 0.388M t - 0.362A ad + 0.033V ad - 0.365S t,ad ,

[0139] wherein, Q gr,ad Indicates the net calorific value at air-dried basis, unit MJ / kg, M t Indicates total moisture, A ad Indicates ash content, V ad Indicates volatile matter, S t,ad Indicates sulfur content.

[0140] In some embodiments, when the received basis volatile matter is within the first interval, the present application embodiment can obtain the first final coal quality regression analysis model; wherein, the expression of the first final coal quality regression analysis model can be but is not limited to:

[0141] Q gr,ad = 41.106 - 0.478M t - 0.418A ad - 0.251V ad - 0.363S t,ad ,

[0142] wherein, Q gr,ad Indicates the net calorific value at air-dried basis, unit MJ / kg, M t Indicates total moisture, A ad Indicates ash content, Vad Indicates volatile matter, M t,ad Indicates sulfur content.

[0143] In some embodiments, the embodiments of the present application can obtain a second final coal quality regression analysis model when the received basis volatile matter is in the second interval; wherein, the expression of the second final coal quality regression analysis model can be but is not limited to:

[0144] Q gr,ad = 39.797 - 0.465M t - 0.414A ad - 0.205V ad - 0.144S t,ad ,

[0145] wherein, Q gr,ad Indicates the net calorific value at air-dried basis, unit MJ / kg, M t Indicates total moisture, A ad Indicates ash content, V ad Indicates volatile matter, S t,ad Indicates sulfur content.

[0146] In some embodiments, the embodiments of the present application can obtain a third final coal quality regression analysis model when the received basis volatile matter is in the third interval; wherein, the expression of the third final coal quality regression analysis model can be but is not limited to:

[0147] Q gr,ad = 32.884 - 0.391M t - 0.373A ad + 0.001V ad - 0.358S t,ad ,

[0148] wherein, Q gr,ad Indicates the net calorific value at air-dried basis, unit MJ / kg, M t Indicates total moisture, A ad Indicates ash content, V ad Indicates volatile matter, S t,ad Indicates sulfur content.

[0149] In some embodiments, the embodiments of the present application can obtain a fourth final coal quality regression analysis model when the received basis volatile matter is in the fourth interval. Wherein, the expression of the fourth final coal quality regression analysis model can be but is not limited to:

[0150] Q gr,ad = 31.816 - 0.388M t - 0.362A ad + 0.033V ad - 0.365S t,ad,

[0151] Among them, Q gr,ad represents the net calorific value at dry basis, with the unit of MJ / kg, M t represents the total moisture, A ad represents the ash content, V ad represents the volatile matter, S t,ad represents the sulfur content.

[0152] Exemplarily, the embodiments of the present application can be modeled respectively according to the four equal - interval of volatile matter, and the corresponding final coal quality regression analysis model is obtained. Its expression and accuracy index are shown in Table 1. Among them, Table 1 is a schematic table of the expression and accuracy index of the final coal quality regression analysis model provided according to an embodiment of the present application.

[0153] Table 1

[0154]

[0155]

[0156] In step S105, the first verification result during carbon verification is generated by using the final coal quality regression analysis model.

[0157] In some embodiments, the embodiments of the present application can use the final coal quality regression analysis model to generate the first verification result during carbon verification.

[0158] Exemplarily, the embodiments of the present application can use the final coal quality regression analysis model to test the carbon verification data of XX Power Plant for 12 months, and then obtain the corresponding first verification result. Compared with other methods, the accuracy of the average R 2 is increased by 3.4%, the error of the average RMSE is reduced by 31.1%, and the error rate of the carbon emission error is increased by 63.2%. Its schematic table is shown in Table 2. Among them, Table 2 is a comparison table of the implementation effects of other methods and the present application provided according to an embodiment of the present application.

[0159] Table 2

[0160] Method <![CDATA[Average R 2 > Average RMSE (MJ / kg) Carbon emission error Other methods 0.937 0.463 ±8.7％ This application 0.969 0.319 ±3.2％

[0161] Next, a carbon verification coal quality analysis data verification method proposed by the embodiments of the present application will be introduced in combination with a specific embodiment.

[0162] Among them, Figure 2 is a schematic diagram of the working principle of the carbon verification coal quality analysis data verification method provided according to an embodiment of the present application.

[0163] Step S201: Data collection and processing.

[0164] Among them, the embodiments of the present application can extract coal quality analysis parameters from coal samples, combine the net calorific value at air-dried basis as the dependent variable, and construct a data set. The data is preliminarily screened to eliminate obvious error values, ensuring the integrity and validity of the data, and obtaining the initial coal quality analysis data.

[0165] Further, the embodiments of the present application can segment the initial coal quality analysis data by the received basis volatile matter, divide the initial coal quality analysis data into the first interval, such as low volatile coal; the second interval, such as medium-low volatile coal; the third interval, such as medium-high volatile coal; and the fourth interval, such as high volatile coal, etc., and screen the coal quality analysis interval data, so as to obtain the corresponding final coal quality analysis interval data.

[0166] Step S202: Regression model fitting.

[0167] Among them, the embodiments of the present application can use four methods, namely linear regression, stepwise regression, ordinary least squares regression, and robust regression, to model the coal quality data respectively, obtain the influence degree of each variable on the low calorific value, and generate different initial coal quality regression analysis models.

[0168] Step S203: Model evaluation and comparison.

[0169] Among them, the embodiments of the present application can evaluate the fitting effect of each regression analysis model through indicators such as R 2 and RMSE. The robust regression model has stronger anti-interference ability against outliers in the data and can effectively reduce the influence of outliers on the results.

[0170] Step S204: Data verification and outlier processing.

[0171] Among them, the embodiments of the present application can identify abnormal data through residual analysis according to the deviation between the predicted value and the actual measured value of different initial coal quality regression analysis models. For abnormal data with a deviation exceeding the set threshold, an iterative optimization process of "outlier removal - model re-evaluation" is adopted to eliminate the interference of data noise on the model stability, and then the final coal quality regression analysis model is obtained.

[0172] Step S205: Generate a verification report.

[0173] Among them, the embodiments of the present application can use the final coal quality regression analysis model to output a detailed verification report including the regression model results, error analysis, outlier identification and processing conditions, providing scientific and reliable data support for carbon verification.

[0174] According to the coal quality analysis data verification method for carbon verification proposed in the embodiments of the present application, initial coal quality analysis data can be extracted from coal samples using coal quality analysis parameters and segmented, so as to obtain coal quality analysis interval data that meet different interval conditions. By modeling, an initial coal quality regression analysis model is obtained, the corresponding coal quality analysis interval data is screened to obtain the final coal quality analysis interval data, and the final coal quality regression analysis model is determined. Then, the first verification result during carbon verification is generated using the final coal quality regression analysis model. Through segmented modeling, the deviation caused by data heterogeneity in the global model is avoided, making the prediction result of the model more in line with the actual data distribution. By comparing the output values of different interval models, abnormal data is identified, the reliability of the verification report is improved, and then the carbon emissions of coal-fired power plants are accurately calculated, thereby optimizing the emission reduction management and optimization strategies of the power plants. Thus, the problems in the related art are solved, such as using a single regression model for processing, ignoring the influence of coal quality parameters on the low calorific value, resulting in insufficient model fitting degree and low prediction accuracy. In addition, the processing of extreme values lacks robustness, and the contribution degrees of different parameters cannot be clarified according to different volatile matter intervals, seriously affecting the reliability of the verification results.

[0175] Next, a carbon verification coal quality analysis data verification device according to an embodiment of the present application will be described with reference to the accompanying drawings.

[0176] Figure 3 It is a block diagram of a carbon verification coal quality analysis data verification device provided according to an embodiment of the present application.

[0177] As Figure 3 shown, the carbon verification coal quality analysis data verification device 30 is applied from the perspective of industrial analysis. Among them, the device 30 includes: an extraction module 301, a first generation module 302, a first construction module 303, a first determination module 304, and a second generation module 305.

[0178] Among them, the extraction module 301 is used to extract initial coal quality analysis data from coal samples using at least one coal quality analysis parameter.

[0179] The first generation module 302 is used to segment the initial coal quality analysis data based on the received basis volatile matter to obtain coal quality analysis interval data that meet different interval conditions.

[0180] The first construction module 303 is used to model the coal quality analysis interval data through regression analysis to obtain at least one initial coal quality regression analysis model.

[0181] The first determination module 304 is used to screen the corresponding coal quality analysis interval data based on the output values of different initial coal quality regression analysis models to obtain the final coal quality analysis interval data, and determine the final coal quality regression analysis model based on the final coal quality analysis interval data.

[0182] The second generation module 305 is used to generate the first verification result during carbon verification by using the final coal quality regression analysis model.

[0183] Optionally, in an embodiment of the present application, the first determination module 304 includes: a first generation unit, a second generation unit, a third generation unit, and a fourth generation unit.

[0184] Among them, the first generation unit is used to obtain the first final coal quality regression analysis model when the received basis volatile matter in the final coal quality analysis interval data is in the first interval condition.

[0185] The second generation unit is used to obtain the second final coal quality regression analysis model when the received basis volatile matter in the final coal quality analysis interval data is in the second interval condition.

[0186] The third generation unit is used to obtain the third final coal quality regression analysis model when the received basis volatile matter in the final coal quality analysis interval data is in the third interval condition.

[0187] The fourth generation unit is used to obtain the fourth final coal quality regression analysis model when the received basis volatile matter in the final coal quality analysis interval data is in the fourth interval condition.

[0188] Optionally, in an embodiment of the present application, among them,

[0189] The expression of the first final coal quality regression analysis model can be but is not limited to:

[0190] Q gr,ad = 41.106 - 0.478M t - 0.418A ad - 0.251V ad - 0.363S t,ad ,

[0191] Among them, Q gr,ad represents the air-dried basis low calorific value, unit MJ / kg, M t represents the total moisture, a ad represents the ash, V ad represents the volatile matter, S t,ad represents the sulfur content;

[0192] The expression of the second final coal quality regression analysis model can be but is not limited to:

[0193] Q gr,ad = 39.797 - 0.465M t - 0.414A ad - 0.205V ad - 0.144S t,ad ,

[0194] Among them, Q gr,ad represents the net calorific value at constant volume on an air-dried basis, with the unit of MJ / kg, M t represents the total moisture, A ad represents the ash content, V ad represents the volatile matter, S t,ad represents the sulfur content;

[0195] The expression of the third final coal quality regression analysis model can be but is not limited to:

[0196] Q gr,ad = 32.884 - 0.391M t - 0.373A ad + 0.001V ad - 0.358S t,ad ,

[0197] Among them, Q gr,ad represents the net calorific value at constant volume on an air-dried basis, with the unit of MJ / kg, M t represents the total moisture, a ad represents the ash content, V ad represents the volatile matter, S t,ad represents the sulfur content;

[0198] The expression of the fourth final coal quality regression analysis model can be but is not limited to:

[0199] Q gr,ad = 31.816 - 0.388M t - 0.362a ad + 0.033V ad - 0.365S t,ad ,

[0200] Among them, Q gr,ad represents the net calorific value at constant volume on an air-dried basis, with the unit of MJ / kg, M t represents the total moisture, A ad represents the ash content, V ad represents the volatile matter, S t,ad represents the sulfur content.

[0201] Optionally, in an embodiment of the present application, the first determination module 304 includes: a first acquisition unit, a first determination unit, and a first screening unit.

[0202] Among them, the first acquisition unit is configured to acquire at least one evaluation index corresponding to different initial coal quality regression analysis models.

[0203] The first determination unit is configured to determine, based on at least one evaluation index and the output value, the abnormal data in the corresponding coal quality analysis interval data that satisfies the preset abnormal condition.

[0204] The first screening unit is configured to screen the coal quality analysis interval data based on the abnormal data to obtain the final coal quality analysis interval data.

[0205] It should be noted that the foregoing explanation of the embodiments of the carbon verification coal quality analysis data verification method also applies to the carbon verification coal quality analysis data verification device of this embodiment, and will not be elaborated here.

[0206] According to the carbon verification coal quality analysis data verification device proposed in the embodiments of the present application, the initial coal quality analysis data can be extracted from the coal sample using the coal quality analysis parameters, segmented, and then the coal quality analysis interval data that meets different interval conditions can be obtained. An initial coal quality regression analysis model is obtained through modeling, the corresponding coal quality analysis interval data is screened to obtain the final coal quality analysis interval data, and the final coal quality regression analysis model is determined. Furthermore, the first verification result during carbon verification is generated using the final coal quality regression analysis model. Through segmented modeling, the deviation caused by data heterogeneity in the global model is avoided, making the prediction result of the model more consistent with the actual data distribution. By comparing the output values of different interval models, abnormal data is identified, the reliability of the verification report is improved, and then the carbon emissions of the coal-fired power plant are accurately calculated, thereby optimizing the emission reduction management and optimization strategy of the power plant. Thus, in the related art, using a single regression model for processing ignores the influence of coal quality parameters on the low calorific value, resulting in insufficient model fitting and low prediction accuracy. In addition, the processing of extreme values lacks robustness, and the contribution of different parameters cannot be clarified according to different volatile matter intervals, seriously affecting the reliability of the verification results and other problems are solved.

[0207] The above embodiments are described from the perspective of proximate analysis. The embodiments from the perspective of ultimate analysis will be described below.

[0208] Figure 4 It is a flowchart of a carbon verification coal quality analysis data verification method provided by another embodiment of the present application.

[0209] As Figure 4 shown, this carbon verification coal quality analysis data verification method is applied from the perspective of ultimate analysis, and the method includes the following steps:

[0210] In step S401, the initial coal quality analysis data is obtained.

[0211] As a possible implementation, in the embodiments of the present application, during carbon verification, analysis is performed from the perspective of ultimate analysis. Among them, in the embodiments of the present application, the initial coal quality analysis data can be obtained first. For example, in the embodiments of the present application, the initial coal quality analysis data of XX power plant for 12 months can be obtained.

[0212] In step S402, the air-dried basis low calorific value in the initial coal quality analysis data is determined.

[0213] It can be understood that in the embodiments of the present application, the air-dried basis lower calorific value can be understood as the ratio of the net heat released after complete combustion of a fuel containing a certain amount of moisture to the dry basis mass under atmospheric pressure, and it is a key parameter for evaluating the utilization efficiency of coal energy.

[0214] In some embodiments, the air-dried basis lower calorific value in the initial coal quality analysis data of the embodiments of the present application can be determined by the national standard GB / T213-2008.

[0215] In step S403, based on the air-dried basis lower calorific value and regression analysis, the initial coal quality analysis data is modeled to obtain at least one initial coal quality regression analysis model.

[0216] As a possible implementation manner, the embodiments of the present application can model the initial coal quality analysis data based on the air-dried basis lower calorific value through regression analysis, and then obtain at least one initial coal quality regression analysis model.

[0217] Exemplarily, the embodiments of the present application can take the initial coal quality analysis data of XX Power Plant for 12 months as an example, use the air-dried basis moisture, air-dried basis carbon, air-dried basis hydrogen, air-dried basis sulfur, etc. as independent variables, and use the air-dried basis lower calorific value as the dependent variable, and establish an initial coal quality regression analysis model through regression analysis.

[0218] In step S404, based on the output values of different initial coal quality regression analysis models, the corresponding initial coal quality analysis data is screened to obtain the final coal quality analysis data, and the final coal quality regression analysis model is determined based on the final coal quality analysis data. Among them, the expression of the final coal quality regression analysis model can be but not limited to:

[0219] Q gr,ad =-0.795 - 0.01*M t +0.348*C ad +0.786*H ad +0.096*S t,ad ,

[0220] where, Q gr,ad represents the air-dried basis lower calorific value, with the unit of MJ / kg, M t represents the air-dried basis moisture, C ad represents the air-dried basis carbon, H ad represents the air-dried basis hydrogen, S t,ad represents the air-dried basis sulfur.

[0221] In the actual implementation process, embodiments of the present application can screen corresponding initial coal quality analysis data through the output values of different initial coal quality regression analysis models, and then obtain the final coal quality analysis data, so as to determine the final coal quality regression analysis model. Among them, the expression of the final coal quality regression analysis model can be, but is not limited to:

[0222] Q gr,ad =-0.795 - 0.01*M t +0.348*C ad +0.786*H ad +0.096*S t,ad ,

[0223] wherein, Q gr,ad represents the net calorific value at air-dried basis, unit MJ / kg, M t represents the moisture at air-dried basis, C ad represents the carbon at air-dried basis, H ad represents the hydrogen at air-dried basis, S t,ad represents the sulfur at air-dried basis.

[0224] Optionally, in an embodiment of the present application, based on the output values of different initial coal quality regression analysis models, screening the corresponding initial coal quality analysis data to obtain the final coal quality analysis data includes: obtaining at least one evaluation index corresponding to different initial coal quality regression analysis models; determining the abnormal data that meets the preset abnormal conditions in the corresponding initial coal quality analysis data based on the at least one evaluation index and the output value; screening the initial coal quality analysis data based on the abnormal data to obtain the final coal quality analysis data.

[0225] In some embodiments, embodiments of the present application can use R 2 , MSE and RMSE as the evaluation indexes of different initial coal quality regression analysis models, and then determine the abnormal data that meets the preset abnormal conditions in the corresponding initial coal quality analysis data, and screen the initial coal quality analysis data, removing the abnormal data to obtain the final coal quality analysis data. Among them, the preset abnormal conditions can be set by those skilled in the art according to the actual situation, and the present application does not make specific limitations.

[0226] In addition, it should be noted that in embodiments of the present application, 82% of the traceability of abnormal data comes from coal sample collection pollution (moisture adsorption) and measurement instrument drift, and the present application does not make specific limitations.

[0227] Exemplarily, in the embodiments of the present application, through robust regression correction (using the Huber function with the adjustment parameter k = 1.345), after removing 3.2% of the abnormal data: the RMSE decreases from 0.763 to 0.652, a decrease of 14.5%; the MSE is optimized from 0.41 to 0.29, and the kurtosis coefficient increases from 2.1 to 3.8; the 95% confidence interval of the final coal quality analysis data is narrowed to ±1.28 MJ / kg (meeting the requirements of GB / T 30733-2014).

[0228] In step S405, the second verification result during carbon verification is generated using the final coal quality regression analysis model.

[0229] During the actual execution process, in the embodiments of the present application, the second verification result during carbon verification can be obtained through the final coal quality regression analysis model.

[0230] Exemplarily, in the embodiments of the present application, the second verification result during carbon verification can be obtained through the final coal quality regression analysis model, where the inversion error of the carbon content in the final coal quality regression analysis model is compressed from ±7.6% to ±3.3%, providing high-precision data support for carbon verification.

[0231] Next, a carbon verification coal quality analysis data verification method proposed in the embodiments of the present application will be introduced in combination with a specific embodiment.

[0232] Among them, Figure 5 is a flowchart of the working principle of the carbon verification coal quality analysis data verification method provided according to an embodiment of the present application.

[0233] Step S501: Obtain the initial coal quality analysis data.

[0234] Among them, in the embodiments of the present application, the initial coal quality analysis data of XX Power Plant for 12 months can be obtained.

[0235] Step S502: Construct the initial coal quality regression analysis model.

[0236] Among them, in the embodiments of the present application, the air-dried basis moisture, air-dried basis carbon, air-dried basis hydrogen, air-dried basis sulfur, etc. can be used as independent variables, and the air-dried basis net calorific value can be used as the dependent variable. Through regression analysis, the initial coal quality regression analysis model is established.

[0237] Step S503: Determine the abnormal data and screen the initial coal quality analysis data.

[0238] Among them, in the embodiments of the present application, the abnormal data can be removed through robust regression correction to obtain the final coal quality analysis data.

[0239] Step S504: Obtain the final coal quality regression analysis model.

[0240] Among them, the embodiment of the present application can determine the final coal quality regression analysis model based on the final coal quality analysis data.

[0241] Step S505: Generate a second verification result during carbon verification.

[0242] Among them, the embodiment of the present application can use the final coal quality regression analysis model to generate a second verification result during carbon verification.

[0243] According to the carbon verification coal quality analysis data verification method proposed by the embodiment of the present application, the initial coal quality analysis data can be modeled by determining the air-dried basis low calorific value in the initial coal quality analysis data, and then the initial coal quality regression analysis model can be obtained. After screening the corresponding initial coal quality analysis data, the final coal quality regression analysis model can be determined, and then the second verification result during carbon verification can be generated. Establishing a regression model using the air-dried basis low calorific value and coal quality parameters can more accurately reflect the internal relationship between coal quality characteristics and calorific value, improve the prediction accuracy, and screen data based on the output values of different initial coal quality regression analysis models to ensure that the final coal quality regression analysis model can cover the entire volatile matter range, reduce the model deviation caused by data heterogeneity, and be more flexible in adapting to changes in parameters such as volatile matter, maintaining the prediction stability. Thus, it solves the problems in the related technology that using a single regression model for processing ignores the influence of coal quality parameters on the low calorific value, resulting in insufficient model fitting degree and low prediction accuracy. In addition, the processing of extreme values lacks robustness, and the contribution degrees of different parameters cannot be determined according to different volatile matter ranges, seriously affecting the reliability of the verification results.

[0244] Next, a carbon verification coal quality analysis data verification device according to an embodiment of the present application will be described with reference to the accompanying drawings.

[0245] Figure 6 It is a block diagram of a carbon verification coal quality analysis data verification device provided according to another embodiment of the present application.

[0246] As Figure 6 shown, the carbon verification coal quality analysis data verification device 60 is applied from the perspective of elemental analysis. Among them, the device 60 includes: an acquisition module 601, a second determination module 602, a second construction module 603, a third determination module 604, and a third generation module 605.

[0247] Among them, the acquisition module 601 is used to acquire the initial coal quality analysis data.

[0248] The second determination module 602 is used to determine the air-dried basis low calorific value in the initial coal quality analysis data.

[0249] The second construction module 603 is used to model the initial coal quality analysis data based on the air-dried basis low calorific value and regression analysis to obtain at least one initial coal quality regression analysis model.

[0250] A third determination module 604, configured to screen corresponding initial coal quality analysis data based on the output values of different initial coal quality regression analysis models to obtain final coal quality analysis data, and determine a final coal quality regression analysis model based on the final coal quality analysis data.

[0251] A third generation module 605, configured to generate a second verification result during carbon verification by using the final coal quality regression analysis model.

[0252] Optionally, in an embodiment of the present application, the expression of the final coal quality regression analysis model may, but is not limited to, be:

[0253] Q gr,ad =-0.795 - 0.01*M t +0.348*C ad +0.786*H ad +0.096*S t,ad ,

[0254] wherein, Q gr,ad represents the calorific value at constant volume in air-dried basis, with the unit of MJ / kg, M t represents the moisture in air-dried basis, C ad represents the carbon in air-dried basis, H ad represents the hydrogen in air-dried basis, S t,ad represents the sulfur in air-dried basis.

[0255] Optionally, in an embodiment of the present application, the third determination module 604 includes: a second acquisition unit, a second determination unit, and a second screening unit.

[0256] The second acquisition unit is configured to acquire at least one evaluation index corresponding to different initial coal quality regression analysis models.

[0257] The second determination unit is configured to determine abnormal data that meets a preset abnormal condition in the corresponding initial coal quality analysis data based on the at least one evaluation index and the output value.

[0258] The second screening unit is configured to screen the initial coal quality analysis data based on the abnormal data to obtain final coal quality analysis data.

[0259] It should be noted that the foregoing explanation of the embodiments of the carbon verification coal quality analysis data verification method is also applicable to the carbon verification coal quality analysis data verification device in this embodiment, and will not be elaborated here.

[0260] According to the carbon verification coal quality analysis data verification device proposed in the embodiments of the present application, the initial coal quality analysis data can be modeled by determining the net calorific value at air-dried basis in the initial coal quality analysis data, and then the initial coal quality regression analysis model can be obtained. After screening the corresponding initial coal quality analysis data, the final coal quality regression analysis model can be determined, and then the second verification result during carbon verification can be generated. By establishing a regression model using the net calorific value at air-dried basis and coal quality parameters, the internal relationship between coal quality characteristics and calorific value can be more accurately reflected, and the prediction accuracy can be improved. Screening data based on the output values of different initial coal quality regression analysis models ensures that the final coal quality regression analysis model can cover the entire volatile matter range, reduces model deviation caused by data heterogeneity, and can more flexibly adapt to changes in parameters such as volatile matter, maintaining prediction stability. Thus, it solves the problems in the related art that when using a single regression model for processing, the influence of coal quality parameters on the net calorific value is ignored, resulting in insufficient model fitting degree and low prediction accuracy. In addition, the processing of extreme values lacks robustness, and the contribution degrees of different parameters cannot be clarified according to different volatile matter ranges, seriously affecting the reliability of the verification results.

[0261] Figure 7 FIG. is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device may include:

[0262] A memory 701, a processor 702, and a computer program stored on the memory 701 and executable on the processor 702.

[0263] When the processor 702 executes the program, it implements the carbon verification coal quality analysis data verification method provided in the above embodiment.

[0264] Furthermore, the electronic device further includes:

[0265] A communication interface 703 for communication between the memory 701 and the processor 702.

[0266] The memory 701 is used to store a computer program executable on the processor 702.

[0267] The memory 701 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.

[0268] If the memory 701, the processor 702, and the communication interface 703 are implemented independently, the communication interface 703, the memory 701, and the processor 702 can be interconnected through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 only a thick line is used to represent it in Figure 7 , but it does not mean that there is only one bus or one type of bus.

[0269] Optionally, in a specific implementation, if the memory 701, the processor 702, and the communication interface 703 are integrated on a single chip, the memory 701, the processor 702, and the communication interface 703 can communicate with each other through an internal interface.

[0270] The processor 702 may be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0271] The embodiments of the present application also provide a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the above carbon verification coal quality analysis data verification method is implemented.

[0272] The embodiments of the present application also provide a computer program product, including a computer program, and when the program is executed, the above carbon verification coal quality analysis data verification method is implemented.

[0273] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0274] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0275] Any process or method description shown in a flowchart or described in other ways herein may be understood to represent a module, segment, or portion of code including one or N executable instructions for implementing a customized logic function or process, and the scope of the preferred embodiments of this application includes additional implementations, where the functions may be executed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed, which should be understood by those skilled in the art to which the embodiments of this application pertain.

[0276] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definitional sequence list of executable instructions for implementing logical functions, which can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in conjunction with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection portion (electronic device) having one or N wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then stored in a computer memory.

[0277] It should be understood that various parts of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or a combination of the following techniques known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.

[0278] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the method of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0279] In addition, each functional unit in various embodiments of the present application may be integrated into one processing module, may exist independently physically for each unit, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0280] The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present application.

Claims

1. A method for verifying coal quality analysis data in carbon verification, characterized in that, Applied to the industrial analysis perspective, wherein the method comprises the following steps: Extracting initial coal quality analysis data from coal samples using at least one coal quality analysis parameter; Segmenting the initial coal quality analysis data based on the received basis volatile matter to obtain coal quality analysis interval data satisfying different interval conditions; Modeling the coal quality analysis interval data through regression analysis to obtain at least one initial coal quality regression analysis model; Based on the output values of different initial coal quality regression analysis models, screening the corresponding coal quality analysis interval data to obtain final coal quality analysis interval data, and determining a final coal quality regression analysis model based on the final coal quality analysis interval data; Generating a first verification result during carbon verification using the final coal quality regression analysis model.

2. The method according to claim 1, wherein The determining the final coal quality regression analysis model based on the final coal quality analysis interval data includes: When the received basis volatile matter in the final coal quality analysis interval data is in the first interval condition, obtaining a first final coal quality regression analysis model; When the received basis volatile matter in the final coal quality analysis interval data is in the second interval condition, obtaining a second final coal quality regression analysis model; When the received basis volatile matter in the final coal quality analysis interval data is in the third interval condition, obtaining a third final coal quality regression analysis model; When the received basis volatile matter in the final coal quality analysis interval data is in the fourth interval condition, obtaining a fourth final coal quality regression analysis model.

3. The method according to claim 2, characterized in that, Wherein, The expression of the first final coal quality regression analysis model is: Q gr,ad = 41.106 - 0.478M t - 0.418A ad - 0.251V ad - 0.363S t,ad , Among them, Q gr,ad represents the net calorific value at dry basis, unit MJ / kg, M t represents the total moisture, A ad represents the ash content, V ad represents the volatile matter, S t,ad represents the sulfur content; The expression of the second final coal quality regression analysis model is: Q gr,ad = 39.797 - 0.465M t - 0.414A ad - 0.205V ad - 0.144S t,ad , Among them, Q gr,ad represents the net calorific value at constant volume on a dry basis, with the unit of MJ / kg, M t represents the total moisture, A ad represents the ash content, V ad represents the volatile matter, S t,ad represents the sulfur content; The expression of the third final coal quality regression analysis model is: Q gr,ad = 32.884 - 0.391M t - 0.373A ad + 0.001V ad - 0.358S t,ad , Among them, Q gr,ad represents the net calorific value at dry basis, unit MJ / kg, M t represents the total moisture, A ad represents the ash content, V ad represents the volatile matter, S t,ad represents the sulfur content; The expression of the fourth final coal quality regression analysis model is: Q gr,ad = 31.816 - 0.388M t - 0.362A ad + 0.033V ad - 0.365S t,ad , Among them, Q gr,ad represents the net calorific value at dry basis, unit MJ / kg, M t represents the total moisture, A ad represents the ash content, V ad represents the volatile matter, S t,ad represents the sulfur content.

4. The method according to claim 1, wherein The screening the corresponding coal quality analysis interval data based on the output values of different initial coal quality regression analysis models to obtain final coal quality analysis interval data includes: Obtaining at least one evaluation index corresponding to the different initial coal quality regression analysis models; Based on the at least one evaluation index and the output values, determining abnormal data in the corresponding coal quality analysis interval data that satisfy a preset abnormal condition; Based on the abnormal data, screening the coal quality analysis interval data to obtain the final coal quality analysis interval data.

5. A carbon verification method for verifying coal quality analysis data, characterized in that, Applied to the elemental analysis perspective, wherein the method comprises the following steps: Obtaining initial coal quality analysis data; Determining the air-dried basis net calorific value in the initial coal quality analysis data; Modeling the initial coal quality analysis data based on the air-dried basis net calorific value and regression analysis to obtain at least one initial coal quality regression analysis model; Based on the output values of different initial coal quality regression analysis models, screening the corresponding initial coal quality analysis data to obtain final coal quality analysis data, and determining a final coal quality regression analysis model based on the final coal quality analysis data; Generating a second verification result during carbon verification using the final coal quality regression analysis model.

6. The method according to claim 5, characterized in that, The expression of the final coal quality regression analysis model is: Q gr,ad = -0.795 - 0.01 * M t + 0.348 * C ad + 0.786 * H ad + 0.096 * S t,ad , Among them, Q gr,ad represents the net calorific value at constant volume on an air-dried basis, with the unit of MJ / kg, M t represents the moisture content on an air-dried basis, C ad represents the carbon content on an air-dried basis, H ad represents the hydrogen content on an air-dried basis, S t,ad represents the sulfur content on an air-dried basis.

7. The method according to claim 5, wherein The screening the corresponding initial coal quality analysis data based on the output values of different initial coal quality regression analysis models to obtain final coal quality analysis data includes: Obtain at least one evaluation index corresponding to the different initial coal quality regression analysis models; Based on the at least one evaluation index and the output value, determine the abnormal data in the corresponding initial coal quality analysis data that satisfies the preset abnormal conditions; Based on the abnormal data, screen the initial coal quality analysis data to obtain the final coal quality analysis data.

8. An electronic device, characterized in that, Comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the carbon verification coal quality analysis data verification method according to any one of claims 1-4 or the carbon verification coal quality analysis data verification method according to any one of claims 5-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to be used to implement the carbon verification coal quality analysis data verification method according to any one of claims 1-4 or the carbon verification coal quality analysis data verification method according to any one of claims 5-7.

10. A computer program product, characterized in that, Comprising a computer program, which when executed is used to implement the carbon verification coal quality analysis data verification method according to any one of claims 1-4 or the carbon verification coal quality analysis data verification method according to any one of claims 5-7.

Images