Carbon verification data governance method and system based on big data platform

Abstract

The present application relates to the field of carbon verification data governance, in particular to a carbon verification data governance method and system based on a big data platform. The method first analyzes the fluctuation of temperature data of different areas of the reaction furnace in the abnormal production cycle of enterprise carbon emission, and the difference between the carbon dioxide concentration and the carbon monoxide concentration at each moment at the outlet of the reaction furnace, to obtain the carbon emission abnormality degree of the abnormal production cycle. According to the carbon emission amount and the carbon emission abnormality degree of the abnormal production cycle, and the time series data sequence of various process parameters, a reference historical production cycle is selected from the historical production cycles in the database, and based on the governance scheme of the reference historical production cycle, the carbon emission of the abnormal production cycle is governed. The present application can accurately evaluate the similarity of carbon emission between production cycles, match the abnormal production cycle to a suitable governance scheme, and improve the effect of carbon emission governance of the abnormal production cycle.

Description

Technical Field

[0001] This invention relates to the field of carbon verification data governance, specifically to a carbon verification data governance method and system based on a big data platform. Background Technology

[0002] Carbon verification data is accurate data on greenhouse gas emissions and related information of enterprises or organizations, determined through professional verification procedures. Carbon verification data is the basis for carbon emission quota allocation and trading, supporting compliance requirements in the carbon market. Carbon verification data mainly includes the total amount of greenhouse gases directly and indirectly emitted by an enterprise or organization within a certain period of time, as well as emission source data, activity data, and emission coefficients. Based on carbon verification data, it is possible to effectively control and manage carbon emissions of enterprises or organizations in their production activities.

[0003] Because the carbon emission anomalies that occur in different production cycles vary among enterprises or organizations, related technologies typically use governance schemes from historical production cycles with similar carbon emission anomalies to the current abnormal production cycle to address the current abnormal production cycle. However, since carbon emissions throughout the entire production cycle are affected by a variety of factors, existing methods cannot accurately assess the similarity of carbon emissions between production cycles, leading to mismatches in governance schemes and reducing the effectiveness of carbon emission control for abnormal production cycles. Summary of the Invention

[0004] To address the technical problem that existing methods cannot accurately assess the similarity of carbon emissions between production cycles, leading to mismatched remediation plans and reduced effectiveness of carbon emission control for abnormal production cycles, this invention aims to provide a carbon verification data governance method and system based on a big data platform. The specific technical solution adopted is as follows:

[0005] This invention proposes a carbon verification data governance method based on a big data platform, the method comprising:

[0006] The system acquires temperature data of different areas of the reactor at each moment during abnormal production cycles of enterprise carbon emissions, as well as carbon dioxide and carbon monoxide concentrations at the reactor outlet at each moment. It also acquires time-series data sequences of different process parameters during abnormal production cycles.

[0007] The temperature fluctuation of the abnormal production cycle is obtained based on the temperature fluctuation differences between different areas of the reactor during the abnormal production cycle, the temperature differences between different areas at the same time, and the temperature changes at the same time. The incomplete combustion period of the abnormal production cycle is obtained based on the differences in carbon dioxide and carbon monoxide concentrations at the reactor outlet at each moment during the abnormal production cycle. The carbon emission anomaly of the abnormal production cycle is obtained based on the temperature fluctuation and the length of the incomplete combustion period.

[0008] Based on the carbon emissions and the degree of carbon emission anomaly in the abnormal production cycle, as well as the time series data sequence of different process parameters in the abnormal production cycle, reference historical production cycles are selected from the historical production cycles in the database.

[0009] Based on governance plans that reference historical production cycles, carbon emissions from abnormal production cycles are addressed.

[0010] Furthermore, obtaining the temperature fluctuation of the abnormal production cycle includes:

[0011] Based on the temperature fluctuations of each region of the reactor at all times, the temperature fluctuation coefficient of each region of the reactor is obtained.

[0012] The dispersion of the temperature fluctuation coefficients in all areas of the reactor during abnormal production cycles is analyzed to obtain the temperature fluctuation difference degree during abnormal production cycles.

[0013] By analyzing the dispersion of temperature data in all regions at the same time, the temperature difference at each moment of the abnormal production cycle can be obtained.

[0014] The difference in temperature data between each region at each time point and the next adjacent time point is taken as the temperature change of each region at each time point. The dispersion of the temperature change of all regions at the same time point is analyzed to obtain the temperature change difference at each time point of the abnormal production cycle.

[0015] The temperature fluctuation of the abnormal production cycle is obtained based on the temperature fluctuation difference of the abnormal production cycle, the temperature difference of all moments in the abnormal production cycle, and the temperature change difference.

[0016] Furthermore, the temperature fluctuation coefficient for each region of the reactor is obtained as follows:

[0017] Take any region of the reactor as the target region, extract the extreme values ​​from the temperature data of all times in the target region, and take any two adjacent extreme values ​​as an extreme value group. Take the absolute value of the difference between the two extreme values ​​in each extreme value group as the numerator, take the absolute value of the difference between the times corresponding to the two extreme values ​​in each extreme value group as the denominator, and take the ratio as the data change rate of each extreme value group.

[0018] The average rate of change of the data from all extreme value groups is used as the first temperature fluctuation assessment value for the target area.

[0019] The dispersion of temperature data at all times in the target area is analyzed to obtain a second temperature fluctuation assessment value for the target area.

[0020] The temperature fluctuation coefficient of the target area is obtained by combining the number of extreme values ​​in the temperature data of the target area with the first temperature fluctuation assessment value and the second temperature fluctuation assessment value of the target area.

[0021] Further, obtaining the temperature fluctuation degree of the abnormal production cycle based on the temperature fluctuation difference degree of the abnormal production cycle, the temperature difference degree at all times of the abnormal production cycle, and the temperature change difference degree includes:

[0022] The average of the temperature differences at all times during the abnormal production cycle is taken as the overall temperature difference of the abnormal production cycle.

[0023] The average of the temperature variation differences at all times during the abnormal production cycle is taken as the overall temperature variation difference of the abnormal production cycle.

[0024] The temperature fluctuation degree of the abnormal production cycle is obtained by combining the temperature fluctuation difference degree of the abnormal production cycle, the overall temperature difference degree, and the overall temperature change difference degree.

[0025] Furthermore, the period of incomplete combustion during the abnormal production cycle includes:

[0026] The carbon monoxide concentration at the reactor outlet at each moment is used as the numerator, the carbon dioxide concentration at the reactor outlet at each moment is used as the denominator, and the ratio is used as the combustion evaluation value at the reactor outlet at each moment.

[0027] The moment when the combustion assessment value is greater than the preset combustion threshold is taken as the moment of incomplete combustion in the abnormal production cycle, and the time period consisting of consecutive moments of incomplete combustion is taken as the period of incomplete combustion in the abnormal production cycle.

[0028] Furthermore, the degree of carbon emission anomaly in obtaining abnormal production cycles includes:

[0029] The sum of the lengths of all the incomplete combustion periods is used as the numerator, the length of the abnormal production cycle is used as the denominator, and the ratio is used as the proportion of incomplete combustion time in the abnormal production cycle.

[0030] The carbon emission anomaly degree of the abnormal production cycle is obtained by combining the maximum length of all incomplete combustion periods in the abnormal production cycle, the proportion of incomplete combustion duration in the abnormal production cycle, and the temperature fluctuation.

[0031] Furthermore, the step of filtering reference historical production cycles from the historical production cycles in the database includes:

[0032] The two-dimensional sequence consisting of the carbon emissions of the abnormal production cycle and the degree of carbon emission anomaly is used as the characteristic sequence of the abnormal production cycle.

[0033] Abnormal production cycles and historical production cycles in the database are used as production cycles to be clustered. The Euclidean distance between the feature sequences of any two production cycles to be clustered is used as the distance metric between any two production cycles to be clustered. Based on the distance metric, each production cycle to be clustered is clustered to obtain a cluster.

[0034] The historical production cycles in the cluster where the abnormal production cycle is located are taken as the historical production cycles to be screened. Based on the dynamic time warping algorithm, the time series data sequences with the same process parameters between the abnormal production cycle and each historical production cycle to be screened are processed to obtain the parameter similarity between the abnormal production cycle and each historical production cycle to be screened.

[0035] Negative correlation mapping is performed on the distance metric between the abnormal production cycle and each historical production cycle to be screened to obtain the feature similarity between the abnormal production cycle and each historical production cycle to be screened.

[0036] The parameter similarity and feature similarity are combined to obtain the comprehensive similarity between the abnormal production cycle and each historical production cycle to be screened;

[0037] The maximum number of historical production cycles corresponding to the comprehensive similarity scores are selected as reference historical production cycles.

[0038] Furthermore, the parameter similarity between the obtained abnormal production cycle and each historical production cycle to be screened includes:

[0039] Based on the dynamic time warping algorithm, the time series data sequences with the same process parameters between the abnormal production cycle and each historical production cycle to be screened are processed to obtain the data similarity between the abnormal production cycle and each historical production cycle to be screened for each process parameter.

[0040] The average of the data similarity for all process parameters between the abnormal production cycle and each historical production cycle to be screened is taken as the parameter similarity between the abnormal production cycle and each historical production cycle to be screened.

[0041] Furthermore, the control of carbon emissions from abnormal production cycles includes:

[0042] Carbon emissions from abnormal production cycles are addressed using a governance scheme that references historical production cycles.

[0043] The present invention also proposes a carbon verification data governance system based on a big data platform. The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any of the steps of a carbon verification data governance method based on a big data platform.

[0044] The present invention has the following beneficial effects:

[0045] This invention addresses the limitation of existing methods in accurately assessing the similarity of carbon emissions between production cycles, which can lead to mismatched remediation plans and reduced effectiveness in controlling carbon emissions during abnormal production cycles. Therefore, it first acquires temperature data for different regions of the reactor at each moment during the abnormal production cycle, as well as the carbon dioxide and carbon monoxide concentrations at the reactor outlet at each moment. Simultaneously, it acquires time-series data of different process parameters during the abnormal production cycle. Considering that more pronounced temperature fluctuations in different regions of the reactor during abnormal production cycles indicate a greater degree of carbon emission anomaly, the acquired temperature fluctuations can reflect the extent of temperature fluctuations in the reactor during abnormal production cycles. Subsequently, the degree of carbon emission anomaly in abnormal production cycles can be accurately calculated and analyzed based on temperature fluctuations. Considering that when the combustion efficiency of the reactor is low and incomplete combustion occurs, it indicates a greater degree of carbon emission anomaly in the abnormal production cycle. Therefore, the length of the incomplete combustion period is further combined to obtain the degree of carbon emission anomaly in the abnormal production cycle. Then, based on the carbon emission amount and degree of carbon emission anomaly in the abnormal production cycle, as well as the time series data sequence of various process parameters in the abnormal production cycle, the similarity of carbon emission between the abnormal production cycle and historical production cycles in the database is analyzed. This allows for the accurate selection of reference historical production cycles, thereby matching appropriate treatment solutions for the abnormal production cycle and improving the effectiveness of carbon emission control in the abnormal production cycle. Attached Figure Description

[0046] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is a flowchart of a carbon verification data governance method based on a big data platform, provided as an embodiment of the present invention. Detailed Implementation

[0048] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a carbon verification data governance method and system based on a big data platform proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0050] The following description, in conjunction with the accompanying drawings, details a specific scheme for a carbon verification data governance method and system based on a big data platform provided by this invention.

[0051] Please see Figure 1 The diagram illustrates a flowchart of a carbon verification data governance method based on a big data platform, according to an embodiment of the present invention. The method includes:

[0052] Step S1: Obtain temperature data of different areas of the reactor at each moment during the abnormal production cycle of the enterprise's carbon emissions, as well as carbon dioxide and carbon monoxide concentrations at the reactor outlet at each moment. At the same time, obtain time-series data sequences of different process parameters during the abnormal production cycle.

[0053] This invention takes the carbon emission scenario of an industrial steelmaking process as an example. In the industrial steelmaking process, coal or coke is used to heat the reactor to a high temperature, reduce the iron ore in the reactor, and melt the iron ore into molten iron. When an abnormality occurs in a certain link of the industrial steelmaking production cycle, the company's carbon emissions will also be abnormal. Here, one production cycle of industrial steelmaking refers to one production process of industrial steelmaking from start to finish. Therefore, this invention first obtains the raw material input and actual carbon emissions of the current production cycle from the company's production report, and obtains the standard carbon emissions corresponding to the raw material input through relevant specifications. If the actual carbon emissions of the current production cycle are greater than the standard carbon emissions, the current production cycle is considered to be an abnormal production cycle.

[0054] For abnormal production cycles, this embodiment of the invention first installs temperature sensors in different areas of the reactor to collect temperature data of different areas of the reactor at each moment. Then, a gas concentration sensor is installed at the reactor outlet to collect the carbon dioxide and carbon monoxide concentrations at the reactor outlet at each moment. In addition to temperature and gas concentration, industrial steelmaking involves a variety of process parameters, such as the pressure inside the reactor, the fan speed, and the temperature of molten iron. Therefore, this embodiment of the invention also requires the use of relevant detection devices or equipment to collect the time-series data sequence of each process parameter in the abnormal production cycle. The time-series data sequence of the process parameter refers to the sequence obtained by arranging the data of a certain process parameter at different moments in chronological order.

[0055] Step S2: Based on the temperature fluctuation differences between different areas of the reactor during the abnormal production cycle, the differences in temperature data at the same time between different areas, and the differences in temperature data changes at the same time, obtain the temperature fluctuation degree of the abnormal production cycle; based on the differences in carbon dioxide concentration and carbon monoxide concentration at the reactor outlet at each moment during the abnormal production cycle, obtain the period of incomplete combustion in the abnormal production cycle; based on the temperature fluctuation degree and the length of the period of incomplete combustion in the abnormal production cycle, obtain the carbon emission anomaly degree of the abnormal production cycle.

[0056] Generally, enterprises have standardized production processes. Under established production technologies and processes, a certain amount of raw material input usually corresponds to relatively stable energy consumption and production processes. Therefore, carbon emissions also show certain regularity and relative stability. Because the energy use and chemical reaction processes involved in the processing and conversion of raw materials are relatively fixed, carbon emissions are also relatively stable. In the industrial steelmaking process, the temperature in the reactor is the most critical parameter. Therefore, when carbon emissions are abnormal during an abnormal production cycle, the temperature fluctuation in the reactor will be more obvious. Thus, the temperature fluctuation of the abnormal production cycle can be obtained by measuring the temperature fluctuation differences between different areas of the reactor during the abnormal production cycle, the differences in temperature data between different areas at the same time, and the differences in temperature data changes at the same time. The temperature fluctuation reflects the degree of temperature fluctuation in the reactor during the abnormal production cycle. Subsequently, the degree of abnormality in carbon emissions during the abnormal production cycle can be accurately calculated and analyzed based on the temperature fluctuation.

[0057] Preferably, in one embodiment of the present invention, the method for obtaining the temperature fluctuation of abnormal production cycles specifically includes:

[0058] First, the temperature data of each region is analyzed over time. Based on the temperature data fluctuation of each region of the reactor at all times, the temperature fluctuation coefficient of each region of the reactor is obtained. The larger the temperature fluctuation coefficient, the greater the degree of temperature fluctuation in each region.

[0059] Preferably, in one embodiment of the present invention, the method for obtaining the temperature fluctuation coefficient of each region of the reactor specifically includes:

[0060] Taking any region of the reactor as the target region, extreme values ​​are extracted from the temperature data of all times in the target region. These extreme values ​​include maximum and minimum values. Any two adjacent extreme values ​​are taken as an extreme value group. The absolute value of the difference between the two extreme values ​​in each extreme value group is used as the numerator, and the absolute value of the difference between the times corresponding to the two extreme values ​​in each extreme value group is used as the denominator. The ratio is used as the data change rate of each extreme value group. The larger the data change rate, the more obvious the change between the two adjacent extreme values ​​in the target region. The average value of the data change rates of all extreme value groups can be used as the first temperature fluctuation assessment value of the target region. The larger the first temperature fluctuation assessment value, the greater the temperature data fluctuation in the target region.

[0061] In embodiments of the present invention, extreme values ​​can be selected by curve fitting or local comparison, which is not limited here. The process of selecting extreme values ​​by curve fitting is as follows: First, curve fitting methods such as least squares are used to fit the temperature data of the target area at each time moment, and the temperature data corresponding to the point with a slope of 0 on the fitted curve is taken as the extreme value. The process of selecting extreme values ​​by local comparison is as follows: The temperature data of the target area at each time moment is compared with the temperature data of other times moment in the preset window. If the temperature data of the current time moment is greater than or less than the temperature data of other times moment in the preset window, then the temperature data of the current time moment is taken as the extreme value. The length of the preset window can be set to 5, that is, the preset window includes the 4 other times moment closest to the current time moment and the current time moment itself. The length of the preset window can also be set by the implementer according to the specific implementation scenario, which is not limited here.

[0062] The dispersion of temperature data at all times in the target area is analyzed to obtain a second temperature fluctuation assessment value for the target area. The larger the second temperature fluctuation assessment value, the more inconsistent the temperature data at all times in the target area, and the greater the temperature fluctuation of the target area.

[0063] In embodiments of the present invention, the variance, standard deviation, or range of temperature data at all times in the target area can be used as a second temperature fluctuation assessment value for the target area to analyze the dispersion of temperature data at all times in the target area. This is not limited here.

[0064] The more extreme values ​​there are in the temperature data of the target area, and the larger the first and second temperature fluctuation assessment values ​​of the target area, the more obvious the temperature fluctuation of the target area is. Therefore, the temperature fluctuation coefficient of the target area can be obtained by combining the number of extreme values ​​in the temperature data of the target area with the first and second temperature fluctuation assessment values ​​of the target area.

[0065] In embodiments of the present invention, the number of extreme values ​​in all temperature data of the target area and the sum or product of the first temperature fluctuation assessment value and the second temperature fluctuation assessment value of the target area can be used as the temperature fluctuation coefficient of the target area to achieve a comprehensive consideration of the three, which is not limited here.

[0066] As an example, in one embodiment of the present invention, the expression for the temperature fluctuation coefficient of the target region can be specifically as follows:

[0067]

[0068] Where A represents the temperature fluctuation coefficient of the target area; B represents the number of extreme values ​​in the temperature data of the target area; σ represents the average rate of change of the data for all extreme value groups, i.e., the first temperature fluctuation assessment value for the target area; σ represents the variance of the temperature data for all moments in the target area, i.e., the second temperature fluctuation assessment value for the target area.

[0069] Then, the temperature fluctuation coefficient of each region can be obtained by using the same method as above. This allows for the analysis of the dispersion of the temperature fluctuation coefficients of all regions of the reactor during abnormal production cycles, thus obtaining the temperature fluctuation difference during abnormal production cycles. The greater the temperature fluctuation difference, the greater the difference in temperature fluctuation between different regions of the reactor.

[0070] The dispersion of temperature data in all regions at the same time is analyzed to obtain the temperature difference at each moment of the abnormal production cycle. The greater the temperature difference, the greater the temperature difference in different regions of the reactor at the same time in the abnormal production cycle, and thus the greater the temperature fluctuation at each moment of the abnormal production cycle.

[0071] The difference in temperature data between each region at each time point and the next adjacent time point is taken as the temperature change of each region at each time point. The dispersion of the temperature change of all regions at the same time point is analyzed to obtain the temperature change difference at each time point of the abnormal production cycle. The greater the temperature change difference, the greater the difference in temperature change of different regions in the reactor at the same time point in the abnormal production cycle, and thus the greater the temperature fluctuation at each time point of the abnormal production cycle.

[0072] It should be noted that there is no adjacent next moment after the last moment of each region. Therefore, the average of the temperature changes of all moments before the last moment of each region can be used as the temperature change of each region at the last moment.

[0073] It should be noted that, in the embodiments of the present invention, when analyzing the dispersion of various data, the analysis of the dispersion of the corresponding data can be achieved by calculating statistical measures such as variance, standard deviation or range of the corresponding data, and no limitation is made here.

[0074] Furthermore, the temperature fluctuation of an abnormal production cycle can be obtained based on the temperature fluctuation difference of the abnormal production cycle, the temperature difference at all times of the abnormal production cycle, and the temperature change difference.

[0075] Preferably, in one embodiment of the present invention, the method for obtaining the temperature fluctuation of abnormal production cycles further includes:

[0076] The average temperature difference at all times during the abnormal production cycle is taken as the overall temperature difference of the abnormal production cycle. The greater the overall temperature difference, the greater the temperature fluctuation of the abnormal production cycle.

[0077] The average temperature variation at all times during the abnormal production cycle is taken as the overall temperature variation variation of the abnormal production cycle. The greater the overall temperature variation variation, the greater the temperature fluctuation of the abnormal production cycle.

[0078] Then, the temperature fluctuation difference of the abnormal production cycle, the overall temperature difference, and the overall temperature change difference are combined to obtain the temperature fluctuation of the abnormal production cycle.

[0079] In embodiments of the present invention, the sum or product of the temperature fluctuation difference of the abnormal production cycle, the overall temperature difference, and the overall temperature change difference can be used as the temperature fluctuation of the abnormal production cycle to achieve a comprehensive consideration of the three factors, without limitation.

[0080] As an example, in one embodiment of the present invention, the expression for the temperature fluctuation of abnormal production cycles can be specifically as follows:

[0081]

[0082] Where W represents the temperature fluctuation degree of the abnormal production cycle; σ1 represents the variance of the temperature fluctuation coefficient of all areas of the reactor, i.e., the temperature fluctuation difference degree of the abnormal production cycle; σ (r,2) This represents the variance of temperature data for all regions of the reactor at time r, i.e., the temperature difference at time r during an abnormal production cycle. Indicates the overall temperature variation during abnormal production cycles; σ (r,3) This represents the variance of the temperature change in all areas of the reactor at time r, i.e., the temperature change difference at time r of the abnormal production cycle. R represents the overall temperature variation variation during the abnormal production cycle; R represents the number of moments in the abnormal production cycle.

[0083] Besides the temperature in the reactor reflecting the degree of carbon emission abnormality in an abnormal production cycle, the relative difference between carbon monoxide and carbon dioxide concentrations at the reactor outlet can also reflect the degree of carbon emission abnormality in an abnormal production cycle. In industrial steelmaking, when combustion is incomplete, fuel is not completely converted into carbon dioxide, but rather produces more carbon monoxide, hydrocarbons, and other incompletely burned substances. The higher the concentration of carbon monoxide relative to the concentration of carbon dioxide, the greater the degree of carbon emission abnormality in the abnormal production cycle. Therefore, the period of incomplete combustion in the abnormal production cycle can be obtained by first determining the difference between the carbon dioxide and carbon monoxide concentrations at the reactor outlet at each moment during the abnormal production cycle. Subsequently, based on the length of the incomplete combustion period and combined with the temperature fluctuation of the abnormal production cycle obtained above, the degree of carbon emission abnormality in the abnormal production cycle can be accurately analyzed.

[0084] Preferably, in one embodiment of the present invention, the method for obtaining the incomplete combustion period of an abnormal production cycle specifically includes:

[0085] The carbon monoxide concentration at the reactor outlet at each moment is used as the numerator, and the carbon dioxide concentration at the reactor outlet at each moment is used as the denominator. The ratio is used as the combustion assessment value at the reactor outlet at each moment. The larger the combustion assessment value at a certain moment, the greater the possibility that the moment is incomplete combustion. Therefore, the moment when the combustion assessment value is greater than the preset combustion threshold can be used as the moment of incomplete combustion in the abnormal production cycle, and the time period consisting of consecutive moments of incomplete combustion can be used as the period of incomplete combustion in the abnormal production cycle. The preset combustion threshold ranges from [0.01, 0.02]. In one embodiment of the present invention, the preset combustion threshold is set to 0.01. The specific value of the preset combustion threshold can also be set by the implementer according to the specific implementation scenario, and is not limited here.

[0086] The greater the temperature fluctuation in an abnormal production cycle, and the greater the proportion of incomplete combustion periods in that cycle, the greater the degree of carbon emission abnormality. Therefore, the degree of carbon emission abnormality in an abnormal production cycle can be obtained based on the temperature fluctuation and the length of incomplete combustion periods, providing a data basis for subsequent matching analysis of remediation solutions.

[0087] Preferably, in one embodiment of the present invention, the method for obtaining the carbon emission anomaly degree of abnormal production cycles specifically includes:

[0088] The sum of the lengths of all incomplete combustion periods is used as the numerator, and the length of the abnormal production cycle is used as the denominator. The ratio is taken as the proportion of incomplete combustion time in the abnormal production cycle. The larger the proportion of incomplete combustion time, the longer the incomplete combustion time in the abnormal production cycle, and thus the greater the degree of abnormality in carbon emissions in the abnormal production cycle. The length of the incomplete combustion period or the abnormal production cycle can be determined by the difference between the corresponding termination time and the initial time, or the number of moments included in the incomplete combustion period or the abnormal production cycle can be used as the length of the incomplete combustion period or the abnormal production cycle. There is no limitation here.

[0089] Furthermore, the maximum length of all incomplete combustion periods in the abnormal production cycle, the proportion of incomplete combustion duration in the abnormal production cycle, and the temperature fluctuation can be combined to obtain the carbon emission anomaly degree of the abnormal production cycle.

[0090] In embodiments of the present invention, the maximum value of the length of all incomplete combustion periods in the abnormal production cycle, the sum or product of the proportion of incomplete combustion duration and temperature fluctuation in the abnormal production cycle can be used as the carbon emission anomaly degree of the abnormal production cycle to achieve a comprehensive consideration of the three factors, without limitation.

[0091] As an example, in one embodiment of the present invention, the expression for the carbon emission anomaly degree of an abnormal production cycle can be specifically as follows:

[0092]

[0093] Where C represents the degree of carbon emission anomaly in the abnormal production cycle; l represents the cumulative value of the lengths of all periods of incomplete combustion; and L represents the length of the abnormal production cycle. This indicates the percentage of incomplete combustion time during abnormal production cycles; max W represents the maximum length of all incomplete combustion periods in the abnormal production cycle; W represents the temperature fluctuation of the abnormal production cycle.

[0094] Thus, the carbon emission anomaly level of the abnormal production cycle was obtained.

[0095] Step S3: Based on the carbon emissions and carbon emission anomaly of the abnormal production cycle, as well as the time series data sequence of different process parameters in the abnormal production cycle, select reference historical production cycles from the historical production cycles in the database.

[0096] Since the historical production cycles in the database refer to past abnormal production cycles analyzed using the same method and added to the database for future analysis of abnormal production cycles, the remediation plan for each historical production cycle in the database is known. Furthermore, the carbon emissions, carbon emission anomaly levels, and time-series data sequences of various process parameters for each historical production cycle in the database are also known. Therefore, based on the carbon emissions and carbon emission anomaly levels of abnormal production cycles, combined with the time-series data sequences of various process parameters within the abnormal production cycles, the similarity of carbon emissions between abnormal production cycles and historical production cycles in the database can be analyzed. This allows for the accurate selection of reference historical production cycles from the database, enabling the subsequent accurate matching of remediation plans for abnormal carbon emissions, thereby improving the effectiveness of carbon emission remediation for abnormal production cycles.

[0097] Preferably, in one embodiment of the present invention, the method for obtaining the historical production cycle specifically includes:

[0098] First, the two-dimensional sequence consisting of carbon emissions and carbon emission anomaly degree of abnormal production cycles is used as the feature sequence of abnormal production cycles, thereby realizing the quantitative processing of carbon emissions and anomalies in abnormal production cycles. For example, if the carbon emissions and carbon emission anomaly degree of abnormal production cycles are 5 and 10 respectively, then the corresponding feature sequence is (5,10).

[0099] Abnormal production cycles and historical production cycles in the database are used as production cycles to be clustered. The Euclidean distance between the feature sequences of any two production cycles to be clustered is used as the distance metric between them. Based on the distance metric, each production cycle to be clustered is clustered to obtain clusters. In one embodiment of the present invention, the K-means clustering algorithm can be used, and the number of clusters can be determined using the existing elbow method. In other embodiments of the present invention, other clustering algorithms can also be used to implement the clustering operation, which is not limited here.

[0100] Since the carbon emissions and anomalies of production cycles within the same cluster are similar, historical production cycles in the cluster containing the abnormal production cycle can be used as historical production cycles to be screened. Furthermore, since carbon emission anomalies in production cycles are caused by multiple factors, to improve the accuracy of the similarity analysis between abnormal and historical production cycles, further analysis can be performed using time-series data sequences of various process parameters. Therefore, this embodiment of the invention uses a dynamic time warping algorithm to process the time-series data sequences of the same process parameters between the abnormal production cycle and each historical production cycle to be screened, obtaining the parameter similarity between the abnormal production cycle and each historical production cycle to be screened. The greater the parameter similarity, the more similar the time-series data of the same process parameters between the abnormal production cycle and each historical production cycle to be screened, thus indicating a greater similarity in carbon emissions between the abnormal production cycle and each historical production cycle to be screened. The dynamic time warping algorithm, which can evaluate the similarity between time-series sequences, is a well-known technique and will not be elaborated upon here.

[0101] Preferably, in one embodiment of the present invention, the method for obtaining the parameter similarity between abnormal production cycles and each historical production cycle to be screened specifically includes:

[0102] Based on the dynamic time warping algorithm, the time series data sequences of the same process parameters between the abnormal production cycle and each historical production cycle to be screened are processed to obtain the data similarity of each process parameter between the abnormal production cycle and each historical production cycle to be screened. Then, the average value of the data similarity of all process parameters between the abnormal production cycle and each historical production cycle to be screened is used as the parameter similarity between the abnormal production cycle and each historical production cycle to be screened.

[0103] It should be noted that since the output of the dynamic time warping algorithm actually reflects the distance between two time series, in order to achieve similarity calculation, it is also necessary to perform negative correlation mapping on the output of the dynamic time warping algorithm to obtain the data similarity between the abnormal production cycle and each historical production cycle to be screened regarding each process parameter.

[0104] As an example, in one embodiment of the present invention, the expression for the parameter similarity between abnormal production cycles and each historical production cycle to be screened can be specifically as follows:

[0105]

[0106] Among them, S n DTW represents the parameter similarity between an abnormal production cycle and the nth historical production cycle to be screened. (n,m)The output result is the time series data sequence of the abnormal production cycle and the m-th process parameter of the nth historical production cycle to be screened, after being processed by the dynamic time warping algorithm; The value represents the data similarity between the abnormal production cycle and the nth historical production cycle to be screened regarding the mth process parameter; M represents the number of process parameters; ε1 represents the preset first adjustment coefficient, used to prevent the denominator from being 0. The value range of ε1 is [0.001, 0.01]. In one embodiment of the present invention, ε1 is set to 0.01. The specific value of ε1 can also be set by the implementer according to the specific implementation scenario, and is not limited here.

[0107] It should be noted that negative correlation mapping can also be achieved through other basic mathematical operations in other embodiments of the present invention, which will not be elaborated here.

[0108] Then, a negative correlation mapping is performed on the distance metric between the abnormal production cycle and each historical production cycle to be screened to obtain the feature similarity between the abnormal production cycle and each historical production cycle to be screened. The greater the feature similarity, the more similar the carbon emission situation and the abnormal situation are between the abnormal production cycle and each historical production cycle to be screened. Then, the parameter similarity and feature similarity can be combined to obtain the comprehensive similarity between the abnormal production cycle and each historical production cycle to be screened.

[0109] In embodiments of the present invention, the sum or product of parameter similarity and feature similarity can be used as the comprehensive similarity between the abnormal production cycle and each historical production cycle to be screened, thereby achieving a comprehensive assessment of the two, without limitation.

[0110] As an example, in one embodiment of the present invention, the expression for the comprehensive similarity between abnormal production cycles and each historical production cycle to be screened can be specifically as follows:

[0111]

[0112] Among them, U n S represents the overall similarity between the abnormal production cycle and the nth historical production cycle to be screened; n D represents the parameter similarity between the abnormal production cycle and the nth historical production cycle to be screened; n This represents the distance metric between the abnormal production cycle and the nth historical production cycle to be screened. ε1 represents the feature similarity between the abnormal production cycle and the nth historical production cycle to be screened; ε2 represents the preset second adjustment coefficient, which is used to prevent the denominator from being 0. The value range of ε2 is [0.001, 0.01]. In one embodiment of the present invention, ε2 is set to 0.01. The specific value of ε2 can also be set by the implementer according to the specific implementation scenario, and is not limited here.

[0113] The greater the overall similarity, the more similar the carbon emissions are between the abnormal production cycle and each historical production cycle. In order to improve the accuracy of matching the governance plan for the abnormal production cycle, a preset number of historical production cycles with the largest overall similarity can be used as reference historical production cycles. In one embodiment of the present invention, the preset number is set to 3. The specific value of the preset number can also be set by the implementer according to the specific implementation scenario, and is not limited here.

[0114] At this point, reference historical production cycles for abnormal production cycles have been selected.

[0115] Step S4: Based on the governance plan for reference to historical production cycles, manage the carbon emissions of abnormal production cycles.

[0116] Since the carbon emission data between historical production cycles and abnormal production cycles are highly similar, and the abnormal conditions are also similar, the governance solutions based on historical production cycles are also applicable to abnormal production cycles. Therefore, carbon emissions during abnormal production cycles can be addressed based on governance solutions based on historical production cycles, thereby improving the effectiveness of carbon emission control during abnormal production cycles.

[0117] Preferably, in one embodiment of the present invention, a treatment scheme based on historical production cycles can be used to treat carbon emissions during abnormal production cycles.

[0118] For example, if the abnormal carbon emissions are caused by the energy structure, such as a significant increase in carbon emissions due to a period of abundant coal supply or low prices leading to increased coal consumption, then it is necessary to optimize the energy structure and increase the proportion of low-carbon energy use. If the abnormal carbon emissions are caused by improper production processes or operations, such as improper setting of certain process parameters, unreasonable operation, or equipment failure, which may lead to energy waste and increased carbon emissions, then it is necessary to maintain the equipment and standardize related operations to reduce the increase in carbon emissions caused by operation or failure.

[0119] One embodiment of the present invention provides a carbon verification data governance system based on a big data platform. The system includes a memory, a processor, and a computer program. The memory is used to store the corresponding computer program, and the processor is used to run the corresponding computer program. When the computer program runs in the processor, it can implement the methods described in steps S1 to S4.

[0120] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0121] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A carbon verification data governance method based on a big data platform, characterized in that, The method includes: The system acquires temperature data of different areas of the reactor at each moment during abnormal production cycles of enterprise carbon emissions, as well as carbon dioxide and carbon monoxide concentrations at the reactor outlet at each moment. It also acquires time-series data sequences of different process parameters during abnormal production cycles. Based on the temperature fluctuation differences between different areas of the reactor during the abnormal production cycle, the temperature differences between different areas at the same time, and the temperature changes at the same time, the temperature fluctuation of the abnormal production cycle is obtained; based on the differences in carbon dioxide and carbon monoxide concentrations at the reactor outlet at each moment during the abnormal production cycle, the period of incomplete combustion in the abnormal production cycle is obtained. The carbon emission anomaly degree of the abnormal production cycle is obtained based on the temperature fluctuation and the length of the incomplete combustion period of the abnormal production cycle. This includes: using the cumulative value of the lengths of all the incomplete combustion periods as the numerator, the length of the abnormal production cycle as the denominator, and the ratio as the proportion of incomplete combustion duration in the abnormal production cycle; and combining the maximum value of the length of all the incomplete combustion periods in the abnormal production cycle, the proportion of incomplete combustion duration in the abnormal production cycle, and the temperature fluctuation to obtain the carbon emission anomaly degree of the abnormal production cycle. Based on the carbon emissions and carbon emission anomaly degree of the abnormal production cycle, and the time-series data sequence of different process parameters within the abnormal production cycle, reference historical production cycles are selected from the historical production cycles in the database. This includes: using the two-dimensional sequence formed by the carbon emissions and carbon emission anomaly degree of the abnormal production cycle as the feature sequence of the abnormal production cycle; using the abnormal production cycle and the historical production cycles in the database as production cycles to be clustered; using the Euclidean distance between the feature sequences of any two production cycles to be clustered as the distance metric between them; and clustering each production cycle to be clustered based on the distance metric to obtain clusters; and using the historical production cycles in the cluster where the abnormal production cycle is located as reference historical production cycles to be clustered. Historical production cycles are screened by processing time-series data sequences with the same process parameters between abnormal production cycles and each historical production cycle to be screened, based on a dynamic time warping algorithm, to obtain parameter similarity between the abnormal production cycles and each historical production cycle to be screened; negative correlation mapping is performed on the distance metric between the abnormal production cycles and each historical production cycle to be screened to obtain feature similarity between the abnormal production cycles and each historical production cycle to be screened; the parameter similarity and feature similarity are combined to obtain comprehensive similarity between the abnormal production cycles and each historical production cycle to be screened; and the historical production cycles to be screened corresponding to the largest number of comprehensive similarities are selected as reference historical production cycles. Based on governance plans that reference historical production cycles, carbon emissions from abnormal production cycles are addressed.

2. The carbon verification data governance method based on a big data platform according to claim 1, characterized in that, The temperature fluctuations obtained during abnormal production cycles include: Based on the temperature fluctuations of each region of the reactor at all times, the temperature fluctuation coefficient of each region of the reactor is obtained. The dispersion of the temperature fluctuation coefficients in all areas of the reactor during abnormal production cycles is analyzed to obtain the temperature fluctuation difference degree during abnormal production cycles. By analyzing the dispersion of temperature data in all regions at the same time, the temperature difference at each moment of the abnormal production cycle can be obtained. The difference in temperature data between each region at each time point and the next adjacent time point is taken as the temperature change of each region at each time point. The dispersion of the temperature change of all regions at the same time point is analyzed to obtain the temperature change difference at each time point of the abnormal production cycle. The temperature fluctuation of the abnormal production cycle is obtained based on the temperature fluctuation difference of the abnormal production cycle, the temperature difference of all moments in the abnormal production cycle, and the temperature change difference.

3. The carbon verification data governance method based on a big data platform according to claim 2, characterized in that, The temperature fluctuation coefficient for each region of the obtained reactor includes: Take any region of the reactor as the target region, extract the extreme values ​​from the temperature data of all times in the target region, and take any two adjacent extreme values ​​as an extreme value group. Take the absolute value of the difference between the two extreme values ​​in each extreme value group as the numerator, take the absolute value of the difference between the times corresponding to the two extreme values ​​in each extreme value group as the denominator, and take the ratio as the data change rate of each extreme value group. The average rate of change of the data from all extreme value groups is used as the first temperature fluctuation assessment value for the target area. The dispersion of temperature data at all times in the target area is analyzed to obtain a second temperature fluctuation assessment value for the target area. The temperature fluctuation coefficient of the target area is obtained by combining the number of extreme values ​​in the temperature data of the target area with the first temperature fluctuation assessment value and the second temperature fluctuation assessment value of the target area.

4. The carbon verification data governance method based on a big data platform according to claim 2, characterized in that, The step of obtaining the temperature fluctuation degree of the abnormal production cycle based on the temperature fluctuation difference degree of the abnormal production cycle, the temperature difference degree of all moments in the abnormal production cycle, and the temperature change difference degree includes: The average of the temperature differences at all times during the abnormal production cycle is taken as the overall temperature difference of the abnormal production cycle. The average of the temperature variation differences at all times during the abnormal production cycle is taken as the overall temperature variation difference of the abnormal production cycle. The temperature fluctuation degree of the abnormal production cycle is obtained by combining the temperature fluctuation difference degree of the abnormal production cycle, the overall temperature difference degree, and the overall temperature change difference degree.

5. The carbon verification data governance method based on a big data platform according to claim 1, characterized in that, The incomplete combustion period during which the abnormal production cycle is obtained includes: The carbon monoxide concentration at the reactor outlet at each moment is used as the numerator, the carbon dioxide concentration at the reactor outlet at each moment is used as the denominator, and the ratio is used as the combustion evaluation value at the reactor outlet at each moment. The moment when the combustion assessment value is greater than the preset combustion threshold is taken as the moment of incomplete combustion in the abnormal production cycle, and the time period consisting of consecutive moments of incomplete combustion is taken as the period of incomplete combustion in the abnormal production cycle.

6. The carbon verification data governance method based on a big data platform according to claim 1, characterized in that, The parameter similarity between the obtained abnormal production cycle and each historical production cycle to be screened includes: Based on the dynamic time warping algorithm, the time series data sequences with the same process parameters between the abnormal production cycle and each historical production cycle to be screened are processed to obtain the data similarity between the abnormal production cycle and each historical production cycle to be screened for each process parameter. The average of the data similarity for all process parameters between the abnormal production cycle and each historical production cycle to be screened is taken as the parameter similarity between the abnormal production cycle and each historical production cycle to be screened.

7. The carbon verification data governance method based on a big data platform according to claim 1, characterized in that, The measures to control carbon emissions from abnormal production cycles include: Carbon emissions from abnormal production cycles are addressed using a governance scheme that references historical production cycles.

8. A carbon verification data governance system based on a big data platform, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

Images