Regional carbon emission intensity detection method and system based on big data

Abstract

The present invention relates to the field of carbon emission detection, and more specifically, the present invention relates to a method and system for detecting regional carbon emission intensity based on big data, the method comprising: obtaining a number of carbon emission data and a number of electric power data corresponding to the same reaction pool in an industrial production process, determining the error variation of each carbon emission data using a cumulative and detection algorithm, and calculating a correction factor of a preset initial threshold of the error variation of each carbon emission data, updating the initial threshold of the error variation of the corresponding carbon emission data according to the correction factor, the updated initial threshold being positively correlated with the correction factor, so as to realize the detection of carbon emission intensity according to the updated initial threshold corresponding to each carbon emission data. The present invention can reduce the influence of noise data on carbon emission intensity detection by adaptively adjusting the initial threshold corresponding to the error variation of each carbon emission data, thereby improving the accuracy of the detected carbon emission intensity.

Description

Technical Field

[0001] The present invention relates to the field of carbon emission detection, and more specifically, to a method and system for detecting regional carbon emission intensity based on big data. Background Art

[0002] With the continuous growth of energy demand, the supply of traditional fossil fuels is facing pressure. At the same time, the unstable supply of energy and price fluctuations have also brought considerable pressure to the economy and society. Therefore, strengthening energy management and transformation and upgrading has become an urgent issue. The use of big data can monitor carbon emissions in industrial production processes in real time, help companies detect anomalies and optimize production processes in a timely manner, and thus formulate more effective emission reduction measures to reduce carbon emission intensity in the region.

[0003] In the related technology, the patent application document with publication number CN116859001A discloses an online carbon emission monitoring platform and analysis method, which includes: measuring the carbon dioxide concentration at different points on a straight line, thereby analyzing the abnormal diffusion of carbon dioxide concentration, generating a wind speed diffusion coefficient, and monitoring the temperature of the environment, combining the average temperature, calculating the temperature diffusion coefficient, fitting the diffusion of carbon dioxide at the monitoring point, constructing a carbon emission evaluation coefficient, and using the temperature diffusion coefficient and the wind speed diffusion coefficient to correct the carbon emission evaluation coefficient to detect the carbon emission situation.

[0004] However, when the above scheme uses temperature data and carbon dioxide concentration to calculate the wind speed diffusion coefficient and the temperature diffusion coefficient, it does not take into account the influence of the acquired temperature data and the noise data in carbon dioxide, which may cause a large deviation between the determined carbon emission content and the true value, and may reduce the accuracy of the determination of the carbon emission content to a certain extent. Summary of the invention

[0005] In order to solve the problem of low accuracy of determined carbon emissions due to the influence of noise data, the present invention provides a regional carbon emission intensity detection method and system based on big data.

[0006] According to a first aspect of an embodiment of the present invention, a method for detecting regional carbon emission intensity based on big data is provided, comprising:

[0007] Obtain a number of carbon emission data and a number of electric power data corresponding to the same reaction pool in the industrial production process, and use the electric power data corresponding to any carbon emission data as reference data for any carbon emission data;

[0008] The error change of carbon emission data is determined by using the cumulative sum detection algorithm, and the correction factor of the preset initial threshold of the error change of each carbon emission data is calculated. , For the The possibility that carbon emission data is noise data, is the reference angle, For the The first point in the scatter plot corresponding to the preset data segment of carbon emission data The angle between the data point and the line connecting the data points on the left and right sides, is the length of the preset data segment, For the The degree of influence of the carbon emission data and the corresponding reference data on the correlation between all carbon emission data and the corresponding reference data in the preset data segment. The base is a natural number The exponential function of

[0009] The initial threshold of the error change amount of the corresponding carbon emission data is updated according to the correction factor, and the updated initial threshold is positively correlated with the correction factor, so as to realize the detection of carbon emission intensity according to the updated initial threshold corresponding to each carbon emission data.

[0010] The present invention can reduce the updated initial threshold corresponding to the carbon emission data with a greater possibility of noise data by calculating the correction factor of the preset initial threshold of the error change amount of each carbon emission data, so that the influence of noise data on the carbon emission intensity detection can be reduced, thereby improving the accuracy of the determined carbon emission intensity to a certain extent; and comprehensively determine the correction factor corresponding to each carbon emission data from multiple aspects, thereby ensuring the accuracy of the correction factor determination, thereby improving the accuracy of the carbon emission intensity detection.

[0011] In an exemplary embodiment of the present invention, the initial threshold of the error change amount corresponding to the carbon emission data is updated according to the correction factor to satisfy the following relationship:

[0012] ;

[0013] In the formula, For the The updated initial threshold corresponding to the carbon emission data; For the A preset initial threshold for the error change of each carbon emission data; For the The correction factor for the initial threshold of the error change of each carbon emission data; is the normalization function.

[0014] The present invention uses a correction factor to correct the initial threshold of the error change amount of carbon emission data, and can adaptively adjust the initial threshold corresponding to each carbon emission data. The carbon emission data with a greater possibility of noise data has a lower initial threshold, thereby reducing the impact of noise data on carbon emission intensity detection.

[0015] In an exemplary embodiment of the present invention, the detection of carbon emission intensity is implemented according to the updated initial threshold corresponding to each carbon emission data, including:

[0016] If the updated initial threshold corresponding to the current carbon emission data is greater than or equal to the preset alarm threshold, an alarm will be issued to remind the operator that the carbon emission intensity at the current moment exceeds the set value.

[0017] The present invention detects the carbon emission intensity using the updated initial threshold corresponding to the carbon emission data, which can ensure the accuracy of the carbon emission intensity detection result.

[0018] In an exemplary embodiment of the present invention, the possibility that the carbon emission data is noise data includes:

[0019] The difference between the variance of all carbon emission data in a preset data segment of any carbon emission data and the variance of all carbon emission data except any carbon emission data in the preset data segment is taken as the first difference, and the difference between any carbon emission data and the mean of all carbon emission data in the preset data segment is taken as the second difference;

[0020] The possibility that any carbon emission data is noise data is determined according to the first difference and the second difference, and the possibility that any carbon emission data is noise data is positively correlated with both the first difference and the second difference.

[0021] In an exemplary embodiment of the present invention, the possibility that any carbon emission data is noise data satisfies the following relationship:

[0022] ;

[0023] In the formula, For the The possibility that the carbon emission data is noise data; For the The value of carbon emission data; For the The mean value of all carbon emission data within a preset data segment of carbon emission data; For the The variance of all carbon emission data within a preset data segment of a carbon emission data; For the Within the preset data segment of carbon emission data, except for the The variance of all carbon emission data except the carbon emission data; is the normalization function.

[0024] The present invention integrates the variation characteristics of the surrounding carbon emission data of the carbon emission data to ensure the accuracy of the determined carbon emission data as noise data.

[0025] In an exemplary embodiment of the present invention, after obtaining a plurality of carbon emission data and a plurality of electric power data corresponding to a same reaction pool in an industrial production process, the method further includes:

[0026] Determine a carbon emission data segment corresponding to a first preset period, and an electric power data segment corresponding to a second preset period, wherein the end time of the first preset period and the second preset period are the same, and the duration of the second preset period is greater than the duration of the first preset period;

[0027] Multiple comparison data segments corresponding to the carbon emission data segment are selected from the electric power data segment in turn, and the sampling time difference between the comparison data segment with the largest Pearson correlation coefficient with the carbon emission data segment and the carbon emission data segment is determined, so as to eliminate the time difference between the electric power data and the carbon emission data by lagging the electric power data by the sampling time difference.

[0028] The present invention can eliminate the time difference between the electric power data and the carbon emission data, thereby reducing the difficulty of determining the correlation between the electric power data and the carbon emission data, thereby ensuring the accuracy of the correction factors corresponding to each determined carbon emission data to a certain extent.

[0029] In an exemplary embodiment of the present invention, the degree of influence satisfies the following relationship:

[0030] ;

[0031] In the formula, For the the degree of influence of the individual carbon emission data and the corresponding reference data on the correlation between all carbon emission data and the corresponding reference data in the preset data segment; For the preset data segment except All carbon emission data except the carbon emission data of The Pearson correlation coefficient between all reference data except the reference data corresponding to the carbon emission data; is the Pearson correlation coefficient between all carbon emission data in the preset data segment and the corresponding reference data.

[0032] In an exemplary embodiment of the present invention, the error variation of carbon emission data is determined using a cumulative sum detection algorithm, including:

[0033] The difference between the cumulative statistics corresponding to the current carbon emission data and the cumulative statistics corresponding to the left adjacent carbon emission data is taken as the error change amount of the carbon emission data, thereby obtaining the error change amount of the carbon emission data.

[0034] According to the second aspect of an embodiment of the present invention, a regional carbon emission intensity detection system based on big data is provided. The regional carbon emission intensity detection system based on big data includes a memory and a processor. A computer program is stored in the memory. The processor executes the computer program to implement the steps of the first aspect of the embodiment of the present invention.

[0035] The present invention has the following effects:

[0036] The present invention can reduce the impact of noise data on carbon emission intensity detection by lowering the updated initial threshold corresponding to carbon emission data with a greater possibility of noise data, thereby improving the accuracy of the determined carbon emission intensity to a certain extent; and comprehensively determines the correction factor of the initial threshold of the error change amount of carbon emission data from multiple aspects, thereby ensuring the accuracy of the correction factor determination, thereby improving the accuracy of carbon emission intensity detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0038] Figure 1 It is a schematic diagram of the steps of the method for detecting regional carbon emission intensity based on big data according to an embodiment of the present invention;

[0039] Figure 2 It is a flowchart of the steps of eliminating the time difference between electric power data and carbon emission data in an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0041] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0042] Reference Figure 1 , a regional carbon emission intensity detection method based on big data, including steps S1-S3, specifically as follows:

[0043] S1: Obtain a number of carbon emission data and a number of electric power data corresponding to the same reaction pool in the industrial production process, and use the electric power data corresponding to any carbon emission data as reference data for any carbon emission data.

[0044] It should be noted that in the industrial production process, changes in environmental conditions, such as fluctuations in temperature, humidity, pressure and other factors, may cause noise data in the collected carbon emission data, and the existence of noise data will affect the detection of carbon emission intensity. Therefore, in order to ensure accurate detection of carbon emission intensity in the industrial production process, it is necessary to determine the noise data in the carbon emission data to reduce the impact of noise data on the carbon emission intensity detection results.

[0045] In an exemplary embodiment of the present invention, carbon emission data refers to the data of carbon emission corresponding to the reactants in the reaction pool collected during the industrial production process, which is used as a data basis to determine the noise data, so as to reduce the influence of the noise data on the carbon emission intensity detection results in the industrial production process by processing the noise data. Specifically, the collection frequency can be set to 1 time / second, and the collection time can be set to thirty minutes. The laser absorption spectrometer is used to collect carbon emission data at the chimney mouth starting from any time in the industrial production process. Of course, it is also possible to select appropriate instruments, locations, collection frequencies and collection times according to specific circumstances. This embodiment does not specifically limit the method of collecting carbon emission data.

[0046] Electric power data refers to the data on how fast the production equipment connected to the reaction pool consumes electric energy during the industrial production process. It can reflect the amount of reactants added to the reaction pool to a certain extent, and can further characterize the actual carbon emissions. It should be noted that the electric power data characterizes the amount of reactants added, and the carbon emission data characterizes the amount of carbon emissions generated by the collected reactants. Therefore, the correlation between the electric power data and the carbon emission data can be used to determine the noise data in the carbon emission data. There is a certain time difference between the electric power data and the carbon emission data when reflecting the carbon emissions corresponding to the same reaction pool. Therefore, the start time of collecting the electric power data should be before the start time of collecting the carbon emission data. When using the correlation between the electric power data and the carbon emission data to determine the noise data in the carbon emission data, the time difference between the electric power data and the carbon emission data needs to be eliminated.

[0047] Optionally, the time of collecting carbon emission data can be traced back 10 minutes, and then the time 10 minutes later can be used as the starting time, and the electric power data of the production equipment connected to the reaction pool can be collected at a collection frequency of 1 time / second, so as to obtain the carbon emission data and electric power data corresponding to the same reaction pool. This embodiment does not impose any special restrictions on the traceback period and collection frequency, as long as the collection frequency of the electric power data is the same as the collection frequency of the carbon emission data.

[0048] In an exemplary embodiment of the present invention, reference Figure 2As shown, after obtaining a number of carbon emission data and a number of electric power data corresponding to the same reaction cell, the time difference between the electric power data and the carbon emission data can be eliminated by the following steps:

[0049] S101: Determine a carbon emission data segment corresponding to a first preset period, and an electric power data segment corresponding to a second preset period, wherein the end time of the first preset period and the second preset period are the same, and the duration of the second preset period is greater than the duration of the first preset period;

[0050] Among them, the first preset time period refers to a time period selected arbitrarily within the collection period of carbon emission data, which is used to determine the selected carbon emission data segment. In this embodiment, the duration of the first preset time period is 10 minutes; the second preset time period refers to the time period determined according to the first preset time period, which is used to determine the selected electric power data segment. The determination of the second preset time period is related to the determination of the first preset time period. If the duration of the first preset time period is 10 minutes, the duration of the second preset time period is greater than the duration of the first preset time period, and the end time of the first preset time period and the second preset time period is the same. It should be noted that the duration of the second preset time period greater than the first preset time period can be determined based on empirical values. This embodiment does not specifically limit the duration, and the duration of the second preset time period in this embodiment is 20 minutes.

[0051] S102: Select multiple comparison data segments corresponding to the carbon emission data segment from the electric power data segment in turn, and determine the sampling time difference between the comparison data segment with the largest Pearson correlation coefficient with the carbon emission data segment and the carbon emission data segment, so as to eliminate the time difference between the electric power data and the carbon emission data by lagging the electric power data by the sampling time difference.

[0052] Exemplarily, first, the data segment corresponding to the first 10 minutes in the electric power data segment can be used as the first comparison data segment of the carbon emission data segment, and then the time period corresponding to the first comparison data segment is delayed by 1 second to obtain a new time period, and the data segment in the electric power data segment that is in the new time period is used as the second comparison data segment of the carbon emission data segment, and so on, to obtain multiple comparison data segments in the electric power data segment corresponding to the carbon emission data segment. It should be noted that since the present invention collects electric power data and carbon emission data at a frequency of 1 time / second, the second comparison data segment is determined by the time period corresponding to the first comparison data segment after a lag of 1 second.

[0053] Secondly, after obtaining multiple comparison data segments corresponding to the carbon emission data, the Pearson correlation coefficient between the electric power data in each comparison data segment and the carbon emission data in the carbon emission data segment can be calculated respectively, so as to determine a comparison data segment with the largest Pearson correlation coefficient with the carbon emission data in the carbon emission data segment, and then use the sampling time difference corresponding to the comparison data segment and the carbon emission data segment as the time difference between the electric power data and the carbon emission data; it should be noted that the Pearson correlation coefficient can measure the correlation between two data segments. The Pearson correlation coefficient can be used to select the comparison data segment with the largest correlation with the carbon emission data segment, and then use the sampling time difference between the comparison data segment with the largest correlation and the carbon emission data segment as the time difference between the electric power data and the carbon emission data, wherein calculating the Pearson correlation coefficient between two data segments is a prior art and will not be described in detail here.

[0054] Finally, the electric power data can be lagged by the time difference calculated to achieve alignment between the electric power data and the carbon emission data, thereby eliminating the time difference between the electric power data and the carbon emission data. Therefore, according to the collection time corresponding to each data point in the carbon emission data, the electric power data corresponding to each carbon emission data can be accurately determined, and the reference data corresponding to each carbon emission data can be obtained.

[0055] S2: Determine the error variation of the carbon emission data using a cumulative sum detection algorithm, and calculate a correction factor of a preset initial threshold value of the error variation of each carbon emission data.

[0056] It should be noted that the CUSUM (Cumulative Sum) detection algorithm is an algorithm used to monitor changes in data sequences. By executing the detection algorithm on carbon emission data, the cumulative statistics of the deviation between the target carbon emissions and the actual carbon emissions can be determined. When the difference between the cumulative statistics corresponding to a certain carbon emission data and the cumulative statistics corresponding to the previous carbon emission data, that is, the error change of the carbon emission data is large, it means that the deviation between the target carbon emissions and the actual carbon emissions is large, and the corresponding carbon emission intensity is relatively high. When the error change of the carbon emission data is greater than a certain value, an alarm can be issued to remind the operator that the carbon emission intensity is too high, and guide the operator to adjust the amount of reactants added in the reaction pool, thereby realizing the detection of carbon emission intensity in the industrial production process.

[0057] It needs to be further explained that when executing the CUSUM (Cumulative Sum) detection algorithm on carbon emission data, due to the existence of noise data, the corresponding carbon emission data with higher error changes may be excessive, resulting in false alarms, causing certain waste of resources, and may reduce the accuracy of carbon emission intensity detection to a certain extent. Therefore, when executing the CUSUM detection algorithm on carbon emission data, it is necessary to reduce the impact of noise data in the carbon emission data, so as to achieve accurate detection of carbon emission intensity.

[0058] In an exemplary embodiment of the present invention, the determination of the error variation of carbon emission data can be achieved by the following steps:

[0059] The difference between the cumulative statistics corresponding to the current carbon emission data and the cumulative statistics corresponding to the left adjacent carbon emission data is taken as the error change amount of the carbon emission data, thereby obtaining the error change amount of the carbon emission data.

[0060] Optionally, after determining the error change of each carbon emission data, if any carbon emission data is likely to be noise data, the correction factor corresponding to the carbon emission data can be used to update the initial threshold of the error change of the carbon emission data, and obtain the updated initial threshold corresponding to the carbon emission data, so as to lower the initial threshold of the error change of the carbon emission data, thereby avoiding issuing an alarm when the error change corresponding to the noise data is too large, so as to accurately detect the carbon emission intensity.

[0061] In an exemplary embodiment of the present invention, the possibility that the carbon emission data is noise data can be determined by the following steps:

[0062] The difference between the variance of all carbon emission data within a preset data segment of any carbon emission data and the variance of all carbon emission data within the preset data segment except any carbon emission data is taken as the first difference, and the difference between any carbon emission data and the mean of all carbon emission data in the preset data segment is taken as the second difference; the possibility of any carbon emission data being noise data is determined based on the first difference and the second difference, and the possibility of any carbon emission data being noise data is positively correlated with the first difference and the second difference.

[0063] Among them, the preset data segment of any carbon emission data refers to a data segment with a length of 61 centered on the carbon emission data; it should be noted that if the number of carbon emission data on one side of the carbon emission data is less than 30, a corresponding number of carbon emission data can be selected on the other side of the carbon emission data to ensure that the length of the preset data segment of the carbon emission data remains unchanged. This embodiment does not specifically limit the length of the preset data segment.

[0064] The first difference refers to the ability to measure the impact of the carbon emission data on the overall fluctuation of the preset data segment of the carbon emission data. The larger the value, the greater the impact of the carbon emission data on the overall fluctuation of the preset data segment, and the greater the possibility that the carbon emission data is noise data; the second difference refers to the ability to measure the abnormal value of the carbon emission data. If the second difference corresponding to the carbon emission data is larger, the greater the possibility that the carbon emission data is noise data.

[0065] Furthermore, the possibility that any carbon emission data is noise data satisfies the following relationship:

[0066] ;

[0067] In the formula, For the The possibility that the carbon emission data is noise data; For the The value of carbon emission data; For the The mean value of all carbon emission data within a preset data segment of carbon emission data; For the The variance of all carbon emission data within a preset data segment of a carbon emission data; For the Within the preset data segment of carbon emission data, except for the The variance of all carbon emission data except the carbon emission data; is the normalization function.

[0068] in, Reflects the The first difference value corresponding to the carbon emission data is greater, and the greater the value, the greater the possibility that the carbon emission data is noise data; It reflects the abnormality of the carbon emission data. The larger the value, the greater the possibility that the carbon emission data is noise data.

[0069] In another embodiment, the possibility of each carbon emission data being noise data may be calculated by other formulas, for example, not by a product calculation formula but by a gamma transform calculation formula.

[0070] Optionally, after determining the possibility that any carbon emission data is noise data, the influence of the carbon emission data and the corresponding reference data on the correlation between all carbon emission data in a preset data segment and the corresponding reference data can be calculated. Specifically, the influence degree satisfies the following relationship:

[0071] ;

[0072] In the formula, For the The influence of a carbon emission data and the corresponding reference data on the correlation between all carbon emission data and the corresponding reference data in the preset data segment. The larger the value, the stronger the correlation between the carbon emission data and the corresponding electric power data in the preset data segment, in addition to the carbon emission data and the reference data corresponding to the carbon emission data. The greater the influence of the carbon emission data and the corresponding reference data on the correlation, the greater the possibility that the carbon emission data is noise data. For the preset data segment except All carbon emission data except the carbon emission data of The Pearson correlation coefficient between all reference data except the reference data corresponding to the carbon emission data; is the Pearson correlation coefficient between all carbon emission data in the preset data segment and the corresponding reference data.

[0073] Further, after determining the possibility that each carbon emission data is noise data, and the influence degree of each carbon emission data and the corresponding reference data on the correlation between all carbon emission data and the corresponding reference data in the preset data segment, the correction factor of the preset initial threshold value of the error change amount of each carbon emission data can be calculated. Specifically, the calculation formula of the correction factor satisfies the following relationship:

[0074] ;

[0075] In the formula, For the A correction factor for a preset initial threshold value of the error change amount of carbon emission data. The smaller the value, the greater the correction amplitude of the initial threshold value of the error change amount of the carbon emission data. In this embodiment, the initial threshold value is set to 8 according to the empirical value; For the The possibility that the carbon emission data is noise data; is the reference angle. ; For the The first point in the scatter plot corresponding to the preset data segment of carbon emission data The angle between the data point and the line connecting the data points on the left and right sides; All data points except the first data point and the last data point in the scatter plot corresponding to the preset data segment. It should be noted that the value of each carbon emission data in the preset data segment can be used as the vertical coordinate, and the position number corresponding to each carbon emission data can be used as the horizontal coordinate to construct the scatter plot corresponding to the preset data segment; is the length of the preset data segment; For the the degree of influence of the individual carbon emission data and the corresponding reference data on the correlation between all carbon emission data and the corresponding reference data in the preset data segment; The base is a natural number The exponential function of .

[0076] in, It reflects the changing trend of all carbon emission data in the preset data segment. The larger the value, the more drastic the change of carbon emission data in the preset data segment, the worse the corresponding gradual change, and the greater the possibility that the preset data segment contains noise data. The greater the possibility that a piece of carbon emission data is noise data, the larger the correction amplitude is needed to correct the initial threshold of the error change amount of the carbon emission data, so as to reduce the influence of the error change amount of the carbon emission data on the carbon emission intensity detection.

[0077] It should be noted that the methods for obtaining the preset data segments and the reference data in the present invention are consistent.

[0078] S3: updating the initial threshold of the error change amount of the corresponding carbon emission data according to the correction factor, wherein the updated initial threshold is positively correlated with the correction factor, so as to realize the detection of carbon emission intensity according to the updated initial threshold corresponding to each carbon emission data.

[0079] In an exemplary embodiment of the present invention, the initial threshold of the error change amount corresponding to the carbon emission data is updated according to the correction factor to satisfy the following relationship:

[0080] ;

[0081] In the formula, For the The updated initial threshold corresponding to the carbon emission data; For the The preset initial threshold of the error change amount of carbon emission data is ; For the The correction factor for the initial threshold of the error change of each carbon emission data; is the normalization function.

[0082] In an exemplary embodiment of the present invention, the detection of carbon emission intensity can be achieved by the following steps:

[0083] If the updated initial threshold corresponding to the current carbon emission data is greater than or equal to the preset alarm threshold, an alarm will be issued to remind the operator that the carbon emission intensity at the current moment exceeds the set value.

[0084] Optionally, the alarm threshold can be determined based on an empirical value. In this embodiment, the alarm threshold is 0.6. If the updated initial threshold corresponding to the current carbon emission data is greater than 0.6, it means that the carbon emission intensity at the current moment is too high, and an alarm is issued to remind the operator that the carbon emission intensity at the current moment exceeds the set value, and then adjust the amount of reactants added to the reaction pool to reduce the carbon emission intensity.

[0085] The present invention also provides a regional carbon emission intensity detection system based on big data. The system includes a memory and a processor, and a computer program is stored in the memory. The computer program integrates the functions of the regional carbon emission intensity detection method based on big data. When the computer program is executed, the regional carbon emission intensity detection method based on big data can reduce the influence of noise data on carbon emission intensity detection by adaptively adjusting the initial threshold corresponding to the error change amount of each carbon emission data, thereby improving the accuracy of the detected carbon emission intensity.

[0086] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0087] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A regional carbon emission intensity detection method based on big data, characterized in that: include: Acquire a number of carbon emission data and a number of electric power data corresponding to the same reaction pool in the industrial production process, and use the electric power data corresponding to any carbon emission data as reference data for any carbon emission data; The error variation of the carbon emission data is determined by using a cumulative sum detection algorithm, and a correction factor of a preset initial threshold value of the error variation of each carbon emission data is calculated. , For the The possibility that carbon emission data is noise data, is the reference angle, For the The first point in the scatter plot corresponding to the preset data segment of carbon emission data The angle between the data point and the line connecting the data points on the left and right sides, is the length of the preset data segment, For the The degree of influence of the carbon emission data and the corresponding reference data on the correlation between all carbon emission data and the corresponding reference data in the preset data segment. The base is a natural number The exponential function of The possibility that any carbon emission data is noise data satisfies the following relationship: ； In the formula, For the The value of carbon emission data; For the The mean value of all carbon emission data within a preset data segment of carbon emission data; For the The variance of all carbon emission data within a preset data segment of a carbon emission data; For the Within the preset data segment of carbon emission data, except for the The variance of all carbon emission data except the carbon emission data; is the normalization function; An initial threshold of the error change amount of the corresponding carbon emission data is updated according to the correction factor, and the updated initial threshold is positively correlated with the correction factor, so as to detect the carbon emission intensity according to the updated initial threshold corresponding to each carbon emission data; The initial threshold of the error change amount of the corresponding carbon emission data is updated according to the correction factor to satisfy the following relationship: ； In the formula, For the The updated initial threshold corresponding to the carbon emission data; For the A preset initial threshold for the error change of each carbon emission data; For the The correction factor for the initial threshold of the error change of carbon emission data.

2. The regional carbon emission intensity detection method based on big data according to claim 1 is characterized in that: The detecting of carbon emission intensity according to the updated initial threshold corresponding to each carbon emission data includes: If the updated initial threshold corresponding to the current carbon emission data is greater than or equal to the preset alarm threshold, an alarm will be issued to remind the operator that the carbon emission intensity at the current moment exceeds the set value.

3. The regional carbon emission intensity detection method based on big data according to claim 1 is characterized in that: The possibility that the carbon emission data is noise data includes: The difference between the variance of all carbon emission data in a preset data segment of any carbon emission data and the variance of all carbon emission data in the preset data segment except the any carbon emission data is taken as a first difference, and the difference between the any carbon emission data and the mean of all carbon emission data in the preset data segment is taken as a second difference; The possibility that any carbon emission data is noise data is determined according to the first difference and the second difference, and the possibility that any carbon emission data is noise data is positively correlated with both the first difference and the second difference.

4. The regional carbon emission intensity detection method based on big data according to claim 1 is characterized in that: After obtaining some carbon emission data and some electric power data corresponding to the same reaction pool in the industrial production process, it also includes: Determine a carbon emission data segment corresponding to a first preset period, and an electric power data segment corresponding to a second preset period, wherein the end time of the first preset period and the second preset period are the same, and the duration of the second preset period is greater than the duration of the first preset period; Select multiple comparison data segments corresponding to the carbon emission data segment from the electric power data segment in turn, and determine the sampling time difference between the comparison data segment with the largest Pearson correlation coefficient with the carbon emission data segment and the carbon emission data segment, so as to eliminate the time difference between the electric power data and the carbon emission data by lagging the electric power data by the sampling time difference.

5. The regional carbon emission intensity detection method based on big data according to claim 1 is characterized in that: The degree of influence satisfies the following relationship: ； In the formula, For the the degree of influence of the individual carbon emission data and the corresponding reference data on the correlation between all carbon emission data and the corresponding reference data in the preset data segment; The preset data segment except the All carbon emission data except the carbon emission data of The Pearson correlation coefficient between all reference data except the reference data corresponding to the carbon emission data; is the Pearson correlation coefficient between all carbon emission data in the preset data segment and the corresponding reference data.

6. The regional carbon emission intensity detection method based on big data according to claim 1 is characterized in that: The method of determining the error variation of the carbon emission data by using a cumulative sum detection algorithm includes: The difference between the cumulative statistic corresponding to the current carbon emission data and the cumulative statistic corresponding to the left adjacent carbon emission data is taken as the error variation of the carbon emission data, thereby obtaining the error variation of the carbon emission data.

7. Regional carbon emission intensity detection system based on big data, characterized by: The regional carbon emission intensity detection system based on big data includes a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the steps of the method as described in any one of claims 1 to 6.

Images