Method, device and equipment for monitoring abnormal carbon emission of coal-fired power plant and medium

Abstract

The invention provides a coal-fired power plant carbon emission abnormity monitoring method, device and equipment and a medium, and belongs to the technical field of environment monitoring. According to the method, carbon emission data of a coal-fired power plant at different time periods are analyzed, a normal range is identified by using a plurality of abnormal value detection methods, and a target normal range is determined. And screening out carbon emission data in the target abnormal time period, and calculating an abnormal ratio. And according to a preset carbon emission abnormity processing table, corresponding processing measures are obtained through matching. According to the invention, by integrating a plurality of anomaly detection methods, the carbon emission anomaly is rapidly positioned and quantified, and accurate treatment measures are provided for the coal-fired power plant, so that the carbon emission is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the field of environmental monitoring technology, and in particular to a method for monitoring abnormal carbon emissions in a coal-fired power plant, a device for monitoring abnormal carbon emissions in a coal-fired power plant, an electronic device and a computer-readable storage medium. Background Art

[0002] With the development of industry and the growth of energy demand, coal-fired power plants, as important energy production facilities, have increasingly received attention for their carbon emissions. Carbon emissions from coal-fired power plants directly affect the quality of the atmospheric environment and the greenhouse effect. Therefore, it is of great significance to monitor and control carbon emissions from coal-fired power plants.

[0003] At present, the existing carbon emission management technologies of coal-fired power plants mainly include carbon emission monitoring, data anomaly identification and anomaly handling. Specifically, carbon emission monitoring mainly relies on manual regular inspections and equipment instrument records, data anomaly identification mainly relies on manual experience judgment or simple statistical analysis, and anomaly handling usually adopts relatively general carbon emission anomaly handling measures.

[0004] However, the existing carbon emission management technology of coal-fired power plants has the following problems: (1) The data acquisition method is relatively simple, which cannot achieve real-time monitoring and is difficult to capture sudden carbon emission abnormalities; (2) The outlier identification method is relatively simple and lacks scientific outlier detection methods, which can easily lead to misjudgment or missed judgments; (3) It is impossible to formulate personalized treatment plans for different carbon emission abnormalities, and thus it is impossible to effectively solve the problem of carbon emission abnormalities.

[0005] In general, existing carbon emission management technologies for coal-fired power plants cannot accurately identify and solve the problem of abnormal carbon emissions. Summary of the invention

[0006] The purpose of the embodiments of the present invention is to provide a method, device, equipment and medium for monitoring abnormal carbon emissions in coal-fired power plants, so as to solve the problem that existing carbon emission management technologies for coal-fired power plants cannot accurately identify and solve excessive carbon emissions.

[0007] In order to achieve the above object, an embodiment of the present invention provides a method for monitoring abnormal carbon emissions in a coal-fired power plant, comprising: Obtain carbon emission data for coal-fired power plants over multiple time periods; According to different outlier detection methods, the carbon emission data of multiple time periods are processed to identify the normal range of carbon emission data under different outlier detection methods; Based on the overlap of normal ranges of carbon emission data under different outlier detection methods, the normal range of target carbon emission data is determined; Determine the carbon emission data that is not within the normal range of the target carbon emission data as the carbon emission data for the target abnormal period; Calculate the ratio of the number of carbon emission data in the target abnormal period to the number of carbon emission data in multiple periods to determine the abnormal proportion of carbon emissions; The carbon emission abnormality ratio is matched with the preset carbon emission abnormality processing table of the coal-fired power plant to obtain the carbon emission abnormality processing measures; wherein, the preset carbon emission abnormality processing table of the coal-fired power plant includes the mapping relationship between the carbon emission abnormality ratio and the carbon emission abnormality processing measures.

[0008] Optionally, before the step of processing the carbon emission data of multiple time periods according to different outlier detection methods to identify the normal range of the carbon emission data under different outlier detection methods, the method further includes: The carbon emission data of coal-fired power plants in multiple time periods are preprocessed; wherein the preprocessing includes: format conversion and interpolation processing.

[0009] Optionally, according to different outlier detection methods, the carbon emission data of multiple time periods are processed to identify the normal range of carbon emission data under different outlier detection methods, including: According to the Z-value discrimination method, the carbon emission data of multiple time periods are calculated to determine the standard scores of the carbon emission data of multiple time periods; Determine the carbon emission data corresponding to the standard score whose absolute value is less than the preset standard score as the carbon emission data of the normal period under the Z value discrimination method, and use the minimum and maximum values ​​of the carbon emission data of the normal period under the Z value discrimination method as boundaries to determine the normal range of carbon emission data under the Z value discrimination method; According to the quartile discrimination method, the carbon emission data of multiple time periods are calculated to determine the normal range of carbon emission data under the quartile discrimination method; Based on the 595th quantile discrimination method, the carbon emission data of multiple time periods are calculated to determine the normal range of carbon emission data under the 595th quantile discrimination method.

[0010] Optionally, the carbon emission data of multiple time periods are calculated according to the Z value discrimination method to determine the standard scores of the carbon emission data of multiple time periods, including: Calculate the average of carbon emission data for multiple periods; Calculate the standard deviation of carbon emission data for multiple time periods; Carbon emissions data for each period: The following formula is used to calculate the average value of carbon emission data in multiple periods, the standard deviation of carbon emission data in multiple periods and the carbon emission data in any period to obtain the standard score of carbon emission data in any period; ;in, Represents the standard score of carbon emission data in any period, Represents the carbon emission data for any period of time, Represents the average value of carbon emission data over multiple periods. Represents the standard deviation of carbon emission data for multiple time periods.

[0011] Optionally, the carbon emission data of multiple time periods are calculated according to the quartile discrimination method to determine the normal range of carbon emission data under the quartile discrimination method, including: Sort the carbon emission data of multiple time periods from small to large to obtain sorted carbon emission data of multiple time periods; Divide the sorted carbon emission data of multiple time periods into four equal parts to obtain four groups of carbon emission data of multiple time periods; Calculate the average of the last carbon emission data in the first group of carbon emission data for multiple time periods and the first carbon emission data in the second group of carbon emission data for multiple time periods to obtain the lower quartile of the carbon emission data; Calculate the average of the last carbon emission data in the third group of carbon emission data for multiple time periods and the first carbon emission data in the fourth group of carbon emission data for multiple time periods to obtain the upper quartile of the carbon emission data; Calculate the difference between the upper quartile of carbon emission data and the lower quartile of carbon emission data to obtain the interquartile range of carbon emission data; The following formula is used to calculate the lower quartile of carbon emission data, the upper quartile of carbon emission data, the interquartile range of carbon emission data and the first preset coefficient to obtain the minimum and maximum values ​​of carbon emission data in the normal period of the quartile discrimination method, and the normal range of carbon emission data under the quartile discrimination method is determined based on the minimum and maximum values ​​of carbon emission data in the normal period of the quartile discrimination method; ;in, It represents the minimum value of carbon emission data in normal period of quartile discrimination method. It represents the maximum value of carbon emission data in normal period of quartile discrimination method. represents the lower quartile of carbon emission data, represents the upper quartile of carbon emission data, represents the first preset coefficient, Represents the interquartile range of carbon emission data.

[0012] Optionally, the carbon emission data of multiple time periods are calculated according to the 595th percentile discrimination method to determine the normal range of carbon emission data under the 595th percentile discrimination method, including: Sort the carbon emission data of multiple time periods from small to large to obtain sorted carbon emission data of multiple time periods; Divide the sorted carbon emission data of multiple time periods into five equal parts to obtain five groups of carbon emission data of multiple time periods; Calculate the average of the last carbon emission data in the first group of carbon emission data for multiple time periods and the first carbon emission data in the second group of carbon emission data for multiple time periods to obtain the quintile of the carbon emission data; The first carbon emission data in the fifth group of carbon emission data for multiple time periods is taken as the 95th percentile of the carbon emission data; The following formula is used to calculate the quintile of carbon emission data, the ninety-fifth quantile of carbon emission data, and the second preset coefficient to obtain the minimum and maximum values ​​of carbon emission data during the normal period of the ninety-fifth quantile discrimination method, and the normal range of carbon emission data under the ninety-fifth quantile discrimination method is determined based on the minimum and maximum values ​​of carbon emission data during the normal period of the ninety-fifth quantile discrimination method; ;in, It represents the minimum value of carbon emission data in normal period of the 95th percentile discrimination method. It represents the maximum value of carbon emission data in normal period of the 95th percentile discrimination method. represents the quintile of carbon emission data, represents the 95th percentile of carbon emission data, Indicates the second preset coefficient.

[0013] Optionally, based on the overlap of normal ranges of carbon emission data under different outlier detection methods, determining the normal range of target carbon emission data includes: If the normal range of carbon emission data under the Z value discrimination method, the normal range of carbon emission data under the quartile discrimination method, and the normal range of carbon emission data under the 595th quartile discrimination method do not overlap with each other, the normal range of carbon emission data under the Z value discrimination method shall be used as the target normal range of carbon emission data; If there is any overlap between the normal range of carbon emission data under the Z-value discrimination method, the normal range of carbon emission data under the quartile discrimination method, and the normal range of carbon emission data under the 595th quartile discrimination method, the normal range of carbon emission data of the overlapping parts shall be taken as the target normal range of carbon emission data; If the normal range of carbon emission data under the Z value discrimination method, the normal range of carbon emission data under the quartile discrimination method, and the normal range of carbon emission data under the 595th quartile discrimination method do not completely overlap, the normal range of carbon emission data of the overlapping part of the three shall be used as the target normal range of carbon emission data; If the normal range of carbon emission data under the Z-value discriminant method, the normal range of carbon emission data under the quartile discriminant method and the normal range of carbon emission data under the 595th quartile discriminant method completely overlap, any one of the normal range of carbon emission data under the Z-value discriminant method, the normal range of carbon emission data under the quartile discriminant method and the normal range of carbon emission data under the 595th quartile discriminant method shall be taken as the target normal range of carbon emission data.

[0014] In a second aspect of an embodiment of the present invention, a device for monitoring abnormal carbon emissions in a coal-fired power plant is provided, comprising: A data acquisition module, used to acquire carbon emission data of coal-fired power plants in multiple time periods; A range determination module is used to process carbon emission data of multiple time periods according to different outlier detection methods to identify the normal range of carbon emission data under different outlier detection methods; A range overlap module is used to determine the normal range of target carbon emission data based on the overlap of normal ranges of carbon emission data under different outlier detection methods; An abnormality determination module, used to determine carbon emission data that is not within the normal range of target carbon emission data as carbon emission data for a target abnormal period; A ratio calculation module is used to calculate the ratio of the amount of carbon emission data in the target abnormal period to the amount of carbon emission data in multiple periods to determine the abnormal carbon emission ratio; The abnormality handling module is used to match the carbon emission abnormality ratio with the preset carbon emission abnormality handling table of the coal-fired power plant to obtain the carbon emission abnormality handling measures; wherein, the preset carbon emission abnormality handling table of the coal-fired power plant includes the mapping relationship between the carbon emission abnormality ratio and the carbon emission abnormality handling measures.

[0015] In a third aspect of the embodiments of the present invention, an electronic device is provided, comprising: a processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the machine-readable instructions are executed by the processor, the above-mentioned method for monitoring abnormal carbon emissions in coal-fired power plants is executed.

[0016] In a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided, storing computer instructions, which, when executed on a computer, enable the computer to execute the above-mentioned method for monitoring abnormal carbon emissions from coal-fired power plants.

[0017] Beneficial effects of the present invention: (1) High anomaly detection accuracy: Using multiple outlier detection methods and combining the normal range overlap of multiple methods to make judgments can improve the accuracy of anomaly detection and avoid false positives and false negatives.

[0018] (2) Rapid location of abnormal periods: Carbon emission data during abnormal periods can be quickly located, thereby helping coal-fired power plants to take timely treatment measures.

[0019] (3) Quantifying the degree of carbon emission abnormality: By calculating the proportion of carbon emission abnormalities, the degree of carbon emission abnormality can be quantified, providing data support for the carbon emission management of coal-fired power plants.

[0020] (4) Abnormal carbon emission handling: According to the preset abnormal handling table, coal-fired power plants can be guided to take corresponding treatment measures to reduce carbon emissions and protect the environment.

[0021] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings: Figure 1 It is a flow chart of a method for monitoring abnormal carbon emissions from a coal-fired power plant provided by an embodiment of the present invention; Figure 2 It is a structural schematic diagram of a device for monitoring abnormal carbon emissions in a coal-fired power plant provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0025] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0026] Embodiment 1 Please refer to Figure 1 , Figure 1 : is a flow chart of a method for monitoring abnormal carbon emissions in a coal-fired power plant provided by an embodiment of the present invention, the method comprising the following steps: S100, obtaining carbon emission data of coal-fired power plants in multiple time periods; It is understandable that the multiple time periods may be time periods arbitrarily selected by the user, and these time periods may be continuous or discontinuous. The embodiment of the present invention does not make any specific limitation on this, and the span of the time periods is also not specifically limited.

[0027] In one embodiment, before step S200, the method further includes: The carbon emission data of coal-fired power plants in multiple time periods are preprocessed; wherein the preprocessing includes: format conversion and interpolation processing.

[0028] In an embodiment of the present invention, format conversion refers to converting raw data from one format to another format that is more suitable for analysis. For example, when processing a global carbon dioxide emissions data set, it may be necessary to filter out certain unnecessary fields, such as the ISO code of the country, or exclude certain specific fields in the data set (such as fields representing global and international emissions). Such conversion makes the data more suitable for subsequent analysis and processing.

[0029] In an embodiment of the present invention, interpolation processing refers to a method for processing missing values ​​or outliers in a data set. In the carbon emission data of coal-fired power plants, the data for certain years or certain countries may be incomplete due to various reasons. Interpolation processing involves using mathematical methods to estimate these missing data points. This can ensure the integrity of the data set and the accuracy of subsequent analysis. For example, the carbon emissions of a country in a specific year can be estimated by interpolation processing, even if this data is missing in the original data set.

[0030] S200, processing carbon emission data of multiple time periods according to different outlier detection methods to identify normal ranges of carbon emission data under different outlier detection methods; In one embodiment, step S200 specifically includes: S210, calculating the carbon emission data of the multiple time periods according to the Z value discrimination method, and determining the standard scores of the carbon emission data of the multiple time periods; The Z-score is a statistical measure that describes the relationship between a value and the mean of a group of values. It represents the standard deviation of an element from the mean.

[0031] Specifically, step S210 includes: S211, calculating the average value of carbon emission data in multiple time periods; S212, calculating the standard deviation of carbon emission data for multiple time periods; Carbon emissions data for each period: S213, using the following formula, calculating the average value of the carbon emission data of multiple time periods, the standard deviation of the carbon emission data of multiple time periods, and the carbon emission data of any time period to obtain a standard score of the carbon emission data of any time period; ;in, Represents the standard score of carbon emission data in any period, Represents the carbon emission data for any period of time, Represents the average value of carbon emission data over multiple periods. Represents the standard deviation of carbon emission data for multiple time periods.

[0032] For ease of understanding, the following is an example of steps S211-S213 with reference to Table 1: Assume that the carbon emission data (in tons) of a coal-fired plant at different times are as shown in Table 1: Table 1 Carbon emission data of coal-fired plants

[0033] Average value = (120+115+125+118+130+122+117+123+119+121+105+110+100) / 13≈1.1731 million tons.

[0034] Standard deviation = √[(120-117.31) 2 + (115-117.31) 2 + (125-117.31) 2 + (118-117.31) 2 + (130-117.31) 2 + (122-117.31) 2 + (117-117.31) 2 + (123-117.31) 2 + (119-117.31) 2 + (121-117.31) 2 + (105-117.31) 2 + (110-117.31) 2 +(100-117.31) 2 ] / 13=78,900 (10,000 tons).

[0035] Calculate the standard score of carbon emission data at each moment: 8-9 o'clock: (120-117.31) / 7.89=0.34 9-10 o'clock: (115-117.31) / 7.89=-0.29 10-11 o'clock: (125-117.31) / 7.89=0.97 11-12 o'clock: (118-117.31) / 7.89=0.09 12-13 o'clock: (130-117.31) / 7.89=1.61 13-14 o'clock: (122-117.31) / 7.89=0.59 14-15 o'clock: (117-117.31) / 7.89=-0.04 15-16 o'clock: (123-117.31) / 7.89=0.72 16-17 o'clock: (119-117.31) / 7.89=0.21 17-18 o'clock: (121-117.31) / 7.89=0.47 18-19 o'clock: (105-117.31) / 7.89=-1.56 19-20 points: (110-117.31) / 7.89=-0.93 20-21 points: (100-117.31) / 7.89=-2.19 S220, determining that the carbon emission data corresponding to the absolute value of the standard score is less than the preset standard score is the carbon emission data of the normal period under the Z value discrimination method, and using the minimum and maximum values ​​of the carbon emission data of the normal period under the Z value discrimination method as boundaries, determining the normal range of the carbon emission data under the Z value discrimination method; It is understandable that since the standard score of carbon emission data may have negative values, but the standard score of carbon emission data represents the relationship between a value and the average of a group of values, the absolute value is needed here to convert the negative standard score of carbon emission data into a positive value.

[0036] In this embodiment, it is assumed that the preset standard score is 1.5, but the embodiment of the present invention does not specifically limit this, and it can be set according to the actual needs of the user.

[0037] Specifically, according to the results calculated earlier, the standard scores whose absolute values ​​are less than the preset standard score (1.5) include 8-9 points (0.34), 9-10 (-0.29), 10-11 points (0.97), 11-12 points (0.09), 13-14 points (0.59), 14-15 points (-0.04), 15-16 points (0.72), 16-17 points (0.21), 17-18 points (0.47) and 19-20 points (-0.93). The carbon emission data corresponding to the standard scores of these 10 time periods are 1.2 million tons, 1.15 million tons, 1.25 million tons, 1.18 million tons, 1.22 million tons, 1.17 million tons, 1.23 million tons, 1.19 million tons, 1.21 million tons and 1.1 million tons. Then the normal range of carbon emission data under the Z value discrimination method is: 1.1 million tons to 1.25 million tons.

[0038] S230, calculating the carbon emission data for multiple time periods according to the quartile discrimination method, and determining the normal range of the carbon emission data under the quartile discrimination method; Specifically, step S230 includes: S231, sorting the carbon emission data of multiple time periods from small to large to obtain sorted carbon emission data of multiple time periods; S232, dividing the sorted carbon emission data of the multiple time periods into four equal parts to obtain four groups of carbon emission data of the multiple time periods; S233, calculating the average of the last carbon emission data in the first group of carbon emission data for multiple time periods and the first carbon emission data in the second group of carbon emission data for multiple time periods to obtain the lower quartile of the carbon emission data; S234, calculating the average of the last carbon emission data in the third group of carbon emission data for multiple time periods and the first carbon emission data in the fourth group of carbon emission data for multiple time periods to obtain the upper quartile of the carbon emission data; S235, calculating the difference between the upper quartile of the carbon emission data and the lower quartile of the carbon emission data to obtain the interquartile range of the carbon emission data; S236, using the following formula, calculating the lower quartile of the carbon emission data, the upper quartile of the carbon emission data, the interquartile range of the carbon emission data, and the first preset coefficient, to obtain the minimum and maximum values ​​of the carbon emission data in the normal period of the quartile discrimination method, and determining the normal range of the carbon emission data under the quartile discrimination method based on the minimum and maximum values ​​of the carbon emission data in the normal period of the quartile discrimination method; ;in, It represents the minimum value of carbon emission data in normal period of quartile discrimination method. It represents the maximum value of carbon emission data in normal period of quartile discrimination method. represents the lower quartile of carbon emission data, represents the upper quartile of carbon emission data, represents the first preset coefficient, Represents the interquartile range of carbon emission data.

[0039] For ease of understanding, the following is an example with reference to Table 2: The carbon emission data for multiple time periods in Table 1 are sorted from small to large, and the sorted results are shown in Table 2 below.

[0040] Table 2 Carbon emission data of coal-fired plants after sorting

[0041] The carbon emission data of multiple time periods after sorting are divided into four equal parts. The results after the division are: the first group of data (100, 105, 110); the second group of data (115, 117, 118); the third group of data (119, 120, 121); the fourth group of data (122, 123, 125 and 130).

[0042] The lower quartile of carbon emission data = (110+115) / 2 = 1.125 million tons.

[0043] The upper quartile of carbon emission data = (121+122) / 2 = 1.215 million tons.

[0044] The interquartile range of carbon emission data = 121.5-112.5 = 90,000 tons.

[0045] Assuming that the first preset coefficient is 2, the minimum value of the carbon emission data during the normal period of the quartile discriminant method = 112.5-2x9 = 945,000 tons, and the maximum value of the carbon emission data during the normal period of the quartile discriminant method = 121.5+2x9 = 139.5 million tons.

[0046] Finally, the normal range of carbon emission data under the quartile discrimination method is: 945,000 tons to 1.395 million tons.

[0047] S240, calculating the carbon emission data of multiple time periods according to the 595th quantile discrimination method, and determining the normal range of the carbon emission data under the 595th quantile discrimination method.

[0048] Specifically, step S240 includes: S241, sorting the carbon emission data of multiple time periods from small to large to obtain sorted carbon emission data of multiple time periods; S242, dividing the sorted carbon emission data of the multiple time periods into five equal parts to obtain five groups of carbon emission data of the multiple time periods; S243, calculating the average of the last carbon emission data in the first group of carbon emission data for multiple time periods and the first carbon emission data in the second group of carbon emission data for multiple time periods to obtain the quintile of the carbon emission data; S244, taking the first carbon emission data in the fifth group of carbon emission data for multiple time periods as the 95th percentile of the carbon emission data; S245, using the following formula, calculating the quintile of carbon emission data, the 95th quantile of carbon emission data, and the second preset coefficient, to obtain the minimum and maximum values ​​of carbon emission data in a normal period of the 95th quantile discrimination method, and determining the normal range of carbon emission data under the 95th quantile discrimination method based on the minimum and maximum values ​​of carbon emission data in a normal period of the 95th quantile discrimination method; ;in, It represents the minimum value of carbon emission data in normal period of the 95th percentile discrimination method. It represents the maximum value of carbon emission data in normal period of the 95th percentile discrimination method. represents the quintile of carbon emission data, represents the 95th percentile of carbon emission data, Indicates the second preset coefficient.

[0049] For ease of understanding, the following is an example with reference to Table 2 above: The carbon emission data for multiple time periods in Table 1 are sorted from small to large, and the sorted results are shown in Table 2 below.

[0050] Table 2 Carbon emission data of coal-fired plants after sorting

[0051] The carbon emission data of multiple time periods after sorting were divided into five equal parts. The results after division were: the first group of data (100, 105, 110); the second group of data (115, 117); the third group of data (118, 119); the fourth group of data (120, 121); the fifth group of data (122, 123, 125, 130).

[0052] The quintile of carbon emission data = (110+115) / 2 = 1.125 million tons.

[0053] The 95th percentile of carbon emissions data = 1.22 million tons.

[0054] Assuming that the first preset coefficient is 3, the minimum value of the carbon emission data during the normal period of the quartile discriminant method = 112.5-3x (122-112.5) = 840,000 tons, and the maximum value of the carbon emission data during the normal period of the quartile discriminant method = 122 + 3x (122-112.5) = 1.505 million tons.

[0055] Finally, the normal range of carbon emission data under the 95th percentile discrimination method is: 840,000 tons to 1.505 million tons.

[0056] S300, determining a normal range of target carbon emission data based on overlaps of normal ranges of carbon emission data under different outlier detection methods; In one embodiment, step S300 specifically includes: S310, if the normal range of carbon emission data under the Z value discrimination method, the normal range of carbon emission data under the quartile discrimination method, and the normal range of carbon emission data under the 595th quartile discrimination method do not overlap with each other, the normal range of carbon emission data under the Z value discrimination method is used as the target normal range of carbon emission data; S320, if there is any overlap between the normal range of carbon emission data under the Z value discrimination method, the normal range of carbon emission data under the quartile discrimination method, and the normal range of carbon emission data under the 595th quartile discrimination method, then the normal range of carbon emission data of the overlapping parts is used as the target normal range of carbon emission data; S330, if the normal range of carbon emission data under the Z value discrimination method, the normal range of carbon emission data under the quartile discrimination method, and the normal range of carbon emission data under the 595th quartile discrimination method do not completely overlap, the normal range of carbon emission data of the overlapping part of the three is used as the target normal range of carbon emission data; S340, if the normal range of carbon emission data under the Z value discrimination method, the normal range of carbon emission data under the quartile discrimination method and the normal range of carbon emission data under the 595th quartile discrimination method completely overlap, then any one of the normal range of carbon emission data under the Z value discrimination method, the normal range of carbon emission data under the quartile discrimination method and the normal range of carbon emission data under the 595th quartile discrimination method shall be used as the target normal range of carbon emission data.

[0057] For ease of understanding, the following is an explanation of the normal range of carbon emission data under the Z value discrimination method, the normal range of carbon emission data under the quartile discrimination method, and the normal range of carbon emission data under the 595th quartile discrimination method obtained from Tables 1 and 2: Based on the above, the normal range of carbon emission data under the Z-value discrimination method is: 1.1 million tons to 1.25 million tons; the normal range of carbon emission data under the quartile discrimination method is: 945,000 tons to 1.395 million tons; the normal range of carbon emission data under the 95th quartile discrimination method is: 840,000 tons to 1.505 million tons.

[0058] When the three are overlapped, it is found that they are not completely overlapping. Therefore, the normal range of carbon emission data of the overlapping part is taken as the target carbon emission data normal range, that is, 1.1 million tons to 1.25 million tons.

[0059] It is understandable that the overlapping situation in the above embodiment is incomplete overlapping, and the other three overlapping situations can be deduced by analogy, which will not be described in detail here.

[0060] S400, determining carbon emission data that is not within the normal range of target carbon emission data as carbon emission data for a target abnormal period; Specifically, according to step S300, the normal range of the target carbon emission data calculated is 1.1 million tons to 1.25 million tons. Then, referring to Table 1 or Table 2 above, it can be known that there are three carbon emission data that are not within the range of 1.1 million tons to 1.25 million tons, namely, the carbon emission data at 12-13 o'clock (1.3 million tons), the carbon emission data at 18-19 o'clock (1.05 million tons) and the carbon emission data at 20-21 o'clock (1 million tons).

[0061] S500, calculating the ratio of the amount of carbon emission data in the target abnormal period to the amount of carbon emission data in multiple periods, and determining the abnormal proportion of carbon emissions; Specifically, according to step S400, it is determined that the number of carbon emission data in the target abnormal period is 3, and the number of carbon emission data in multiple periods is 13, then the carbon emission abnormality accounts for 3 / 13.

[0062] S600, matching the carbon emission anomaly ratio with the preset carbon emission anomaly processing table of the coal-fired power plant to obtain carbon emission anomaly processing measures; wherein the preset carbon emission anomaly processing table of the coal-fired power plant includes a mapping relationship between the carbon emission anomaly ratio and the carbon emission anomaly processing measures.

[0063] For ease of understanding, the following is explained with reference to Table 3: Table 3 Abnormal carbon emission treatment table for pre-set coal-fired power plants

[0064] The abnormality ratio calculated in step S500 is 3 / 13, and 3 / 13 is within the range of 0-30%, so the corresponding processing measures are: 1. Check the faulty equipment immediately; 2. Perform necessary repairs or replace parts; 3. Review the operation log to find out the erroneous operation; 4. Re-educate and train the operators; 5. Check the sensors and monitoring system; 6. Recalibrate the equipment; 7. Confirm that the data transmission is correct.

[0065] Beneficial effects of the present invention: (1) High anomaly detection accuracy: Using multiple outlier detection methods and combining the normal range overlap of multiple methods to make judgments can improve the accuracy of anomaly detection and avoid false positives and false negatives.

[0066] (2) Rapid location of abnormal periods: Carbon emission data during abnormal periods can be quickly located, thereby helping coal-fired power plants to take timely treatment measures.

[0067] (3) Quantifying the degree of carbon emission abnormality: By calculating the proportion of carbon emission abnormalities, the degree of carbon emission abnormality can be quantified, providing data support for the carbon emission management of coal-fired power plants.

[0068] (4) Abnormal carbon emission handling: According to the preset abnormal handling table, coal-fired power plants can be guided to take corresponding treatment measures to reduce carbon emissions and protect the environment.

[0069] Embodiment 2 Based on the same inventive concept, Figure 2 As shown, the embodiment of the present invention further provides a device 200 for monitoring abnormal carbon emissions in a coal-fired power plant, comprising: The data acquisition module 210 is used to acquire carbon emission data of a coal-fired power plant in multiple time periods; A range determination module 20 is used to process carbon emission data of multiple time periods according to different outlier detection methods to identify normal ranges of carbon emission data under different outlier detection methods; A range overlap module 230, configured to determine a normal range of target carbon emission data based on overlaps of normal ranges of carbon emission data under different outlier detection methods; An abnormality determination module 240, used to determine carbon emission data that is not within the normal range of target carbon emission data as carbon emission data of a target abnormal period; The ratio calculation module 250 is used to calculate the ratio of the amount of carbon emission data in the target abnormal period to the amount of carbon emission data in multiple periods to determine the abnormal carbon emission ratio; The exception handling module 260 is used to match the carbon emission exception ratio with the preset carbon emission exception handling table of the coal-fired power plant to obtain carbon emission exception handling measures; wherein the preset carbon emission exception handling table of the coal-fired power plant includes a mapping relationship between the carbon emission exception ratio and the carbon emission exception handling measures.

[0070] It should be understood that the device corresponds to the above-mentioned coal-fired power plant carbon emission abnormality monitoring method embodiment, and can execute the various steps involved in the above-mentioned method embodiment. The specific functions of the device can be found in the description above. To avoid repetition, the detailed description is appropriately omitted here. The device includes at least one software function module that can be stored in a memory in the form of software or firmware or fixed in the operating system (OS) of the device.

[0071] Embodiment 3 Based on the same inventive concept, an embodiment of the present invention also provides an electronic device, including: a processor and a memory, the memory storing machine-readable instructions executable by the processor, and the machine-readable instructions, when executed by the processor, execute the above-mentioned method for monitoring abnormal carbon emissions from coal-fired power plants.

[0072] In a typical configuration, an electronic device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0073] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0074] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0075] Embodiment 4 Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium storing computer instructions. When the computer instructions are executed on a computer, the computer executes the above-mentioned method for monitoring abnormal carbon emissions from coal-fired power plants.

[0076] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0077] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0078] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0079] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0080] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not further describe various possible combinations.

[0081] In addition, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part.

[0082] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0083] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for monitoring abnormal carbon emissions in a coal-fired power plant, characterized in that: include: Obtain carbon emission data for coal-fired power plants over multiple time periods; According to different outlier detection methods, the carbon emission data of multiple time periods are processed to identify the normal range of carbon emission data under different outlier detection methods; Based on the overlap of normal ranges of carbon emission data under different outlier detection methods, the normal range of target carbon emission data is determined; Determine the carbon emission data that is not within the normal range of the target carbon emission data as the carbon emission data for the target abnormal period; Calculate the ratio of the number of carbon emission data in the target abnormal period to the number of carbon emission data in multiple periods to determine the abnormal proportion of carbon emissions; The carbon emission abnormality ratio is matched with the preset carbon emission abnormality processing table of the coal-fired power plant to obtain the carbon emission abnormality processing measures; wherein, the preset carbon emission abnormality processing table of the coal-fired power plant includes the mapping relationship between the carbon emission abnormality ratio and the carbon emission abnormality processing measures.

2. The method for monitoring abnormal carbon emissions in a coal-fired power plant according to claim 1, characterized in that: According to different outlier detection methods, the carbon emission data of multiple time periods are processed to identify the normal range of carbon emission data under different outlier detection methods, and the step also includes: The carbon emission data of coal-fired power plants in multiple time periods are preprocessed; wherein the preprocessing includes: format conversion and interpolation processing.

3. The method for monitoring abnormal carbon emissions in a coal-fired power plant according to claim 1, characterized in that: According to different outlier detection methods, the carbon emission data of multiple time periods are processed to identify the normal range of carbon emission data under different outlier detection methods, including: According to the Z-value discrimination method, the carbon emission data of multiple time periods are calculated to determine the standard scores of the carbon emission data of multiple time periods; Determine the carbon emission data corresponding to the standard score whose absolute value is less than the preset standard score as the carbon emission data of the normal period under the Z value discrimination method, and use the minimum and maximum values ​​of the carbon emission data of the normal period under the Z value discrimination method as boundaries to determine the normal range of carbon emission data under the Z value discrimination method; According to the quartile discrimination method, the carbon emission data of multiple time periods are calculated to determine the normal range of carbon emission data under the quartile discrimination method; Based on the 595th quantile discrimination method, the carbon emission data of multiple time periods are calculated to determine the normal range of carbon emission data under the 595th quantile discrimination method.

4. The method for monitoring abnormal carbon emissions in a coal-fired power plant according to claim 3, characterized in that: Based on the Z-value discrimination method, the carbon emission data of multiple periods are calculated to determine the standard scores of the carbon emission data of multiple periods, including: Calculate the average of carbon emission data for multiple periods; Calculate the standard deviation of carbon emission data for multiple time periods; Carbon emissions data for each period: The following formula is used to calculate the average value of carbon emission data in multiple periods, the standard deviation of carbon emission data in multiple periods and the carbon emission data in any period to obtain the standard score of carbon emission data in any period; ;in, Represents the standard score of carbon emission data in any period, Represents the carbon emission data for any period of time, Represents the average value of carbon emission data over multiple periods. Represents the standard deviation of carbon emission data for multiple time periods.

5. The method for monitoring abnormal carbon emissions in a coal-fired power plant according to claim 3, characterized in that: Based on the quartile discrimination method, the carbon emission data of multiple periods are calculated to determine the normal range of carbon emission data under the quartile discrimination method, including: Sort the carbon emission data of multiple time periods from small to large to obtain sorted carbon emission data of multiple time periods; Divide the sorted carbon emission data of multiple time periods into four equal parts to obtain four groups of carbon emission data of multiple time periods; Calculate the average of the last carbon emission data in the first group of carbon emission data for multiple time periods and the first carbon emission data in the second group of carbon emission data for multiple time periods to obtain the lower quartile of the carbon emission data; Calculate the average of the last carbon emission data in the third group of carbon emission data for multiple time periods and the first carbon emission data in the fourth group of carbon emission data for multiple time periods to obtain the upper quartile of the carbon emission data; Calculate the difference between the upper quartile of carbon emission data and the lower quartile of carbon emission data to obtain the interquartile range of carbon emission data; The following formula is used to calculate the lower quartile of carbon emission data, the upper quartile of carbon emission data, the interquartile range of carbon emission data and the first preset coefficient to obtain the minimum and maximum values ​​of carbon emission data in the normal period of the quartile discrimination method, and the normal range of carbon emission data under the quartile discrimination method is determined based on the minimum and maximum values ​​of carbon emission data in the normal period of the quartile discrimination method; ;in, It represents the minimum value of carbon emission data in normal period of quartile discrimination method. It represents the maximum value of carbon emission data in normal period of quartile discrimination method. represents the lower quartile of carbon emission data, represents the upper quartile of carbon emission data, represents the first preset coefficient, Represents the interquartile range of carbon emission data.

6. The method for monitoring abnormal carbon emissions in coal-fired power plants according to claim 3, characterized in that: Based on the 595th percentile discrimination method, the carbon emission data of multiple time periods are calculated to determine the normal range of carbon emission data under the 595th percentile discrimination method, including: Sort the carbon emission data of multiple time periods from small to large to obtain sorted carbon emission data of multiple time periods; Divide the sorted carbon emission data of multiple time periods into five equal parts to obtain five groups of carbon emission data of multiple time periods; Calculate the average of the last carbon emission data in the first group of carbon emission data for multiple time periods and the first carbon emission data in the second group of carbon emission data for multiple time periods to obtain the quintile of the carbon emission data; The first carbon emission data in the fifth group of carbon emission data for multiple time periods is taken as the 95th percentile of the carbon emission data; The following formula is used to calculate the quintile of carbon emission data, the ninety-fifth quantile of carbon emission data, and the second preset coefficient to obtain the minimum and maximum values ​​of carbon emission data during the normal period of the ninety-fifth quantile discrimination method, and the normal range of carbon emission data under the ninety-fifth quantile discrimination method is determined based on the minimum and maximum values ​​of carbon emission data during the normal period of the ninety-fifth quantile discrimination method; ;in, It represents the minimum value of carbon emission data in normal period of the 95th percentile discrimination method. It represents the maximum value of carbon emission data in normal period of the 95th percentile discrimination method. represents the quintile of carbon emission data, represents the 95th percentile of carbon emission data, Indicates the second preset coefficient.

7. The method for monitoring abnormal carbon emissions in a coal-fired power plant according to claim 3, characterized in that: Based on the overlap of the normal range of carbon emission data under different outlier detection methods, the normal range of target carbon emission data is determined, including: If the normal range of carbon emission data under the Z value discrimination method, the normal range of carbon emission data under the quartile discrimination method, and the normal range of carbon emission data under the 595th quartile discrimination method do not overlap with each other, the normal range of carbon emission data under the Z value discrimination method shall be used as the target normal range of carbon emission data; If there is any overlap between the normal range of carbon emission data under the Z-value discrimination method, the normal range of carbon emission data under the quartile discrimination method, and the normal range of carbon emission data under the 595th quartile discrimination method, the normal range of carbon emission data of the overlapping parts shall be taken as the target normal range of carbon emission data; If the normal range of carbon emission data under the Z value discrimination method, the normal range of carbon emission data under the quartile discrimination method, and the normal range of carbon emission data under the 595th quartile discrimination method do not completely overlap, the normal range of carbon emission data of the overlapping part of the three shall be used as the target normal range of carbon emission data; If the normal range of carbon emission data under the Z-value discriminant method, the normal range of carbon emission data under the quartile discriminant method and the normal range of carbon emission data under the 595th quartile discriminant method completely overlap, any one of the normal range of carbon emission data under the Z-value discriminant method, the normal range of carbon emission data under the quartile discriminant method and the normal range of carbon emission data under the 595th quartile discriminant method shall be taken as the target normal range of carbon emission data.

8. A device for monitoring abnormal carbon emissions in a coal-fired power plant, characterized in that: include: A data acquisition module, used to acquire carbon emission data of coal-fired power plants in multiple time periods; A range determination module is used to process carbon emission data of multiple time periods according to different outlier detection methods to identify the normal range of carbon emission data under different outlier detection methods; A range overlap module is used to determine the normal range of target carbon emission data based on the overlap of normal ranges of carbon emission data under different outlier detection methods; An abnormality determination module, used to determine carbon emission data that is not within the normal range of target carbon emission data as carbon emission data for a target abnormal period; A ratio calculation module is used to calculate the ratio of the amount of carbon emission data in the target abnormal period to the amount of carbon emission data in multiple periods to determine the abnormal carbon emission ratio; The abnormality handling module is used to match the carbon emission abnormality ratio with the preset carbon emission abnormality handling table of the coal-fired power plant to obtain the carbon emission abnormality handling measures; wherein, the preset carbon emission abnormality handling table of the coal-fired power plant includes the mapping relationship between the carbon emission abnormality ratio and the carbon emission abnormality handling measures.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the machine-readable instructions are executed by the processor, the method for monitoring abnormal carbon emissions from a coal-fired power plant according to any one of claims 1 to 7 is executed.

10. A computer-readable storage medium storing computer instructions, characterized in that: When the computer instructions are executed on a computer, the computer is enabled to execute the method for monitoring abnormal carbon emissions from a coal-fired power plant as described in any one of claims 1 to 7.

Images