Regional carbon emission analysis and early warning system and method based on big data
Through the regional carbon emission analysis and early warning system based on big data, the use of historical data to establish prediction models and real-time detection has solved the problem of insufficient prediction in carbon emission monitoring, achieved accurate prediction and timely early warning of carbon emissions, and supported scientific carbon emission management.
Patent Information
- Application Number
- CN202510655552.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-21
- Publication Date
- 2025-09-16
AI Technical Summary
Carbon emission monitoring in existing technologies can only collect data in real time and cannot effectively predict, resulting in the inability to prevent excessive carbon emissions in a timely manner, affecting the implementation of energy-saving and emission reduction policies.
By establishing a regional carbon emission analysis and early warning system based on big data, using historical data to build a prediction model, real-time detection of coal weight and type, setting carbon emission thresholds, sending early warning signals, and adjusting the sampling frequency and correcting model parameters after receiving the warning, accurate prediction of carbon emissions and timely early warning can be achieved.
It achieves accurate prediction and timely warning of carbon emissions, ensures that combustion activities are carried out within a reasonable range, improves the accuracy of prediction and response speed, and supports scientific carbon emission management.
Smart Images
Figure CN120654930A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of carbon emission detection technology, and in particular to a regional carbon emission analysis and early warning system and method based on big data. Background Art
[0002] Greenhouse gas emissions, often referred to as carbon emissions, are primarily carbon dioxide (CO2). The combustion of fossil fuels continuously releases large amounts of CO2 and other greenhouse gases into the atmosphere, which is considered a core driver of global climate change. To effectively address climate change, it is necessary to quantify CO2 emission levels and develop scientific reduction strategies based on monitoring data.
[0003] Existing technologies use real-time monitoring to control carbon emissions. Carbon emission data can only be obtained after the monitoring equipment collects the specific carbon emissions at the current moment. It is impossible to effectively predict carbon emissions. If excessive carbon emissions cannot be stopped in time, it will be detrimental to the implementation of energy conservation and emission reduction policies. Summary of the Invention
[0004] The purpose of the present invention is to provide a regional carbon emission analysis and early warning system and method based on big data to solve the problems raised in the prior art.
[0005] To achieve the above objectives, the present invention provides the following technical solution: a regional carbon emission analysis and early warning method based on big data, the method comprising the following steps:
[0006] Step S1: Obtain historical data on the weight of coal used for power generation in the monitoring area, historical data on the type of coal, and historical data on carbon emissions generated by the weight of the coal consumed; and establish a prediction model for the same type of coal based on the historical data;
[0007] Step S2: Obtain the weight and type of the coal to be tested in the monitoring area, predict the carbon emissions generated by the combustion of the coal to be tested using a prediction model, and obtain predicted carbon emissions and predicted total carbon emissions; set a carbon emission threshold; if the predicted total carbon emissions are less than the carbon emission threshold, burn the coal normally; if the predicted total carbon emissions are greater than or equal to the carbon emission threshold, send an early warning signal to the user terminal;
[0008] Step S3: preset a sampling frequency, and detect the actual coal consumption weight and actual carbon emissions of the coal to be tested according to the sampling frequency; and modify the parameters of the model according to the actual coal consumption weight and the actual carbon emissions;
[0009] Step S4: When the warning signal 1 is received, the sampling frequency is adjusted to generate a new sampling frequency, the actual carbon emissions of the coal to be tested are detected according to the new sampling frequency, and the real-time carbon emissions are compared with the predicted carbon emissions; an accuracy threshold is set, and an accuracy probability value is calculated based on the comparison result. If the accuracy probability value is greater than or equal to the accuracy threshold, a warning signal 2 is sent to the user terminal.
[0010] Furthermore, step S1 includes the following specific steps:
[0011] The monitoring area is a spatial area where carbon emissions monitoring is required; historical data on the weight of coal used for power generation each time for the same type of coal in the monitoring area is linearly correlated with historical data on carbon emissions generated by the weight of the coal consumed, a slope parameter of the linear correlation is obtained by the least squares method, and a prediction model is established using the slope parameter of the linear correlation, the prediction model comprising:
[0012] C=βM
[0013]
[0014] Where C is the carbon emissions generated by the weight of coal consumed, β is the slope parameter, M is the weight of coal consumed, i is the number of sampling times, n is the total number of samples in the historical data, and M i is the weight of coal consumed during the i-th sampling, C i is the carbon emission at the time of sampling i; each type of coal corresponds to an independent slope parameter.
[0015] Furthermore, step S2 includes the following specific steps:
[0016] A pressure-resistant weighing coal feeder is provided at the entrance of the monitoring area, and the weight of the coal to be tested is detected by using the weighing coal feeder; the coal to be tested is sampled, and the type of the coal to be tested is determined by an industrial analyzer;
[0017] The coal weight and coal type of the coal to be tested are input into the prediction model to obtain the predicted carbon emissions, and a predicted carbon emissions graph is drawn with the consumed coal weight as the horizontal axis and the carbon emissions generated by the consumed coal weight as the vertical axis; the starting point of the predicted carbon emissions graph is the coordinate origin, and the end point is the point corresponding to when the consumed coal weight reaches the maximum, and the vertical coordinate value of the end point is the predicted total carbon emissions.
[0018] Furthermore, step S3 includes the following specific steps:
[0019] A belt electronic scale and a CEMS system are provided in the monitoring area, the actual coal consumption weight of the coal to be tested is obtained by the belt electronic scale, and the actual carbon emissions are detected by the CEMS system; an actual carbon emissions graph is generated based on the actual coal consumption weight and the actual carbon emissions, and the horizontal and vertical coordinates and starting points of the actual carbon emissions graph and the predicted carbon emissions graph are the same;
[0020] Compare the actual carbon emissions and the predicted carbon emissions when the same weight of coal is consumed. If the actual carbon emissions are different from the predicted carbon emissions, the actual coal weight consumed and the actual carbon emissions of the current coal to be tested are input into the prediction model, and the parameters of the prediction model are corrected. The parameter correction process includes:
[0021]
[0022] where β new is the corrected slope parameter, M new is the actual coal consumption weight, C new is the actual carbon emission; the corrected slope parameter is used as the slope parameter of the prediction model.
[0023] Furthermore, step S4 includes the following specific steps:
[0024] A seriously excessive carbon emissions threshold is preset, and the seriously excessive carbon emissions threshold is greater than the carbon emissions threshold; when the first warning signal is received, if the predicted total carbon emissions are less than the seriously excessive carbon emissions threshold, the preset sampling frequency is doubled; if the predicted total carbon emissions are greater than or equal to the seriously excessive carbon emissions threshold, the preset sampling frequency is doubled to obtain a new sampling frequency;
[0025] Set a calibration time, compare the real-time carbon emissions and the predicted carbon emissions based on the new sampling frequency within the calibration time, and record the number of accurate predictions, which is the number of times the real-time carbon emissions and the predicted carbon emissions are within the error; at the end of the calibration time, calculate the percentage of the accurate prediction number to the number of sampling times within the calibration time to obtain the accuracy probability value.
[0026] A regional carbon emission analysis and early warning system based on big data, the system comprising a data acquisition module, a database module, a data analysis module, a trimming module, and an early warning module; the data acquisition module acquires the weight and type of coal to be tested in the monitoring area, as well as the actual weight of coal consumed and the actual carbon emissions; the database module establishes and stores the prediction model and stores historical data at the same time; the data analysis module obtains predicted carbon emissions through the prediction model in the database module based on the data collected by the data acquisition module, and draws a predicted carbon emissions graph; the early warning module determines whether to issue an early warning signal by comparing the predicted total carbon emissions with a carbon emission threshold, and determines whether to issue an early warning signal based on an accurate threshold; the trimming module corrects the prediction model in the database module and adjusts the sampling frequency;
[0027] The output end of the data acquisition module is electrically connected to the input end of the database module; the output end of the database module is electrically connected to the input end of the data analysis module; the output end of the data analysis module is electrically connected to the input end of the trimming module and the input end of the early warning module; the output end of the trimming module is electrically connected to the input end of the database module and the input end of the early warning module.
[0028] The data acquisition module includes an initial sampling unit and a real-time sampling unit; the initial sampling unit uses a pressure-resistant weighing coal feeder to weigh and sample the coal to be tested and determines the type of coal through an industrial analyzer; the real-time sampling unit obtains the actual weight of coal consumed and the actual carbon emissions through a belt electronic scale and a CEMS system;
[0029] The database module includes a modeling unit and a storage unit; the modeling unit performs modeling according to coal weight and coal type; the storage unit is used to store prediction models, historical data and data obtained by real-time detection; and the data in the storage unit can be manually modified.
[0030] The data analysis module includes a calculation unit and a drawing unit; the calculation unit derives the predicted carbon emissions based on the data in the database module; the drawing unit is used to draw a graph of actual carbon emissions and a graph of predicted carbon emissions.
[0031] The early warning module includes a signal unit 1 and a signal unit 2; the signal unit 1 is used to compare the predicted total carbon emissions and the carbon emissions threshold to determine whether to issue an early warning signal 1; the signal unit 2 is used to compare the accurate probability value and the accurate threshold to determine whether to issue an early warning signal 2.
[0032] The trimming module includes a model correction unit and a frequency adjustment unit; the model correction unit corrects the data in the database module according to the data in the data result module; the frequency adjustment unit adjusts the sampling frequency when receiving the warning signal.
[0033] Compared with the prior art, the present invention has the following beneficial effects:
[0034] 1. This invention acquires historical data on coal-fired power generation in the monitored area and establishes a prediction model for each type of coal, accurately predicting the carbon emissions of the coal after combustion. Setting carbon emission thresholds for early warning allows users to promptly monitor carbon emissions and avoid excessive emissions. This provides an effective basis for preliminary regional carbon emissions control and ensures that power generation activities remain within a reasonable carbon emission range.
[0035] 2. This invention improves prediction accuracy by monitoring the actual coal consumption and carbon emissions of the coal being tested in real time. It then adjusts the prediction model parameters and receives an early warning signal. It then compares the real-time and predicted carbon emissions, calculates the probability of an error, and issues an early warning, enabling a more timely and accurate response to abnormal carbon emissions.
[0036] 3. This invention builds a modular system, enabling each module to work collaboratively to achieve data collection, model building, analysis and prediction, model correction, and early warning functions. With a clear system structure and distinct division of labor among units, it can efficiently and comprehensively analyze and provide early warnings for regional carbon emissions, helping regions achieve scientific carbon emissions management. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] Figure 1 This is a flow chart of a regional carbon emission analysis and early warning method based on big data according to the present invention;
[0038] Figure 2 This is a structural schematic diagram of a regional carbon emission analysis and early warning method based on big data of the present invention. DETAILED DESCRIPTION
[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only 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 ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.
[0040] Example 1: Figure 1 As shown, the present invention provides a technical solution, a regional carbon emission analysis and early warning method based on big data, the regional carbon emission analysis and early warning method comprises the following steps:
[0041] Step S1: Obtain historical data on the weight of coal used for power generation in the monitoring area, historical data on the type of coal, and historical data on carbon emissions generated by the weight of the coal consumed; and establish a prediction model for the same type of coal based on the historical data;
[0042] The monitoring area is a spatial area where carbon emissions monitoring is required; historical data on the weight of coal used for power generation each time for the same type of coal in the monitoring area is linearly correlated with historical data on carbon emissions generated by the weight of the coal consumed, a slope parameter of the linear correlation is obtained by the least squares method, and a prediction model is established using the slope parameter of the linear correlation, the prediction model comprising:
[0043] C=βM
[0044]
[0045] Where C is the carbon emissions generated by the weight of coal consumed, β is the slope parameter, M is the weight of coal consumed, i is the number of sampling times, n is the total number of samples in the historical data, and M i is the weight of coal consumed during the i-th sampling, C i is the carbon emission at the time of sampling i; each type of coal corresponds to an independent slope parameter.
[0046] Step S2: Obtain the weight and type of the coal to be tested in the monitoring area, predict the carbon emissions generated by the combustion of the coal to be tested using a prediction model, and obtain predicted carbon emissions and predicted total carbon emissions; set a carbon emission threshold; if the predicted total carbon emissions are less than the carbon emission threshold, burn the coal normally; if the predicted total carbon emissions are greater than or equal to the carbon emission threshold, send an early warning signal to the user terminal;
[0047] A pressure-resistant weighing coal feeder is provided at the entrance of the monitoring area, and the weight of the coal to be tested is detected by using the weighing coal feeder; the coal to be tested is sampled, and the type of the coal to be tested is determined by an industrial analyzer;
[0048] The coal weight and coal type of the coal to be tested are input into the prediction model to obtain the predicted carbon emissions, and a predicted carbon emissions graph is drawn with the consumed coal weight as the horizontal axis and the carbon emissions generated by the consumed coal weight as the vertical axis; the starting point of the predicted carbon emissions graph is the coordinate origin, and the end point is the point corresponding to when the consumed coal weight reaches the maximum, and the vertical coordinate value of the end point is the predicted total carbon emissions.
[0049] Step S3: preset a sampling frequency, and detect the actual coal consumption weight and actual carbon emissions of the coal to be tested according to the sampling frequency; and modify the parameters of the model according to the actual coal consumption weight and the actual carbon emissions;
[0050] A belt electronic scale and a CEMS system are provided in the monitoring area, the actual coal consumption weight of the coal to be tested is obtained by the belt electronic scale, and the actual carbon emissions are detected by the CEMS system; an actual carbon emissions graph is generated based on the actual coal consumption weight and the actual carbon emissions, and the horizontal and vertical coordinates and starting points of the actual carbon emissions graph and the predicted carbon emissions graph are the same;
[0051] Compare the actual carbon emissions and the predicted carbon emissions when the same weight of coal is consumed. If the actual carbon emissions are different from the predicted carbon emissions, the actual coal weight consumed and the actual carbon emissions of the current coal to be tested are input into the prediction model, and the parameters of the prediction model are corrected. The parameter correction process includes:
[0052]
[0053] where β new is the corrected slope parameter, M new is the actual coal consumption weight, C new is the actual carbon emission; the corrected slope parameter is used as the slope parameter of the prediction model.
[0054] Step S4: When the warning signal 1 is received, the sampling frequency is adjusted to generate a new sampling frequency, the actual carbon emissions of the coal to be tested are detected according to the new sampling frequency, and the real-time carbon emissions are compared with the predicted carbon emissions; an accuracy threshold is set, and an accuracy probability value is calculated based on the comparison result. If the accuracy probability value is greater than or equal to the accuracy threshold, a warning signal 2 is sent to the user terminal.
[0055] A seriously excessive carbon emissions threshold is preset, and the seriously excessive carbon emissions threshold is greater than the carbon emissions threshold; when the first warning signal is received, if the predicted total carbon emissions are less than the seriously excessive carbon emissions threshold, the preset sampling frequency is doubled; if the predicted total carbon emissions are greater than or equal to the seriously excessive carbon emissions threshold, the preset sampling frequency is doubled to obtain a new sampling frequency;
[0056] Set a calibration time, compare the real-time carbon emissions and the predicted carbon emissions based on the new sampling frequency within the calibration time, and record the number of accurate predictions, which is the number of times the real-time carbon emissions and the predicted carbon emissions are within the error; at the end of the calibration time, calculate the percentage of the accurate prediction number to the number of sampling times within the calibration time to obtain the accuracy probability value.
[0057] For example:
[0058] There are three sets of historical data on anthracite in the monitoring area:
[0059] M1=2 tons C1=8.5 tons
[0060] M2=7 tons C2=20 tons
[0061] M3=15 tons C3=42 tons
[0062] According to the formula
[0063] C=βM
[0064]
[0065] We can get β≈2.811 C=2.811M
[0066] The coal to be tested in the current monitoring area is 10 tons of anthracite, and the preset carbon emission threshold is 25 tons. Based on the prediction model C = 2.811M, a carbon emission prediction map is obtained, and the total carbon emissions are predicted to be 28.11 tons. The predicted total carbon emissions exceed the preset carbon emission threshold, and an early warning signal is sent to the user terminal.
[0067] When the actual coal consumption is 4 tons, the actual carbon emissions are 12 tons and the predicted carbon emissions are 11.244 tons. Based on the parameter correction process
[0068]
[0069] We can get β new =2.821, the revised prediction model is C=2.821M
[0070] The preset sampling frequency is 2 times per hour, each time for 30 minutes. The threshold for serious excess carbon emissions is 30 tons. The predicted carbon emissions obtained in step S2 are 28.11 tons, which is less than the threshold for serious excess carbon emissions. The sampling frequency is adjusted to 4 times per hour, each time for 15 minutes.
[0071] At this time, sampling 4 times and calculating the error respectively get the following data:
[0072] The actual coal consumption is 1 ton, the actual carbon emissions are 3 tons, the predicted carbon emissions are 2.821 tons, and the calculation error is
[0073] The actual coal consumption is 3 tons, the actual carbon emissions are 8.47 tons, the predicted carbon emissions are 8.463 tons, and the calculation error is
[0074] The actual coal consumption is 5 tons, the actual carbon emissions are 16.52 tons, the predicted carbon emissions are 14.105 tons, and the calculation error is
[0075] The actual coal consumption was 7 tons, the actual carbon emissions were 20.12 tons, and the predicted carbon emissions were 19.677 tons. The calculation error is
[0076] The preset error is 10%, the accuracy threshold is 60%, and the accuracy is If the accuracy probability value is greater than the accuracy threshold, the warning signal 1 is considered accurate and the warning signal 2 is sent to the user terminal.
[0077] Example 2: Figure 2 As shown, the present invention provides a regional carbon emission analysis and early warning system based on big data, which includes a data acquisition module, a database module, a data analysis module, a trimming module, and an early warning module;
[0078] The data acquisition module obtains the weight and type of the coal to be tested in the monitoring area, as well as the actual weight of the coal consumed and the actual carbon emissions;
[0079] The database module establishes and stores the prediction model and stores historical data;
[0080] The data analysis module obtains predicted carbon emissions through the prediction model in the database module based on the data collected by the data collection module, and draws a predicted carbon emissions graph;
[0081] The warning module determines whether to issue a warning signal by comparing the predicted total carbon emissions with the carbon emissions threshold, and determines whether to issue a warning signal according to the accurate threshold.
[0082] The trimming module amends the prediction model in the database module and adjusts the sampling frequency;
[0083] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.
Claims
1. A regional carbon emission analysis and early warning method based on big data, characterized by: The method comprises the following steps: Step S1: Obtain historical data on the weight of coal used for power generation in the monitoring area, historical data on the type of coal, and historical data on carbon emissions generated by the weight of the coal consumed; and establish a prediction model for the same type of coal based on the historical data; Step S2: Obtain the weight and type of the coal to be tested in the monitoring area, predict the carbon emissions generated by the combustion of the coal to be tested using a prediction model, and obtain predicted carbon emissions and predicted total carbon emissions; set a carbon emission threshold; if the predicted total carbon emissions are less than the carbon emission threshold, burn the coal normally; if the predicted total carbon emissions are greater than or equal to the carbon emission threshold, send an early warning signal to the user terminal; Step S3: preset a sampling frequency, and detect the actual coal consumption weight and actual carbon emissions of the coal to be tested according to the sampling frequency; and modify the parameters of the model according to the actual coal consumption weight and the actual carbon emissions; Step S4: When the warning signal 1 is received, the sampling frequency is adjusted to generate a new sampling frequency, the actual carbon emissions of the coal to be tested are detected according to the new sampling frequency, and the real-time carbon emissions are compared with the predicted carbon emissions; an accuracy threshold is set, and an accuracy probability value is calculated based on the comparison result. If the accuracy probability value is greater than or equal to the accuracy threshold, a warning signal 2 is sent to the user terminal.
2. The regional carbon emission analysis and early warning method based on big data according to claim 1 is characterized by: The step S1 comprises: The monitoring area is a spatial area where carbon emissions monitoring is required; historical data on the weight of coal used for power generation each time for the same type of coal in the monitoring area is linearly correlated with historical data on carbon emissions generated by the weight of the coal consumed, a slope parameter of the linear correlation is obtained by the least squares method, and a prediction model is established using the slope parameter of the linear correlation, the prediction model comprising: Where C is the carbon emissions generated by the weight of coal consumed, β is the slope parameter, M is the weight of coal consumed, i is the number of sampling times, n is the total number of samples in the historical data, and M i is the weight of coal consumed during the i-th sampling, C i is the carbon emission at the time of sampling i; each type of coal corresponds to an independent slope parameter.
3. The regional carbon emission analysis and early warning method based on big data according to claim 1 is characterized by: The step S2 comprises: A pressure-resistant weighing coal feeder is provided at the entrance of the monitoring area, and the weight of the coal to be tested is detected by using the weighing coal feeder; the coal to be tested is sampled, and the type of the coal to be tested is determined by an industrial analyzer; The coal weight and coal type of the coal to be tested are input into the prediction model to obtain the predicted carbon emissions, and a predicted carbon emissions graph is drawn with the consumed coal weight as the horizontal axis and the carbon emissions generated by the consumed coal weight as the vertical axis; the starting point of the predicted carbon emissions graph is the coordinate origin, and the end point is the point corresponding to when the consumed coal weight reaches the maximum, and the vertical coordinate value of the end point is the predicted total carbon emissions.
4. The regional carbon emission analysis and early warning method based on big data according to claim 1 is characterized by: The step S3 comprises: A belt electronic scale and a CEMS system are provided in the monitoring area, the actual coal consumption weight of the coal to be tested is obtained by the belt electronic scale, and the actual carbon emissions are detected by the CEMS system; an actual carbon emissions graph is generated based on the actual coal consumption weight and the actual carbon emissions, and the horizontal and vertical coordinates and starting points of the actual carbon emissions graph and the predicted carbon emissions graph are the same; Compare the actual carbon emissions and the predicted carbon emissions when the same weight of coal is consumed. If the actual carbon emissions are different from the predicted carbon emissions, the actual coal weight consumed and the actual carbon emissions of the current coal to be tested are input into the prediction model, and the parameters of the prediction model are corrected. The parameter correction process includes: where β new is the corrected slope parameter, M new is the actual coal consumption weight, C new is the actual carbon emission; the corrected slope parameter is used as the slope parameter of the prediction model.
5. The regional carbon emission analysis and early warning method based on big data according to claim 1 is characterized by: The step S4 includes: presetting a severely excessive carbon emissions threshold, wherein the severely excessive carbon emissions threshold is greater than the carbon emissions threshold; when receiving the first warning signal, if the predicted total carbon emissions are less than the severely excessive carbon emissions threshold, doubling the preset sampling frequency; if the predicted total carbon emissions are greater than or equal to the severely excessive carbon emissions threshold, doubling the preset sampling frequency to obtain a new sampling frequency; Set a calibration time, compare the real-time carbon emissions and the predicted carbon emissions based on the new sampling frequency within the calibration time, and record the number of accurate predictions, which is the number of times the real-time carbon emissions and the predicted carbon emissions are within the error; at the end of the calibration time, calculate the percentage of the accurate prediction number to the number of sampling times within the calibration time to obtain the accuracy probability value.
6. A regional carbon emission analysis and early warning system based on big data, applied to the regional carbon emission analysis and early warning method based on big data according to any one of claims 1 to 5, characterized in that: The system includes a data acquisition module, a database module, a data analysis module, a trimming module, and an early warning module; the data acquisition module obtains the weight and type of coal to be tested in the monitoring area, as well as the actual weight of coal consumed and the actual carbon emissions; the database module establishes and stores the prediction model and stores historical data at the same time; the data analysis module obtains predicted carbon emissions through the prediction model in the database module based on the data collected by the data acquisition module, and draws a predicted carbon emissions graph; the early warning module determines whether to issue an early warning signal by comparing the predicted total carbon emissions with the carbon emissions threshold, and determines whether to issue an early warning signal according to the accuracy threshold; the trimming module corrects the prediction model in the database module and adjusts the sampling frequency; The output end of the data acquisition module is electrically connected to the input end of the database module; the output end of the database module is electrically connected to the input end of the data analysis module; the output end of the data analysis module is electrically connected to the input end of the trimming module and the input end of the early warning module; the output end of the trimming module is electrically connected to the input end of the database module and the input end of the early warning module.
7. The regional carbon emission analysis and early warning system based on big data according to claim 6 is characterized by: The data acquisition module includes an initial sampling unit and a real-time sampling unit; the initial sampling unit uses a pressure-resistant weighing coal feeder to weigh and sample the coal to be tested and determines the type of coal through an industrial analyzer; the real-time sampling unit obtains the actual weight of coal consumed and the actual carbon emissions through a belt electronic scale and a CEMS system; The database module includes a modeling unit and a storage unit; the modeling unit performs modeling according to coal weight and coal type; the storage unit is used to store prediction models, historical data and data obtained by real-time detection; and the data in the storage unit can be manually modified.
8. The regional carbon emission analysis and early warning system based on big data according to claim 6 is characterized by: The data analysis module includes a calculation unit and a drawing unit; the calculation unit derives the predicted carbon emissions based on the data in the database module; the drawing unit is used to draw a graph of actual carbon emissions and a graph of predicted carbon emissions.
9. The regional carbon emission analysis and early warning system based on big data according to claim 6 is characterized by: The early warning module includes a signal unit 1 and a signal unit 2; the signal unit 1 is used to compare the predicted total carbon emissions and the carbon emissions threshold to determine whether to issue an early warning signal 1; the signal unit 2 is used to compare the accurate probability value and the accurate threshold to determine whether to issue an early warning signal 2.
10. The regional carbon emission analysis and early warning system based on big data according to claim 6, characterized in that: The trimming module includes a model correction unit and a frequency adjustment unit; the model correction unit corrects the data in the database module according to the data in the data result module; the frequency adjustment unit adjusts the sampling frequency when receiving the warning signal.