Carbon emission metering method and device in cement industry

Abstract

The invention relates to a carbon emission metering method and device for the cement industry, and belongs to the technical field of carbon emission management.The carbon emission metering method for the cement industry comprises the steps that an emission data set is constructed based on process state data and emission data of multiple process steps at multiple sampling moments; fitting the preprocessed emission data set based on an SVR model, and determining reference emission data corresponding to the plurality of process steps; determining the uncertainty of reference emission data corresponding to the plurality of process steps based on the uncertainty of the emission data set and the uncertainty of the SVR model; and determining a carbon emission metering result of the target production scene and the uncertainty corresponding to the carbon emission metering result of the target production scene based on the process steps included in the target production scene, the reference emission data corresponding to the multiple process steps and the uncertainty of the reference emission data corresponding to the multiple process steps. The flexibility and accuracy of carbon emission metering in the cement industry are effectively improved.

Description

Technical Field

[0001] This invention relates to the field of carbon emission management technology, and in particular to a carbon emission measurement method and device for the cement industry. Background Technology

[0002] Currently, carbon emission accounting in the cement industry is mainly based on industry standards, and often adopts the "macro statistical method" or the "material balance method".

[0003] Existing carbon emission measurement methods in the cement industry suffer from the following drawbacks: They are coarse-grained and have a strong time lag, often calculating on a monthly or annual basis, failing to reflect fluctuations in the production process in real time. By the time emissions exceedances are detected, production has already been completed, making real-time intervention impossible. They lack attribution capabilities; existing methods can only tell companies "how much they emitted," but cannot accurately pinpoint "which stage, which equipment, or what process parameter" caused the high emissions, making it difficult to guide specific optimizations. Simulation capabilities are lacking; new plants or process upgrades often lack data model support, relying heavily on experience, making it difficult to predict actual carbon emission levels before construction. They are highly data-dependent and have poor regional adaptability; calculations require comprehensive knowledge of actual production data (such as actual output, raw material consumption, and other confidential data), which is difficult and time-consuming to collect, making large-scale application to all companies within a region difficult. Furthermore, they do not consider the impact of external factors such as environmental policies and seasonal changes on production duration, limiting the applicability of the model in different regions and time periods.

[0004] Therefore, improving the flexibility and accuracy of carbon emission measurement in the cement industry has become an urgent technical problem to be solved. Summary of the Invention

[0005] In view of this, it is necessary to provide a carbon emission measurement method and device for the cement industry to solve the problems of insufficient flexibility and accuracy of existing carbon emission measurement schemes in the cement industry.

[0006] To address the aforementioned problems, in a first aspect, the present invention provides a carbon emission measurement method for the cement industry, comprising: Acquire process status data and emission data for multiple process steps at multiple sampling times, and construct an emission dataset based on the process status data and emission data for multiple process steps at multiple sampling times; The pre-processed emission dataset was fitted using the SVR model to determine reference emission data for multiple process steps. Based on the uncertainty of the emission dataset and the uncertainty of the SVR model, the uncertainty of the reference emission data corresponding to multiple process steps is determined; Based on the process steps included in the target production scenario, the reference emission data corresponding to multiple process steps, and the uncertainty of the reference emission data corresponding to multiple process steps, the carbon emission measurement results of the target production scenario and the uncertainty corresponding to the carbon emission measurement results of the target production scenario are determined.

[0007] In one possible implementation, the preprocessing of the emissions dataset includes: The time sliding window algorithm is used to perform lag compensation on the emission dataset and remove outlier data from the emission dataset.

[0008] In one possible implementation, fitting the preprocessed emission dataset to the SVR model to determine reference emission data corresponding to multiple process steps includes: Based on the SVR model, quantile regression or envelope analysis is performed on the preprocessed emission dataset to determine reference emission data for multiple process steps.

[0009] In one possible implementation, determining the uncertainty of reference emission data corresponding to multiple process steps based on the uncertainty of the emission dataset and the uncertainty of the SVR model includes: Based on the uncertainty of the emission dataset, the sensitivity coefficient of the SVR model to the emission dataset, and the residual standard deviation of the SVR model, the uncertainty of the reference emission data corresponding to multiple process steps is determined.

[0010] In one possible implementation, determining the carbon emission measurement result of the target production scenario and the uncertainty corresponding to the carbon emission measurement result of the target production scenario based on the process steps included in the target production scenario, reference emission data corresponding to multiple process steps, and the uncertainty of the reference emission data corresponding to multiple process steps includes: The sum of reference emission data corresponding to the process steps included in the target production scenario is determined as the carbon emission measurement result of the target production scenario, and the variance summation result of the uncertainty of the reference emission data corresponding to the process steps included in the target production scenario is determined as the uncertainty corresponding to the carbon emission measurement result of the target production scenario.

[0011] In one possible implementation, the method further includes: Based on the carbon emission measurement results of the target production scenario and the uncertainty corresponding to the carbon emission measurement results of the target production scenario, the carbon emission threshold of the target production scenario is determined. If the actual carbon emissions in the target production scenario exceed the carbon emission threshold, it is determined that there is a carbon emission spillover problem in the target production scenario.

[0012] In one possible implementation, the method further includes: If it is determined that there is a carbon emission spillover problem in the target production scenario, the carbon emission threshold corresponding to the process steps included in the target production scenario is determined based on the reference emission data corresponding to the process steps included in the target production scenario and the uncertainty of the reference emission data corresponding to the process steps included in the target production scenario. Process steps whose actual carbon emissions from the process steps included in the target production scenario exceed the carbon emission threshold corresponding to the process steps included in the target production scenario are identified as process steps to be improved.

[0013] On the other hand, the present invention also provides a carbon emission metering device for the cement industry, comprising: The acquisition module is used to acquire process status data and emission data of multiple process steps at multiple sampling times, and to construct an emission dataset based on the process status data and emission data of multiple process steps at multiple sampling times. The fitting module is used to fit the preprocessed emission dataset based on the SVR model to determine the reference emission data corresponding to multiple process steps. The first determination module is used to determine the uncertainty of reference emission data corresponding to multiple process steps based on the uncertainty of the emission dataset and the uncertainty of the SVR model. The second determining module is used to determine the carbon emission measurement result of the target production scenario and the uncertainty corresponding to the carbon emission measurement result of the target production scenario based on the process steps included in the target production scenario, the reference emission data corresponding to multiple process steps, and the uncertainty of the reference emission data corresponding to multiple process steps.

[0014] Secondly, the present invention also provides a measuring device, including a memory and a processor, wherein, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the carbon emission measurement method for the cement industry as described in any of the above implementations.

[0015] Thirdly, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instructions, which, when executed by a processor, can implement the steps in the carbon emission measurement method for the cement industry described in any of the above implementations.

[0016] The beneficial effects of this invention are as follows: The carbon emission measurement method and apparatus for the cement industry provided by this invention improve the flexibility of carbon emission measurement by dividing the production scenario into multiple process steps. Then, an emission dataset is constructed using process state data and emission data at multiple sampling times of multiple process steps. The SVR model is used for fitting to determine the reference emission data corresponding to multiple process steps, ensuring the accuracy of carbon emission measurement. At the same time, uncertainty is considered in the carbon emission measurement process to further improve the accuracy of carbon emission measurement. Finally, based on the process steps included in the target production scenario, the reference emission data corresponding to multiple process steps, and the uncertainty of the reference emission data corresponding to multiple process steps, the carbon emission measurement result of the target production scenario and the uncertainty corresponding to the carbon emission measurement result of the target production scenario are determined, thereby realizing the carbon emission measurement of the target production scenario. This invention effectively improves the flexibility and accuracy of carbon emission measurement in the cement industry. Attached Figure Description

[0017] Figure 1 A schematic flowchart of an embodiment of the carbon emission measurement method for the cement industry provided by the present invention; Figure 2 A schematic diagram of an embodiment of a typical scenario and data acquisition node in the entire cement production process provided by the present invention; Figure 3 A schematic diagram illustrating an embodiment of the relationship between instantaneous data acquisition and historical datasets provided by the present invention; Figure 4 A schematic flowchart of an embodiment of the carbon emission characteristic curve fitting process provided by the present invention; Figure 5 A schematic flowchart of an embodiment of the real-time production diagnostics and feedback improvement process provided by the present invention; Figure 6 A schematic flowchart of an embodiment of the carbon emission simulation process for a newly built factory provided by the present invention; Figure 7 A schematic diagram of an embodiment of the carbon emission metering device for the cement industry provided by the present invention; Figure 8 A schematic diagram of an embodiment of the metering device provided by the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0019] In the description of the embodiments of the present invention, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0020] The terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a technical feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0021] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0022] This invention provides a carbon emission measurement method and device for the cement industry, which will be described below.

[0023] Figure 1 A schematic flowchart of an embodiment of the carbon emission measurement method for the cement industry provided by the present invention is shown below. Figure 1 As shown, the carbon emission measurement methods in the cement industry include: S101. Obtain process status data and emission data for multiple process steps at multiple sampling times, and construct an emission dataset based on the process status data and emission data for multiple process steps at multiple sampling times.

[0024] It should be noted that the carbon emission measurement method for the cement industry provided by this invention can be applied to carbon emission measurement scenarios in industrial production, especially in the cement industry.

[0025] Before carbon emission measurement, the measurement equipment (such as a portable computer, desktop computer, or industrial all-in-one machine) first acquires process status data and emission data for multiple process steps at multiple sampling times. Then, based on the process status data and emission data for multiple process steps at multiple sampling times, an emission dataset is constructed. Process steps may include raw material preparation, clinker baking, cement grinding, etc. Process status data may include material input amount, temperature, air volume, air pressure, etc., and emission data may include carbon dioxide concentration and emission amount, nitrogen oxide concentration, etc.

[0026] S102. Fit the preprocessed emission dataset based on the SVR model to determine the reference emission data corresponding to multiple process steps.

[0027] It should be noted that after the emission dataset is constructed, it can be preprocessed to improve data accuracy. Then, the preprocessed emission dataset can be fitted using a Support Vector Regression (SVR) model to determine reference emission data for multiple process steps, thereby providing data support for subsequent carbon emission measurement.

[0028] S103. Based on the uncertainty of the emission dataset and the uncertainty of the SVR model, determine the uncertainty of the reference emission data corresponding to multiple process steps.

[0029] It should be noted that, in order to further improve the accuracy of carbon emission measurement, the uncertainty of reference emission data corresponding to multiple process steps can be determined based on the uncertainty of the emission dataset and the uncertainty of the SVR model.

[0030] S104. Based on the process steps included in the target production scenario, the reference emission data corresponding to multiple process steps, and the uncertainty of the reference emission data corresponding to multiple process steps, determine the carbon emission measurement result of the target production scenario and the uncertainty corresponding to the carbon emission measurement result of the target production scenario.

[0031] It should be noted that: Finally, based on the process steps included in the target production scenario, the reference emission data corresponding to multiple process steps, and the uncertainty of the reference emission data corresponding to multiple process steps, the carbon emission measurement result of the target production scenario and the uncertainty corresponding to the carbon emission measurement result can be determined, thus achieving carbon emission measurement for the target production scenario. By dividing the production scenario into multiple process steps for carbon emission measurement, various production scenarios can be flexibly addressed, improving the flexibility of carbon emission measurement. Furthermore, dividing the production scenario into multiple independent process steps for carbon emission measurement can also improve the accuracy of carbon emission measurement.

[0032] In summary, the carbon emission measurement method for the cement industry provided by this invention improves the flexibility of carbon emission measurement by dividing the production scenario into multiple process steps. Then, it constructs an emission dataset using process status data and emission data from multiple process steps at multiple sampling times. An SVR model is used for fitting to determine reference emission data corresponding to multiple process steps, ensuring the accuracy of carbon emission measurement. Furthermore, uncertainty is considered during the carbon emission measurement process to further improve accuracy. Finally, based on the process steps included in the target production scenario, the reference emission data corresponding to multiple process steps, and the uncertainty of the reference emission data corresponding to multiple process steps, the carbon emission measurement result of the target production scenario and the uncertainty corresponding to the carbon emission measurement result of the target production scenario are determined, thus achieving carbon emission measurement of the target production scenario. This invention effectively improves the flexibility and accuracy of carbon emission measurement in the cement industry.

[0033] In some embodiments of the present invention, the preprocessing of the emission dataset includes: The time sliding window algorithm is used to perform lag compensation on the emission dataset and remove outlier data from the emission dataset.

[0034] It should be noted that when preprocessing the emissions dataset, a time sliding window algorithm can be used to calculate the transmission delay between different data collection nodes and perform lag compensation. Furthermore, outlier data in the emissions dataset, such as non-steady-state data like start-up and shutdown, can be removed to ensure data reliability. Additionally, a production time correction coefficient (calculated as the ratio of the number of available days to the total number of days) can be introduced during preprocessing to adapt to the impact of policies such as heavy pollution weather, major events, and staggered production during the heating season, thus correcting for the actual effective production time.

[0035] In some embodiments of the present invention, the step of fitting the preprocessed emission dataset based on the SVR model to determine reference emission data corresponding to multiple process steps includes: Based on the SVR model, quantile regression or envelope analysis is performed on the preprocessed emission dataset to determine reference emission data for multiple process steps.

[0036] It should be noted that when fitting the pre-processed emission dataset to the SVR model to determine the reference emission data corresponding to multiple process steps, quantile regression or envelope analysis can be performed on the pre-processed emission dataset using the SVR model to determine the reference emission data corresponding to multiple process steps.

[0037] In some embodiments of the present invention, determining the uncertainty of reference emission data corresponding to multiple process steps based on the uncertainty of the emission dataset and the uncertainty of the SVR model includes: Based on the uncertainty of the emission dataset, the sensitivity coefficient of the SVR model to the emission dataset, and the residual standard deviation of the SVR model, the uncertainty of the reference emission data corresponding to multiple process steps is determined.

[0038] It should be noted that when determining the uncertainty of reference emission data corresponding to multiple process steps based on the uncertainty of the emission dataset and the uncertainty of the SVR model, the uncertainty of the reference emission data corresponding to multiple process steps can be determined based on the uncertainty of the emission dataset, the sensitivity coefficient of the SVR model to the emission dataset, and the standard deviation of the residuals of the SVR model. For example, the uncertainty of the model output can be determined first based on the uncertainty of the emission dataset and the sensitivity coefficient of the SVR model to the emission dataset, and then the uncertainty of the reference emission data corresponding to multiple process steps can be determined based on the uncertainty of the model output and the standard deviation of the residuals of the SVR model.

[0039] In some embodiments of the present invention, determining the carbon emission measurement result of the target production scenario and the uncertainty corresponding to the carbon emission measurement result of the target production scenario based on the process steps included in the target production scenario, reference emission data corresponding to multiple process steps, and the uncertainty of the reference emission data corresponding to multiple process steps includes: The sum of reference emission data corresponding to the process steps included in the target production scenario is determined as the carbon emission measurement result of the target production scenario, and the variance summation result of the uncertainty of the reference emission data corresponding to the process steps included in the target production scenario is determined as the uncertainty corresponding to the carbon emission measurement result of the target production scenario.

[0040] It should be noted that when determining the carbon emission measurement result of the target production scenario and the uncertainty corresponding to the carbon emission measurement result of the target production scenario based on the process steps included in the target production scenario, the reference emission data corresponding to multiple process steps, and the uncertainty of the reference emission data corresponding to multiple process steps, the sum of the reference emission data corresponding to the process steps included in the target production scenario can be determined as the carbon emission measurement result of the target production scenario, and the variance superposition result of the uncertainty of the reference emission data corresponding to the process steps included in the target production scenario can be determined as the uncertainty corresponding to the carbon emission measurement result of the target production scenario.

[0041] In some embodiments of the present invention, the method further includes: Based on the carbon emission measurement results of the target production scenario and the uncertainty corresponding to the carbon emission measurement results of the target production scenario, the carbon emission threshold of the target production scenario is determined. If the actual carbon emissions in the target production scenario exceed the carbon emission threshold, it is determined that there is a carbon emission spillover problem in the target production scenario.

[0042] It should be noted that after determining the carbon emission measurement results and corresponding uncertainties for the target production scenario, a carbon emission threshold for the target production scenario can be determined based on these results and uncertainties. Then, the actual carbon emissions of the target production scenario can be used to determine whether a carbon emission spillover issue exists. If the actual carbon emissions of the target production scenario exceed the carbon emission threshold, then a carbon emission spillover issue can be identified.

[0043] In some embodiments of the present invention, the method further includes: If it is determined that there is a carbon emission spillover problem in the target production scenario, the carbon emission threshold corresponding to the process steps included in the target production scenario is determined based on the reference emission data corresponding to the process steps included in the target production scenario and the uncertainty of the reference emission data corresponding to the process steps included in the target production scenario. Process steps whose actual carbon emissions from the process steps included in the target production scenario exceed the carbon emission threshold corresponding to the process steps included in the target production scenario are identified as process steps to be improved.

[0044] It should be noted that once it is determined that there is a carbon emission spillover problem in the target production scenario, the carbon emission threshold corresponding to the process steps included in the target production scenario can be determined based on the reference emission data corresponding to the process steps included in the target production scenario and the uncertainty of the reference emission data corresponding to the process steps included in the target production scenario. Then, the process steps that exceed the carbon emission threshold corresponding to the process steps included in the target production scenario are identified as process steps to be improved, so as to realize the rectification of specific process steps.

[0045] This invention proposes a "point-line-surface-volume" modeling approach and a "dynamic benchmark comparison" diagnostic logic to achieve real-time and precise management of carbon emissions.

[0046] Point (data acquisition): Collect basic equipment parameter data, process status data and emission data at a specific moment to construct an instantaneous production snapshot vector.

[0047] Line (Scenario Fitting): By accumulating multi-cycle data after alignment and filtering, and combining the regression relationship between equipment parameters and production characteristics, a dynamic carbon emission characteristic curve for a single scenario (such as rotary kiln calcination) is fitted.

[0048] Surface (Factory Model): Integrates the characteristic curves of all typical process scenarios within a single factory, incorporates production time correction coefficients, and forms a factory-level carbon emission model.

[0049] Industry Model: Aggregates a large number of factory models and combines them with regional verification data for calibration to form an industry carbon emission measurement standard model, which serves as a benchmark for dynamic diagnosis, simulation, and regional inventory compilation.

[0050] The specific steps in constructing a carbon emission measurement model include: 1. Typical scenario division and data acquisition node definition.

[0051] Scene division: combined with Figure 2 Looking at the cement production process, we can divide it into typical process scenarios (e.g., raw meal preparation, clinker calcination, cement grinding, etc.).

[0052] Node definition: Define key acquisition nodes in each scenario: Emissions data nodes: Collect data sets including carbon dioxide concentration / emissions (distinguishing between process carbonate decomposition emissions and fuel combustion emissions), nitrogen oxide concentration, process power consumption, and fuel consumption (focusing on raw coal consumption to meet the needs of clinker burning systems), etc.

[0053] Material / Process Status Node: Collects process data from the DCS system, including parameters such as material feed rate, critical temperature zone temperature, and air volume / pressure.

[0054] Equipment and production infrastructure nodes: Collect enterprise registration and publicly available statistical data, including production line design capacity, actual operating time, and capacity utilization rate (the ratio of daily actual output to design capacity). The data is easy to obtain and does not require enterprise privacy information.

[0055] 2. Synchronous data acquisition and vector construction.

[0056] Combination Figure 3 In this study, the above data is collected synchronously at a specific moment to construct an instantaneous production snapshot vector.

[0057] Supplementing cross-regional, multi-scale sample data: Incorporating production line samples from different regions and with different designed production capacity, and ultimately using data from multiple typical production lines as the core statistical samples to ensure that the dataset covers mainstream production scenarios in the industry.

[0058] By collecting data multiple times during the continuous production process of a single scenario, a historical dataset is formed.

[0059] 3. Multidimensional coupling feature extraction and dynamic benchmark construction.

[0060] Combination Figure 4 In this step, we establish a high-fidelity process-emission model and assess its uncertainty.

[0061] Time-series alignment and steady-state filtering: Addressing the long lag characteristics of cement production lines, a time sliding window algorithm is introduced to calculate the transmission delay between different data acquisition nodes, perform lag compensation, and construct a time-series aligned dataset. Simultaneously, non-steady-state data such as start-up and shutdown are removed (extra exceptions are removed where actual capacity differs from designed capacity by 5 times or more to ensure data reliability).

[0062] Production time correction: Introduce a production time correction coefficient α=T1 / T2 (T1 is the number of days that can be operated, and T2 is the total number of days) to adapt to the impact of policies such as heavy pollution weather, major events, and staggered production during the heating season, and correct the actual effective production time.

[0063] Coupled modeling based on optimal boundaries: Machine learning algorithms (such as SVR and neural networks) are used to uncover the nonlinear coupling relationship between process parameters and emission indicators, establishing a multi-objective mapping function F. Combined with regression analysis, a core parameter correlation model is constructed. Relationship between actual capacity and designed capacity: m = 1.1092 × m0 + 193.1245 (m is the actual capacity t / d, m0 is the designed capacity t / d, R² = 0.6943, P < 0.05).

[0064] Relationship between clinker calcination coal consumption and designed production capacity: h = -0.0037 × m0 + 129.0423 (h is the standard coal consumption per unit of clinker calcination kgce / t, R² = 0.5236, P < 0.05).

[0065] By using quantile regression or envelope analysis, the optimal emission boundary under specific process conditions is fitted and used as a dynamic benchmark. Model uncertainty assessment: 1) Node-level uncertainty quantification.

[0066] First, it is necessary to quantify the uncertainty at key points of data acquisition, which is the basis for all subsequent uncertainty propagation.

[0067]

[0068] Quantization objective: For each instantaneous snapshot vector elements in Includes a standard uncertainty .

[0069] 2) Uncertainty of single-scenario model.

[0070] When fitting the carbon emission characteristic curve, the uncertainty of the model mainly comes from two aspects: error propagation of the input data and the fitting error of the model itself.

[0071] When input parameters (including basic parameters and process parameters) have uncertainty , At that time, they will propagate to the output emission predictions through model F. superior.

[0072]

[0073] in It is the model's response to input parameters The sensitivity coefficient (which can be extracted from the weights of a regression model or neural network). It is the covariance between the input parameters.

[0074] Evaluation of model fit residuals: Machine learning or regression algorithms produce residuals when fitting historical datasets D.

[0075] Residual standard deviation: used to calculate the predicted value from the model. The mean square error (MSE) or residual standard deviation between the measured value a and the actual measured value a , = This residual reflects the model's ability to explain complex production processes and is a manifestation of the model's structural uncertainty.

[0076] Overall uncertainty: The propagation error and model residuals are combined to obtain the comprehensive standard uncertainty of the single-scene model output. :

[0077] Uncertainty in the factory / industry model: When performing model aggregation, uncertainty needs to take into account the correlation between scenarios and the statistical nature of the samples.

[0078] Factory-level polymerization: converting raw materials Firing Grinding The scene models are weighted and integrated.

[0079] Assuming various scenarios (e.g.) and If the carbon emissions of are independent (without strong correlation), they can be synthesized according to the variance superposition principle:

[0080] in For total factory emissions, For the emission in the k-th scenario, These are the weighting coefficients.

[0081] Industry-level aggregation: Statistical averaging or optimal boundary fitting is performed on the characteristic curves of a large number of factories to generate industry-standard models.

[0082] Statistical uncertainty: The uncertainty at this point This mainly reflects the inherent differences between similar processes within the industry and the representativeness of the sample.

[0083] Quantification: Values ​​can be predicted using industry-standard models. It is expressed as a confidence interval, such as a 95% confidence interval ± .

[0084] Regional validation and calibration: The model is validated using regional empirical data to ensure that the relative error between the model's calculated values ​​and the actual statistical values ​​is controlled within 8%.

[0085] 4. Model aggregation and industry benchmark construction.

[0086] Factory-level aggregation: Aggregating data within the same factory (raw materials) (Firing) The model is weighted and integrated with scenario models such as (grinding) and incorporates emission factors (such as clinker emission factors) to form a plant-level model.

[0087] Industry-level aggregation: When the number of connected factories reaches a certain scale, the characteristic curves of similar processes are statistically processed and incorporated into the industry average emission coefficient as a benchmark reference to generate an industry carbon emission measurement standard model. The uncertainty of the industry model is represented by the confidence interval of its predicted values.

[0088] The specific applications of the carbon emission model are as follows: Application 1: Carbon emission diagnosis and closed-loop improvement.

[0089] Combination Figure 5 The application demonstrates that it enables real-time diagnosis and accurate attribution of "carbon emission spillover".

[0090] 1. Real-time data collection: Real-time collection of the actual operating status and actual emissions of a specific scenario in the target factory.

[0091] 2. Baseline Calculation: Input the status into the industry standard model to calculate the theoretical standard emission value.

[0092] 3. Difference Comparison and Judgment: Set dynamic tolerance threshold. k× (in (This refers to model uncertainty). If If so, the node is determined to have "carbon emission spillover".

[0093] 4. Causes and Improvements: The system automatically locked down. For specific abnormal process steps (such as temperature parameters or burner equipment), provide improvement suggestions to achieve targeted improvements.

[0094] Application 2: Simulation and Pre-construction Management of Carbon Emissions from New Construction Projects. Combined with... Figure 6 Here, the application specifically includes: Parameter setting: For new factories or technological upgrading projects, set the expected process parameters.

[0095] Virtual operation: Call the industry standard model, input parameters to carry out virtual operation, and combine the production capacity-coal consumption correlation model to predict fuel consumption.

[0096] Prediction and Assessment: The model outputs predicted carbon emission data and its prediction uncertainty. By comparing with environmental protection requirements, if carbon emission data is found to exceed the standards during the design phase, the process design will be adjusted before construction until the simulation results meet the standards, thus achieving "low carbon design".

[0097] Application 3: Compilation of regional carbon emission inventories and comparison of monitoring data.

[0098] Data collection: Collect production line design capacity and operating time data of all cement enterprises in the region (without relying on the enterprises' private actual output data).

[0099] Inventory accounting: Substitute the factory-level model and combine it with the region-specific production time correction coefficient to calculate the direct CO2 emissions of each enterprise from the bottom up, and integrate them to form a regional carbon emission inventory, realizing the grid-based inventory (such as county-level, industrial park-level).

[0100] Data comparison: The accounting data is compared with data obtained from satellite remote sensing and CO2 mobile monitoring equipment to calibrate the accuracy of the list and provide precise support for the formulation of regional emission reduction policies.

[0101] Compared to traditional measurement methods, this invention can precisely link carbon emission anomalies to specific equipment parameters, solving the industry problem of "knowing emissions exceed limits but not knowing how to correct them." The industry standard model is a dynamic optimal boundary curve fitted from massive amounts of actual production data, rather than static values. Combined with uncertainty assessment, it can more scientifically and rigorously evaluate emission levels under different operating conditions. Through simulation, carbon management can be shifted from "post-event accounting" to "pre-event design," significantly reducing trial-and-error costs. Leveraging the homogeneous processes in the cement industry, the model has strong industry-wide application value. Accounting can be completed using only easily accessible publicly available / registered data such as design capacity and operating time, addressing the pain point of missing or difficult-to-collect actual production data for enterprises, and can be applied on a large scale to all enterprises within a region. It can meet enterprise-level real-time diagnostic needs and support regional-level inventory compilation. Furthermore, the calculated data can be compared with satellite remote sensing and mobile monitoring data, improving the targeting of carbon monitoring and the accuracy of policy formulation. Verified by cement companies in the region, the relative error in production calculation was only 7.81%, and the emission coefficient deviated from the domestic average by 7.27%, showing a good fit with actual production.

[0102] To better implement the carbon emission measurement method for the cement industry in this invention embodiment, based on the carbon emission measurement method for the cement industry, correspondingly, such as... Figure 7 As shown, this embodiment of the invention also provides a carbon emission metering device for the cement industry. The carbon emission metering device 700 for the cement industry includes: The acquisition module 701 is used to acquire process status data and emission data of multiple process steps at multiple sampling times, and to construct an emission dataset based on the process status data and emission data of multiple process steps at multiple sampling times. The fitting module 702 is used to fit the preprocessed emission dataset based on the SVR model to determine the reference emission data corresponding to multiple process steps. The first determination module 703 is used to determine the uncertainty of reference emission data corresponding to multiple process steps based on the uncertainty of the emission dataset and the uncertainty of the SVR model. The second determining module 704 is used to determine the carbon emission measurement result of the target production scenario and the uncertainty corresponding to the carbon emission measurement result of the target production scenario based on the process steps included in the target production scenario, the reference emission data corresponding to multiple process steps, and the uncertainty of the reference emission data corresponding to multiple process steps.

[0103] The carbon emission metering device 700 for the cement industry provided in the above embodiments can realize the technical solutions described in the above embodiments of the carbon emission metering method for the cement industry. The specific implementation principles of each module or unit can be found in the corresponding content in the above embodiments of the carbon emission metering method for the cement industry, and will not be repeated here.

[0104] like Figure 8 As shown, the present invention also provides a measuring device 800. The measuring device 800 includes a processor 801, a memory 802, and a display 803. Figure 8 Only some components of the metering device 800 are shown; however, it should be understood that implementation of all shown components is not required, and more or fewer components may be implemented instead.

[0105] In some embodiments, processor 801 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 802 or process data, such as the carbon emission measurement method for the cement industry in this invention.

[0106] In some embodiments, processor 801 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 801 may be local or remote. In some embodiments, processor 801 may be implemented on a cloud platform. In one embodiment, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-cloud, etc., or any combination thereof.

[0107] In some embodiments, memory 802 may be an internal storage unit of the metering device 800, such as a hard disk or memory of the metering device 800. In other embodiments, memory 802 may also be an external storage device of the metering device 800, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the metering device 800.

[0108] Furthermore, the memory 802 may include both internal storage units of the measuring device 800 and external storage devices. The memory 802 is used to store the application software and various types of data installed on the measuring device 800.

[0109] In some embodiments, display 803 may be an LED display, a liquid crystal display, a touch-screen liquid crystal display, or an organic light-emitting diode (OLED) touchscreen. Display 803 is used to display information from the metering device 800 and to display a visual user interface. Components 801-803 of the metering device 800 communicate with each other via a system bus.

[0110] In one embodiment, when processor 801 executes a carbon emission metering program for the cement industry stored in memory 802, the following steps can be implemented: Acquire process status data and emission data for multiple process steps at multiple sampling times, and construct an emission dataset based on the process status data and emission data for multiple process steps at multiple sampling times; The pre-processed emission dataset was fitted using the SVR model to determine reference emission data for multiple process steps. Based on the uncertainty of the emission dataset and the uncertainty of the SVR model, the uncertainty of the reference emission data corresponding to multiple process steps is determined; Based on the process steps included in the target production scenario, the reference emission data corresponding to multiple process steps, and the uncertainty of the reference emission data corresponding to multiple process steps, the carbon emission measurement results of the target production scenario and the uncertainty corresponding to the carbon emission measurement results of the target production scenario are determined.

[0111] It should be understood that when the processor 801 executes the carbon emission metering program for the cement industry in the memory 802, in addition to the functions mentioned above, it can also perform other functions, as detailed in the description of the corresponding method embodiments above.

[0112] Furthermore, this embodiment of the invention does not specifically limit the type of the measuring device 800 mentioned. The measuring device 800 can be a portable electronic device such as a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, or laptop computer. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic devices can also be other portable electronic devices, such as laptop computers with touch-sensitive surfaces (e.g., touch panels). It should also be understood that in some other embodiments of the invention, the measuring device 800 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0113] Accordingly, this application also provides a computer-readable storage medium for storing computer-readable programs or instructions. When the programs or instructions are executed by a processor, they can implement the steps or functions of the carbon emission measurement method for the cement industry provided in the above-described method embodiments.

[0114] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0115] The carbon emission metering method and device for the cement industry provided by this invention have been described in detail above. Specific examples have been used to illustrate the principle and implementation of this invention. The description of the above embodiments is only for the purpose of helping to understand the method and core idea of ​​this invention. At the same time, for those skilled in the art, there will be changes in the specific implementation and application scope based on the idea of ​​this invention. Therefore, the content of this specification should not be construed as a limitation of this invention.

Claims

1. A method for measuring carbon emissions in the cement industry, characterized in that, include: Acquire process status data and emission data for multiple process steps at multiple sampling times, and construct an emission dataset based on the process status data and emission data for multiple process steps at multiple sampling times; The pre-processed emission dataset was fitted using the SVR model to determine reference emission data for multiple process steps. Based on the uncertainty of the emission dataset and the uncertainty of the SVR model, the uncertainty of the reference emission data corresponding to multiple process steps is determined; Based on the process steps included in the target production scenario, the reference emission data corresponding to multiple process steps, and the uncertainty of the reference emission data corresponding to multiple process steps, the carbon emission measurement results of the target production scenario and the uncertainty corresponding to the carbon emission measurement results of the target production scenario are determined.

2. The carbon emission measurement method for the cement industry according to claim 1, characterized in that, The preprocessing of the emissions dataset includes: The time sliding window algorithm is used to perform lag compensation on the emission dataset and remove outlier data from the emission dataset.

3. The carbon emission measurement method for the cement industry according to claim 1, characterized in that, The preprocessed emission dataset is fitted using the SVR model to determine reference emission data for multiple process steps, including: Based on the SVR model, quantile regression or envelope analysis is performed on the preprocessed emission dataset to determine reference emission data for multiple process steps.

4. The carbon emission measurement method for the cement industry according to claim 1, characterized in that, The uncertainty of the reference emission data corresponding to multiple process steps is determined based on the uncertainty of the emission dataset and the uncertainty of the SVR model, including: Based on the uncertainty of the emission dataset, the sensitivity coefficient of the SVR model to the emission dataset, and the residual standard deviation of the SVR model, the uncertainty of the reference emission data corresponding to multiple process steps is determined.

5. The carbon emission measurement method for the cement industry according to claim 1, characterized in that, The determination of the carbon emission measurement result of the target production scenario and the uncertainty corresponding to the carbon emission measurement result of the target production scenario, based on the process steps included in the target production scenario, the reference emission data corresponding to multiple process steps, and the uncertainty of the reference emission data corresponding to multiple process steps, includes: The sum of reference emission data corresponding to the process steps included in the target production scenario is determined as the carbon emission measurement result of the target production scenario, and the variance summation result of the uncertainty of the reference emission data corresponding to the process steps included in the target production scenario is determined as the uncertainty corresponding to the carbon emission measurement result of the target production scenario.

6. The carbon emission measurement method for the cement industry according to claim 1, characterized in that, The method further includes: Based on the carbon emission measurement results of the target production scenario and the uncertainty corresponding to the carbon emission measurement results of the target production scenario, the carbon emission threshold of the target production scenario is determined. If the actual carbon emissions in the target production scenario exceed the carbon emission threshold, it is determined that there is a carbon emission spillover problem in the target production scenario.

7. The carbon emission measurement method for the cement industry according to claim 6, characterized in that, The method further includes: If it is determined that there is a carbon emission spillover problem in the target production scenario, the carbon emission threshold corresponding to the process steps included in the target production scenario is determined based on the reference emission data corresponding to the process steps included in the target production scenario and the uncertainty of the reference emission data corresponding to the process steps included in the target production scenario. Process steps whose actual carbon emissions from the process steps included in the target production scenario exceed the carbon emission threshold corresponding to the process steps included in the target production scenario are identified as process steps to be improved.

8. A carbon emission metering device for the cement industry, characterized in that, include: The acquisition module is used to acquire process status data and emission data of multiple process steps at multiple sampling times, and to construct an emission dataset based on the process status data and emission data of multiple process steps at multiple sampling times. The fitting module is used to fit the preprocessed emission dataset based on the SVR model to determine the reference emission data corresponding to multiple process steps. The first determination module is used to determine the uncertainty of reference emission data corresponding to multiple process steps based on the uncertainty of the emission dataset and the uncertainty of the SVR model. The second determining module is used to determine the carbon emission measurement result of the target production scenario and the uncertainty corresponding to the carbon emission measurement result of the target production scenario based on the process steps included in the target production scenario, the reference emission data corresponding to multiple process steps, and the uncertainty of the reference emission data corresponding to multiple process steps.

9. A measuring device, characterized in that, Including memory and processor, among which, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the carbon emission measurement method for the cement industry as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the carbon emission measurement method for the cement industry as described in any one of claims 1 to 7.

Images