Cement industry low-carbon control method and system based on energy carbon data

Abstract

The invention relates to the technical field of low-carbon control, in particular to a cement industry low-carbon control method and system based on energy-carbon data. The method comprises the following steps: firstly, determining a carbon emission boundary of a process industry enterprise, determining a direct carbon emission source and an indirect carbon emission source, collecting energy carbon data in real time by utilizing a carbon metering device, then reporting the collected energy carbon data to a carbon monitoring system by utilizing a carbon metering edge controller, and collecting characteristics and working condition data in an existing working condition system of the enterprise in real time; the energy-carbon data, the characteristics and the working condition data serve as input through the carbon monitoring system, the optimal air-fuel ratio serves as output, fitting training is conducted through a stack self-encoding neural network, a large number of data samples are analyzed to obtain control rules for learning, and the parameter range for achieving the optimal air-fuel ratio is determined; finally, a low-carbon control result is displayed through a carbon monitoring system, the clinker decomposition rate can be increased, and the effects of saving energy and reducing carbon are achieved.

Description

Technical Field

[0001] The present invention relates to the field of low-carbon control technologies, and in particular, to a low-carbon control method and system for the cement industry based on energy-carbon data. Background Art

[0002] As one of the important sources of carbon emissions in the global industrial field, the cement industry has a particularly arduous task of carbon emission reduction. According to data from the International Energy Agency, the direct carbon emissions of the cement industry account for as high as 27% of the total industrial carbon emissions, second only to the steel industry. With the proposal and continuous promotion of the global carbon neutrality goal, the cement industry is facing huge carbon emission reduction pressure.

[0003] The carbon emissions in the cement production process mainly come from two aspects: one is the decomposition of raw material carbonates (such as limestone), and the other is the combustion of fuels (such as coal). The CO2 emissions generated by the decomposition of raw material carbonates account for a relatively large proportion of the carbon emissions in cement production.

[0004] In summary, therefore, a low-carbon control method and system for the cement industry based on energy-carbon data that can improve the clinker decomposition rate and achieve the effect of energy conservation and carbon reduction are proposed. Summary of the Invention

[0005] The purpose of the present invention is to provide a low-carbon control method and system for the cement industry based on energy-carbon data, aiming to achieve the effect of improving the clinker decomposition rate and achieving energy conservation and carbon reduction.

[0006] To achieve the above purpose, a low-carbon control method for the cement industry based on energy-carbon data adopted by the present invention includes the following steps:

[0007] Determine the carbon emission boundary of process industrial enterprises, and determine direct carbon emission sources and indirect carbon emission sources;

[0008] Install a carbon metering device at the carbon emission source, and use the carbon metering device to collect energy-carbon data in real time;

[0009] Use the carbon metering edge controller to report the collected energy-carbon data to the carbon monitoring system;

[0010] Use the carbon metering edge controller to collect the characteristics and operating condition data in the existing operating condition system of the enterprise in real time, and report them to the carbon monitoring system;

[0011] Use the carbon monitoring system to take the energy-carbon data, characteristics, and operating condition data as inputs, and the optimal air-fuel ratio as the output, and perform fitting training through a stacked autoencoder neural network. Through the analysis of a large number of data samples to obtain control rules for learning, determine the parameter range to achieve the optimal air-fuel ratio;

[0012] Display the low-carbon control results through the carbon monitoring system.

[0013] Among them, in the steps of determining the carbon emission boundary of process industrial enterprises and determining direct and indirect carbon emission sources:

[0014] Direct carbon emission sources include flue gas emissions.

[0015] Among them, in the steps of determining the carbon emission boundary of process industrial enterprises and determining direct and indirect carbon emission sources:

[0016] Indirect carbon emission sources include enterprise electricity consumption.

[0017] Among them, in the steps of installing carbon metering devices at carbon emission sources and using the carbon metering devices to collect energy and carbon data in real time:

[0018] Install continuous flue gas monitoring equipment at the flue gas emission port, and the collected data includes CO2 concentration, CO2 flow rate, CO2 pressure, and CO2 temperature.

[0019] Among them, in the steps of installing carbon metering devices at carbon emission sources and using the carbon metering devices to collect energy and carbon data in real time:

[0020] Install electricity meters at the electricity access points, and the collected data includes total forward active electric energy, forward active electricity energy at rate 1, forward active electricity energy at rate 2, forward active electricity energy at rate 3, forward active electricity energy at rate 4, total reverse active electric energy, reverse active electricity energy at rate 1, reverse active electricity energy at rate 2, reverse active electricity energy at rate 3, reverse active electricity energy at rate 4, as well as voltage, current, and power.

[0021] Among them, in the steps of using the carbon metering edge controller to collect the characteristics and operating conditions data in the enterprise's existing operating condition system in real time and reporting them to the carbon monitoring system:

[0022] The characteristics and operating conditions data include raw material consumption, pulverized coal consumption, temperature, pressure, clinker output, and the position of the high-temperature fan valve.

[0023] The present invention also provides a low-carbon control system for the cement industry based on energy and carbon data, including a carbon emission source confirmation module, a carbon emission source collection module, a recording module, a reporting module, a processing module, and a display module;

[0024] The carbon emission source confirmation module is used to determine the carbon emission boundary of process industrial enterprises and determine direct and indirect carbon emission sources;

[0025] The carbon emission source collection module is used to collect energy and carbon data in real time;

[0026] The recording module is used to collect energy and carbon data and collect the characteristics and operating conditions data in the enterprise's existing operating condition system and report them to the carbon monitoring system;

[0027] The reporting module is used to upload energy-carbon data, features, and operating condition data to the background;

[0028] The processing module takes energy-carbon data, features, and operating condition data as inputs and the optimal air-fuel ratio as the output, and performs fitting training through a stacked autoencoder neural network. By analyzing a large number of data samples to obtain control rules for learning, it determines the parameter range to achieve the optimal air-fuel ratio;

[0029] The display module is used to display the low-carbon control results.

[0030] A low-carbon control method and system for the cement industry based on energy-carbon data of the present invention first determines the carbon emission boundary of a process industrial enterprise, determines direct carbon emission sources and indirect carbon emission sources, installs carbon metering devices at the carbon emission sources, uses the carbon metering devices to collect energy-carbon data in real time, then uses a carbon metering edge controller to report the collected energy-carbon data to a carbon monitoring system. At the same time, the carbon metering edge controller is used to collect the features and operating condition data in the existing operating condition system of the enterprise in real time and report them to the carbon monitoring system. The carbon monitoring system takes the energy-carbon data, features, and operating condition data as inputs and the optimal air-fuel ratio as the output, and performs fitting training through a stacked autoencoder neural network. By analyzing a large number of data samples to obtain control rules for learning, it determines the parameter range to achieve the optimal air-fuel ratio. Finally, the carbon monitoring system displays the low-carbon control results. Through the above method, it is possible to improve the clinker decomposition rate, achieve the effect of energy conservation and carbon reduction, and increase the economic and environmental benefits brought to the enterprise in production. Description of the Drawings

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0032] Figure 1 is the step flowchart of the low-carbon control method for the cement industry based on energy-carbon data of the present invention.

[0033] Figure 2 is the schematic diagram of the principle of the low-carbon control system for the cement industry based on energy-carbon data of the present invention.

[0034] Figure 3 is the schematic diagram of the stacked autoencoder neural network of the present invention.

[0035] Figure 4 is the schematic diagram of the low-carbon control process of the present invention.

[0036] 701 - Carbon emission source confirmation module, 702 - Carbon emission source collection module, 703 - Recording module, 704 - Reporting module, 705 - Processing module, 706 - Display module. Detailed implementation

[0037] Please refer to Figures 1 to 4 , the present invention provides a low - carbon control method for the cement industry based on energy - carbon data, including the following steps:

[0038] S100: Determine the carbon emission boundary of process industrial enterprises, and determine direct carbon emission sources and indirect carbon emission sources;

[0039] S200: Install carbon metering devices at carbon emission sources, and use the carbon metering devices to collect energy - carbon data in real - time;

[0040] S300: Use the carbon metering edge controller to report the collected energy - carbon data to the carbon monitoring system;

[0041] S400: Use the carbon metering edge controller to collect the characteristics and operating conditions data in the existing operating condition system of the enterprise in real - time, and report them to the carbon monitoring system;

[0042] S500: Use the carbon monitoring system to take the energy - carbon data, characteristics and operating conditions data as inputs, and the optimal air - fuel ratio as the output, and perform fitting training through a stacked auto - encoder neural network, learn by analyzing a large number of data samples to obtain control rules, and determine the parameter range to achieve the optimal air - fuel ratio;

[0043] S600: Display the low - carbon control results through the carbon monitoring system.

[0044] In this embodiment, first, determine the carbon emission boundary of process industrial enterprises, determine direct carbon emission sources and indirect carbon emission sources, install carbon metering devices at carbon emission sources, and use the carbon metering devices to collect energy - carbon data in real - time. Then, use the carbon metering edge controller to report the collected energy - carbon data to the carbon monitoring system. At the same time, use the carbon metering edge controller to collect the characteristics and operating conditions data in the existing operating condition system of the enterprise in real - time, and report them to the carbon monitoring system. Use the carbon monitoring system to take the energy - carbon data, characteristics and operating conditions data as inputs, and the optimal air - fuel ratio as the output, and perform fitting training through a stacked auto - encoder neural network, learn by analyzing a large number of data samples to obtain control rules, and determine the parameter range to achieve the optimal air - fuel ratio. Finally, display the low - carbon control results through the carbon monitoring system. Through the above method, it is possible to improve the clinker decomposition rate, achieve the effect of energy conservation and carbon reduction, and increase the economic and environmental benefits brought to the enterprise in production.

[0045] The present invention also provides a low-carbon control system for the cement industry based on energy-carbon data, including a carbon emission source confirmation module 701, a carbon emission source collection module 702, a recording module 703, a reporting module 704, a processing module 705, and a display module 706;

[0046] The carbon emission source confirmation module 701 is used to determine the carbon emission boundary of process industrial enterprises, and determine direct carbon emission sources and indirect carbon emission sources;

[0047] The carbon emission source collection module 702 is used to collect energy-carbon data in real time;

[0048] The recording module 703 is used to collect energy-carbon data, and collect the characteristics and operating conditions data in the enterprise's existing operating condition system and report them to the carbon monitoring system;

[0049] The reporting module 704 is used to upload energy-carbon data, characteristics, and operating conditions data to the background;

[0050] The processing module 705 uses energy-carbon data, characteristics, and operating conditions data as inputs, and the optimal air-fuel ratio as the output, and performs fitting training through a stacked autoencoder neural network, learns by analyzing a large number of data samples to obtain control rules, and determines the parameter range to achieve the optimal air-fuel ratio;

[0051] The display module 706 is used to display the low-carbon control results.

[0052] In this embodiment, the carbon emission source confirmation module 701 determines the carbon emission boundary of process industrial enterprises, determines direct carbon emission sources and indirect carbon emission sources, uses the carbon emission source collection module 702 to collect energy-carbon data in real time, the recording module 703 collects energy-carbon data, and collects the characteristics and operating conditions data in the enterprise's existing operating condition system and reports them to the carbon monitoring system, the reporting module 704 uploads energy-carbon data, characteristics, and operating conditions data to the background, the processing module 705 uses energy-carbon data, characteristics, and operating conditions data as inputs, and the optimal air-fuel ratio as the output, and performs fitting training through a stacked autoencoder neural network, learns by analyzing a large number of data samples to obtain control rules, and determines the parameter range to achieve the optimal air-fuel ratio, and the display module 706 displays the low-carbon control results.

[0053] The above-disclosed is only a preferred embodiment of the present invention, and of course, it cannot be used to limit the scope of the rights of the present invention. Those of ordinary skill in the art can understand all or part of the processes of implementing the above embodiments, and the equivalent changes made according to the claims of the present invention still fall within the scope covered by the invention.

Claims

1. A low-carbon control method for the cement industry based on energy and carbon data, characterized in that, It includes the following steps: Determine the carbon emission boundary of process industrial enterprises, and identify direct carbon emission sources and indirect carbon emission sources; among them, the direct carbon emission sources include flue gas emissions, and the indirect carbon emission sources include enterprise electricity consumption; Install carbon metering devices at carbon emission sources, and use the carbon metering devices to collect energy and carbon data in real time; Use the carbon metering edge controller to report the collected energy and carbon data to the carbon monitoring system; Use the carbon metering edge controller to collect the characteristics and operating conditions data in the enterprise's existing operating condition system in real time, and report them to the carbon monitoring system; Use the carbon monitoring system to take the energy and carbon data, characteristics and operating conditions data as inputs, and the optimal air-fuel ratio as the output, and perform fitting training through a stacked autoencoder neural network. Learn by analyzing a large number of data samples to obtain control rules, and determine the parameter range to achieve the optimal air-fuel ratio; Display the low-carbon control results through the carbon monitoring system; Among them, in the step of installing carbon metering devices at carbon emission sources and using the carbon metering devices to collect energy and carbon data in real time: Install an electric meter at the electricity gateway, and the collected data includes total forward active power, forward active power rate 1 energy, forward active power rate 2 energy, forward active power rate 3 energy, forward active power rate 4 energy, reverse active total power, reverse active power rate 1 energy, reverse active power rate 2 energy, reverse active power rate 3 energy, reverse active power rate 4 energy, as well as voltage, current, and power.

2. The low-carbon control method for the cement industry based on energy and carbon data according to claim 1, wherein Among them, in the step of installing carbon metering devices at carbon emission sources and using the carbon metering devices to collect energy and carbon data in real time: Install continuous flue gas emission monitoring equipment at the flue gas emission port, and the collected data includes CO2 concentration, CO2 flow rate, CO2 pressure, and CO2 temperature.

3. The low-carbon control method for the cement industry based on energy and carbon data according to claim 1, characterized in that, In the step of using the carbon metering edge controller to collect the characteristics and operating conditions data in the enterprise's existing operating condition system in real time and reporting them to the carbon monitoring system: The characteristics and operating conditions data include raw material consumption, pulverized coal consumption, temperature, pressure, clinker output, and the position of the high-temperature fan valve.

4. A low-carbon control system for the cement industry based on energy and carbon data, which is applied to the low-carbon control method for the cement industry based on energy and carbon data as described in claim 1, characterized in that It includes a carbon emission source confirmation module, a carbon emission source collection module, a recording module, a reporting module, a processing module, and a display module; The carbon emission source confirmation module is used to determine the carbon emission boundary of process industrial enterprises and identify direct carbon emission sources and indirect carbon emission sources; The carbon emission source collection module is used to collect energy and carbon data in real time; The recording module is used to collect energy and carbon data, and collect the characteristics and operating conditions data in the enterprise's existing operating condition system and report them to the carbon monitoring system; The reporting module is used to upload the energy and carbon data, characteristics and operating conditions data to the background; The processing module is used to take the energy and carbon data, characteristics and operating conditions data as inputs, and the optimal air-fuel ratio as the output, and perform fitting training through a stacked autoencoder neural network. Learn by analyzing a large number of data samples to obtain control rules, and determine the parameter range to achieve the optimal air-fuel ratio; The display module is used to display the low-carbon control results.

Images