Carbon emission calculation method and device and electronic equipment

Abstract

The invention provides a carbon emission calculation method and device and electronic equipment, and belongs to the technical field of environmental protection. The method comprises the following steps: acquiring process parameters of a catalytic cracking device in a catalytic cracking reaction process; inputting the process parameters into a charring amount prediction model to obtain a charring amount prediction result output by the charring amount prediction model; calculating the carbon emission based on the prediction result of the scorching amount; wherein the charring amount prediction model is obtained based on sample process parameters and charring amount result label training corresponding to the sample process parameters. According to the method, the scorching amount prediction model is trained through the sample process parameters and the scorching amount result labels corresponding to the sample process parameters, and scorching amount prediction can be carried out on the process parameters in the catalytic cracking reaction process based on the trained scorching amount prediction model. By means of the scorching amount prediction model, the problem that the scorching amount is difficult to accurately and timely calculate in the prior art can be solved, and accurate and timely calculation of the carbon emission in the catalytic cracking process is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental protection, and in particular to a carbon emission calculation method, a carbon emission calculation device and an electronic device. Background Art

[0002] Oil refining enterprises are the country's energy pillar industry and also a key industry for carbon emission reduction. The catalytic cracking (FCC) unit is an important crude oil secondary processing unit for oil refining enterprises. It is the main production unit for liquefied gas, gasoline, diesel and other products. It is also one of the main sources of carbon emissions for oil refining enterprises. During the catalytic cracking reaction, the activity of the catalyst surface will be reduced due to the attachment of coke, and it must be regenerated in the regenerator. The coke attached to the catalyst surface burns at high temperature to generate catalyst regeneration flue gas. This contains a large amount of greenhouse gases such as carbon dioxide. Clarifying the carbon emissions of each link of the catalytic cracking unit plays an important role in formulating emission reduction plans and related measures in a targeted manner.

[0003] The carbon emission accounting of the catalytic cracking unit of the refinery is mainly divided into carbon dioxide emissions brought in by raw materials, carbon dioxide emissions in the process production process and carbon dioxide emissions implied by net purchased electricity and heat. Among them, the carbon dioxide emissions brought in by raw materials and implied by net purchased electricity and heat are mainly calculated based on the amount of raw materials, purchased electricity and hot water steam. Since there are clear ledger data, the calculation is relatively accurate. However, the existing technology calculates the carbon dioxide emissions in the process production process mainly based on the amount of char burnt, and the calculation of the amount of char burnt requires relying on a large amount of laboratory monitoring data, with a long analysis cycle, and it is difficult to achieve accurate and real-time calculation of the amount of char burnt. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a carbon emissions calculation method, a carbon emissions calculation device and an electronic device to solve the defects that the prior art calculates the carbon dioxide emissions in the process production process mainly based on the charred amount, and the calculation of the charred amount requires a large amount of laboratory monitoring data, the analysis cycle is long, and it is difficult to achieve accurate and real-time calculation of the charred amount.

[0005] In order to achieve the above object, an embodiment of the present invention provides a method for calculating carbon emissions, the method comprising:

[0006] Obtaining process parameters of the catalytic cracking unit during the catalytic cracking reaction;

[0007] Inputting the process parameters into a charring amount prediction model to obtain a charring amount prediction result output by the charring amount prediction model;

[0008] Calculating carbon emissions based on the charring amount prediction result;

[0009] The charring amount prediction model is obtained by training based on sample process parameters and charring amount result labels corresponding to the sample process parameters.

[0010] On the other hand, an embodiment of the present invention further provides a carbon emission calculation device, including:

[0011] A first data acquisition module is used to acquire process parameters of the catalytic cracking unit during the catalytic cracking reaction;

[0012] A first model prediction module, used for inputting the process parameters into a charred amount prediction model to obtain a charred amount prediction result output by the charred amount prediction model;

[0013] A carbon emission calculation module, used for calculating the carbon emission based on the charring amount prediction result;

[0014] The charring amount prediction model is obtained by training based on sample process parameters and charring amount result labels corresponding to the sample process parameters.

[0015] On the other hand, the present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the carbon emission calculation methods described above is implemented.

[0016] On the other hand, the present invention further provides a machine-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the carbon emission calculation method as described in any one of the above is implemented.

[0017] Through the above technical solution, the present invention trains the char amount prediction model through sample process parameters and the char amount result labels corresponding to the sample process parameters, and the char amount prediction can be performed on the process parameters in the catalytic cracking reaction process based on the trained char amount prediction model. The char amount prediction model of the present invention can solve the problem that the char amount is difficult to calculate accurately and timely in the prior art, and realize the accurate and timely calculation of carbon emissions in the catalytic cracking process.

[0018] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0020] Figure 1It is one of the flow charts of the carbon emission calculation method provided by the present invention;

[0021] Figure 2 This is the second flow chart of the carbon emission calculation method provided by the present invention;

[0022] Figure 3 This is the third flow chart of the carbon emission calculation method provided by the present invention;

[0023] Figure 4 This is the fourth flow chart of the carbon emission calculation method provided by the present invention;

[0024] Figure 5 It is a structural schematic diagram of a front-end display system of an electronic device provided by the present invention;

[0025] Figure 6 This is the fifth flow chart of the carbon emission calculation method provided by the present invention;

[0026] Figure 7 It is a structural schematic diagram of the carbon emission calculation device provided by the present invention;

[0027] Figure 8 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0028] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0029] Method Embodiment

[0030] Embodiment 1

[0031] Please refer to Figure 1 The present invention provides a method for calculating carbon emissions, the method comprising:

[0032] Step 100: Obtain process parameters of a catalytic cracking unit during a catalytic cracking reaction.

[0033] The electronic device obtains the process parameters of the catalytic cracking unit during the catalytic cracking reaction process. The process parameters include the raw material processing amount, the regeneration main air volume, the regenerator dense phase bottom temperature, the regenerator top outlet oxygen content, the reactor stripping steam volume, the riser second reverse temperature, the regenerator top outlet carbon monoxide content and / or the regenerated catalyst carbon content. That is, the process parameters include any one of the raw material processing amount, the regeneration main air volume, the regenerator dense phase bottom temperature, the regenerator top outlet oxygen content, the reactor stripping steam volume, the riser second reverse temperature, the regenerator top outlet carbon monoxide content and the regenerated catalyst carbon content.

[0034] It should be noted that when there are more process parameters, that is, more reference parameters involved in predicting the amount of charring, the predicted amount of charring is more accurate. Therefore, in one embodiment, the process parameters include raw material processing volume, regeneration main air volume, regenerator dense phase bottom temperature, regenerator top outlet oxygen content, reactor stripping steam volume, riser second reactor temperature, regenerator top outlet carbon monoxide content and regenerated catalyst carbon content.

[0035] In addition, the above process parameters need to be preprocessed before being input into the char burn prediction model. For example, in one embodiment, the data preprocessing of the process parameters includes: real-time collection of all process parameters of the catalytic cracking unit during the catalytic cracking reaction, and deleting the process parameters during the shutdown period to perform process parameter preprocessing.

[0036] For another example, after the process parameters to be input into the charring amount prediction model are screened in the above steps, the data range calculation is uniformly performed to obtain a range of process parameters, and the range is adjusted in combination with the properties of each process parameter and each actual rated working condition to determine the range of each process parameter. Parameters that are not within the range of the process parameters are deleted.

[0037] That is, the preprocessing of process parameters includes data collection in the normal operating period, which is used to extract data in the normal operating period and delete data in the shutdown state; and includes abnormal data elimination, according to a pre-set data threshold range, retaining the collected data within the threshold range and eliminating the data outside the threshold range.

[0038] Step 200: input the process parameters into a charring amount prediction model to obtain a charring amount prediction result output by the charring amount prediction model.

[0039] The electronic device inputs the process parameters into a burn amount prediction model to obtain a burn amount prediction result output by the burn amount prediction model, wherein the burn amount prediction model is trained based on sample process parameters and burn amount result labels corresponding to the sample process parameters.

[0040] The sample process parameters may be selected from the sample raw material processing volume, the sample regeneration main air volume, the sample regenerator dense phase bottom temperature, the sample regenerator top outlet oxygen content, the sample reactor stripping steam volume, the sample riser second temperature and the sample regenerated catalyst carbon content. The char burnt amount result label is the char burnt amount result label of the catalytic cracking unit corresponding to the above sample process parameters. Compared with the existing calculation of the char burnt amount, which relies on a large amount of laboratory monitoring data and has a long analysis cycle, the embodiment of the present invention trains the char burnt amount prediction model through supervised training based on the sample process parameters and the char burnt amount result label. Therefore, the char burnt amount prediction model can calculate the input process parameters of the catalytic cracking unit and obtain the char burnt amount of the catalytic cracking unit in real time. Accurate and timely calculation of carbon emissions in the catalytic cracking process is achieved.

[0041] The burn amount prediction model may use various regression models. For example, in one embodiment, the burn amount prediction model may use an RBF neural network model.

[0042] The RBF neural network model is as follows: In the RBF neural network structure, let X = [x1, x2, ..... x m ] is the input vector of the neural network, let B = [b1,b2,........b m ] is the basis width variable of the neural network. The RBF neural network algorithm uses the Gaussian function as the radial basis function, and the function expression is as follows:

[0043]

[0044] In formula (1): X is the input variable; C j is the center of the Gaussian function; ||X-Cj|| is the Euclidean norm; b is the basis width parameter of the node.

[0045] The output value of the RBF neural network at time k is expressed as follows:

[0046] y m (k) = wh = w1h1 + w2h2 + ... + w m h m (2)

[0048] In formula (2), w is the weight between the hidden layer and the output layer; y m (k) is the actual output.

[0049] When the output value y at time k m When the mean square error between the actual value y(k) at time k and the actual value y(k) at time k is less than the allowable error, it is proved that the output value is available. The calculation formula is as follows:

[0050]

[0051] A method for calculating the amount of charring in one embodiment is described below.

[0052] Step 1: Data collection and processing. 300,000 pieces of original data from March 4, 2018 to December 31, 2020 were collected for data analysis and correlation analysis, and eight process parameters were retained: stripping steam volume, regeneration main air volume, riser second reactor temperature, regenerator dense phase bottom temperature, regenerated catalyst carbon content, regenerator top outlet oxygen content, regenerator top outlet carbon monoxide content, and raw material processing volume.

[0053] Data is deleted according to the respective value ranges of the process parameters imported into the neural network model, and the values ​​within the value range of the process parameters are retained. The data at 8 o'clock every day for a continuous time period (January 1, 2020-December 31, 2021) are intercepted from the model. The two-year data is divided into two parts. A total of 547 data from January 1, 2020 to May 31, 2021 are used as model training data to input into the burnt amount prediction model for model training to improve the model prediction accuracy. A total of 184 data from June 1, 2021 to December 31, 2021 are imported as input variables into the burnt amount prediction model for burnt amount prediction calculation. The calculation here is to use the data of the previous period of the current time period for prediction calculation, and predict the burnt amount of the current time period.

[0054] Step 2: Establish the RBF neural network structure: determine the number of neurons to be 8 and the number of hidden layers (two layers) to construct an 8-input 1-output neural network model as a burn amount prediction model.

[0055] Step 3: RBF neural network training: A total of 547 data from January 1, 2020 to May 31, 2021 were input into the burn amount prediction model as model training data, and the initial weights and thresholds of the neural network links were gradually adjusted to improve the prediction accuracy of the neural network to the best.

[0056] Step 4: RBF neural network prediction output: Use the neural network that has been trained in step 3 to automatically calculate the corresponding predicted value of the amount of charring based on a total of 184 data from June 1, 2021 to December 31, 2021.

[0057] Step 300: Calculate carbon emissions based on the charring amount prediction result.

[0058] The electronic device calculates the carbon emission based on the charring amount prediction result. The present invention trains the charring amount prediction model through sample process parameters and the charring amount result labels corresponding to the sample process parameters, and the charring amount prediction can be performed on the process parameters in the catalytic cracking reaction process based on the trained charring amount prediction model. The charring amount prediction model of the present invention can solve the problem of the difficulty in accurately and timely calculating the charring amount in the prior art, and realize the accurate and timely calculation of the carbon emission in the catalytic cracking process.

[0059] Embodiment 2

[0060] Please refer to Figure 2 , step 200, inputting the process parameters into the charring amount prediction model, specifically comprising: step 210, inputting the process parameters and characteristic parameters into the charring amount prediction model.

[0061] The charring amount prediction model is trained based on the following steps:

[0062] Step 10, obtaining sample process parameters and sample characteristic parameters of the catalytic cracking unit during the catalytic cracking reaction, and the charring amount result labels corresponding to the sample process parameters and the sample characteristic parameters respectively;

[0063] Step 20: training the charring amount prediction model based on the sample process parameters, the sample characteristic parameters and the charring amount result label;

[0064] The characteristic parameters and the sample characteristic parameters are obtained based on the amount of alkaline solution added to the catalytic cracking unit and the amount of acid gas removed from the regenerated flue gas.

[0065] The embodiment of the present invention inputs the process parameters and characteristic parameters in the first embodiment into the charring amount prediction model for prediction. The charring amount prediction model is trained based on the sample process parameters, the sample characteristic parameters, and the charring amount result labels corresponding to the sample process parameters and the sample characteristic parameters.

[0066] The characteristic parameters and sample characteristic parameters characterize the impact of the catalytic cracking unit on carbon emissions. The sodium hydroxide (i.e., the amount of alkaline solution added) in the desulfurization tower of the catalytic cracking unit reacts with the acidic gas in an acid-base neutralization reaction. When sodium hydroxide is insufficient, sodium hydroxide reacts preferentially with the gas with a stronger acidity, that is, it first reacts with the sulfur dioxide in the regeneration flue gas. When sodium hydroxide is excessive, it will further react with the carbon dioxide in the flue gas, thereby removing the carbon dioxide in the regeneration flue gas. During the operation of the catalytic cracking unit, in order to remove the sulfur dioxide in the catalytic regeneration flue gas to the maximum extent, the sodium hydroxide solvent in the desulfurization tower is automatically added to maintain the pH value of the circulating solvent at a high level for a long time. The amount of sodium hydroxide in the desulfurization tower is relatively excessive for the sulfur dioxide in the regeneration flue gas, so the remaining sodium hydroxide in the desulfurization tower will react with the carbon dioxide in the regeneration flue gas. Therefore, the characteristic parameters obtained based on the amount of alkaline solution added to the catalytic cracking unit and the amount of acid gas removed from the regeneration flue gas can represent the degree of influence of the catalytic cracking unit on the carbon dioxide emissions in the regeneration flue gas. In one embodiment, the characteristic parameter and the sample characteristic parameter are both obtained based on the ratio of the sample alkaline solution addition amount of the catalytic cracking unit to the sample acid gas removal amount of the regeneration flue gas.

[0067] The prior art method of calculating carbon emissions by relying on the amount of charring does not consider the impact of the charring flue gas being treated by the desulfurization equipment of the catalytic cracking unit, resulting in a certain gap between the calculated result and the actual emissions of the catalytic cracking unit. The embodiment of the present invention adds characteristic parameters to the charring amount prediction model for prediction, and by exploring the relationship between the amount of alkaline solution added to the catalytic cracking unit and the amount of acid gas removed from the regenerated flue gas, the accuracy of the carbon emissions calculation of the catalytic cracking unit of the present invention is improved.

[0068] Embodiment 3

[0069] Please refer to Figure 3 , step 300, calculating the carbon emission based on the charring amount prediction result, comprises:

[0070] Step 310: Input the prediction result of the burnt amount, the burnt amount stored in the catalytic cracking unit and the residual carbon amount of the regenerated catalyst into a carbon emission prediction model.

[0071] Step 320: Determine the carbon emission prediction result output by the carbon emission prediction model as the carbon emission.

[0072] Based on the calculated char burnt amount prediction result, the char burnt amount prediction result and the char tank storage amount and the regenerated catalyst residual carbon amount of the catalytic cracking unit are input into the trained carbon emission prediction model to obtain the carbon emission prediction result output by the carbon emission prediction model as the carbon emissions.

[0073] Since the carbon emission calculation of the catalytic cracking unit in the prior art has no fixed cycle and cannot provide guidance for production, the embodiment of the present invention selects the residual carbon content of the regenerated catalyst as a characteristic parameter to be input into the carbon emission prediction model. Since the shortest detection cycle of the residual carbon content of the regenerated catalyst data is one day, the carbon emission calculation of the catalytic cracking unit of the carbon emission prediction model in the embodiment of the present invention can achieve a daily carbon emission prediction value, which is used as work guidance data for the refinery staff. Compared with the carbon emission calculation cycle of the catalytic cracking unit in the prior art, which is longer and cannot provide guidance for production, the embodiment of the present invention uses a trained carbon emission prediction model to predict the prediction results of the charring amount and the charring tank storage amount and the residual carbon content of the regenerated catalyst of the catalytic cracking unit, so as to achieve a daily carbon emission prediction value, which is used as work guidance data for the refinery staff.

[0074] Among them, the carbon emission prediction model is trained based on the sample burnt amount prediction result, the sample burnt amount tank storage amount of the catalytic cracking unit, the sample regenerated catalyst carbon residue, and the carbon emission result labels corresponding to the sample burnt amount prediction result, the sample burnt amount tank storage amount and the sample regenerated catalyst carbon residue. The carbon emission prediction model can adopt various neural network models for implementing regression. Specifically, the carbon emission prediction model can adopt an RBF neural network structure. The specific results of the RBF neural network structure can refer to the relevant description of the RBF neural network structure (or RBF neural network model) of the above-mentioned burnt amount prediction model, which will not be repeated here.

[0075] For example, an example is provided below for explanation.

[0076] Step 1: using the burnt tank storage amount, the regenerated catalyst carbon residue amount and the burnt amount prediction result calculated by the burnt amount prediction model as input variables, a total of three input variables;

[0077] Step 2: Establish the RBF neural network structure: determine the number of neurons 3, the number of hidden layers (two layers) to build a 3-input 1-output neural network model;

[0078] Step 3: RBF neural network training: A total of 547 data from January 1, 2020 to May 31, 2021 are input into the carbon emissions prediction model as model training data, and the initial weights and thresholds of the neural network links are gradually adjusted to improve the prediction accuracy of the neural network to the best;

[0079] Step 4: RBF neural network prediction output: Use the neural network trained in step 3 to automatically calculate the corresponding carbon emissions prediction results based on a total of 184 data from June 1, 2021 to December 31, 2021.

[0080] The embodiment of the present invention trains a carbon emission prediction model through supervised training based on the sample char burnt amount prediction result, the sample char burnt tank storage amount of the catalytic cracking unit, the sample regenerated catalyst carbon residue amount and the carbon emission result label. Therefore, the carbon emission prediction model can calculate the input char burnt amount prediction result, the char burnt tank storage amount of the catalytic cracking unit and the regenerated catalyst carbon residue amount to obtain carbon emissions. Accurate and timely calculation of carbon emissions in the catalytic cracking process is achieved.

[0081] Embodiment 4

[0082] Please refer to Figure 4 In the embodiment of the present invention, after step 300, calculating the carbon emission based on the charring amount prediction result, the method further includes:

[0083] Step 400: Determine the electricity consumption and heat consumption of each unit of the catalytic cracking unit.

[0084] The electronic equipment determines the electricity consumption and heat consumption of each unit of the catalytic cracking unit. The units of the catalytic cracking unit include the reaction-regeneration unit, the fractionation unit, the absorption and stabilization unit, etc. of the catalytic cracking unit. The stripping efficiency of the stripping tower in the fractionation process of the fractionation unit affects the energy consumption, and can also increase the energy efficiency of the catalytic cracking unit, affecting the energy loss, mainly steam loss and electric energy loss. The absorption and stabilization tower of the absorption and stabilization unit is an endothermic process, which requires a large amount of high-pressure steam 1.0Mpa steam, etc. The air compressor will cause a large amount of electric energy consumption. At the same time, the feed temperature of the desorption tower, the hot and cold feed method of the desorption tower, and the feed temperature of the stabilization tower can all have a certain impact on energy consumption.

[0085] It should be noted that the carbon emission calculation of the catalytic cracking unit is divided into direct carbon emission calculation and indirect carbon emission calculation, and the direct carbon emission calculation is the carbon emission calculated in the above steps 100 to 300. In this embodiment, steps 100 to 300 calculate indirect carbon emissions.

[0086] Specifically, A.D. 电力 Electricity consumption is the difference between purchased electricity and external electricity. Heat consumption calculation is divided into steam consumption calculation and hot water consumption calculation according to the amount of steam and hot water consumed.

[0087] The calculation formula for hot water consumption is:

[0088] AD hot water = Ma w ×(Tw-20)×4.1868×10 -3

[0089] Among them, AD hot water is the heat of hot water, the unit is GJ; Ma w is the mass of hot water, in tons of hot water; Tw is the temperature of hot water, in °C; 4.1868 is the specific heat of water at room temperature and pressure, in kJ / (kg·°C).

[0090] The formula for calculating steam consumption is:

[0091] AD steam = Ma st ×(En st -83.74)×10 -3

[0092] Among them, AD steam is the heat of steam, the unit is GJ; Ma st is the mass of steam, in tons of steam; En st It is the thermal enthalpy of each kilogram of steam at the temperature and pressure corresponding to the steam, with the unit of kJ / kg.

[0093] Based on the sum of steam consumption and hot water consumption, the heat consumption is obtained.

[0094] Step 500: Calculate the carbon emissions implied by the net purchased electricity and the carbon emissions implied by the net purchased heat of each unit based on the electricity consumption and heat consumption of each unit.

[0095] The electronic device calculates the carbon emissions implied by the net purchased electricity and the carbon emissions implied by the net purchased heat of each unit based on the electricity consumption and the heat consumption of each unit.

[0096] Specifically, the calculation formula for the carbon emissions implied by each unit of net purchased electricity (i.e. indirect carbon emissions) is as follows:

[0097] E CO2-净电 =AD 电力 ×EF 电力

[0098] Among them, E CO2-净电 The carbon emissions embodied in the net purchased electricity for each unit, in tons of CO2; AD 电力 The net electricity consumption purchased by the enterprise is expressed in megawatt-hours (MWh); EF 电力 is the CO2 emission factor for electricity supply, in tons CO2 / MWh; as above, AD 电力 Electricity consumption is the difference between purchased electricity and externally supplied electricity, EF 电力 The carbon emission factor of electricity supply is the average CO2 emission factor of the regional power grid to which the enterprise's production site is located.

[0099] The formula for calculating the carbon emissions embodied in the net purchased heat per unit is as follows:

[0100] E CO2-净热 =AD热力 ×EF 热力

[0101] Among them, E CO2-净热 The CO2 emissions implied by the reporting entity’s net purchased heat, in tons of CO2; AD 热力 The net purchased heat consumption of the enterprise, in GJ; EF 热力 It is the CO2 emission factor for heat supply, in tons CO2 / GJ.

[0102] Step 600: Based on a preset mapping relationship, determine and display the warning type and emission reduction plan for each unit corresponding to the carbon emissions implied by the net purchased electricity and the carbon emissions implied by the net purchased heat of each unit.

[0103] It should be noted that the preset mapping relationship in the implementation of the present invention includes different warning types and emission reduction plans corresponding to the carbon emissions implied by the net purchased electricity and the carbon emissions implied by the net purchased heat. For example, see Figure 5 , the carbon emissions implied by the net purchased electricity of the fractionation unit A1 and the carbon emissions implied by the net purchased heat A2, the corresponding alarm warning type is a low-level alarm (referred to as low alarm), at this time the carbon emission mode corresponds to indirect carbon emissions, and the emission reduction plan is to reduce the injection of fresh water. In addition, the front-end display system of the electronic equipment can also display the process flow chart of the reaction-regeneration unit, the process flow chart of the fractionation unit, and the process flow chart of the absorption stabilization unit.

[0104] The carbon emission calculation of the catalytic cracking unit in the prior art is only for the entire catalytic cracking unit, without segmenting the carbon emissions for each unit (including the reaction-regeneration unit (including the waste heat boiler), the distillation unit, and the absorption and stabilization unit), and it is impossible to clearly define the carbon emissions of each unit and link of the catalytic cracking unit. The embodiment of the present invention analyzes the carbon emission details of each unit according to the energy consumption and carbon emission mode of each unit, clarifies the indirect carbon emissions and alarm warning types of each unit, formulates emission reduction plans and related measures in a targeted manner, and transmits them to the front-end display system for display.

[0105] In summary, please refer to Figure 6 , the following introduces a method for calculating carbon emissions according to an embodiment of the present invention.

[0106] S1: Collect all process parameters in a catalytic cracking unit within a certain period of time;

[0107] S2: Parameter preprocessing is performed on the collected data, the normal operating condition section is extracted, the data in the shutdown state is deleted, and the threshold value of all process parameters is calculated;

[0108] S3: Delete abnormal data from the collected and processed data, and preliminarily determine the process parameters to be included in the charring amount prediction model;

[0109] S4: Perform key parameter analysis on the parameters initially included in the char burn amount prediction model to determine the process parameters that are finally included in the char burn amount prediction model (i.e., raw material processing volume, regeneration main air volume, regenerator dense phase bottom temperature, regenerator top outlet oxygen content, reactor stripping steam volume, riser second reactor temperature, regenerator top outlet carbon monoxide content and regenerated catalyst carbon content);

[0110] S5: obtaining characteristic parameters (i.e., the ratio of the amount of alkaline solution added to the sample of the catalytic cracking unit and the amount of acid gas removed from the regenerated flue gas) through business analysis and data analysis;

[0111] S6: Incorporating characteristic parameters and process parameters into the charring amount prediction model;

[0112] S7: Obtaining a burnt amount prediction result using the trained burnt amount prediction model;

[0113] S8: Based on the prediction results of the amount of coke, the amount of coke stored in the catalytic cracking unit and the amount of residual carbon in the regenerated catalyst, the trained carbon emission prediction model is used to obtain the carbon emission prediction results;

[0114] S9: Collect data and information required for indirect carbon emission calculations, including electricity data and heat data, namely, electricity consumption, carbon emission factors of electricity supply, heat consumption, and carbon emission factors of heat supply;

[0115] S10: Calculate indirect carbon emissions through transmitted power and heat data;

[0116] S11: Analyze indirect carbon emissions and provide emission reduction measures, which are then transmitted to the front-end display system for display;

[0117] S12: Based on the indirect carbon emissions, the alarm type and emission method obtained from the analysis are transmitted to the front-end display system for display.

[0118] Therefore, the embodiment of the present invention calculates direct carbon emissions and indirect carbon emissions based on the actual operating conditions of the catalytic cracking unit of the refinery, and obtains the carbon emissions of the catalytic cracking unit of the refinery. The direct carbon emissions are first calculated by a char burnt amount prediction model, and the carbon dioxide emissions in the current time period are predicted using the calculated char burnt amount prediction result and the residual carbon content of the regenerated catalyst. The embodiment of the present invention can accurately calculate the carbon emissions of the catalytic cracking unit, solves the problem of inaccurate carbon emission calculation due to the inability to accurately obtain the char burnt amount of the catalytic cracking unit, and can better carry out energy conservation and emission reduction work.

[0119] In addition, the embodiment of the present invention performs real-time accounting of carbon emissions in the catalytic cracking unit, can timely grasp the details of carbon dioxide emissions from the catalytic cracking unit, guide the production and emission of subsequent catalytic cracking units, play a key guiding role in the regulation of the catalytic cracking unit, and has a relatively broad prospect for promotion and application in the carbon emission reduction business of the catalytic cracking unit.

[0120] Device Embodiment

[0121] Please refer to Figure 7 The present invention provides a carbon emission calculation device, comprising:

[0122] The first data acquisition module 701 is used to acquire the process parameters of the catalytic cracking unit during the catalytic cracking reaction;

[0123] The first model prediction module 702 is used to input the process parameters into the charring amount prediction model to obtain the charring amount prediction result output by the charring amount prediction model;

[0124] A carbon emission calculation module 703 is used to calculate the carbon emission based on the charring amount prediction result;

[0125] The charring amount prediction model is obtained by training based on sample process parameters and charring amount result labels corresponding to the sample process parameters.

[0126] The carbon emission calculation device of the present invention trains the char amount prediction model through sample process parameters and the char amount result labels corresponding to the sample process parameters, and can predict the char amount of the process parameters in the catalytic cracking reaction process based on the trained char amount prediction model. The char amount prediction model of the present invention can solve the problem that the char amount is difficult to calculate accurately and timely in the prior art, and realize the accurate and timely calculation of carbon emissions in the catalytic cracking process.

[0127] Optionally, the first model prediction module is used to input the process parameters and characteristic parameters into a charring amount prediction model;

[0128] The burnt amount prediction model is trained based on the following modules:

[0129] A second data acquisition module is used to acquire sample process parameters and sample characteristic parameters of the catalytic cracking unit during the catalytic cracking reaction, as well as charring amount result labels corresponding to the sample process parameters and the sample characteristic parameters respectively;

[0130] A training module, used for training the charring amount prediction model based on the sample process parameters, the sample characteristic parameters and the charring amount result label;

[0131] The characteristic parameters and the sample characteristic parameters are both obtained based on the amount of alkaline solution added to the catalytic cracking unit and the amount of acid gas removed from the regenerated flue gas.

[0132] Optionally, the carbon emissions calculation module further includes:

[0133] A data input module, used for inputting the prediction result of the coke amount, the coke tank storage amount of the catalytic cracking unit and the residual carbon amount of the regenerated catalyst into the carbon emission prediction model;

[0134] A second model prediction module is used to determine the carbon emission prediction result output by the carbon emission prediction model as the carbon emission;

[0135] Among them, the carbon emission prediction model is obtained by training based on the sample burnt amount prediction results, the sample burnt amount tank storage amount of the catalytic cracking unit, the sample regenerated catalyst residual carbon amount, and the carbon emission result labels corresponding to the sample burnt amount prediction results, the sample burnt amount tank storage amount and the sample regenerated catalyst residual carbon amount.

[0136] Optionally, the carbon emissions calculation device further includes:

[0137] a data determination module for determining the power consumption and heat consumption of each unit of the catalytic cracking unit;

[0138] an indirect carbon emission calculation module, used to calculate the carbon emissions implied by the net purchased electricity and the carbon emissions implied by the net purchased heat of each unit based on the electricity consumption and heat consumption of each unit;

[0139] An emission reduction scheme determination module, used to determine and display the warning type and emission reduction scheme of each unit corresponding to the carbon emissions implied by the net purchased electricity and the carbon emissions implied by the net purchased heat of each unit based on a preset mapping relationship;

[0140] The preset mapping relationship includes warning types and emission reduction plans corresponding to different carbon emissions implied by net purchased electricity and carbon emissions implied by net purchased heat.

[0141] Optionally, the characteristic parameter and the sample characteristic parameter are both obtained based on the ratio of the sample alkaline solution addition amount of the catalytic cracking unit to the sample acid gas removal amount of the regeneration flue gas.

[0142] The carbon emission calculation device includes a processor and a memory. The first data acquisition module 701, the first model prediction module 702 and the carbon emission calculation module 703 are all stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.

[0143] The processor includes a kernel, which calls the corresponding program unit from the memory. There can be one or more kernels.

[0144] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0145] Figure 8 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 8 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute the carbon emission calculation method, which includes: obtaining the process parameters of the catalytic cracking unit during the catalytic cracking reaction; inputting the process parameters into the char burn prediction model to obtain the char burn prediction results output by the char burn prediction model; calculating the carbon emission based on the char burn prediction results; wherein the char burn prediction model is trained based on the sample process parameters and the char burn result labels corresponding to the sample process parameters.

[0146] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0147] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a machine-readable storage medium. When the computer program is executed by a processor, the computer can execute the carbon emissions calculation method provided by the above-mentioned methods, which method includes: obtaining the process parameters of the catalytic cracking unit during the catalytic cracking reaction; inputting the process parameters into a char burnt amount prediction model to obtain a char burnt amount prediction result output by the char burnt amount prediction model; and calculating the carbon emissions based on the char burnt amount prediction result; wherein the char burnt amount prediction model is trained based on sample process parameters and char burnt amount result labels corresponding to the sample process parameters.

[0148] On the other hand, the present invention also provides a machine-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the carbon emission calculation method provided by the above-mentioned methods, the method comprising: obtaining process parameters of a catalytic cracking unit during a catalytic cracking reaction; inputting the process parameters into a char burnt amount prediction model to obtain a char burnt amount prediction result output by the char burnt amount prediction model; and calculating carbon emissions based on the char burnt amount prediction result; wherein the char burnt amount prediction model is trained based on sample process parameters and char burnt amount result labels corresponding to the sample process parameters.

[0149] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0150] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0151] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for calculating carbon emissions, characterized in that: The method comprises: Obtaining process parameters of the catalytic cracking unit during the catalytic cracking reaction; Inputting the process parameters into a charring amount prediction model to obtain a charring amount prediction result output by the charring amount prediction model; Calculating carbon emissions based on the charring amount prediction result; The charring amount prediction model is obtained by training based on sample process parameters and charring amount result labels corresponding to the sample process parameters.

2. The carbon emission calculation method according to claim 1, characterized in that: The step of inputting the process parameters into the charring amount prediction model comprises: Inputting the process parameters and characteristic parameters into a charring amount prediction model; The charring amount prediction model is trained based on the following steps: Acquire sample process parameters and sample characteristic parameters of the catalytic cracking unit during the catalytic cracking reaction, and coke amount result labels corresponding to the sample process parameters and the sample characteristic parameters respectively; Based on the sample process parameters, the sample characteristic parameters and the charring amount result label, training the charring amount prediction model; The characteristic parameters and the sample characteristic parameters are both obtained based on the amount of alkaline solution added to the catalytic cracking unit and the amount of acid gas removed from the regenerated flue gas.

3. The carbon emission calculation method according to claim 1, characterized in that: The calculating of carbon emissions based on the charring amount prediction result comprises: Inputting the prediction result of the amount of coke burnt, the amount of coke burnt in the catalytic cracking unit and the amount of residual carbon in the regenerated catalyst into a carbon emission prediction model; Determining a carbon emission prediction result output by the carbon emission prediction model as the carbon emission; Among them, the carbon emission prediction model is obtained by training based on the sample burnt amount prediction results, the sample burnt amount tank storage amount of the catalytic cracking unit, the sample regenerated catalyst residual carbon amount, and the carbon emission result labels corresponding to the sample burnt amount prediction results, the sample burnt amount tank storage amount and the sample regenerated catalyst residual carbon amount.

4. The carbon emission calculation method according to claim 1, characterized in that: After calculating the carbon emission based on the charring amount prediction result, the method further includes: Determine the electricity and heat consumption of each unit of the FCC; Based on the electricity consumption and heat consumption of each unit, calculate the carbon emissions implied by the net purchased electricity and the carbon emissions implied by the net purchased heat of each unit; Based on the preset mapping relationship, determine and display the warning type and emission reduction plan of each unit corresponding to the carbon emissions implied by the net purchased electricity and the carbon emissions implied by the net purchased heat of each unit; The preset mapping relationship includes warning types and emission reduction plans corresponding to different carbon emissions implied by net purchased electricity and carbon emissions implied by net purchased heat.

5. The carbon emission calculation method according to claim 2, characterized in that: The characteristic parameter and the sample characteristic parameter are both obtained based on the ratio of the sample alkaline solution addition amount of the catalytic cracking unit to the sample acid gas removal amount of the regeneration flue gas.

6. A carbon emissions calculation device, characterized in that: include: A first data acquisition module is used to acquire process parameters of the catalytic cracking unit during the catalytic cracking reaction; A first model prediction module, used for inputting the process parameters into a charred amount prediction model to obtain a charred amount prediction result output by the charred amount prediction model; A carbon emission calculation module, used for calculating the carbon emission based on the charring amount prediction result; The charring amount prediction model is obtained by training based on sample process parameters and charring amount result labels corresponding to the sample process parameters.

7. The carbon emission calculation device according to claim 6, characterized in that: The first model prediction module is used to input the process parameters and characteristic parameters into the charring amount prediction model; The burnt amount prediction model is trained based on the following modules: A second data acquisition module is used to acquire sample process parameters and sample characteristic parameters of the catalytic cracking unit during the catalytic cracking reaction, as well as charring amount result labels corresponding to the sample process parameters and the sample characteristic parameters respectively; A training module, used for training the charring amount prediction model based on the sample process parameters, the sample characteristic parameters and the charring amount result label; The characteristic parameters and the sample characteristic parameters are both obtained based on the amount of alkaline solution added to the catalytic cracking unit and the amount of acid gas removed from the regenerated flue gas.

8. The carbon emission calculation device according to claim 6, characterized in that: The carbon emission calculation module includes: A data input module, used for inputting the prediction result of the coke amount, the coke tank storage amount of the catalytic cracking unit and the residual carbon amount of the regenerated catalyst into the carbon emission prediction model; A second model prediction module is used to determine the carbon emission prediction result output by the carbon emission prediction model as the carbon emission; Among them, the carbon emission prediction model is obtained by training based on the sample burnt amount prediction results, the sample burnt amount tank storage amount of the catalytic cracking unit, the sample regenerated catalyst residual carbon amount, and the carbon emission result labels corresponding to the sample burnt amount prediction results, the sample burnt amount tank storage amount and the sample regenerated catalyst residual carbon amount.

9. The carbon emission calculation device according to claim 6, characterized in that: The carbon emission calculation device further includes: a data determination module for determining the power consumption and heat consumption of each unit of the catalytic cracking unit; an indirect carbon emission calculation module, used to calculate the carbon emissions implied by the net purchased electricity and the carbon emissions implied by the net purchased heat of each unit based on the electricity consumption and heat consumption of each unit; An emission reduction scheme determination module, used to determine and display the warning type and emission reduction scheme of each unit corresponding to the carbon emissions implied by the net purchased electricity and the carbon emissions implied by the net purchased heat of each unit based on a preset mapping relationship; The preset mapping relationship includes warning types and emission reduction plans corresponding to different carbon emissions implied by net purchased electricity and carbon emissions implied by net purchased heat.

10. The carbon emission calculation device according to claim 7, characterized in that: The characteristic parameter and the sample characteristic parameter are both obtained based on the ratio of the sample alkaline solution addition amount of the catalytic cracking unit to the sample acid gas removal amount of the regeneration flue gas.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the carbon emission calculation method according to any one of claims 1 to 5 is implemented.

12. A machine-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the carbon emission calculation method according to any one of claims 1 to 5 is implemented.

Images