Desulfurization process optimization method, device, electronic equipment and storage medium

Abstract

The present application provides a desulfurization process optimization method, device, electronic device and storage medium. The method includes: modeling the desulfurization system to generate a desulfurization model; a concentration prediction step: based on process data, using the desulfurization model, obtaining a predicted value of sulfur dioxide emission concentration and a predicted value of sulfur dioxide absorption slurry pH; process data includes: real-time indicator data and process operation data; a loss determination step: calculating process loss based on the predicted value of sulfur dioxide emission concentration and the predicted value of sulfur dioxide absorption slurry pH; using a heuristic algorithm to adjust the process operation data, repeatedly executing the concentration prediction step and the loss determination step until the preset termination condition is met, and obtaining the optimal process operation data. The above method simulates the working conditions in the desulfurization process by the desulfurization model, improves the accuracy and credibility of the sulfur dioxide emission concentration prediction, and uses a heuristic algorithm to adjust the process operation data, thereby avoiding the subjectivity of manual operation data optimization and reducing labor costs.

Description

Technical Field

[0001] The present application relates to the technical field of desulfurization processes, and in particular to a desulfurization process optimization method, device, electronic equipment, and storage medium. Background Art

[0002] Wet flue gas desulfurization (FGD) is a widely used FGD technology both domestically and internationally. Its working principle is to use a sulfur dioxide absorption slurry as a scrubbing agent to scrub the flue gas in a desulfurization tower, thereby removing sulfur dioxide from the flue gas. However, as the most efficient and widely used FGD technology, operating a wet FGD system involves significant material and electricity consumption.

[0003] To optimize the wet flue gas desulfurization (WFGD) desulfurization process, current approaches primarily involve two steps: first, predicting sulfur dioxide emission concentrations, and then optimizing the process operating data within the desulfurization process based on the predicted results. Existing technology primarily predicts sulfur dioxide emission concentrations through machine learning, using historical data to train a neural network and then use the trained neural network to predict sulfur dioxide emission concentrations. For process optimization, based on the predicted sulfur dioxide emission concentrations, process operating data is manually optimized based on experience. However, manual optimization of process operating data in existing technologies is often subjective and labor-intensive. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide a desulfurization process optimization method, device, electronic equipment and storage medium to improve the technical problems of low confidence in the prediction results of the above-mentioned sulfur dioxide emission concentration, overly subjective process operation data and excessively high labor costs.

[0005] In the first aspect, an embodiment of the present application provides a desulfurization process optimization method, which includes the following steps: modeling the desulfurization system to generate a desulfurization model; a concentration prediction step: based on the process data, using the desulfurization model, obtaining a predicted value of sulfur dioxide emission concentration and a predicted value of sulfur dioxide absorption slurry pH; the process data includes: real-time indicator data and process operation data; wherein the real-time indicator data is data obtained in real time within a preset time for predicting sulfur dioxide emission concentration, and the process operation data is used to adjust the actual emission concentration of sulfur dioxide; a loss determination step: calculating the process loss based on the predicted value of sulfur dioxide emission concentration and the predicted value of sulfur dioxide absorption slurry pH; using a heuristic algorithm to adjust the process operation data, repeatedly executing the concentration prediction step and the loss determination step until the preset termination condition is met to obtain the optimal process operation data, wherein the preset termination condition includes the process loss being the minimum value.

[0006] In the implementation of the above method, the desulfurization model can accurately simulate the operating conditions of the sulfur dioxide desulfurization process, thereby improving the accuracy and credibility of the sulfur dioxide emission concentration prediction. Furthermore, since the process loss is determined based on the predicted value of the sulfur dioxide emission concentration, the accuracy and credibility of the sulfur dioxide emission concentration prediction are improved, and the calculation of the process loss will also be more accurate, which is more conducive to determining the optimal process operation data based on the process loss. In addition, the method of the present application uses a heuristic algorithm to adjust the process operation data, which increases the automation of the process operation data optimization, avoids the subjectivity of manual operation data optimization, and reduces labor costs.

[0007] In an implementation of the first aspect, the physical property model of the desulfurization model is an electrolyte model; the Henry components of the desulfurization model include: sulfur dioxide, oxygen, nitrogen and carbon dioxide; and the water vapor equilibrium partial pressure of the desulfurization model is a STEAMNBS physical property method.

[0008] In the implementation of the above method, since the desulfurization model involves chemical reactions of the solution, it is necessary to consider the influence of the electrolyte on each component in the solution. Setting the physical property model in the desulfurization model to the electrolyte model can simulate the influence of the electrolyte in the solution on the concentration of each component. Sulfur dioxide, oxygen, nitrogen and carbon dioxide are non-condensable gases in the sulfur dioxide desulfurization process. By setting the above gases as Henry components, the concentrations of the above gases in the gas phase and liquid phase can be simulated, thereby improving the accuracy of calculating the concentration of each component in the gas phase. The saturated water partial pressure in the gas phase at different pressures and temperatures can be calculated by the STEAMNBS physical property method, and the water vapor content in the atmosphere can be accurately calculated in combination with the meteorological fugacity of other substances. Overall, the above setting of the desulfurization model makes the data obtained by the desulfurization model simulation closer to the real data.

[0009] In one implementation of the first aspect, the desulfurization model includes: a sulfur dioxide absorption slurry preparation section, a sulfur dioxide absorption section, and an oxidation section; wherein the sulfur dioxide absorption slurry preparation section is used to simulate the process of preparing sulfur dioxide absorption slurry; the sulfur dioxide absorption section is used to simulate the process of sulfur dioxide absorption slurry absorbing sulfur dioxide; and the oxidation section is used to simulate the oxidation process of sulfite in the sulfur dioxide absorption slurry after oxidizing air is introduced into the sulfur dioxide absorption slurry for oxidation absorption.

[0010] In the implementation of the above method, it should be understood that the sulfur dioxide absorption slurry preparation section, the sulfur dioxide absorption section and the oxidation section are sections in the sulfur dioxide desulfurization process that have a direct impact on the amount of sulfur dioxide absorbed. Therefore, setting the above sections in the desulfurization model can accurately simulate the working conditions in the actual sulfur dioxide desulfurization process.

[0011] In an implementation of the first aspect, the process data further includes: dimensional information of the desulfurization equipment.

[0012] The dimensional information of the desulfurization equipment (e.g., absorption tower), such as the height, width, head form, and placement form of the desulfurization equipment, is closely related to the desulfurization effect of sulfur dioxide. By setting the dimensional information of the desulfurization equipment in the desulfurization model, the desulfurization model can more accurately simulate the actual desulfurization process, thereby improving the accuracy of the sulfur dioxide emission concentration prediction.

[0013] In an implementation of the first aspect, the process loss is calculated based on the predicted value of sulfur dioxide emission concentration and the predicted value of sulfur dioxide absorption slurry pH, including using the following formula to calculate the process loss: loss = α1*CL+α2*EL+α3*SL; wherein CL is the sulfur dioxide concentration loss value, EL is the electricity loss value, SL is the material loss value, α1, α2 and α3 are weighting coefficients, and CL is calculated based on the predicted value of sulfur dioxide emission concentration, and SL is calculated based on the predicted value of sulfur dioxide absorption slurry pH.

[0014] The above implementation method provides a simple and effective way to calculate the losses in the desulfurization process. The sulfur dioxide loss value, power consumption loss value and material consumption loss value can well reflect the losses in the desulfurization process. Therefore, the process operation data can be adjusted according to the process losses calculated above to obtain the optimal process operation data. The sizes of α1, α2 and α3 in the above formula represent the strictness of control over the factors corresponding to the weighting coefficient (here referring to CL, EL and SL). Technical personnel in this field can adjust the sizes of α1, α2 and α3 as needed to adapt to different requirements.

[0015] In an implementation of the first aspect, the sulfur dioxide concentration loss value, the power consumption loss value, and the material consumption loss value are calculated according to the following formula:

[0016] CL=γ1(y pred -y limit1 )+γ2(y pred -y limit2 );

[0017]

[0018] SL=γ4(X ρred -y limit3 )+γ5[X ρred -y limit4 +γ6(X ρred -y limit5 )];

[0019] Among them, y predis the predicted value of sulfur dioxide emission concentration, X ρred is the predicted pH value of sulfur dioxide absorption slurry, y limit1 is the first emission limit indicator, y limit2 The second emission limit index, W pumpi is the electric power of the circulating pump, y limit3 is the preset upper limit of the pH value of the sulfur dioxide absorption slurry, y limit4 is the preset lower limit of the pH value of the sulfur dioxide absorption slurry, y limit5 are other preset limit values, and γ1, γ2, γ3, γ4, γ5 and γ6 are adjustment thresholds.

[0020] The above implementation method provides a calculation method for the sulfur dioxide loss value, the power consumption loss value and the material consumption loss value. Among them, the sulfur dioxide concentration loss value can reflect whether the sulfur dioxide emission concentration meets the first emission limit index and the second emission limit index, the power consumption loss value can reflect the power consumption cost of the desulfurization process, and the material consumption loss value can reflect the material consumption cost of the desulfurization process. According to the above three loss values, the cost loss situation of the desulfurization process can be better reflected, which is convenient for subsequent adjustment of the process operation data to control the above three loss values.

[0021] In an implementation manner of the first aspect, the heuristic algorithm is a heuristic genetic algorithm.

[0022] In the implementation of the above method, the heuristic genetic algorithm can fully adjust and calculate the process operation data so that the process loss continuously approaches the minimum value. It does not require manual adjustment and is automatic, which can save the labor cost in the process data operation data optimization stage and avoid the subjectivity brought about by manual optimization.

[0023] In the second aspect, the embodiment of the present application also provides a desulfurization process optimization device, including: a prediction module, which is used to obtain a predicted value of sulfur dioxide emission concentration and a predicted value of sulfur dioxide absorption slurry pH based on process data and a desulfurization model; process data includes: real-time indicator data and process operation data; wherein the real-time indicator data is data obtained in real time within a preset time for predicting sulfur dioxide emission concentration, and the process operation data is used to adjust the actual emission concentration of sulfur dioxide; a loss determination module, which is used to calculate the process loss based on the predicted value of sulfur dioxide emission concentration and the predicted value of sulfur dioxide absorption slurry pH; an optimization module, which uses a heuristic algorithm to adjust the process operation data, repeatedly executes the concentration prediction step and the loss determination step until the preset termination condition is met, and obtains the optimal process operation data, wherein the preset termination condition includes the process loss being the minimum value.

[0024] In a third aspect, an embodiment of the present application further provides an electronic device comprising: a processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the machine-readable instructions are executed by the processor, the method described in the first aspect is performed.

[0025] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, the method described in the first aspect is executed.

[0026] The desulfurization process optimization method provided in this application can simulate the operating conditions of a real sulfur dioxide desulfurization process, thereby improving the accuracy and reliability of sulfur dioxide emission concentration predictions. Furthermore, the process losses determined based on process operating data and predicted sulfur dioxide concentrations are closer to the actual data. Furthermore, the method of this application utilizes a genetic heuristic algorithm to fully adjust process operating data to determine the optimal process operating data corresponding to the minimum process losses, thereby increasing the automation of process optimization and reducing labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0028] Figure 1 A schematic flow chart of a desulfurization process optimization method provided in an embodiment of the present application;

[0029] Figure 2 A schematic structural diagram of a desulfurization process device provided in an embodiment of the present application;

[0030] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The technical solutions in the embodiments of the present application will be described below in conjunction with the accompanying drawings. It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0032] The terms "comprises," "comprising," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0033] The terms "first," "second," etc. are only used to distinguish one entity or operation from another entity or operation, and are not to be understood as indicating or implying relative importance, nor are they to be understood as requiring or implying any actual relationship or order between these entities or operations.

[0034] It should be noted that the desulfurization process optimization method provided in the embodiment of the present application can be executed by an electronic device, where the electronic device refers to a device terminal or server with the function of executing a computer program, and the device terminal is, for example: a personal computer (PC), a tablet computer, a personal digital assistant (PDA), a mobile Internet device (MID), a network switch or a network router, etc.

[0035] Before introducing the desulfurization process optimization method provided in the embodiment of the present application, the application scenarios to which the desulfurization process optimization method is applicable are first introduced. The application scenarios here include: when optimizing the operating data of the desulfurization process, it is necessary to predict the emission concentration of sulfur dioxide based on real-time indicator data, and optimize the operating data based on the predicted value of the emission concentration of sulfur dioxide to ensure that the emission concentration of sulfur dioxide in the future time period will not exceed the national emission standard and also reduce power consumption and material consumption as much as possible. The existing technology usually predicts the emission concentration of sulfur dioxide mainly through a machine learning model, and then manually optimizes the operating data based on the predicted emission concentration of sulfur dioxide. The ability of machine learning is limited, which leads to a low credibility of the above-mentioned results. At the same time, the method of manually optimizing the operating data also has the problem of being too subjective and having too high a labor cost. Therefore, the above-mentioned application scenario can adopt the sulfur process optimization method provided in the present invention, simulate the desulfurization process flow through the desulfurization model to predict the emission concentration of sulfur dioxide, and then determine the optimal operating data through a heuristic algorithm.

[0036] Please refer to Figure 1 , Figure 1 A schematic flow chart of a desulfurization process optimization method provided in an embodiment of the present application, the desulfurization process optimization method comprising:

[0037] Step S100: Modeling the desulfurization system to generate a desulfurization model.

[0038] Desulfurization systems are used to remove sulfur dioxide from flue gas. A complete desulfurization system includes multiple stages, such as sulfur dioxide absorption slurry preparation, sulfur dioxide absorption, oxidation, and filtration. Modeling a desulfurization system involves constructing a desulfurization model using software that simulates each stage of a real desulfurization system.

[0039] The above modeling method is not limited in this application. For example, the desulfurization model can be modeled using Aspen Plus software.

[0040] Step S200 (concentration prediction step): Based on the process data and using the desulfurization model, a predicted value of sulfur dioxide emission concentration and a predicted value of sulfur dioxide absorption slurry pH are obtained.

[0041] Process data includes real-time indicator data and process operation data. Real-time indicator data is data acquired in real time within a preset timeframe and used to predict sulfur dioxide emission concentrations. Process operation data is used to adjust actual sulfur dioxide emission concentrations. It should be noted that the length of the preset timeframe is not limited in this application and can be, for example, 30 minutes or 40 minutes.

[0042] In an optional scheme, based on the process data, using the desulfurization model, the specific implementation methods for obtaining the predicted value of sulfur dioxide emission concentration and the predicted value of sulfur dioxide absorption slurry pH include but are not limited to the following methods: the first method is to input the real-time data curve of the process data within a preset time into the desulfurization model, and then select the data at a certain point on the curve as the value of the process data in the desulfurization model, for example, select the value of the 30th minute as the value of the process data; the second method is to directly input the value of the process data as the value of the process data in the desulfurization model.

[0043] It should be noted that after the process data is input into the model, the desulfurization model outputs not a definite sulfur dioxide emission concentration prediction value and sulfur dioxide absorption slurry pH prediction value, but a curve chart of the change of the sulfur dioxide emission concentration prediction value and the sulfur dioxide absorption slurry pH prediction value for a future time period. The data at a certain time point on the curve chart can be selected as the predicted sulfur oxide emission concentration prediction value and the sulfur dioxide absorption slurry pH prediction value. As for the specific time point to be taken as the predicted sulfur oxide emission concentration value and the sulfur dioxide absorption slurry pH value, this application does not limit it. For example, the sulfur oxide emission concentration value and the sulfur dioxide absorption slurry pH value corresponding to the 10th minute on the curve can be taken as the predicted value, or the sulfur oxide emission concentration value and the sulfur dioxide absorption slurry pH value corresponding to the 5th minute on the curve can be taken as the predicted value, and so on. Note that the time points corresponding to the values of the sulfur dioxide emission concentration prediction value and the sulfur dioxide absorption slurry pH prediction value need to be consistent.

[0044] In an optional solution, the real-time indicator data include: sulfur dioxide concentration at the desulfurization tower inlet, sulfur dioxide flow at the desulfurization tower inlet, sulfur dioxide absorption slurry circulation volume, sulfur dioxide absorption slurry pH value and material inlet temperature.

[0045] It should be understood that the above-mentioned real-time indicator data are of great significance for predicting the sulfur dioxide emission concentration. For example, under the same other conditions, the sulfur dioxide emission concentration is positively correlated with the sulfur dioxide concentration at the desulfurization tower inlet and the sulfur dioxide flow rate at the desulfurization tower inlet, and is negatively correlated with the circulation volume of the sulfur dioxide absorption slurry, the pH value of the sulfur dioxide absorption slurry and the material inlet temperature.

[0046] As for how to obtain the above-mentioned real-time indicator data, this application does not limit this. For example, corresponding data can be collected by placing sensors on each unit, or the above-mentioned real-time indicator data can be obtained by calculation based on the material balance table of the PFD and PID drawings, etc.

[0047] In an optional solution, the process operation data includes: circulation pump operation time, circulation pump flow rate, sulfur dioxide absorption slurry pH operation time and sulfur dioxide absorption slurry pH conversion value.

[0048] It should be noted that the above-mentioned real-time indicator data and process operation data may also include more or less data, and those skilled in the art may make adjustments.

[0049] Step S300 (loss determination step): Calculate process losses based on the predicted value of sulfur dioxide emission concentration and the predicted value of sulfur dioxide absorption slurry pH.

[0050] In the above step S300, how to calculate the process loss will be described in detail later.

[0051] Step S400: using a heuristic algorithm to adjust the process operation data, repeatedly executing the concentration prediction step and the loss determination step until a preset termination condition is met, thereby obtaining the optimal process operation data.

[0052] The preset termination condition includes that the process loss is minimized. How to achieve the minimum process loss will be described in detail later.

[0053] The following is a brief summary of steps S100 to S400: In the implementation of the above method, the desulfurization model can accurately simulate the working conditions in the sulfur dioxide desulfurization process, thereby improving the accuracy and credibility of the sulfur dioxide emission concentration prediction; further, since the process loss is determined based on the predicted value of the sulfur dioxide emission concentration, when the accuracy and credibility of the sulfur dioxide emission concentration prediction are improved, the calculation of the process loss will also be more accurate, which is more conducive to determining the optimal process operation data based on the process loss. In addition, the method of the present application uses a heuristic algorithm to adjust the process operation data, which increases the automation of the process operation data optimization, avoids the subjectivity of manual operation data optimization, and also reduces labor costs.

[0054] In an optional solution, the physical property model of the desulfurization model is an electrolyte model; the Henry components of the desulfurization model include: sulfur dioxide, oxygen, nitrogen and carbon dioxide; and the water vapor equilibrium partial pressure of the desulfurization model is a STEAMNBS physical property method.

[0055] In the implementation of the above method, since the desulfurization model involves chemical reactions of the solution, it is necessary to consider the effect of the electrolyte on each component in the solution. Setting the physical property model in the desulfurization model to the electrolyte model can simulate the effect of the electrolyte in the solution on the concentration of each component. Sulfur dioxide, oxygen, nitrogen and carbon dioxide are non-condensable gases in the sulfur dioxide desulfurization process. By setting the above gases as Henry components, the concentrations of the above gases in the gas phase and liquid phase can be simulated, thereby improving the accuracy of calculating the concentration of each component in the gas phase. The STEAMNBS physical property method counts the water vapor content in the gas phase at different pressures and temperatures. Therefore, the saturated water partial pressure in the gas phase at different pressures and temperatures can be calculated by the STEAMNBS physical property method. Combined with the meteorological fugacity of other substances, the water vapor content in the atmosphere can be accurately calculated. Overall, the above setting of the desulfurization model makes the data obtained by the desulfurization model simulation closer to the real data.

[0056] In an optional scheme, the desulfurization model includes: a sulfur dioxide absorption slurry preparation section, a sulfur dioxide absorption section and an oxidation section; wherein, the sulfur dioxide absorption slurry preparation section is used to simulate the process of preparing sulfur dioxide absorption slurry; the sulfur dioxide absorption section is used to simulate the process of sulfur dioxide absorption slurry absorbing sulfur dioxide; the oxidation section is used to simulate the oxidation process of sulfite in the sulfur dioxide absorption slurry after oxidizing air is introduced into the sulfur dioxide absorption slurry for oxidation absorption.

[0057] In an optional scheme, the sulfur dioxide absorption slurry in the desulfurization model is a lime slurry solution, and the desulfurization model includes: a gypsum preparation section, a sulfur dioxide absorption section and a calcium sulfite oxidation section; wherein the gypsum preparation section is used to simulate the process of mixing water and lime to form a lime slurry solution; the sulfur dioxide absorption section is used to simulate the process of lime slurry solution absorbing sulfur dioxide; the calcium sulfite oxidation section is used to simulate the oxidation process of calcium sulfite in the lime slurry solution after oxidizing air is introduced into the lime slurry solution for oxidation absorption.

[0058] Optionally, the chemical reaction in the gypsum preparation section can be set as the dissolution and ionization equilibrium reaction of calcium carbonate; the chemical reaction in the sulfur dioxide absorption section is the variance coupling solution of the dissolution and ionization equilibrium of sulfur dioxide, carbon dioxide, calcium carbonate and calcium sulfite; the chemical reaction in the calcium sulfite oxidation section is simulated by minimizing the Gibbs free energy of the system.

[0059] It should be noted that the above-mentioned chemical reaction mode can also be set to other chemical reaction modes, and this application does not limit the specific chemical reaction mode of each work section.

[0060] It should be understood that the above-mentioned sulfur dioxide absorption slurry preparation section, sulfur dioxide absorption section and oxidation section are sections in the sulfur dioxide desulfurization process that have a direct impact on the amount of sulfur dioxide absorbed. Therefore, by setting the above-mentioned sections in the desulfurization model, the working conditions in the actual sulfur dioxide desulfurization process can be accurately simulated.

[0061] In an optional solution, the desulfurization model may further include: a filtration section; the filtration section is used to simulate the separation of water and solids in the sulfur dioxide absorption slurry after oxidation by calcium sulfite.

[0062] The complete desulfurization process also includes a filtration section. The water after solid-liquid separation will be reused in the sulfur dioxide absorption slurry preparation section. Therefore, the filtration section can also be set in the desulfurization model to ensure that the desulfurization model fully simulates the entire desulfurization process.

[0063] In an optional solution, the process data also includes: dimensional information of the desulfurization equipment.

[0064] Optionally, the desulfurization equipment is a desulfurization tower, and the size information of the desulfurization equipment includes: placement of the desulfurization tower, head form of the desulfurization tower, and height and width of the desulfurization tower.

[0065] Since flue gas desulfurization primarily involves introducing flue gas into a desulfurization tower, the flue gas comes into contact with the sulfur dioxide absorption slurry in the desulfurization tower, dissolving the sulfur dioxide in the flue gas into the sulfur dioxide absorption slurry, thereby reducing the sulfur dioxide concentration in the flue gas. It should be understood that, with other conditions remaining unchanged, the more sulfur dioxide absorption slurry there is, the more sulfur dioxide it can absorb. The larger the contact area between the flue gas and the sulfur dioxide absorption slurry in the desulfurization tower, and the longer the contact time, the more fully the sulfur dioxide in the flue gas can be absorbed by the sulfur dioxide absorption slurry. The desulfurization tower's dimensional information (e.g., tower placement, tower head type, and tower height and width) will affect the capacity of the sulfur dioxide absorption slurry in the desulfurization tower and the time the flue gas stays in the desulfurization tower. Therefore, the desulfurization model needs to be configured based on the desulfurization tower's dimensional information in a real factory to better simulate the actual desulfurization operating conditions, thereby making the predicted sulfur dioxide emission concentration more accurate.

[0066] The following is a detailed description of how to calculate process loss:

[0067] In an alternative solution, the process loss is calculated as:

[0068] loss=α1*CL+α2*EL+α3*SL;

[0069] Among them, CL is the sulfur dioxide concentration loss value, EL is the electricity loss value, SL is the material loss value, α1, α2 and α3 are weighting coefficients, and CL is calculated based on the predicted value of sulfur dioxide emission concentration, and SL is calculated based on the predicted value of sulfur dioxide absorption slurry pH.

[0070] The above-mentioned weighting coefficients α1, α2 and α3 are set by technical personnel in this field according to actual needs. Specifically, the larger the weighting coefficient, the stricter the control over the factors corresponding to the weighting coefficient (here referring to CL, EL and SL). For example, if it is necessary to strictly control the sulfur dioxide emission concentration, the weighting coefficient α1 corresponding to CL can be increased; if it is necessary to strictly control the power consumption, the weighting coefficient α2 corresponding to EL can be increased; if it is necessary to strictly control the material consumption, the weighting coefficient α3 corresponding to SL can be increased.

[0071] The above implementation method provides a simple and effective way to calculate the losses in the desulfurization process. The sulfur dioxide loss value, power consumption loss value and material consumption loss value can well reflect the losses in the desulfurization process. Therefore, the process operation data can be adjusted according to the process losses calculated above to obtain the optimal process operation data. The sizes of α1, α2 and α3 in the above formula represent the strictness of control over the factors corresponding to the weighting coefficient (here referring to CL, EL and SL). Technical personnel in this field can adjust the sizes of α1, α2 and α3 as needed to adapt to different requirements.

[0072] In an optional solution, the sulfur dioxide concentration loss value, the power loss value, and the material loss value are calculated according to the following formula:

[0073] CL=γ1(y pred -y limit1 )+γ2(y pred -y limit2 );

[0074]

[0075] SL=γ4(X ρred -y limit3 )+γ5[X ρred -y limit4 +γ6(X ρred -y limit5 )];

[0076] Among them, y pred is the predicted value of sulfur dioxide emission concentration, X ρred is the predicted pH value of sulfur dioxide absorption slurry, y limit1 is the first emission limit indicator, y limit2 The second emission limit index, W pumpi is the electric power of the circulating pump, y limit3 is the preset upper limit of the pH value of the sulfur dioxide absorption slurry, y limit4 is the preset lower limit of the pH value of the sulfur dioxide absorption slurry, y limit5 are other preset limit values, and γ1, γ2, γ3, γ4, γ5 and γ6 are adjustment thresholds.

[0077] The meaning of adjusting the thresholds γ1, γ2, γ3, γ4, γ5 and γ6 is similar to the weighting coefficients α1, α2 and α3. For example, if you want to strictly limit the difference between the sulfur dioxide emission concentration prediction and the first emission limit index, you can set (y pred -y limit1 ) The corresponding adjustment threshold γ1 increases, and no further examples are given here.

[0078] The above implementation method provides a calculation method for the sulfur dioxide loss value, the power consumption loss value and the material consumption loss value. Among them, the sulfur dioxide concentration loss value can reflect whether the sulfur dioxide emission concentration meets the first emission limit index and the second emission limit index, the power consumption loss value can reflect the power consumption cost of the desulfurization process, and the material consumption loss value can reflect the material consumption cost of the desulfurization process. According to the above three loss values, the cost loss situation of the desulfurization process can be better reflected, which is convenient for subsequent adjustment of the process operation data to control the above three loss values.

[0079] In one optional solution, the first emission limit indicator can be set to the national emission limit standard, and the second and third emission limit indicators can be specified by those skilled in the art based on actual needs. For example, the second emission limit indicator can be an internal factory emission limit indicator, and the third emission limit indicator can be an industry-specified emission limit indicator, etc. This application does not impose any restrictions on this.

[0080] In an optional solution, the heuristic algorithm is a heuristic genetic algorithm.

[0081] The heuristic genetic algorithm adjusts the process operation data and repeatedly executes the concentration prediction step and the loss determination step until a preset termination condition is met to obtain the optimal process operation data, wherein the preset termination condition includes that the process loss is minimized.

[0082] Since the heuristic genetic algorithm only continuously adjusts the process operation data to make the process loss approach the minimum value, it does not necessarily achieve the minimum process loss in the end. Therefore, it is necessary to set a termination condition to stipulate that the process loss is the minimum when the termination condition is met.

[0083] In an optional solution, the preset termination condition can be the preset number of repeated executions of the concentration prediction step and the loss determination step. As for the number of repeated executions, this application does not limit it. For example, it can be 50 times, 60 times, and so on.

[0084] In another optional solution, it can also be stipulated that if the calculated process loss no longer changes significantly while the process operation data is continuously adjusted, the termination condition is met.

[0085] The heuristic genetic algorithm can fully adjust and calculate the process operation data so that the process loss continuously approaches the minimum value. It does not require manual adjustment and is automatic. It can save labor costs in the process data operation data optimization stage and avoid the subjectivity brought about by manual optimization.

[0086] Of course, the heuristic algorithm can also be other algorithms, such as simulated annealing algorithm, ant colony algorithm, differential evolution algorithm, etc.

[0087] Figure 2The present invention provides a desulfurization process optimization device, referring to Figure 2 , the desulfurization process optimization device 200 includes:

[0088] Modeling module 201, used to model the desulfurization system and generate a desulfurization model;

[0089] Prediction module 202 is used to obtain a predicted value of sulfur dioxide emission concentration and the pH value of the sulfur dioxide absorption slurry based on process data and a desulfurization model. The process data includes real-time indicator data and process operation data. The real-time indicator data is data obtained in real time within a preset time period for predicting sulfur dioxide emission concentration, and the process operation data is used to adjust the actual sulfur dioxide emission concentration.

[0090] a loss determination module 203 for calculating process losses based on the predicted sulfur dioxide emission concentration and the pH value of the sulfur dioxide absorption slurry;

[0091] The optimization module 204 adjusts the process operation data using a heuristic algorithm, repeatedly performs the concentration prediction step and the loss determination step, and obtains the optimal process operation data until a preset termination condition is met, wherein the preset termination condition includes the process loss being a minimum value.

[0092] In one implementation of the desulfurization process optimization device 200, the physical property model of the desulfurization model generated by the modeling module 201 is an electrolyte model; the Henry components of the desulfurization model generated by the modeling module 201 include: sulfur dioxide, oxygen, nitrogen and carbon dioxide; the equilibrium partial pressure of the desulfurization model generated by the modeling module 201 is the STEAMNBS physical property method.

[0093] In one implementation of the desulfurization process optimization device 200, the desulfurization model generated by the modeling module 201 includes: a sulfur dioxide absorption slurry preparation section, a sulfur dioxide absorption section and an oxidation section; wherein, the sulfur dioxide absorption slurry preparation section is used to simulate the process of preparing sulfur dioxide absorption slurry; the sulfur dioxide absorption section is used to simulate the process of sulfur dioxide absorption slurry absorbing sulfur dioxide; the oxidation section is used to simulate the oxidation process of sulfite in the sulfur dioxide absorption slurry after oxidizing air is introduced into the sulfur dioxide absorption slurry for oxidation absorption.

[0094] In one implementation of the desulfurization process optimization device 200 , the process data further includes: dimensional information of the desulfurization equipment.

[0095] In one implementation of the desulfurization process optimization device 200, the loss determination module 203 uses the following formula to calculate the process loss: loss = α1*CL+α2*EL+α3*SL; wherein, CL is the sulfur dioxide concentration loss value, EL is the electricity consumption loss value, SL is the material consumption loss value, α1, α2 and α3 are weighting coefficients, and CL is calculated based on the predicted value of sulfur dioxide emission concentration, and SL is calculated based on the predicted value of sulfur dioxide absorption slurry pH.

[0096] In one implementation of the desulfurization process optimization device 200, the loss determination module 203 calculates the sulfur dioxide concentration loss value, the power consumption loss value, and the material consumption loss value using the following formula:

[0097] CL=γ1(y pred -y limit1 )+γ2(y pred -y limit2 );

[0098]

[0099] SL=γ4(X ρred -y limit3 )+γ5[X ρred -y limit4 +γ6(X ρred -y limit5 )];

[0100] Among them, y pred is the predicted value of sulfur dioxide emission concentration, X ρred is the predicted pH value of sulfur dioxide absorption slurry, y limit1 is the first emission limit indicator, y limit2 The second emission limit index, W pumpi is the electric power of the circulating pump, y limit3 is the preset upper limit of the pH value of the sulfur dioxide absorption slurry, y limit4 is the preset lower limit of the pH value of the sulfur dioxide absorption slurry, y limit5 are other preset limit values, and γ1, γ2, γ3, γ4, γ5 and γ6 are adjustment thresholds.

[0101] In one implementation of the desulfurization process optimization device 200 , the heuristic algorithm applied by the optimization module 204 is a heuristic genetic algorithm.

[0102] The desulfurization process optimization device 200 provided in the embodiment of the present application, its implementation principle and the technical effects produced have been introduced in the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference can be made to the corresponding content in the method embodiment.

[0103] Figure 3This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 3 The electronic device 4 includes a processor 401 and a memory 402 . These components are interconnected and communicate with each other via a communication bus 403 and / or other connection mechanisms (not shown).

[0104] The memory 402 includes one or more (only one is shown in the figure), which can be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc. The processor 401 and other possible components can access the memory 402 and read and / or write data therein.

[0105] The processor 401 includes one or more (only one is shown in the figure), which can be an integrated circuit chip with signal processing capabilities. The above-mentioned processor 401 can be a general-purpose processor, including a central processing unit (CPU), a micro control unit (MCU), a network processor (NP) or other conventional processors; it can also be a special-purpose processor, including a neural network processor (NPU), a graphics processing unit (GPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. In addition, when there are multiple processors 401, some of them can be general-purpose processors and the other part can be special-purpose processors.

[0106] One or more computer program instructions may be stored in the memory 402 , and the processor 401 may read and execute these computer program instructions to implement a desulfurization process optimization method provided in an embodiment of the present application.

[0107] Understandably, Figure 3 The structure shown is for illustration only. The electronic device 4 may also include Figure 3 More or fewer components than shown, or with Figure 3 Different structures are shown. Figure 3 Each component shown in the figure can be implemented using hardware, software, or a combination thereof. The electronic device 4 may be a physical device, such as a PC, laptop, tablet, mobile phone, server, embedded device, etc., or a virtual device, such as a virtual machine, virtualized container, etc. Furthermore, the electronic device 4 is not limited to a single device and may also be a combination of multiple devices or a cluster consisting of a large number of devices.

[0108] The present application also provides a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are read and executed by a computer processor, the desulfurization process optimization method provided by the present application is executed. For example, the computer-readable storage medium can be implemented as Figure 3 The memory 402 in the electronic device 4.

[0109] In the embodiments provided in this application, it should be understood that the disclosed devices and systems can be implemented in other ways. The system embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interface, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0110] In addition, the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0111] Furthermore, the functional modules in each embodiment of the present application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0112] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, various modifications and variations of the present application are possible. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A desulfurization process optimization method, characterized in that: The method comprises the following steps: Modeling the desulfurization system to generate a desulfurization model; constructing the desulfurization model corresponding to the desulfurization system through software; the desulfurization model is used to simulate each section of the desulfurization system; Concentration prediction step: Based on process data and the desulfurization model, a predicted value of sulfur dioxide emission concentration and a predicted value of sulfur dioxide absorption slurry pH are obtained; the process data includes real-time indicator data and process operation data; wherein the real-time indicator data is data acquired in real time within a preset time for predicting sulfur dioxide emission concentration, and the process operation data is used to adjust the actual sulfur dioxide emission concentration; Loss determination step: calculating process losses based on the predicted value of sulfur dioxide emission concentration and the predicted value of pH of the sulfur dioxide absorption slurry; Adjusting the process operation data using a heuristic algorithm, repeatedly performing the concentration prediction step and the loss determination step until a preset termination condition is satisfied, thereby obtaining optimal process operation data, wherein the preset termination condition includes the process loss being a minimum value; The calculating of the process loss based on the predicted value of the sulfur dioxide emission concentration and the predicted value of the pH of the sulfur dioxide absorption slurry includes calculating the process loss using the following formula: + Among them, CL is the sulfur dioxide concentration loss value, EL is the electricity loss value, and SL is the material loss value. is a weighting coefficient, and CL is calculated based on the predicted value of sulfur dioxide emission concentration. It is calculated based on the predicted pH value of the sulfur dioxide absorption slurry; The process operation data includes: the sulfur dioxide concentration loss value, the power consumption loss value and the material consumption loss value are calculated according to the following formula: ; ; in, is the predicted value of sulfur dioxide emission concentration, is the predicted pH value of sulfur dioxide absorption slurry, is the first emission limit indicator, The second emission limit indicator, is the electric power of the circulation pump, is the preset upper limit of the pH value of the sulfur dioxide absorption slurry, is the preset lower limit of the pH value of the sulfur dioxide absorption slurry, For other preset limit values, To adjust the threshold.

2. The method according to claim 1, characterized in that The physical property model of the desulfurization model is an electrolyte model; the Henry components of the desulfurization model include: sulfur dioxide, oxygen, nitrogen and carbon dioxide; the water vapor equilibrium partial pressure of the desulfurization model is a STEAMNBS physical property method.

3. The method according to claim 1, characterized in that The desulfurization model includes: a sulfur dioxide absorption slurry preparation section, a sulfur dioxide absorption section and an oxidation section; wherein the sulfur dioxide absorption slurry preparation section is used to simulate the process of preparing sulfur dioxide absorption slurry; the sulfur dioxide absorption section is used to simulate the process of the sulfur dioxide absorption slurry absorbing sulfur dioxide; the oxidation section is used to simulate the oxidation process of sulfite in the sulfur dioxide absorption slurry after oxidizing air is introduced into the sulfur dioxide absorption slurry for oxidation absorption.

4. The method according to claim 1, characterized in that The process data also includes: dimensional information of the desulfurization equipment.

5. The method according to claim 1, characterized in that: The heuristic algorithm is a heuristic genetic algorithm.

6. A desulfurization process optimization device, characterized in that: The device comprises: A modeling module is used to model the desulfurization system and generate a desulfurization model; the desulfurization model corresponding to the desulfurization system is constructed by software; the desulfurization model is used to simulate each section of the desulfurization system; A prediction module, configured to obtain a predicted value of sulfur dioxide emission concentration and a predicted value of sulfur dioxide absorption slurry pH based on process data and the desulfurization model; the process data includes real-time indicator data and process operation data; wherein the real-time indicator data is data acquired in real time within a preset time period for predicting sulfur dioxide emission concentration, and the process operation data is used to adjust the actual sulfur dioxide emission concentration; a loss determination module, configured to calculate process losses based on the predicted value of sulfur dioxide emission concentration and the predicted value of pH of the sulfur dioxide absorption slurry; an optimization module, adjusting the process operation data using a heuristic algorithm, repeatedly executing the concentration prediction step and the loss determination step until a preset termination condition is satisfied, thereby obtaining optimal process operation data, wherein the preset termination condition includes the process loss being a minimum value; The loss determination module is specifically configured to: Use the following formula to calculate process loss: + Among them, CL is the sulfur dioxide concentration loss value, EL is the electricity loss value, and SL is the material loss value. is a weighting coefficient, and CL is calculated based on the predicted value of sulfur dioxide emission concentration. It is calculated based on the predicted pH value of the sulfur dioxide absorption slurry; The process operation data includes: the sulfur dioxide concentration loss value, the power consumption loss value and the material consumption loss value are calculated according to the following formula: ; ; in, is the predicted value of sulfur dioxide emission concentration, is the predicted pH value of sulfur dioxide absorption slurry, is the first emission limit indicator, The second emission limit indicator, is the electric power of the circulation pump, is the preset upper limit of the pH value of the sulfur dioxide absorption slurry, is the preset lower limit of the pH value of the sulfur dioxide absorption slurry, For other preset limit values, To adjust the threshold.

7. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores machine-readable instructions executable by the processor, and when the machine-readable instructions are executed by the processor, the method according to any one of claims 1 to 5 is performed.

8. A computer-readable storage medium, characterized in that The storage medium stores a computer program, which is used to execute the method according to any one of claims 1 to 5 when executed by a processor.

Images