High-sulfur flue gas treatment system and treatment method

Abstract

The invention discloses a high-sulfur flue gas treatment system and method, and particularly relates to the technical field of flue gas purification. Historical high-sulfur flue gas purification data is analyzed, a deep learning model is utilized for analysis, a mapping relation between process parameters and preset purification efficiency is established, and a purification efficiency prediction model is output; based on a linear regression equation, establishing a mapping relation between the process parameters and preset energy consumption cost, and outputting an energy consumption cost prediction model; preset process parameters are output based on the optimization algorithm, a limited interval of preset purification efficiency is used as a constraint, a target function of the optimization algorithm is set to enable the purification resource utilization rate to be the highest, and the purification resource utilization rate means that the ratio of the preset purification efficiency to the preset energy consumption cost is maximized; the optimal process parameter combination is searched through the optimization algorithm, and the problem that the consumption of purification resources cannot be minimized on the premise that certain purification efficiency is guaranteed in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of flue gas purification, and more specifically, to a high-sulfur flue gas treatment system and method. Background Art

[0002] From the perspective of environmental protection, it is necessary to treat sulfur-containing high-temperature flue gas. If sulfur-containing flue gas is directly discharged without treatment, it will cause serious pollution to the atmospheric environment, affecting air quality and human health. With the increasing shortage of resources, it is becoming more and more important to recycle sulfur resources in flue gas. The sulfur-containing high-temperature flue gas treatment system can convert sulfur in flue gas into valuable chemicals such as sodium sulfate, thereby realizing resource reuse, which is in line with the concept of sustainable development, can further reduce energy consumption, save production costs for enterprises, and also help achieve energy conservation and emission reduction goals.

[0003] However, in the process of sulfur-containing flue gas purification, improving purification efficiency often means increasing the consumption of purification resources. As the cost of purification resources increases, the improvement of flue gas purification efficiency shows a phenomenon of diminishing marginal effects. That is, when the purification resource investment reaches a certain level, the improvement in purification effect brought about by further investment will gradually decrease. Therefore, how to minimize the consumption of purification resources while ensuring a certain purification efficiency has become a problem that needs to be solved urgently. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the present invention provides a high-sulfur flue gas treatment system and a treatment method to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: a high-sulfur flue gas treatment system, comprising:

[0006] A treatment scheme generation module is used to output preset process parameters and corresponding preset purification efficiency and preset energy consumption cost; the preset process parameters constitute a high-sulfur flue gas treatment scheme; the treatment scheme generation module includes a purification efficiency prediction model and an energy consumption cost prediction model;

[0007] By analyzing the historical high-sulfur flue gas purification data and using deep learning model analysis, a mapping relationship between process parameters and preset purification efficiency is established, and a purification efficiency prediction model is output to complete the prediction of the preset purification efficiency.

[0008] Based on the linear regression equation, a mapping relationship between process parameters and preset energy consumption costs is established, and an energy consumption cost prediction model is output. The linear regression equation parameters are obtained by analyzing historical high-sulfur flue gas purification data to complete the prediction of the preset energy consumption cost.

[0009] Based on the preset process parameters output by the optimization algorithm, with the limited interval of the preset purification efficiency as a constraint, the objective function of the optimization algorithm is set to maximize the purification resource utilization rate, and the purification resource utilization rate refers to maximizing the ratio of the preset purification efficiency to the preset energy consumption cost;

[0010] A processing process monitoring module is used to execute the high-sulfur flue gas treatment plan and record the flue gas treatment data, which at least includes actual process parameters and corresponding actual purification efficiency and actual energy consumption cost;

[0011] The first-level warning module is used to compare the relationship between the flue gas treatment data and the preset values ​​to obtain the difference. When the difference exceeds the corresponding threshold, a first-level warning is issued; the preset values ​​include preset process parameters, preset purification efficiency and preset energy consumption cost.

[0012] Preferably, the preset process parameters refer to preset values ​​of cooling and dust removal operation process parameters, absorption tower environment control process parameters, spraying operation process parameters and cooling crystallization operation process parameters.

[0013] Preferably, the high-sulfur flue gas treatment scheme comprises the following steps:

[0014] Step S01, flue gas pretreatment: used to cool down and remove dust from high-sulfur flue gas, reduce the temperature of high-sulfur flue gas by heat replacement, reduce the concentration of particulate matter by setting an electrostatic precipitator or a wet electrostatic precipitator, and set the temperature reduction range and particulate matter concentration after the cooling and dust removal operations based on preset process parameters;

[0015] Step S02: setting the environmental parameters in the absorption tower based on the preset process parameters, the pretreated high-sulfur flue gas enters the absorption tower through the negative pressure equipment, and the flue gas inlet operating temperature, the pressure and temperature in the absorption tower are set;

[0016] Step S03, spraying treatment: setting spraying operation process parameters based on preset process parameters, using limestone or white mud as desulfurizer, the flue gas is fully in contact with the desulfurizer solution in the tower, sulfur dioxide is absorbed and converted into sodium sulfite, and then oxidized into sodium sulfate, and sodium sulfate solution is output;

[0017] Step S04: Cooling and crystallizing the sodium sulfate solution to obtain sodium sulfate crystals, and controlling the temperature of the crystallization process based on preset process parameters.

[0018] Preferably, the method for obtaining the preset purification efficiency includes: building a purification efficiency prediction model based on historical data and experimental verification, inputting the process parameter combination into the purification efficiency prediction model, and outputting the corresponding preset purification efficiency, including the following steps:

[0019] Step S11, collecting historical data: collecting historical data sets including purification efficiency data under different process parameter combinations;

[0020] Step S12, data preprocessing: cleaning data, removing outliers, and performing standardization or normalization processing; using statistical methods to identify and remove outliers; standardizing or normalizing process parameter data of different dimensions and ranges;

[0021] Step S13, building a model: selecting a neural network to build a prediction model, and selecting features that have a significant impact on purification efficiency from the process parameters as inputs to the purification efficiency prediction model;

[0022] Step S14, model training: input the preprocessed data into the purification efficiency prediction model for training, and adjust the neural network parameters to minimize the prediction error;

[0023] Step S15, model verification: using the verification data set to evaluate the prediction performance of the purification efficiency prediction model, ensuring that the model has good generalization ability, and outputting the trained purification efficiency prediction model;

[0024] Step S16: input the process parameter combination into the trained purification efficiency prediction model, and output the corresponding preset purification efficiency.

[0025] Preferably, in the first-level warning module, the differences include a first difference, a second difference and a third difference. The first difference is obtained by comparing the actual process parameters with the preset process parameters, and the second difference is obtained by comparing the actual purification efficiency with the preset purification efficiency; the third difference is obtained by comparing the actual energy consumption cost with the preset energy consumption cost; when the difference exceeds the corresponding threshold, the first-level warning is automatically triggered and a first-level warning is issued.

[0026] Preferably, the high-sulfur flue gas treatment system further comprises:

[0027] The area division module is used to divide the flue gas treatment data into several intervals according to the time intervals and number them. Assuming there are n time intervals, i represents the number of the time interval;

[0028] A process parameter analysis module is used to obtain the average value of the process reliability index Gk_avg and the process stability index Gw;

[0029] Flue gas treatment performance analysis module, used to obtain the average value of flue gas treatment quality abnormality index X an _avg and flue gas treatment performance stability index Xw;

[0030] The risk factor assessment module obtains the flue gas treatment risk factor F based on the analysis results of the process parameter analysis module and the flue gas treatment performance analysis module. na ,include

[0031] The average value of process reliability index, average value of flue gas treatment quality abnormality index, treatment process stability index and flue gas treatment performance stability index are standardized so that the value range is limited to the interval of 0 to 1. The analysis results after standardization are input into formula F na =(X an _avg-Gk_avg)*e -k1*(1-Gw )*e -k2*(1-Xw ) Calculate the flue gas treatment risk factor F na , where k1 is used to adjust the influence of the treatment process stability index on the flue gas treatment risk coefficient, and k2 is used to adjust the influence of the flue gas treatment performance stability index on the flue gas treatment risk coefficient;

[0032] The secondary warning module determines whether a warning is needed based on the relationship between the flue gas treatment risk coefficient and the preset value. If the flue gas treatment risk coefficient exceeds the preset value, a secondary warning will be issued.

[0033] Preferably, the process parameter analysis module includes:

[0034] Obtain the preset process parameters, the actual process parameters, and the upper and lower limits of the preset process parameters, obtain the deviation of the process parameters based on the upper and lower limits, and record the deviation of the sth process parameter as PL_s; ​​record the actual process parameters and the preset process parameters of the sth process parameter as G as , G bs , the allowable range of the preset process parameters is recorded as G ys ; Through the formula PL_s = The deviation of the sth process parameter is calculated;

[0035] Calculate the process deviation set [PL_1, PL_2, ..., PL_s, ..., PL_K]; analyze the process deviation set, and use the formula Obtain the processing process reliability index Gk;

[0036] Analyze the time series data of the process reliability index to obtain the standard deviation σ_b of the reliability index time series data and the average value Gk_avg of the reliability index time series data. The formula The processing stability index is obtained.

[0037] Preferably, the flue gas treatment performance analysis module includes:

[0038] Get the preset energy consumption cost and actual energy consumption cost through the formula Calculate the energy consumption abnormality index E an ; Get the preset purification efficiency and actual purification efficiency through the formula Calculate the purification efficiency abnormality index E an ; Through the formula X an=E an *WE+P an *WP, jointly analyze the energy consumption abnormality index and purification efficiency abnormality index to obtain the flue gas treatment performance abnormality index X for each time interval an ; Analyze the time series data of the flue gas treatment quality abnormality index and obtain the average value of the flue gas treatment performance abnormality index X an _avg and standard deviation of flue gas treatment performance abnormality index X an _σ, through the formula Xw=e Xan_σ The flue gas treatment performance stability index Xw is calculated.

[0039] The present invention provides the following technical solution: a method for treating high-sulfur flue gas, comprising the following steps:

[0040] Step 1: Generate a treatment plan, which is used to output preset process parameters and corresponding preset purification efficiency and preset energy consumption cost; the preset process parameters constitute a high-sulfur flue gas treatment plan, including:

[0041] By analyzing the historical high-sulfur flue gas purification data and using deep learning model analysis, we established a mapping relationship between process parameters and preset purification efficiency, obtained a purification efficiency prediction model, and completed the prediction of the preset purification efficiency.

[0042] Based on the linear regression equation, a mapping relationship between process parameters and preset energy consumption costs is established to obtain an energy consumption cost prediction model. The parameters of the linear regression equation are obtained by analyzing historical high-sulfur flue gas purification data to complete the prediction of the preset energy consumption cost.

[0043] Based on the preset process parameters output by the optimization algorithm, with the limited range of purification efficiency as a constraint, the objective function of the optimization algorithm is set to maximize the purification resource utilization rate, and the purification resource utilization rate refers to maximizing the ratio of the preset purification efficiency to the preset energy consumption cost;

[0044] Step 2: Execute the high-sulfur flue gas treatment plan and record the flue gas treatment data, which at least includes the actual process parameters and the corresponding actual purification efficiency and actual energy consumption cost;

[0045] Step 3: Compare the actual process parameters with the preset process parameters. If there is a difference, issue a first-level warning.

[0046] Preferably, the high-sulfur flue gas treatment method further comprises the following steps:

[0047] A process parameter analysis step is used to obtain an average value of a process reliability index Gk_avg and a process stability index Gw;

[0048] Flue gas treatment performance analysis steps: used to obtain the average value of flue gas treatment quality abnormality index X an_avg and flue gas treatment performance stability index Xw;

[0049] The risk factor evaluation step is to obtain the flue gas treatment risk factor F based on the analysis results of the process parameter analysis module and the flue gas treatment performance analysis module. na ;

[0050] The second-level warning step determines whether a warning is needed based on the relationship between the flue gas treatment risk coefficient and the preset value. If the flue gas treatment risk coefficient exceeds the preset value, a second-level warning is issued.

[0051] Technical effects and advantages of the present invention:

[0052] (1) The high-sulfur flue gas treatment system and treatment method provided by the present invention analyzes historical high-sulfur flue gas purification data and uses a deep learning model to analyze, establishes a mapping relationship between process parameters and preset purification efficiency, outputs a purification efficiency prediction model, and completes the prediction of the preset purification efficiency; based on a linear regression equation, establishes a mapping relationship between process parameters and preset energy consumption costs, outputs an energy consumption cost prediction model, obtains linear regression equation parameters through analysis of historical high-sulfur flue gas purification data, and completes the prediction of the preset energy consumption cost; based on an optimization algorithm, outputs preset process parameters, takes a limited range of preset purification efficiency as a constraint, and sets the objective function of the optimization algorithm to maximize the purification resource utilization rate, and the purification resource utilization rate refers to maximizing the ratio of the preset purification efficiency to the preset energy consumption cost; the optimization algorithm searches for the optimal process parameter combination based on the purification efficiency prediction model and the energy consumption cost prediction model, as well as the set objective function, and by continuously adjusting the process parameters, the optimization algorithm finds the parameter combination that makes the purification resource utilization rate the highest, and outputs these parameters as the preset process parameters, thereby solving the problem that the prior art cannot minimize the consumption of purification resources while ensuring a certain purification efficiency.

[0053] (2) The high-sulfur flue gas treatment system and treatment method provided by the present invention calculate the flue gas treatment risk coefficient by comprehensively considering the process reliability index, the flue gas treatment quality abnormality index, the treatment process stability index and the flue gas treatment performance stability index, and can quantitatively evaluate the risk level in the flue gas treatment process, providing a scientific basis for early warning and decision-making; through comprehensive analysis, evaluation and early warning of flue gas treatment data, the safety and reliability of the system are improved, providing strong support for the optimization and improvement of the flue gas treatment process. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 This is a structural block diagram of the high-sulfur flue gas treatment system of the present invention.

[0055] Figure 2 This is a structural block diagram of the high-sulfur flue gas treatment system based on flue gas treatment risk analysis of the present invention. DETAILED DESCRIPTION

[0056] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0057] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0058] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the present application, its application, or uses.

[0059] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0060] Example 1, see Figure 1 The structural block diagram of the high-sulfur flue gas treatment system of the present invention provides the following Figure 1 A high-sulfur flue gas treatment system is shown, comprising:

[0061] A treatment scheme generation module is used to output preset process parameters and corresponding preset purification efficiency and preset energy consumption cost; the preset process parameters constitute a high-sulfur flue gas treatment scheme; the treatment scheme generation module includes a purification efficiency prediction model and an energy consumption cost prediction model;

[0062] By analyzing the historical high-sulfur flue gas purification data and using deep learning model analysis, a mapping relationship between process parameters and preset purification efficiency is established, and a purification efficiency prediction model is output to complete the prediction of the preset purification efficiency.

[0063] Based on the linear regression equation, a mapping relationship between process parameters and preset energy consumption costs is established, and an energy consumption cost prediction model is output. The linear regression equation parameters are obtained by analyzing historical high-sulfur flue gas purification data to complete the prediction of the preset energy consumption cost.

[0064] Based on the preset process parameters output by the optimization algorithm, with the limited interval of the preset purification efficiency as a constraint, the objective function of the optimization algorithm is set to maximize the purification resource utilization rate, and the purification resource utilization rate refers to maximizing the ratio of the preset purification efficiency to the preset energy consumption cost;

[0065] Explanation: The objective function is the indicator that the optimization algorithm wants to maximize. Here, it is set to the highest purification resource utilization rate. The purification resource utilization rate refers to the ratio of the preset purification efficiency to the preset energy consumption cost, that is, the purification efficiency that can be obtained per unit energy consumption cost. By maximizing this ratio, the energy consumption cost can be reduced as much as possible while ensuring the purification efficiency.

[0066] A processing process monitoring module is used to execute the high-sulfur flue gas treatment plan and record the flue gas treatment data, which at least includes actual process parameters and corresponding actual purification efficiency and actual energy consumption cost;

[0067] The first-level warning module is used to compare the relationship between the flue gas treatment data and the preset values ​​to obtain the difference. When the difference exceeds the corresponding threshold, a first-level warning is issued; the preset values ​​include preset process parameters, preset purification efficiency and preset energy consumption cost.

[0068] It needs to be further explained in the embodiments of the present invention that the preset process parameters refer to the preset values ​​of the cooling and dust removal operation process parameters, the absorption tower environment control process parameters, the spraying operation process parameters and the cooling crystallization operation process parameters.

[0069] In a possible embodiment, the cooling and dust removal operation process parameters include cooling amplitude and particulate matter concentration; the absorption tower environmental control process parameters include the absorption tower pressure, temperature, water vapor content, flue gas inlet temperature, and flue gas circulation velocity; the spraying operation process parameters include desulfurizer dosage, desulfurizer concentration and spraying time; the cooling crystallization operation process parameters include the cooling rate and crystallization temperature of the cooling crystallization process, that is, the process parameters include cooling amplitude, particulate matter concentration, absorption tower pressure, temperature, water vapor content, flue gas inlet temperature, flue gas circulation velocity, desulfurizer dosage, desulfurizer concentration, spraying time, cooling rate and crystallization temperature of the cooling crystallization process.

[0070] It needs to be further explained in the embodiment of the present invention that the high-sulfur flue gas treatment solution includes the following steps:

[0071] Step S01, flue gas pretreatment: used to cool down and remove dust from high-sulfur flue gas, reduce the temperature of high-sulfur flue gas by heat replacement, reduce the concentration of particulate matter by setting an electrostatic precipitator or a wet electrostatic precipitator, and set the cooling range and particulate matter concentration after cooling and dust removal based on preset process parameters; it helps to prevent the evaporation of alkali solution caused by excessive temperature in subsequent desulfurization equipment, and improve the desulfurization efficiency;

[0072] Step S02: setting the environmental parameters in the absorption tower based on the preset process parameters, the pretreated high-sulfur flue gas enters the absorption tower through the negative pressure equipment, and the flue gas inlet operating temperature, the pressure and temperature in the absorption tower are set;

[0073] Step S03, spraying treatment: setting spraying operation process parameters based on preset process parameters, using limestone or white mud as desulfurizer, the flue gas is fully in contact with the desulfurizer solution in the tower, sulfur dioxide is absorbed and converted into sodium sulfite, and then oxidized into sodium sulfate, and sodium sulfate solution is output;

[0074] Step S04: Cooling and crystallizing the sodium sulfate solution to obtain sodium sulfate crystals, and controlling the temperature of the crystallization process based on preset process parameters.

[0075] It is necessary to further explain in the embodiment of the present invention that the method for obtaining the preset purification efficiency includes: building a purification efficiency prediction model based on historical data and experimental verification, inputting the process parameter combination into the purification efficiency prediction model, and outputting the corresponding preset purification efficiency, including the following steps:

[0076] Step S11, collecting historical data: collecting historical data sets containing purification efficiency data under different process parameter combinations, including but not limited to desulfurizer concentration, spraying amount, flue gas temperature, flue gas flow rate, and corresponding purification efficiency results;

[0077] Step S12, data preprocessing: cleaning data, removing outliers, and performing standardization or normalization processing; using statistical methods (such as box plots, Z scores, etc.) to identify and remove outliers, which may be caused by measurement errors or equipment failures; standardizing or normalizing process parameter data of different dimensions and ranges so that they have similar scales for easy processing;

[0078] Step S13, building a model: selecting a neural network to build a prediction model, and selecting features that have a significant impact on purification efficiency from the process parameters as inputs to the purification efficiency prediction model;

[0079] Step S14, model training: input the preprocessed data into the purification efficiency prediction model for training, and adjust the neural network parameters to minimize the prediction error;

[0080] Step S15, model verification: using the verification data set to evaluate the prediction performance of the purification efficiency prediction model, ensuring that the model has good generalization ability, and outputting the trained purification efficiency prediction model;

[0081] Step S16: input the process parameter combination into the trained purification efficiency prediction model, and output the corresponding preset purification efficiency.

[0082] What needs to be further explained in the embodiments of the present invention is that, in the first-level warning module, the differences include a first difference, a second difference and a third difference. By comparing the actual process parameters with the preset process parameters, the first difference is obtained, and by comparing the actual purification efficiency with the preset purification efficiency, the second difference is obtained; by comparing the actual energy consumption cost with the preset energy consumption cost, the third difference is obtained; when the difference exceeds the corresponding threshold, the first-level warning is automatically triggered, and a first-level warning is performed. It is explained that when any of the above differences exceeds the preset threshold, the first-level warning module will automatically trigger a warning signal. The threshold can be set according to the specific requirements of the system, historical data and experience, so as to ensure the accuracy and timeliness of the warning.

[0083] Example 2, see Figure 2 The structural block diagram of the high-sulfur flue gas treatment system based on flue gas treatment risk analysis is shown in FIG. The difference between the embodiment of the present invention and embodiment 1 is that the high-sulfur flue gas treatment system further includes:

[0084] The area division module is used to divide the flue gas treatment data into several intervals according to the time intervals and number them. Assuming there are n time intervals, i represents the number of the time interval;

[0085] A process parameter analysis module is used to obtain the average value of the process reliability index Gk_avg and the process stability index Gw;

[0086] Flue gas treatment performance analysis module, used to obtain the average value of flue gas treatment quality abnormality index X an _avg and flue gas treatment performance stability index Xw;

[0087] The risk factor assessment module obtains the flue gas treatment risk factor F based on the analysis results of the process parameter analysis module and the flue gas treatment performance analysis module. na ,include

[0088] The average value of process reliability index, average value of flue gas treatment quality abnormality index, treatment process stability index and flue gas treatment performance stability index are standardized so that the value range is limited to the interval of 0 to 1. The analysis results after standardization are input into formula F na =(X an _avg-Gk_avg)*e -k1*(1-Gw )*e -k2*(1-Xw) Calculate the flue gas treatment risk factor F na , where k1 is used to adjust the influence of the treatment process stability index on the flue gas treatment risk coefficient, and k2 is used to adjust the influence of the flue gas treatment performance stability index on the flue gas treatment risk coefficient;

[0089] The secondary warning module determines whether a warning is needed based on the relationship between the flue gas treatment risk coefficient and the preset value. If the flue gas treatment risk coefficient exceeds the preset value, a secondary warning will be issued.

[0090] It needs to be further explained in the embodiment of the present invention that the process parameter analysis module includes:

[0091] Obtain the preset process parameters, the actual process parameters, and the upper and lower limits of the preset process parameters, obtain the deviation of the process parameters based on the upper and lower limits, and record the deviation of the sth process parameter as PL_s; ​​record the actual process parameters and the preset process parameters of the sth process parameter as G as , G bs , the allowable range of the preset process parameters is recorded as G ys ; Through the formula PL_s = The deviation of the sth process parameter is calculated;

[0092] Calculate the process deviation set [PL_1, PL_2, ..., PL_s, ..., PL_K]; analyze the process deviation set, and use the formula Obtain the processing process reliability index Gk;

[0093] Analyze the time series data of the process reliability index to obtain the standard deviation σ_b of the reliability index time series data and the average value Gk_avg of the reliability index time series data. The formula The processing stability index is obtained.

[0094] It needs to be further explained in the embodiment of the present invention that the flue gas treatment performance analysis module includes:

[0095] Get the preset energy consumption cost and actual energy consumption cost through the formula Calculate the energy consumption abnormality index E an ; Get the preset purification efficiency and actual purification efficiency through the formula Calculate the purification efficiency abnormality index E an ; Through the formula X an =E an *WE+P an *WP, jointly analyze the energy consumption abnormality index and purification efficiency abnormality index to obtain the flue gas treatment performance abnormality index X for each time interval an ; Analyze the time series data of the flue gas treatment quality abnormality index and obtain the average value of the flue gas treatment performance abnormality index X an _avg and standard deviation of flue gas treatment performance abnormality index X an _σ, through the formula Xw=e Xan_σ The flue gas treatment performance stability index Xw is calculated.

[0096] Explanation: The regional division module divides and numbers the flue gas treatment data according to time intervals. This module makes data analysis and processing more orderly and efficient, helps to identify data change trends and abnormal points in different time periods, and provides a basis for subsequent analysis and early warning;

[0097] Process parameter analysis module: By calculating the average value of the process reliability index and the process stability index, this module can comprehensively evaluate the reliability and stability of the flue gas treatment process, and help to timely discover anomalies and fluctuations in process parameters, thereby ensuring the safety and stability of the flue gas treatment process;

[0098] Flue gas treatment performance analysis module: By calculating the average value of flue gas treatment quality abnormality index and flue gas treatment performance stability index, this module can accurately reflect the quality and performance level of flue gas treatment, help identify quality problems in the flue gas treatment process, and take corresponding measures to improve and optimize;

[0099] Risk factor assessment module: By comprehensively considering the process reliability index, flue gas treatment quality abnormality index, treatment process stability index and flue gas treatment performance stability index, the flue gas treatment risk factor is calculated, which can quantitatively assess the risk level in the flue gas treatment process and provide a scientific basis for early warning and decision-making.

[0100] Embodiment 3, the embodiment of the present invention provides the following technical solution: a method for treating high-sulfur flue gas, comprising the following steps:

[0101] Step 1: Generate a treatment plan, which is used to output preset process parameters and corresponding preset purification efficiency and preset energy consumption cost; the preset process parameters constitute a high-sulfur flue gas treatment plan, including:

[0102] By analyzing the historical high-sulfur flue gas purification data and using deep learning model analysis, we established a mapping relationship between process parameters and preset purification efficiency, obtained a purification efficiency prediction model, and completed the prediction of the preset purification efficiency.

[0103] Based on the linear regression equation, a mapping relationship between process parameters and preset energy consumption costs is established to obtain an energy consumption cost prediction model. The parameters of the linear regression equation are obtained by analyzing historical high-sulfur flue gas purification data to complete the prediction of the preset energy consumption cost.

[0104] Based on the preset process parameters output by the optimization algorithm, with the limited range of purification efficiency as a constraint, the objective function of the optimization algorithm is set to maximize the purification resource utilization rate, and the purification resource utilization rate refers to maximizing the ratio of the preset purification efficiency to the preset energy consumption cost;

[0105] Step 2: Execute the high-sulfur flue gas treatment plan and record the flue gas treatment data, which at least includes the actual process parameters and the corresponding actual purification efficiency and actual energy consumption cost;

[0106] Step 3: Compare the actual process parameters with the preset process parameters. If there is a difference, issue a first-level warning.

[0107] It needs to be further explained in the embodiment of the present invention that the high-sulfur flue gas treatment method further includes the following steps:

[0108] Step 4, obtaining the average value of the processing process reliability index Gk_avg and the processing process stability index Gw;

[0109] Step 5: Obtain the average value X of the flue gas treatment quality abnormality index an _avg and flue gas treatment performance stability index Xw;

[0110] Step 6: Based on the analysis results of the process parameter analysis module and the flue gas treatment performance analysis module, the flue gas treatment risk factor F is obtained. na ;

[0111] Step 7: Based on the relationship between the flue gas treatment risk coefficient and the preset value, determine whether an early warning is needed. If the flue gas treatment risk coefficient exceeds the preset value, a second-level early warning is issued.

[0112] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A high-sulfur flue gas treatment system, characterized in that: include: A treatment plan generation module is used to output preset process parameters and corresponding preset purification efficiency and preset energy consumption cost; The preset process parameters constitute a high-sulfur flue gas treatment solution; The treatment scheme generation module includes a purification efficiency prediction model and an energy consumption cost prediction model; By analyzing the historical high-sulfur flue gas purification data and using deep learning model analysis, a mapping relationship between process parameters and preset purification efficiency is established, and a purification efficiency prediction model is output to complete the prediction of the preset purification efficiency. Based on the linear regression equation, a mapping relationship between process parameters and preset energy consumption costs is established, and an energy consumption cost prediction model is output. The linear regression equation parameters are obtained by analyzing historical high-sulfur flue gas purification data to complete the prediction of the preset energy consumption cost. Based on the preset process parameters output by the optimization algorithm, with the limited interval of the preset purification efficiency as a constraint, the objective function of the optimization algorithm is set to maximize the purification resource utilization rate, and the purification resource utilization rate refers to maximizing the ratio of the preset purification efficiency to the preset energy consumption cost; A processing process monitoring module is used to execute the high-sulfur flue gas treatment plan and record the flue gas treatment data, which at least includes actual process parameters and corresponding actual purification efficiency and actual energy consumption cost; The first-level warning module is used to compare the relationship between the flue gas treatment data and the preset values ​​to obtain the difference. When the difference exceeds the corresponding threshold, a first-level warning is issued; the preset values ​​include preset process parameters, preset purification efficiency and preset energy consumption cost.

2. A high-sulfur flue gas treatment system according to claim 1, characterized in that: The preset process parameters refer to the preset values ​​of the cooling and dust removal operation process parameters, the absorption tower environment control process parameters, the spraying operation process parameters and the cooling crystallization operation process parameters.

3. A high-sulfur flue gas treatment system according to claim 1, characterized in that: The high-sulfur flue gas treatment scheme comprises the following steps: Step S01, flue gas pretreatment: used to cool down and remove dust from high-sulfur flue gas, reduce the temperature of high-sulfur flue gas by heat replacement, reduce the concentration of particulate matter by setting an electrostatic precipitator or a wet electrostatic precipitator, and set the temperature reduction range and particulate matter concentration after the cooling and dust removal operations based on preset process parameters; Step S02: setting the environmental parameters in the absorption tower based on the preset process parameters, the pretreated high-sulfur flue gas enters the absorption tower through the negative pressure equipment, and the flue gas inlet operating temperature, the pressure and temperature in the absorption tower are set; Step S03, spraying treatment: setting spraying operation process parameters based on preset process parameters, using limestone or white mud as desulfurizer, the flue gas is fully in contact with the desulfurizer solution in the tower, sulfur dioxide is absorbed and converted into sodium sulfite, and then oxidized into sodium sulfate, and sodium sulfate solution is output; Step S04: Cooling and crystallizing the sodium sulfate solution to obtain sodium sulfate crystals, and controlling the temperature of the crystallization process based on preset process parameters.

4. A high-sulfur flue gas treatment system according to claim 1, characterized in that: The method for obtaining the preset purification efficiency includes: building a purification efficiency prediction model based on historical data and experimental verification, inputting the process parameter combination into the purification efficiency prediction model, and outputting the corresponding preset purification efficiency, including the following steps: Step S11, collecting historical data: collecting historical data sets including purification efficiency data under different process parameter combinations; Step S12, data preprocessing: cleaning data, removing outliers, and performing standardization or normalization processing; using statistical methods to identify and remove outliers; standardizing or normalizing process parameter data of different dimensions and ranges; Step S13, building a model: selecting a neural network to build a prediction model, and selecting features that have a significant impact on purification efficiency from the process parameters as inputs to the purification efficiency prediction model; Step S14, model training: input the preprocessed data into the purification efficiency prediction model for training, and adjust the neural network parameters to minimize the prediction error; Step S15, model verification: using the verification data set to evaluate the prediction performance of the purification efficiency prediction model, ensuring that the model has good generalization ability, and outputting the trained purification efficiency prediction model; Step S16: input the process parameter combination into the trained purification efficiency prediction model, and output the corresponding preset purification efficiency.

5. A high-sulfur flue gas treatment system according to claim 1, characterized in that: In the first-level warning module, the difference includes a first difference, a second difference and a third difference. The actual process parameters are compared with the preset process parameters to obtain the first difference, and the actual purification efficiency is compared with the preset purification efficiency to obtain the second difference. Compare the actual energy consumption cost with the preset energy consumption cost to obtain the third difference; when the difference exceeds the corresponding threshold, the first-level warning is automatically triggered and a first-level warning is issued.

6. A high-sulfur flue gas treatment system according to claim 1, characterized in that: The high-sulfur flue gas treatment system also includes: The area division module is used to divide the flue gas treatment data into several intervals according to the time intervals and number them. Assuming there are n time intervals, i represents the number of the time interval; A process parameter analysis module is used to obtain the average value of the process reliability index Gk_avg and the process stability index Gw; Flue gas treatment performance analysis module, used to obtain the average value of flue gas treatment quality abnormality index X an _avg and flue gas treatment performance stability index Xw; The risk factor assessment module obtains the flue gas treatment risk factor F based on the analysis results of the process parameter analysis module and the flue gas treatment performance analysis module. na ,include The average value of process reliability index, average value of flue gas treatment quality abnormality index, treatment process stability index and flue gas treatment performance stability index are standardized so that the value range is limited to the interval of 0 to 1. The analysis results after standardization are input into formula F na =(X an _avg-Gk_avg)*e -k1*(1-Gw )*e -k2*(1-Xw ) Calculate the flue gas treatment risk factor F na , where k1 is used to adjust the influence of the treatment process stability index on the flue gas treatment risk coefficient, and k2 is used to adjust the influence of the flue gas treatment performance stability index on the flue gas treatment risk coefficient; The secondary warning module determines whether a warning is needed based on the relationship between the flue gas treatment risk coefficient and the preset value. If the flue gas treatment risk coefficient exceeds the preset value, a secondary warning will be issued.

7. A high-sulfur flue gas treatment system according to claim 6, characterized in that: The process parameter analysis module includes: Obtain the preset process parameters, the actual process parameters, and the upper and lower limits of the preset process parameters, obtain the deviation of the process parameters based on the upper and lower limits, and record the deviation of the sth process parameter as PL_s; ​​record the actual process parameters and the preset process parameters of the sth process parameter as G as , G bs , the allowable range of the preset process parameters is recorded as G ys ; Through the formula The deviation of the sth process parameter is calculated; Calculate the process deviation set [PL_1, PL_2, ..., PL_s, ..., PL_K]; analyze the process deviation set, and use the formula Obtain the processing process reliability index Gk; Analyze the time series data of the process reliability index to obtain the standard deviation σ_b of the reliability index time series data and the average value Gk_avg of the reliability index time series data. The formula The processing stability index Gw is obtained.

8. A high-sulfur flue gas treatment system according to claim 6, characterized in that: The flue gas treatment performance analysis module includes: Get the preset energy consumption cost and actual energy consumption cost through the formula Calculate the energy consumption abnormality index E an ; Get the preset purification efficiency and actual purification efficiency through the formula Calculate the purification efficiency abnormality index E an ; Through the formula X an =E an *WE+P an *WP, jointly analyze the energy consumption abnormality index and purification efficiency abnormality index to obtain the flue gas treatment performance abnormality index X for each time interval an ; Analyze the time series data of the flue gas treatment quality abnormality index and obtain the average value of the flue gas treatment performance abnormality index X an _avg and standard deviation of flue gas treatment performance abnormality index X an _σ, through the formula Xw=e Xan_σ The flue gas treatment performance stability index Xw is calculated.

9. A high-sulfur flue gas treatment method according to claim 1, used to implement a high-sulfur flue gas treatment system according to any one of claims 1 to 4, characterized in that: The following steps are involved: Step 1: Generate a treatment plan to output preset process parameters and corresponding preset purification efficiency and preset energy consumption cost; The preset process parameters constitute the high sulfur flue gas treatment solution, including: By analyzing the historical high-sulfur flue gas purification data and using deep learning model analysis, we established a mapping relationship between process parameters and preset purification efficiency, obtained a purification efficiency prediction model, and completed the prediction of the preset purification efficiency. Based on the linear regression equation, a mapping relationship between process parameters and preset energy consumption costs is established to obtain an energy consumption cost prediction model. The parameters of the linear regression equation are obtained by analyzing historical high-sulfur flue gas purification data to complete the prediction of the preset energy consumption cost. Based on the preset process parameters output by the optimization algorithm, with the limited range of purification efficiency as a constraint, the objective function of the optimization algorithm is set to maximize the purification resource utilization rate, and the purification resource utilization rate refers to maximizing the ratio of the preset purification efficiency to the preset energy consumption cost; Step 2: Execute the high-sulfur flue gas treatment plan and record the flue gas treatment data, which at least includes the actual process parameters and the corresponding actual purification efficiency and actual energy consumption cost; Step 3: Compare the actual process parameters with the preset process parameters. If there is a difference, issue a first-level warning.

10. A high-sulfur flue gas treatment method according to claim 9, characterized in that: The high-sulfur flue gas treatment method further comprises the following steps: A process parameter analysis step is used to obtain an average value of a process reliability index Gk_avg and a process stability index Gw; Flue gas treatment performance analysis steps: used to obtain the average value of flue gas treatment quality abnormality index X an _avg and flue gas treatment performance stability index Xw; The risk factor evaluation step is to obtain the flue gas treatment risk factor F based on the analysis results of the process parameter analysis module and the flue gas treatment performance analysis module. na ; The second-level warning step determines whether a warning is needed based on the relationship between the flue gas treatment risk coefficient and the preset value. If the flue gas treatment risk coefficient exceeds the preset value, a second-level warning is issued.

Images