Intelligent regulation and control system and method for whole process of desulfurization by-product generation

Abstract

The invention relates to a desulfurization by-product generation whole-process intelligent regulation and control system and method, and the method comprises the steps: firstly building an operation database, building a parameter identification model based on the database, and correcting parameters gamma and Y based on real-time monitoring data; further establishing a desulfurization tower bottom slurry sulfite ion concentration accurate prediction model, a cyclone underflow solid content accurate prediction model and a vacuum belt dehydrator outlet gypsum water content accurate prediction model, and performing real-time regulation and control on a gypsum discharge pump, an oxidation fan, a cyclone and a vacuum belt dehydrator based on the models. And then, in combination with a particle swarm optimization algorithm, full-flow regulation and control of desulfurization by-product generation are realized through a DSC controller. Under the constraint of the condition that the gypsum quality reaches the standard, global optimization regulation and control with low energy consumption as a target are carried out on the byproduct generation process, high efficiency of system operation is guaranteed, and low-energy-consumption high-quality intelligent control over the whole desulfurization byproduct generation process is achieved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of air pollutant treatment, and in particular relates to a desulfurization by-product generation full-process intelligent regulation and control system and method with quality and energy consumption constraints. BACKGROUND

[0002] At present, most coal-fired power plants adopt the limestone-gypsum method to remove sulfur dioxide (SO2) in flue gas, but the quality of desulfurization by-products in the desulfurization process changes with the operating conditions, and simply relying on the experience and knowledge of operating personnel to judge the fluctuations is relatively large, and the key parameters such as the number of gypsum discharge pumps, the number of gypsum cyclone cyclones / pressure, the speed of the belt dewatering machine, and the vacuum degree of the vacuum pump are simply set by relying on the experience and knowledge of operating personnel, which can cause problems such as the inability of the gypsum quality to meet the requirements of the national standards, and the high energy consumption of the equipment operation.

[0003] Chinese patent CN109459988 A provides a desulfurization device dewatering system optimization control method based on big data, which gives the optimal operation and start-stop scheme suggestion of the gypsum discharge pump based on real-time operation data and analysis and calculation by combining big data means, and realizes the system low-energy consumption operation target. However, this method uses artificial on-site inspection visual inspection, remote video monitoring artificial visual inspection, on-site sampling and laboratory testing means to monitor the gypsum quality of the wet desulfurization system. The visual inspection means relies on the experience of the person to judge whether the gypsum quality meets the requirements, and the judgment process and result are difficult to quantify and have poor repeatability, and are subject to the energy and mental capacity of the person and cannot be continuously online. The on-site sampling and laboratory testing means have high accuracy and good repeatability, but are time-consuming and can only be implemented intermittently. Chinese patent CN113694714 A provides an online monitoring method for slurry condition and gypsum quality, which can systematically monitor part of the by-product formation process, but the equipment operation energy consumption is relatively high under part of the operating conditions, and it is difficult to realize industrial application. SUMMARY

[0004] In order to overcome the deficiencies in the prior art, the present application provides a desulfurization by-product generation full-process intelligent regulation and control (full-process monitoring and global optimization regulation and control) system and method, which respectively establishes precise prediction models for the sulfite ion concentration in the by-product generation process, the underflow solid content in the cyclone dewatering process, and the gypsum moisture content in the belt dewatering process, and based on the models, the gypsum discharge pump, the oxidation fan, the cyclone, and the vacuum belt dewatering machine are real-time regulated and controlled, and then combined with the particle swarm optimization algorithm, the desulfurization by-product generation full-process regulation and control is realized through the DSC controller; under the condition of meeting the gypsum quality requirements, the present application performs global optimization regulation and control of the by-product generation process with the target of low energy consumption, ensures the efficiency of the system operation, and realizes intelligent control of the desulfurization by-product generation full-process with low energy consumption and high quality.

[0005] The application discloses a desulfurization by-product generation full-process intelligent regulation and control system, and relates to the field of desulfurization by-product generation. The parameters detected by the online monitoring module include desulfurization tower inlet flue gas flow, flue gas temperature, SO2 concentration, O2 concentration, desulfurization tower spraying slurry amount, oxidation fan power, desulfurization tower bottom slurry sulfite ion concentration, slurry pH, slurry density, gypsum discharge pump flow, cyclone pressure, cyclone number, cyclone underflow solid content, cyclone outlet slurry amount, vacuum belt dewatering machine rotating speed, vacuum pump pressure, gypsum washing water pump power and vacuum belt dewatering machine outlet gypsum quality. The desulfurization tower inlet and outlet flue gas flow, flue gas temperature, SO2 concentration and O2 concentration are monitored by a flue gas analyzer; the desulfurization tower bottom slurry density is monitored by a densimeter; and the vacuum belt dewatering machine gypsum spreading thickness is monitored by a thickness detector. The key parameter prediction module comprises a desulfurization tower bottom slurry sulfite ion concentration precise prediction model, a cyclone underflow solid content precise prediction model and a vacuum belt dewatering machine outlet gypsum quality precise prediction model. The key parameter control module controls parameters including gypsum discharge pump operation parameter control, oxidation fan operation parameter control, cyclone operation parameter control and vacuum belt dewatering machine operation parameter control.

[0006] The application further provides a desulfurization by-product generation full-process intelligent regulation and control method, which comprises the following steps: (1) correcting the desulfurization by-product state by constructing a precise prediction model and combining historical operation and online monitoring data, wherein the precise prediction model comprises a desulfurization tower bottom slurry sulfite ion concentration precise prediction model, a cyclone underflow solid content precise prediction model and a vacuum belt dewatering machine outlet gypsum water content precise prediction model. (2) Based on the established accurate prediction models for the sulfite ion concentration in the slurry at the bottom of the desulfurization tower, the solid content in the bottom flow of the cyclone, and the moisture content in the gypsum at the outlet of the vacuum belt dehydrator, the operating parameters of the gypsum discharge pump, oxidation fan, cyclone, and vacuum belt dehydrator were adjusted in combination with the particle swarm optimization algorithm to achieve global optimization and control of the generation of desulfurization by-products.

[0007] Preferably, the construction of the accurate prediction model for the sulfite ion concentration of the desulfurization tower bottom slurry, the accurate prediction model for the solid content of the cyclone underflow, and the accurate prediction model for the gypsum moisture content at the vacuum belt dehydrator outlet includes the following steps: Step S1: Based on historical and online operation data, a multidimensional operation database for the entire desulfurization by-product generation-dehydration process is established, covering the flue gas flow rate at the desulfurization tower inlet, flue gas temperature, SO2 concentration, O2 concentration, desulfurization tower spray slurry volume, oxidation fan power, desulfurization tower bottom slurry sulfite ion concentration, slurry pH, slurry density, gypsum discharge pump flow rate, cyclone pressure, number of cyclones, cyclone underflow solids content, cyclone outlet slurry volume, vacuum belt dehydrator speed, vacuum pump pressure, gypsum flushing water pump power, and vacuum belt dehydrator outlet gypsum moisture content; Step S2: Based on the database built in step S1, for the SO2 absorption and removal process, based on the SO2 absorption and oxidation mechanism, the response relationship between the flue gas flow rate at the desulfurization tower inlet, the flue gas temperature, the SO2 concentration, the O2 concentration, the amount of slurry sprayed in the desulfurization tower, the slurry pH, the slurry density, the oxidation fan power and the sulfite ion concentration of the slurry at the bottom of the desulfurization tower is analyzed, and a sulfite ion concentration prediction model for the slurry at the bottom of the desulfurization tower under different operating conditions is constructed. The sulfite ion concentration prediction model for the slurry at the bottom of the desulfurization tower is further modified by combining the historical operating data and online monitoring data of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower to form an accurate prediction model for the sulfite ion concentration of the slurry at the bottom of the desulfurization tower that combines mechanism and data; Step S3: Based on the database built in step S1, the response relationship between the gypsum discharge pump flow rate, cyclone pressure, number of cyclones, and cyclone underflow solids content is analyzed for the cyclone dehydration process. A cyclone underflow solids content prediction model under different operating conditions is established. The cyclone underflow solids content prediction model is further modified based on historical operating data and online monitoring data of the cyclone underflow solids content, forming a knowledge- and data-driven accurate prediction model for the cyclone underflow solids content. Step S4: Based on the database established in step S1, the response relationship of the slurry amount at the outlet of the cyclone, the solid content of the underflow of the cyclone, the rotating speed of the vacuum belt dewatering machine, the pressure of the vacuum pump, the power of the gypsum flushing water pump, and the water content of the gypsum at the outlet of the vacuum belt dewatering machine is analyzed for the belt dewatering process, a gypsum quality prediction model at the outlet of the vacuum belt dewatering machine under different working conditions is established, and the gypsum quality prediction model at the outlet of the vacuum belt dewatering machine is further corrected by combining the historical operation data and online monitoring data of the gypsum quality at the outlet of the vacuum belt dewatering machine, so as to form a knowledge and data driven precise prediction model of the gypsum quality at the outlet of the vacuum belt dewatering machine.

[0008] As preferred, step S2 specifically comprises: Step S2.1: Based on the SO2 absorption and oxidation mechanism, a natural oxidation process and a forced oxidation process model of the desulfurization and oxidation system is established. In the formula, is a SO2 natural oxidation factor of the desulfurization tower; is a SO2 forced oxidation factor of the desulfurization tower; is the SO2 molar concentration in the flue gas at the inlet of the desulfurization tower; Q is the flue gas flow at the inlet of the desulfurization tower; is the O2 molar concentration in the flue gas at the inlet of the desulfurization tower; q is the slurry spraying amount of the desulfurization tower; is the slurry spraying amount of the desulfurization tower value; is the slurry spraying density of the desulfurization tower; W is the operating power of the oxidation fan; Step S2.2: Based on the natural oxidation process and the forced oxidation process model of the desulfurization and oxidation system, a model of the absorbed SO2 molar amount per unit time and the oxidized SO2 molar amount per unit time is established. In the formula, is the absorbed SO2 molar amount per unit time; is the unit time period; is the SO2 removal efficiency; is the oxidized SO2 molar amount per unit time; is the air flow introduced by the oxidation fan; is the O2 molar concentration in the air introduced by the oxidation fan; Step S2.3: Based on the absorbed SO2 molar amount per unit time and the oxidized SO2 molar amount per unit time model, a slurry sulfite ion concentration prediction model of the bottom of the desulfurization tower is established. The molar amount of SO2 absorbed per unit time, the molar amount of SO2 oxidized per unit time, and the model are substituted into the prediction model of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower to obtain: In the formula, is the sulfite ion concentration of the slurry at the bottom of the desulfurization tower; is the sulfite ion concentration of the slurry at the bottom of the desulfurization tower at the moment t; is the sulfite ion concentration of the slurry at the bottom of the desulfurization tower at the moment t; Step S2.4: Based on the historical operation data and online sampling detection data of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower, the prediction model of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower is corrected to form a precise prediction model of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower combined with mechanism and data: In the formula, is the corrected sulfite ion concentration of the slurry at the bottom of the desulfurization tower, is the correction coefficient; The parameters in the prediction model of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower are identified (the correction parameter γ is established through the parameter identification model), and the process of parameter identification is represented by an optimization problem, that is: In the formula, is the root mean square error between the predicted value and the actual measured value of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower; is the actual measured value of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower; is the number of slurry samples in the slurry pool at the bottom of the desulfurization tower.

[0009] As preferred, step S3 specifically includes: Step S3.1: A cyclone separation efficiency model is established based on the inlet pressure of the cyclone, the slurry flow at the outlet of the gypsum discharge pump, the number of cyclones, the structure size of the cyclone, the slurry density at the outlet of the gypsum discharge pump, and the sulfite ion concentration of the slurry at the outlet of the gypsum discharge pump: In the formula, is the cyclone separation efficiency; P is the inlet pressure of the cyclone; is the slurry flow at the outlet of the gypsum discharge pump; n is the number of cyclones; D is the structure size of the cyclone; is the slurry density at the outlet of the gypsum discharge pump; ​Step S3.2: Based on the cyclone separation efficiency, combined with the cyclone outlet pressure drop, the cyclone inlet solid volume percentage, the separation efficiency model is corrected by the solid specific gravity of the inlet, and the corrected cyclone separation efficiency model: In the formula, is the corrected cyclone separation efficiency; is the cyclone pressure drop, since the cyclone dewatering process is carried out in an atmospheric pressure environment, the cyclone outlet pressure drop P* = P; is the cyclone inlet solid volume percentage; s is the solid specific gravity of the inlet; Step S3.3: Based on the corrected cyclone separation efficiency, combined with the slurry flow at the outlet of the gypsum discharge pump, the slurry density, and the slurry sulfite ion concentration at the bottom of the desulfurization tower, a knowledge and data-driven cyclone underflow solid content accurate prediction model is established: In the formula, m is the cyclone underflow solid content.

[0010] As preferred, step S4 specifically includes: Step S4.1: Based on the cyclone outlet slurry amount and the vacuum belt dewatering machine speed, a vacuum belt dewatering machine slurry thickness calculation formula is established: In the formula, h is the vacuum belt dewatering machine slurry thickness; is the vacuum belt dewatering machine speed; is the cyclone outlet slurry amount; b is the width of the vacuum belt dewatering machine filter cloth; Step S4.2: Based on the vacuum belt dewatering machine slurry thickness, the cyclone outlet slurry amount, the cyclone outlet slurry solid content, the vacuum belt dewatering machine speed, the vacuum pump pressure, and the belt dewatering process spray liquid amount, a belt dewatering process dewatering amount prediction model is established: In the formula, is the belt dewatering process dewatering amount, p is the vacuum pump pressure, is the belt dewatering process spray liquid amount; Step S4.3: Based on the belt dewatering process dewatering amount historical operation data and online sampling detection data, the belt dewatering process dewatering amount prediction model is corrected, and a mechanism and data combined belt dewatering process dewatering amount accurate prediction model is formed: In the formula, is the corrected belt dewatering process dewatering amount, Y is the correction coefficient; The belt dewatering process dewatering amount prediction model Parameter identification (establishing the correction parameter Y through the parameter identification model) is performed, and the process of parameter identification is represented by an optimization problem, that is: In the formula, is the root mean square error between the predicted value and the actual measured value of the dewatering amount of the belt dewatering process; is the actual measured value of the dewatering amount of the belt dewatering process; y is the sample quantity of the dewatering amount of the belt dewatering process; Step S4.4: Based on the corrected dewatering amount model of the belt dewatering process, combined with the slurry amount at the outlet of the cyclone, the solid content of the slurry at the outlet of the cyclone, and the spraying liquid amount of the belt dewatering process, a mechanism and data combined accurate prediction model of the gypsum moisture content at the outlet of the vacuum belt dewatering machine is established: In the formula, is the gypsum moisture content at the outlet of the vacuum belt dewatering machine.

[0011] As a preferred, the control of the gypsum discharge pump operating parameters is: based on the real-time measurement data of the slurry density meter at the bottom of the desulfurization tower, the gypsum discharge pump start-stop instruction is sent to the DCS controller through the data transmission module after the adjustment of the optimization control strategy, so that the DCS controller sends the instruction to the field device; The DCS controller instruction includes: When the gypsum density reaches the upper limit of the density, a suggestion to start the gypsum discharge pump is given; When the gypsum density reaches the lower limit of the density, a suggestion to close the gypsum discharge pump is given.

[0012] As a preferred, the control of the oxidation fan operating parameters is: through the established accurate prediction model of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower, the predicted value of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower is calculated, and further combined with the real-time operation data of the flue gas amount, temperature, SO2 concentration, and oxidation fan power at the inlet of the desulfurization tower, the oxidation fan power instruction is sent to the DCS controller through the data transmission module after the adjustment of the optimization control strategy, so that the DCS controller sends the instruction to the field device; The predicted value of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower is used as a given instruction, and the flue gas amount, temperature, SO2 concentration, and oxidation fan power at the inlet of the desulfurization tower are used as a feedforward instruction; The optimization control strategy adjustment is to select the lowest oxidation fan power under the condition of setting the sulfite ion concentration of the slurry at the bottom of the desulfurization tower, and set the upper and lower limits of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower to ensure that the gypsum quality meets the standard; The DCS controller instruction includes: When the sulfite ion concentration reaches the lower limit of the concentration, a suggestion to reduce the oxidation fan power is given; When the sulfite ion concentration reaches the upper limit, a suggestion is given to increase the oxidation fan power.

[0013] Preferably, the cyclone operating parameters are controlled as follows: using the established accurate prediction model for sulfite ion concentration in the desulfurization tower bottom slurry and the accurate prediction model for solid content in the cyclone bottom flow, the sulfite ion concentration in the desulfurization tower bottom slurry and the predicted solid content in the cyclone bottom flow are calculated, and further combined with the real-time operating data of the slurry flow at the gypsum discharge pump outlet and the cyclone pressure, after optimizing the control strategy, the cyclone insertion and removal instructions are sent to the DCS controller through the data transmission module, and the DCS controller then sends the instructions to the field equipment; The predicted value of the solid content in the cyclone bottom flow is used as a given instruction, and the sulfite ion concentration of the slurry at the bottom of the desulfurization tower, the slurry flow rate at the outlet of the gypsum discharge pump, and the cyclone pressure are used as feedforward instructions; DCS controller instructions include: When the solid content of the cyclone bottom flow reaches the lower limit, it is recommended to increase the number of cyclones; When the solid content of the cyclone bottom flow reaches the upper limit, a suggestion is given to reduce the number of cyclones.

[0014] As a preferred method, the operating parameters of the vacuum belt dehydrator are adjusted as follows: by using the established accurate prediction model for the sulfite ion concentration of the slurry at the bottom of the desulfurization tower, the accurate prediction model for the solid content of the cyclone underflow, and the accurate prediction model for the gypsum quality at the outlet of the vacuum belt dehydrator, the predicted values ​​of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower, the predicted value of the solid content of the cyclone underflow, and the predicted value of the gypsum quality at the outlet of the vacuum belt dehydrator are calculated; further combined with the slurry volume at the outlet of the cyclone and the pressure of the vacuum pump, after adjustment through a multi-model prediction optimization control strategy, the speed instruction of the vacuum belt dehydrator and the power instruction of the gypsum flushing water pump are sent to the DCS controller through the data communication module, and the DCS controller then sends the instructions to the on-site equipment; The predicted value of the gypsum quality at the outlet of the vacuum belt dehydrator is used as a given instruction, and the predicted value of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower, the predicted value of the solid content of the cyclone bottom flow, the slurry volume at the outlet of the cyclone, and the vacuum pump pressure are used as feedforward instructions; The optimization control strategy is to set the gypsum quality conditions at the outlet of the vacuum belt dehydrator, select the method with the lowest speed of the vacuum belt dehydrator and the lowest power of the gypsum flushing pump, and set the gypsum quality constraint conditions at the outlet of the vacuum belt dehydrator to ensure that the gypsum quality meets the standards; Gypsum quality constraints are as follows: In the formula, is the gypsum chloride ion content at the outlet of the vacuum belt dewaterer; PH is the pH value of the gypsum at the outlet; The DCS controller instructions include: When the slurry spreading thickness reaches the upper limit of the thickness, the gypsum moisture content reaches the upper limit, and the gypsum chloride ion content reaches the lower limit, a suggestion of increasing the speed of the belt dewaterer and increasing the power of the gypsum flushing water pump is given; When the slurry spreading thickness reaches the lower limit of the thickness, the gypsum moisture content reaches the lower limit, and the gypsum chloride ion content reaches the upper limit, a suggestion of reducing the speed of the belt dewaterer and reducing the power of the gypsum flushing water pump is given.

[0015] As a preferred, the process adjusted in combination with the particle swarm optimization algorithm is: Global optimization control is carried out with the target of low energy consumption, that is, the optimal particle fitness: In the formula, , respectively represent the by-product generation process cost, the cyclone dewatering process cost, and the belt dewatering process cost; The by-product generation process cost includes the power consumption Power O generated by the operation of the oxidation fan and the power consumption Power P generated by the operation of the gypsum discharge pump; the cyclone dewatering process cost includes the energy loss Power b caused by the resistance loss along the way; the belt dewatering process cost includes the power consumption Power B of the belt dewaterer, the power consumption Power V of the vacuum pump, and the power consumption Power W of the belt flushing water pump; that is: The optimal particle fitness is: The present application has the following beneficial effects: (1) In view of the frequent fluctuations of the flue gas composition, the SO2 concentration of the flue gas, the flue gas temperature and the like under different working conditions, the present application provides a wet desulfurization whole-process intelligent regulation and control method, which establishes a prediction model, corrects the desulfurization by-product state in combination with historical operation and online monitoring data, further based on a desulfurization tower bottom slurry sulfite ion concentration accurate prediction model, a cyclone underflow solid content accurate prediction model and a vacuum belt dewatering machine outlet gypsum water content accurate prediction model, adjusts the oxidation fan, the gypsum discharge pump, the cyclone, the vacuum belt dewatering machine and the gypsum flushing water pump equipment operation parameters in combination with a particle swarm optimization algorithm, and realizes the global optimization regulation and control of the desulfurization by-product generation.

[0016] (2) The present application carries out desulfurization by-product generation whole-process high-quality low-energy consumption intelligent control based on the equipment low-energy consumption operation target and in combination with the particle swarm optimization algorithm, realizes the low-energy consumption operation of the desulfurization equipment while ensuring the gypsum quality, and proves that 23.7% of energy consumption can be saved in the wet desulfurization process by-product generation stage of a 1000MW coal-fired generating unit, and the economic benefit is quite remarkable.

[0017] (3) The present application analyzes and controls the oxidation fan, the gypsum discharge pump, the cyclone and the vacuum dewatering belt machine through the intelligent algorithm, realizes the optimal gypsum quality control, greatly reduces the operation amount of the operation personnel, the whole system runs more stably, the gypsum quality is higher, the energy consumption is lower, and the economic benefit is improved. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 is a desulfurization system diagram of the present application; Figure 2 is a desulfurization by-product generation whole-process intelligent regulation and control flow chart; Figure 3 is a unit load and natural oxidation rate relationship diagram; Figure 4 is a unit load and oxidation air demand quantity relationship diagram. DETAILED DESCRIPTION

[0019] The technical solutions of the present application are further specifically described below through examples, and these examples are for the description of the present application but not the limitation of the present application. Based on the examples in the present application, all other examples obtained by the person skilled in the art without creative labor are within the protection scope of the present application.

[0020] Example 1 Reference Figure 1A full-process intelligent control system for desulfurization byproduct generation is disclosed. The control system includes a desulfurization byproduct generation system and an intelligent control system. The desulfurization byproduct generation system includes a desulfurization tower 1, a gypsum discharge pump 2, a cyclone 3, a vacuum belt dehydrator 4, and an oxidation blower 5 connected to the desulfurization tower. The desulfurization tower 1, gypsum discharge pump 2, cyclone 3, and vacuum belt dehydrator 4 are sequentially connected. The vacuum belt dehydrator 4 is also respectively connected to a gypsum flushing water pump 6 and a vacuum pump 7. The intelligent control system includes an online monitoring module, a key parameter prediction module, and a key parameter control module.

[0021] The parameters detected by the online monitoring module include the flue gas flow at the desulfurization tower inlet, flue gas temperature, SO2 concentration, O2 concentration, desulfurization tower spray slurry volume, oxidation fan power, sulfite ion concentration of the slurry at the bottom of the desulfurization tower, slurry pH, slurry density, gypsum discharge pump flow, cyclone pressure, number of cyclones, cyclone bottom flow solid content, cyclone outlet slurry volume, vacuum belt dehydrator speed, vacuum pump pressure, gypsum flushing water pump power and vacuum belt dehydrator outlet gypsum quality.

[0022] The flue gas flow rate, flue gas temperature, SO2 concentration, and O2 concentration at the desulfurization tower inlet and outlet are monitored using a flue gas analyzer 8; the slurry density at the desulfurization tower bottom is monitored using a densitometer 9; and the gypsum spread thickness of the vacuum belt dehydrator is monitored using a thickness detector 10. The input ends of the flue gas analyzer 8, densitometer 9, and thickness detector 10 are respectively connected to the flue gas inlet and outlet of the desulfurization tower 1, the slurry pool at the desulfurization tower bottom, and the vacuum belt dehydrator 4, while their output ends are respectively connected to a DCS controller 11.

[0023] The key parameter prediction module includes an accurate prediction model for the sulfite ion concentration of the slurry at the bottom of the desulfurization tower, an accurate prediction model for the solid content of the cyclone bottom flow, and an accurate prediction model for the gypsum quality at the outlet of the vacuum belt dehydrator.

[0024] The parameters controlled by the key parameter control module include the control of the operating parameters of the gypsum discharge pump (gypsum discharge pump start and stop control), the control of the operating parameters of the oxidation fan (oxidation fan power control), the control of the operating parameters of the cyclone (cyclone input and removal control), and the control of the operating parameters of the vacuum belt dehydrator (vacuum belt dehydrator speed control, gypsum flushing water pump power control).

[0025] Reference Figure 2 A method for intelligently controlling the entire process of generating desulfurization by-products comprises the following steps: (1) By constructing a precise prediction model and combining historical operation and online monitoring data to correct the desulfurization by-product state, the precise prediction model includes a precise prediction model of the desulfurization tower bottom slurry sulfite ion concentration, a precise prediction model of the cyclone underflow solid content, and a precise prediction model of the gypsum moisture content at the outlet of the vacuum belt dewaterer; (2) Further based on the established precise prediction model of the desulfurization tower bottom slurry sulfite ion concentration, the precise prediction model of the cyclone underflow solid content, and the precise prediction model of the gypsum moisture content at the outlet of the vacuum belt dewaterer, combined with the particle swarm optimization algorithm, the operating parameters of the gypsum discharge pump, the oxidation fan, the cyclone, and the vacuum belt dewaterer are adjusted to realize global optimization control of the desulfurization by-product generation.

[0026] The construction of the precise prediction model of the desulfurization tower bottom slurry sulfite ion concentration, the precise prediction model of the cyclone underflow solid content, and the precise prediction model of the gypsum moisture content at the outlet of the vacuum belt dewaterer includes the following steps: Step S1: Based on historical and online operation data, a multi-dimensional operation database of the desulfurization by-product generation-dewatering whole process is established, which covers the desulfurization tower inlet flue gas flow, flue gas temperature, SO2 concentration, O2 concentration, desulfurization tower spray slurry amount, oxidation fan power, desulfurization tower bottom slurry sulfite ion concentration, slurry pH, slurry density, gypsum discharge pump flow, cyclone pressure, cyclone number of cyclones, cyclone underflow solid content, cyclone outlet slurry amount, vacuum belt dewaterer speed, vacuum pump pressure, gypsum flushing water pump power, and gypsum moisture content at the outlet of the vacuum belt dewaterer; Step S2: Based on the database established in step S1, for the SO2 absorption and removal process, based on the SO2 absorption and oxidation mechanism, the response relationship of the desulfurization tower inlet flue gas flow, flue gas temperature, SO2 concentration, O2 concentration, desulfurization tower spray slurry amount, slurry pH, slurry density, oxidation fan power, and desulfurization tower bottom slurry sulfite ion concentration is analyzed, a desulfurization tower bottom slurry sulfite ion concentration prediction model under different conditions is constructed, further combined with the historical operation data and online monitoring data of the desulfurization tower bottom slurry sulfite ion concentration, the desulfurization tower bottom slurry sulfite ion concentration prediction model is corrected, and a precise prediction model of the desulfurization tower bottom slurry sulfite ion concentration combining mechanism and data is formed; Step S3: Based on the database established in step S1, for the cyclone dewatering process, the response relationship of the gypsum discharge pump flow, cyclone pressure, number of cyclones, and cyclone underflow solid content is analyzed, a cyclone underflow solid content prediction model under different conditions is established, further combined with the historical operation data and online monitoring data of the cyclone underflow solid content, the cyclone underflow solid content prediction model is corrected, and a precise prediction model of the cyclone underflow solid content driven by knowledge and data is formed; Step S4: Based on the database established in step S1, the response relationship of the slurry amount at the outlet of the cyclone, the solid content of the underflow of the cyclone, the rotational speed of the vacuum belt dewatering machine, the pressure of the vacuum pump, the power of the gypsum flushing water pump, and the water content of the gypsum at the outlet of the vacuum belt dewatering machine is analyzed for the belt dewatering process. A gypsum quality prediction model at the outlet of the vacuum belt dewatering machine under different working conditions is established. Further, the gypsum quality prediction model at the outlet of the vacuum belt dewatering machine is corrected by combining the historical operation data and online monitoring data of the gypsum quality at the outlet of the vacuum belt dewatering machine, to form a knowledge and data driven precise prediction model of the gypsum quality at the outlet of the vacuum belt dewatering machine.

[0027] Further, the step S2 of establishing the mechanism and data combined precise prediction model of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower specifically includes: Step S2.1: Based on the SO2 absorption and oxidation mechanism, a natural oxidation process and a forced oxidation process model of the desulfurization oxidation system is established. In the formula, is a SO2 natural oxidation factor of the desulfurization tower; is a SO2 forced oxidation factor of the desulfurization tower; is the SO2 molar concentration in the flue gas at the inlet of the desulfurization tower; Q is the flue gas flow at the inlet of the desulfurization tower; is the O2 molar concentration in the flue gas at the inlet of the desulfurization tower; q is the slurry spraying amount of the desulfurization tower; is the slurry spraying amount of the desulfurization tower value; is the slurry spraying density of the desulfurization tower; W is the operating power of the oxidation fan; Step S2.2: Based on the natural oxidation process and the forced oxidation process model of the desulfurization oxidation system, a model of the absorbed SO2 molar amount per unit time and the oxidized SO2 molar amount per unit time is established. In the formula, is the absorbed SO2 molar amount per unit time; is the unit time period; is the SO2 removal efficiency; is the oxidized SO2 molar amount per unit time; is the air flow introduced by the oxidation fan; is the O2 molar concentration in the air introduced by the oxidation fan; Step S2.3: Based on the absorbed SO2 molar amount per unit time and the oxidized SO2 molar amount per unit time model, a prediction model of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower is established. The unit time absorbed SO2 molar quantity, the unit time oxidized SO2 molar quantity model is substituted into the desulfurization tower bottom slurry sulfite ion concentration prediction model to obtain: In the formula, is the desulfurization tower bottom slurry sulfite ion concentration; is the desulfurization tower bottom slurry sulfite ion concentration at the moment; Step S2.4: Based on the desulfurization tower bottom slurry sulfite ion concentration historical operation data and online sampling detection data, the desulfurization tower bottom slurry sulfite ion concentration prediction model is corrected to form a mechanism and data combined desulfurization tower bottom slurry sulfite ion concentration accurate prediction model: In the formula, is the corrected desulfurization tower bottom slurry sulfite ion concentration, is a correction coefficient; Further, the parameter identification is performed on in the desulfurization tower bottom slurry sulfite ion concentration prediction model. The process of parameter identification is expressed by an optimization problem, that is: In the formula, is the root mean square error between the desulfurization tower bottom slurry pool sulfite ion concentration model prediction value and the actual measurement value; is the actual measurement value of the desulfurization tower bottom slurry sulfite ion concentration; is the number of slurry samples in the desulfurization tower bottom slurry pool.

[0028] Further, the establishment of the knowledge and data driven cyclone underflow solid content accurate prediction model in step S3 specifically includes: Step S3.1: Based on the cyclone inlet pressure, the gypsum discharge pump outlet slurry flow, the number of cyclones, the cyclone structure size, the gypsum discharge pump outlet slurry density, the gypsum discharge pump outlet slurry sulfite ion concentration, the cyclone separation efficiency model is established: In the formula, is the cyclone separation efficiency; P is the cyclone inlet pressure; is the gypsum discharge pump outlet slurry flow; n is the number of cyclones; is the cyclone structure size; is the gypsum discharge pump outlet slurry density; ​Step S3.2: Based on the cyclone separation efficiency, combined with the cyclone outlet pressure drop, the cyclone feed solid volume percentage, the separation efficiency model is corrected by the feed solid specific gravity, and the corrected cyclone separation efficiency model is: In the formula, is the corrected cyclone separation efficiency; is the cyclone pressure drop, since the cyclone dewatering process is carried out in an atmospheric pressure environment, the cyclone outlet pressure drop P* = P; is the cyclone feed solid volume percentage; s is the feed solid specific gravity; Step S3.3: Based on the corrected cyclone separation efficiency, combined with the gypsum discharge pump outlet slurry flow, slurry density, desulfurization tower bottom slurry sulfite ion concentration, a knowledge and data driven cyclone underflow solid content precise prediction model is established: In the formula, m is the cyclone underflow solid content.

[0029] Further, the establishment of the knowledge and data driven vacuum belt dewatering machine outlet gypsum water content prediction model in step S4 specifically includes: Step S4.1: Based on the cyclone outlet slurry amount and the vacuum belt dewatering machine speed, a vacuum belt dewatering machine slurry thickness calculation formula is established: In the formula, h is the vacuum belt dewatering machine slurry thickness; is the vacuum belt dewatering machine speed; is the cyclone outlet slurry amount; b is the vacuum belt dewatering machine filter cloth width; Step S4.2: Based on the vacuum belt dewatering machine slurry thickness, the cyclone outlet slurry amount, the cyclone outlet slurry solid content, the vacuum belt dewatering machine speed, the vacuum pump pressure, and the belt dewatering process spray liquid amount, a belt dewatering process dewatering amount prediction model is established: In the formula, is the belt dewatering process dewatering amount, p is the vacuum pump pressure, is the belt dewatering process spray liquid amount; Step S4.3: Based on the belt dewatering process dewatering amount historical operation data and online sampling detection data, the belt dewatering process dewatering amount prediction model is corrected, and a mechanism and data combined belt dewatering process dewatering amount precise prediction model is formed: In the formula, is the corrected belt dewatering process dewatering amount, Y is the correction coefficient; Further, in the dehydration amount prediction model of the belt dehydration process Parameter identification is performed, and the process of parameter identification is represented by an optimization problem, that is: In the formula, is the root mean square error between the prediction value of the belt dehydration process dehydration amount model and the actual measured value; is the actual measured value of the belt dehydration process dehydration amount; y is the sample quantity of the belt dehydration process dehydration amount; Step S4.4: Based on the corrected belt dehydration process dehydration amount model, combined with the slurry amount at the outlet of the cyclone, the solid content of the slurry at the outlet of the cyclone, and the spraying liquid amount of the belt dehydration process, a mechanism and data combined accurate prediction model of the gypsum moisture content at the outlet of the vacuum belt dewaterer is established: In the formula, is the gypsum moisture content at the outlet of the vacuum belt dewaterer.

[0030] Further, the control of the running parameters of the gypsum discharge pump (gypsum discharge pump start-stop control) is: based on the real-time measurement data of the slurry density meter at the bottom of the desulfurization tower, the gypsum discharge pump start-stop instruction is sent to the DCS controller through the data transmission module after the optimization control strategy adjustment, so that the DCS controller sends the instruction to the field device; The DCS controller instruction includes: When the gypsum density reaches the upper limit of the density, a suggestion to start the gypsum discharge pump is given; When the gypsum density reaches the lower limit of the density, a suggestion to close the gypsum discharge pump is given.

[0031] Further, the control of the running parameters of the oxidation fan (oxidation fan power control) is: through the established accurate prediction model of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower, the prediction value of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower is calculated, and further combined with the real-time running data of the flue gas amount, temperature, SO2 concentration at the inlet of the desulfurization tower, and the power of the oxidation fan, the oxidation fan power instruction is sent to the DCS controller through the data transmission module after the optimization control strategy adjustment, so that the DCS controller sends the instruction to the field device; The prediction value of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower is used as a given instruction, and the flue gas amount, temperature, SO2 concentration at the inlet of the desulfurization tower, and the power of the oxidation fan are used as feedforward instructions; The optimization regulation strategy adjustment is to select the mode with the lowest power of the oxidation fan under the condition of setting the sulfite ion concentration of the slurry at the bottom of the desulfurization tower. Meanwhile, frequent adjustment of the power of the oxidation fan in actual operation can greatly affect the service life of the equipment. In addition, in order to avoid the problem of non-standard gypsum quality due to untimely adjustment of the power of the oxidation fan, the upper and lower limits of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower are set to ensure that the gypsum quality meets the standard; The DCS controller instructions include: When the sulfite ion concentration reaches the lower limit, a suggestion to reduce the power of the oxidation fan is given. When the sulfite ion concentration reaches the upper limit, a suggestion to increase the power of the oxidation fan is given.

[0032] Further, the control of the operating parameters of the cyclone (cyclone input, cutting control) is as follows: through the established precise prediction model of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower and the precise prediction model of the solids content of the underflow of the cyclone, the predicted values of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower and the solids content of the underflow of the cyclone are calculated, and further combined with the real-time operating data of the slurry flow at the outlet of the gypsum discharge pump and the pressure of the cyclone, the optimization regulation strategy adjustment is carried out, and the cyclone input and cutting instructions are sent to the DCS controller through the data transmission module, so that the DCS controller sends the instructions to the field equipment; The predicted value of the solids content of the underflow of the cyclone is taken as a given instruction, and the sulfite ion concentration of the slurry at the bottom of the desulfurization tower, the slurry flow at the outlet of the gypsum discharge pump and the pressure of the cyclone are taken as feedforward instructions; The DCS controller instructions include: When the solids content of the underflow of the cyclone reaches the lower limit, a suggestion to increase the number of cyclones is given. When the solids content of the underflow of the cyclone reaches the upper limit, a suggestion to reduce the number of cyclones is given.

[0033] Further, the control of the operating parameters of the vacuum belt dewaterer (vacuum belt dewaterer speed control, gypsum flushing water pump power control) is as follows: through the established precise prediction model of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower, the precise prediction model of the solids content of the underflow of the cyclone and the precise prediction model of the gypsum quality at the outlet of the vacuum belt dewaterer, the predicted values of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower, the solids content of the underflow of the cyclone and the gypsum quality at the outlet of the vacuum belt dewaterer are calculated, and further combined with the slurry flow at the outlet of the cyclone and the pressure of the vacuum pump, the multi-model prediction optimization regulation strategy adjustment is carried out, and the speed instruction of the vacuum belt dewaterer and the power instruction of the gypsum flushing water pump are sent to the DCS controller through the data communication module, so that the DCS controller sends the instructions to the field equipment; The predicted value of the gypsum quality at the outlet of the vacuum belt dehydrator is used as a given instruction, and the predicted value of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower, the predicted value of the solid content of the cyclone bottom flow, the slurry volume at the outlet of the cyclone, and the vacuum pump pressure are used as feedforward instructions; The optimization control strategy is to set the vacuum belt dehydrator outlet gypsum quality conditions, select the vacuum belt dehydrator speed, gypsum flushing water pump power to minimize the power. At the same time, in actual operation, frequent adjustments to the vacuum belt dehydrator speed and gypsum flushing water pump power will greatly reduce the service life of the equipment. In addition, to avoid the problem of gypsum quality not meeting the standard due to untimely adjustment of the vacuum belt dehydrator speed and gypsum flushing water pump power, the vacuum belt dehydrator outlet gypsum quality constraints are set to ensure that the gypsum quality meets the standard. Gypsum quality constraints are as follows: Where, Chloride ion content of gypsum at the outlet of vacuum belt dehydrator; PH is the pH value of the export gypsum; DCS controller instructions include: When the slurry spreading thickness reaches the upper limit, the gypsum moisture content reaches the upper limit, and the gypsum chloride ion content reaches the lower limit, suggestions are given to increase the speed of the belt dehydrator and the power of the gypsum flushing pump; When the slurry spreading thickness reaches the lower limit, the gypsum moisture content reaches the lower limit, and the gypsum chloride ion content reaches the upper limit, suggestions are given to reduce the speed of the belt dehydrator and the power of the gypsum flushing water pump.

[0034] The process of adjustment combined with the particle swarm optimization algorithm is as follows: Carry out global optimization and control with low energy consumption as the goal, that is, the optimal particle fitness: in, 、 They represent the cost of by-product generation process, cyclone dehydration process, and belt dehydration process respectively; The cost of the by-product generation process includes the power consumption generated by the oxidation fan operation O , Power consumption generated by the operation of gypsum discharge pump P The cost of the cyclone dehydration process includes the energy loss caused by the resistance loss along the way. b ; The cost of the belt dehydration process includes the power consumption of the belt dehydrator B , Power consumption of vacuum pumpV Power W ; that is: The optimal example fitness is: In the intelligent regulation and control process of the desulfurization by-product generation of the application, firstly, an operation database is established, a parameter identification model is established based on the database, and the parameters γ and Y are corrected based on real-time monitoring data, and a knowledge and data driven desulfurization by-product generation model (a precise prediction model of the desulfurization tower bottom slurry sulfite ion concentration, a precise prediction model of the cyclone underflow solid content, and a precise prediction model of the gypsum water content at the outlet of the vacuum belt dewatering machine) is further established, then the particle swarm optimization algorithm is combined to realize the whole process regulation and control of the desulfurization by-product generation through the DSC controller. The data correction of the application adopts the particle swarm optimization algorithm (particle swarm PSO algorithm), firstly, the parameters γ and Y are initialized, then the real-time operation data is combined to calculate the RMSE (evaluation standard calculation), and then the best position is updated, if the obtained RMSE is the minimum, the data correction is ended, otherwise, the parameters are continuously updated, and the calculation of the RMSE is returned until the RMSE is the minimum.

[0035] Example 2 An oxidation system optimization operation test is carried out on a certain 1000 MW unit desulfurization device, the relationship between the unit load and the natural oxidation rate is as shown in Figure 3 , under the condition of high load (more than 800 MW), the natural oxidation rate of the desulfurization tower is low, less than 15%, under the condition of low load (less than 800 MW), the natural oxidation rate of the desulfurization tower can be up to 30%; the relationship between the unit load and the oxidation air demand is as shown in Figure 4 , the oxidation air demand reaches more than 220 m 3 / min under high load, and the minimum oxidation air demand is only 107 m 3 / min.

[0036] The control of the unit on the oxidation fan, the gypsum discharge pump, the cyclone dewatering equipment, the belt dewatering machine, the vacuum pump and the belt flushing water pump equipment has the following three strategies (parallel two groups). The first is the rated power operation strategy, the DCS does not control the equipment, and the equipment works at the rated frequency for a long time. The second is the optimization strategy based on the operation experience of the equipment, and the DCS will switch the working frequency of the equipment according to the experience of the field operator based on the unit load. When the unit load is at medium and low load, the working frequency of the equipment is reduced; when the unit load is at high load, the equipment is controlled to operate at the rated working frequency. The third is the intelligent control method described in embodiment 1; the energy consumption comparison analysis results of different operation strategies are shown in Table 1. According to the premise of ensuring the quality of the desulfurization by-product gypsum, compared with the rated power operation, the strategy according to the operation experience optimization can save 4.2% of the energy consumption, and the strategy according to the intelligent control method operation can save 23.7% of the energy consumption.

[0037] Table 1 Energy consumption comparison analysis of different operation strategies The above embodiments are only used to illustrate the technical solutions of the present application, but not limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. An intelligent control system for the entire process of desulfurization by-product generation, characterized by: The control system includes a desulfurization by-product generation system and an intelligent control system. The desulfurization by-product generation system includes a desulfurization tower, a gypsum discharge pump, a cyclone, a vacuum belt dehydrator, and an oxidation fan connected to the desulfurization tower. The desulfurization tower, the gypsum discharge pump, the cyclone, and the vacuum belt dehydrator are connected in sequence. The vacuum belt dehydrator is also connected to the gypsum flushing water pump and the vacuum pump respectively. The intelligent control system includes an online monitoring module, a key parameter prediction module, and a key parameter control module. The parameters detected by the online monitoring module include the flue gas flow rate at the desulfurization tower inlet, flue gas temperature, SO2 concentration, O2 concentration, desulfurization tower spray slurry volume, oxidation fan power, desulfurization tower bottom slurry sulfite ion concentration, slurry pH, slurry density, gypsum discharge pump flow rate, cyclone pressure, number of cyclones, cyclone bottom flow solid content, cyclone outlet slurry volume, vacuum belt dehydrator speed, vacuum pump pressure, gypsum flushing water pump power and vacuum belt dehydrator outlet gypsum quality; The key parameter prediction module includes an accurate prediction model for the sulfite ion concentration of the desulfurization tower bottom slurry, an accurate prediction model for the solid content of the cyclone bottom flow, and an accurate prediction model for the gypsum quality at the outlet of the vacuum belt dehydrator; The parameters controlled by the key parameter control module include the control of the operating parameters of the gypsum discharge pump, the control of the operating parameters of the oxidation fan, the control of the operating parameters of the cyclone, and the control of the operating parameters of the vacuum belt dehydrator.

2. A method for intelligently controlling the entire process of desulfurization by-product generation, characterized in that The control system according to claim 1 comprises the following steps: (1) Correcting the state of desulfurization by-products by constructing an accurate prediction model and combining it with historical operation and online monitoring data. The accurate prediction model includes an accurate prediction model for the sulfite ion concentration in the slurry at the bottom of the desulfurization tower, an accurate prediction model for the solid content in the cyclone bottom flow, and an accurate prediction model for the moisture content of gypsum at the outlet of the vacuum belt dehydrator; (2) Based on the established accurate prediction models for the sulfite ion concentration in the slurry at the bottom of the desulfurization tower, the solid content in the bottom flow of the cyclone, and the moisture content in the gypsum at the outlet of the vacuum belt dehydrator, the operating parameters of the gypsum discharge pump, oxidation fan, cyclone, and vacuum belt dehydrator were adjusted in combination with the particle swarm optimization algorithm to achieve global optimization and control of the generation of desulfurization by-products.

3. The method for intelligently controlling the entire process of desulfurization by-product generation according to claim 2, characterized in that: The construction of the accurate prediction model of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower, the accurate prediction model of the solid content of the cyclone underflow, and the accurate prediction model of the gypsum moisture content at the outlet of the vacuum belt dehydrator includes the following steps: Step S1: Based on historical and online operation data, a multidimensional operation database for the entire desulfurization by-product generation-dehydration process is established, covering the flue gas flow rate at the desulfurization tower inlet, flue gas temperature, SO2 concentration, O2 concentration, desulfurization tower spray slurry volume, oxidation fan power, desulfurization tower bottom slurry sulfite ion concentration, slurry pH, slurry density, gypsum discharge pump flow rate, cyclone pressure, number of cyclones, cyclone underflow solids content, cyclone outlet slurry volume, vacuum belt dehydrator speed, vacuum pump pressure, gypsum flushing water pump power, and vacuum belt dehydrator outlet gypsum moisture content; Step S2: Based on the database built in step S1, the response relationship between the flue gas flow rate at the desulfurization tower inlet, the flue gas temperature, the SO2 concentration, the O2 concentration, the amount of slurry sprayed from the desulfurization tower, the slurry pH, the slurry density, the oxidation fan power and the sulfite ion concentration of the slurry at the bottom of the desulfurization tower is analyzed, and a prediction model for the sulfite ion concentration of the slurry at the bottom of the desulfurization tower under different operating conditions is constructed. The historical operating data and online monitoring data of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower are further combined to revise the prediction model for the sulfite ion concentration of the slurry at the bottom of the desulfurization tower, thereby forming an accurate prediction model for the sulfite ion concentration of the slurry at the bottom of the desulfurization tower that combines mechanism and data; Step S3: Based on the database built in step S1, the response relationship between the gypsum discharge pump flow rate, cyclone pressure, number of cyclones, and cyclone underflow solids content is analyzed to establish a cyclone underflow solids content prediction model under different operating conditions. The cyclone underflow solids content prediction model is further modified by combining historical operating data and online monitoring data of the cyclone underflow solids content to form a knowledge- and data-driven accurate prediction model for the cyclone underflow solids content. Step S4: Based on the database built in step S1, the response relationship between the slurry volume at the cyclone outlet, the solid content of the cyclone underflow, the speed of the vacuum belt dehydrator, the pressure of the vacuum pump, the power of the gypsum flushing pump and the moisture content of the gypsum at the vacuum belt dehydrator outlet is analyzed, and a gypsum quality prediction model for the vacuum belt dehydrator outlet under different working conditions is established. The gypsum quality prediction model for the vacuum belt dehydrator outlet is further modified by combining the historical operating data and online monitoring data of the gypsum quality at the vacuum belt dehydrator outlet to form a knowledge and data-driven accurate prediction model for the gypsum quality at the vacuum belt dehydrator outlet.

4. The method for intelligently controlling the entire process of generating desulfurization by-products according to claim 3, characterized in that: Step S2 specifically includes: Step S2.1: Establish the natural oxidation process and forced oxidation process models of the desulfurization oxidation system: Where, It is the natural oxidation factor of SO2 in the desulfurization tower; It is the forced oxidation factor of SO2 in the desulfurization tower; is the SO2 molar concentration in the flue gas at the desulfurization tower inlet; Q is the flue gas flow rate at the desulfurization tower inlet; is the O2 molar concentration in the flue gas at the desulfurization tower inlet; q is the amount of slurry sprayed in the desulfurization tower; Spray slurry for desulfurization tower value; is the density of the desulfurization tower spray slurry, and W is the operating power of the oxidation fan; Step S2.2: Based on the natural oxidation process and forced oxidation process models of the desulfurization oxidation system, establish a model for the molar amount of SO2 absorbed per unit time and the molar amount of SO2 oxidized per unit time: Where, is the molar amount of SO2 absorbed per unit time; is the unit time period; is the SO2 removal efficiency; is the molar amount of SO2 oxidized per unit time; Introducing air flow for oxidation blower; The molar concentration of O2 in the air introduced by the oxidation blower; Step S2.3: Based on the model of the molar amount of SO2 absorbed per unit time and the molar amount of SO2 oxidized per unit time, a prediction model for the sulfite ion concentration in the slurry at the bottom of the desulfurization tower is established: The sulfite ion concentration in the slurry at the bottom of the desulfurization tower is obtained by combining the model of the molar amount of SO2 absorbed per unit time and the molar amount of SO2 oxidized per unit time with the prediction model of the sulfite ion concentration in the slurry at the bottom of the desulfurization tower: Where, is the sulfite ion concentration of the slurry at the bottom of the desulfurization tower; for Sulfite ion concentration in the slurry at the bottom of the desulfurization tower at any moment; Step S2.4: Based on the historical operation data of the sulfite ion concentration of the desulfurization tower bottom slurry and the online sampling test data, the sulfite ion concentration prediction model of the desulfurization tower bottom slurry is modified to form an accurate prediction model of the sulfite ion concentration of the desulfurization tower bottom slurry that combines mechanism and data: Where, is the sulfite ion concentration of the desulfurization tower bottom slurry after correction, is the correction factor; The prediction model of sulfite ion concentration in the desulfurization tower bottom slurry Perform parameter identification.

5. The method for intelligently controlling the entire process of desulfurization by-product generation according to claim 3, characterized in that: Step S3 specifically includes: Step S3.1: Establish a cyclone separation efficiency model based on the cyclone inlet pressure, the slurry flow rate at the gypsum discharge pump outlet, the number of cyclones, the cyclone structure size, the slurry density at the gypsum discharge pump outlet, and the sulfite ion concentration at the slurry at the gypsum discharge pump outlet: Where, is the cyclone separation efficiency; P is the cyclone inlet pressure; The slurry flow rate at the outlet of the gypsum discharge pump; n is the number of vortices; is the structural size of the cyclone; is the slurry density at the outlet of the gypsum discharge pump; Step S3.2: Based on the cyclone separation efficiency, combined with the cyclone outlet pressure drop, the cyclone feed solid volume percentage, and the feed solid specific gravity, the separation efficiency model is modified. The modified cyclone separation efficiency model is: Where, is the corrected cyclone separation efficiency; is the cyclone pressure drop, is the volume percentage of the solids in the cyclone; s is the specific gravity of the solids in the cyclone; Step S3.3: Based on the corrected cyclone separation efficiency, combined with the slurry flow rate and density at the gypsum discharge pump outlet and the sulfite ion concentration at the bottom of the desulfurization tower, a knowledge- and data-driven accurate prediction model for the cyclone underflow solids content is established: Where, m is the solid content of the cyclone bottom flow.

6. The method for intelligently controlling the entire process of generating desulfurization by-products according to claim 3, characterized in that: Step S4 specifically includes: Step S4.1: Based on the slurry volume at the cyclone outlet and the speed of the vacuum belt dehydrator, establish a formula for calculating the slurry thickness of the vacuum belt dehydrator: Where, h is the slurry thickness of the vacuum belt dehydrator; is the speed of the vacuum belt dehydrator; is the slurry volume at the cyclone outlet; b is the filter cloth width of the vacuum belt dehydrator; Step S4.2: Based on the slurry thickness of the vacuum belt dehydrator, the slurry volume at the cyclone outlet, the solid content of the slurry at the cyclone outlet, the speed of the vacuum belt dehydrator, the pressure of the vacuum pump, and the amount of spray liquid during the belt dehydration process, a dehydration volume prediction model for the belt dehydration process is established: Where, The dehydration amount of the belt dehydration process, p is the vacuum pump pressure, The amount of spray liquid for the belt dehydration process; Step S4.3: Based on the historical operation data of the belt dehydration process and the online sampling test data, the belt dehydration process dehydration amount prediction model is modified to form an accurate belt dehydration process dehydration amount prediction model that combines mechanism and data: Where, is the dehydration amount of the belt dehydration process after correction, and Y is the correction coefficient; Dehydration amount prediction model for belt dehydration process Perform parameter identification; Step S4.4: Based on the modified belt dehydration process dehydration volume model, combined with the slurry volume at the cyclone outlet, the solid content of the slurry at the cyclone outlet, and the amount of spray liquid during the belt dehydration process, an accurate prediction model for the gypsum moisture content at the outlet of the vacuum belt dehydrator is established, combining mechanism and data: Where, It is the moisture content of gypsum at the outlet of vacuum belt dehydrator.

7. The method for intelligently controlling the entire process of generating desulfurization by-products according to claim 2, characterized in that: The gypsum discharge pump operating parameters are controlled as follows: Based on the real-time measurement data of the slurry density meter at the bottom of the desulfurization tower, after optimizing the control strategy, the start and stop instructions of the gypsum discharge pump are sent to the DCS controller through the data transmission module, and the DCS controller then sends the instructions to the field equipment; The oxidation fan operating parameters are controlled by: using the established accurate prediction model for sulfite ion concentration in the desulfurization tower bottom slurry, the predicted value of sulfite ion concentration in the desulfurization tower bottom slurry is calculated. This is further combined with the real-time operating data of the desulfurization tower inlet flue gas volume, temperature, SO2 concentration, and oxidation fan power. After optimizing the control strategy, the oxidation fan power command is sent to the DCS controller through the data transmission module, and the DCS controller then sends the command to the field equipment. The predicted value of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower is used as a given instruction, and the flue gas volume, temperature, SO2 concentration and oxidation fan power at the desulfurization tower inlet are used as feedforward instructions; The optimization control strategy is to select the method with the lowest oxidation fan power under the condition of setting the sulfite ion concentration of the slurry at the bottom of the desulfurization tower, and set the upper and lower limits of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower to ensure that the gypsum quality meets the standards.

8. The method for intelligently controlling the entire process of desulfurization by-product generation according to claim 2, characterized in that: The cyclone operating parameters are controlled by: using the established accurate prediction models for sulfite ion concentration in the desulfurization tower bottom slurry and solid content in the cyclone underflow, the sulfite ion concentration in the desulfurization tower bottom slurry and the predicted solid content in the cyclone underflow are calculated. Furthermore, combined with the real-time operating data of the slurry flow rate at the gypsum discharge pump outlet and the cyclone pressure, after optimizing the control strategy, the cyclone insertion and removal instructions are sent to the DCS controller through the data transmission module, and the DCS controller then sends the instructions to the field equipment. The predicted value of the solid content in the cyclone bottom flow is used as a given instruction, and the sulfite ion concentration of the slurry at the bottom of the desulfurization tower, the slurry flow rate at the outlet of the gypsum discharge pump, and the cyclone pressure are used as feedforward instructions.

9. The method for intelligently controlling the entire process of desulfurization by-product generation according to claim 2, characterized in that: The operating parameters of the vacuum belt dehydrator are controlled as follows: using the established accurate prediction models for sulfite ion concentration in the desulfurization tower bottom slurry, solid content in the cyclone underflow, and gypsum quality at the vacuum belt dehydrator outlet, the predicted values ​​of sulfite ion concentration in the desulfurization tower bottom slurry, solid content in the cyclone underflow, and gypsum quality at the vacuum belt dehydrator outlet are calculated. Furthermore, combined with the slurry volume at the cyclone outlet and the vacuum pump pressure, the vacuum belt dehydrator speed command and gypsum flushing pump power command are sent to the DCS controller via the data communication module through a multi-model prediction optimization control strategy. The DCS controller then sends the commands to the field equipment. The predicted value of the gypsum quality at the outlet of the vacuum belt dehydrator is used as a given instruction, and the predicted value of the sulfite ion concentration of the slurry at the bottom of the desulfurization tower, the predicted value of the solid content of the cyclone bottom flow, the slurry volume at the outlet of the cyclone, and the vacuum pump pressure are used as feedforward instructions; The optimization control strategy is to set the gypsum quality conditions at the outlet of the vacuum belt dehydrator, select the lowest speed of the vacuum belt dehydrator and the gypsum flushing pump power, and set the gypsum quality constraint conditions at the outlet of the vacuum belt dehydrator to ensure that the gypsum quality meets the standards.

10. The method for intelligently controlling the entire process of desulfurization by-product generation according to claim 2, characterized in that: The process of adjustment combined with the particle swarm optimization algorithm is as follows: Calculate the optimal particle fitness: in, 、 They represent the cost of by-product generation process, cyclone dehydration process, and belt dehydration process respectively; The cost of the by-product generation process includes the power consumption generated by the oxidation fan operation O And the power consumption generated by the operation of the gypsum discharge pump P The cost of the cyclone dehydration process includes the energy loss caused by the resistance loss along the way. b ; The cost of the belt dehydration process includes the power consumption of the belt dehydrator B , Power consumption of vacuum pump V And the power consumption of the belt flushing pump W .

Images