Full-load desulfurization wastewater zero discharge system and method

Abstract

The invention relates to the technical field of desulfurization wastewater zero discharge, and discloses a full-load desulfurization wastewater zero discharge system and method, and the system comprises an acquisition module which is used for constructing a first control parameter group, a second control parameter group and a third control parameter group of a unit full load, and carrying out the neural network training as training data, a corresponding control parameter prediction model is obtained; the generation module is used for acquiring a real-time load value and inputting the real-time load value into the control parameter prediction model to obtain a plurality of prediction control parameters and generate a desulfurization wastewater treatment instruction; the evaluation module is used for acquiring real-time monitoring parameters of the wastewater based on the monitoring time nodes and generating real-time operation evaluation values of the corresponding modules according to the real-time monitoring parameters; the optimization module is used for judging whether optimization is needed or not according to the real-time operation evaluation value, if yes, the control parameters to be optimized are screened out, an optimization instruction is generated, full-load desulfurization wastewater zero discharge of the desulfurization wastewater system is achieved, the wastewater discharge requirement is met, and environmental pollution is reduced.

Description

Technical Field

[0001] This application relates to the technical field of zero discharge of desulfurized wastewater, and particularly to a full-load zero-discharge system and method for desulfurized wastewater. Background Art

[0002] The current zero-discharge technology for desulfurized wastewater in thermal power plants, which is "low-temperature flue gas concentration + harmless treatment of heavy metals + evaporation of desulfurized wastewater by bypass flue gas", is limited by the unit load. The evaporated flue gas is taken from before the air preheater and returned to after the air preheater. When the unit is at low load, due to the low differential pressure of the air preheater, the wastewater in the evaporator cannot be atomized well and caked, and it is forced to stop operating. The concentration system is also forced to stop operating, resulting in serious corrosion of the flue duct of the concentration system and affecting the normal operation of the zero-discharge system for wastewater.

[0003] Therefore, the current zero-discharge technology for desulfurized wastewater has not achieved zero discharge of desulfurized wastewater at full load. Therefore, there is an urgent need for a full-load zero-discharge system and method for desulfurized wastewater to meet the requirements of full-load wastewater discharge, improve the control efficiency of the system, and reduce environmental pollution. Summary of the Invention

[0004] To solve the above technical problems, this application provides a full-load zero-discharge system and method for desulfurized wastewater. By constructing a control parameter prediction module under full-load conditions and combining the real-time load value, the predicted control parameters of the current module are determined and a desulfurized wastewater treatment instruction is generated. According to the real-time operation evaluation value, it is judged whether optimization is needed. If so, the control parameters to be optimized are determined and an optimization instruction is generated, realizing zero discharge of desulfurized wastewater in the full-load desulfurized wastewater system, improving the control efficiency and control accuracy of the zero-discharge system, meeting the requirements of wastewater discharge, and reducing environmental pollution.

[0005] In some embodiments of this application, a full-load zero-discharge system for desulfurized wastewater is provided, including: An acquisition module, configured to construct a first control parameter group, a second control parameter group, and a third control parameter group for the full load of the unit, and use them as training data for neural network training to obtain a corresponding control parameter prediction model; A generation module, configured to obtain the real-time load value and input it into the control parameter prediction model to obtain several predicted control parameters, and generate a desulfurized wastewater treatment instruction according to the predicted control parameters; An evaluation module, configured to obtain the real-time monitoring parameters of the wastewater based on a preset monitoring time node, and generate a real-time operation evaluation value of the corresponding module according to the real-time monitoring parameters; An optimization module, configured to judge whether optimization is needed according to the real-time operation evaluation value. If so, screen out the control parameters to be optimized in the current module and generate an optimization instruction.

[0006] In some embodiments of the present application, the first control parameter group includes several first control parameters of the low-temperature flue gas concentration module, and the several first control parameters include the flue gas temperature, flue gas flow rate, wastewater flow rate, and concentrated liquid concentration of the low-temperature flue gas concentration module; The second control parameter group includes several second control parameters of the heavy metal treatment module, and the several second control parameters include the reaction pH value, the chemical dosing parameter of the calcium carbonate slurry, the reaction temperature, the stirring intensity, and the reaction time; The third control parameter group includes several third control parameters of the high-temperature bypass flue gas evaporation module, and the several third control parameters include the evaporation temperature of the high-temperature bypass flue gas evaporation module, the wastewater atomization particle size, the moisture content of the flue gas, and the atomization effect.

[0007] In some embodiments of the present application, before constructing the first control parameter group, the second control parameter group, and the third control parameter group for the full load of the unit, it further includes: Obtain the historical wastewater treatment log, screen out the preferred wastewater treatment log according to the historical wastewater treatment results, and use the historical treatment duration of each module in each preferred wastewater treatment log as the time reference line; Based on the preset time interval and the historical treatment duration of each module, set the historical acquisition nodes of the corresponding module; Collect the historical unit load and the historical control parameters of the corresponding module according to the historical acquisition nodes, and construct the historical unit load change curve and the historical control parameter change curve corresponding to each module; Pre-divide the full load of the unit into several preset sub-load intervals on average; Mark the historical unit load change curve corresponding to each module according to the boundary load values of each preset sub-load interval to obtain several historical unit load change curve segments, and map each historical unit load change curve segment to the corresponding preset sub-load interval one by one; Analyze the historical control parameter change curve at the same historical acquisition nodes of each historical unit load change curve segment to obtain the historical fluctuation characteristics of each historical control parameter at several historical acquisition nodes of each historical unit load change curve segment; Generate the historical fluctuation evaluation value of the corresponding historical control parameter in the corresponding historical unit load change curve segment according to the historical fluctuation characteristics, and generate the operation influence evaluation value of the preset sub-load interval mapped by the corresponding historical load change curve segment for the corresponding module according to the historical fluctuation evaluation value of each historical control parameter; Generate the operation influence evaluation values of several preset sub-load intervals for each module in turn; Preset the first preset operation influence evaluation value interval, the second preset operation influence evaluation value interval, and the third preset operation influence evaluation value interval; Judge whether it is necessary to adjust the corresponding preset sub - load interval according to the relationship between the operation impact evaluation value and the preset operation impact evaluation value interval; When the operation impact evaluation value is within the first preset operation impact evaluation value interval, perform a similarity analysis on the historical change characteristics of each historical control parameter in the corresponding preset sub - load interval and the historical change characteristics of the corresponding historical control parameters in the adjacent preset sub - load interval to obtain the similarity; Merge the corresponding preset sub - load interval into the adjacent preset sub - load interval with the maximum similarity; When the operation impact evaluation value is within the second preset operation impact evaluation value interval, do not adjust the preset sub - load interval; When the operation impact evaluation value is within the third preset operation impact evaluation value interval, re - divide the corresponding preset sub - load interval; Generate several adjusted sub - load intervals for each module according to the adjustment result.

[0008] In some embodiments of the present application, the operation impact evaluation value includes: The historical fluctuation characteristics include the historical fluctuation degree, historical fluctuation magnitude, and historical volatility at several historical acquisition nodes in the corresponding historical unit load change curve segment; Compare the historical fluctuation characteristics with the preset fluctuation characteristics to obtain and quantify the historical fluctuation characteristic differences, and obtain the first value, the second value, and the third value; Generate a historical fluctuation evaluation value according to the first value, the second value, and the third value; Compare the historical fluctuation evaluation values of multiple historical control parameters in each preset sub - load interval of each module with the preset fluctuation evaluation value threshold, screen out the number of historical control parameters whose historical fluctuation evaluation values are greater than the preset fluctuation evaluation value threshold according to the comparison result, and calculate the historical fluctuation evaluation value difference; Generate the operation impact evaluation value of the corresponding preset sub - load interval for the corresponding module according to the number of the screened - out historical control parameters and the corresponding historical fluctuation evaluation value difference; The calculation formula of the operation impact evaluation value is: ; Where Y is the operation impact evaluation value, y1 is the operation impact conversion coefficient, n1 is the number of the screened - out historical control parameters, n2 is the total number of historical control parameters of the corresponding module, is the historical fluctuation evaluation value difference of the i - th screened - out historical control parameter.

[0009] In some embodiments of the present application, a first control parameter group, a second control parameter group, and a third control parameter group for the full load of the unit are constructed and used as training data for neural network training to obtain a corresponding control parameter prediction model, including: Generate an operation influence ratio for the corresponding adjustment sub-load interval according to the load change value and the operation influence evaluation value corresponding to each adjustment sub-load interval in each module; Preset a first preset operation influence ratio threshold, a second preset operation influence ratio threshold, and a third preset operation influence ratio threshold; When the operation influence ratio is less than the first preset operation influence ratio threshold, set the standard number of acquisitions for the corresponding adjustment sub-load interval to the fourth preset number of acquisitions; When the operation influence ratio is between the first preset operation influence ratio threshold and the second preset operation influence ratio threshold, set the standard number of acquisitions for the corresponding adjustment sub-load interval to the third preset number of acquisitions; When the operation influence ratio is between the second preset operation influence ratio threshold and the third preset operation influence ratio threshold, set the standard number of acquisitions for the corresponding adjustment sub-load interval to the second preset number of acquisitions; When the operation influence ratio is greater than the third preset operation influence ratio threshold, set the standard number of acquisitions for the corresponding adjustment sub-load interval to the first preset number of acquisitions; Collect data on each historical control parameter change curve at several historical acquisition nodes in the historical load change curve segment mapped by the adjustment sub-load interval according to the standard number of acquisitions, and collect water quality characteristics, to obtain several first control parameters of the low-temperature flue gas concentration module, several second control parameters of the heavy metal treatment module, several third control parameters of the high-temperature bypass flue gas evaporation module, and wastewater water quality characteristics; Among them, there is a mapping relationship between the several first control parameters, the several second control parameters, and the several third control parameters and the corresponding adjustment sub-load intervals of the corresponding modules and the wastewater water quality characteristics; Use the several adjustment sub-loads and wastewater water quality characteristics of each module as training input data, and use the several first control parameters, the several second control parameters, and the several third control parameters of each module that have a mapping relationship with the several adjustment sub-loads as training output data; Perform neural network training according to the training input data and the training output data to obtain a control parameter prediction model.

[0010] In some embodiments of the present application, generate a desulfurized wastewater treatment instruction according to the predicted control parameters, including: Obtain the real-time load value and real-time wastewater water quality characteristics of the current module, and determine the adjustment sub-load interval where the real-time load value is located; Determine the adjustment sub-load interval where the real-time load value of the current module is located and the predictive control parameters of the real-time wastewater quality characteristics based on the control parameter prediction model; Generate a desulfurized wastewater treatment instruction for the corresponding module according to the predictive control parameters of the current module, and control the current module according to the desulfurized wastewater treatment instruction.

[0011] In some embodiments of the present application, generate a real-time operation evaluation value for the corresponding module according to the real-time monitoring parameters, including: Preset the operation inspection period of the current module, and set a number of monitoring time nodes based on the preset time interval and the time length of the operation inspection duration; Obtain the real-time monitoring parameters of the current module according to the monitoring time nodes, and the real-time monitoring parameters include the actual control parameters of the current module, the actual wastewater quality characteristics, and the actual change characteristics of the actual wastewater quality characteristics; Compare the actual wastewater quality characteristics with the standard wastewater quality characteristics of the corresponding module to obtain the actual wastewater quality characteristic difference, and compare the actual change characteristics with the standard change characteristics of the standard wastewater quality characteristics of the corresponding module to obtain the actual change characteristic difference; Generate an initial operation evaluation value according to the actual wastewater quality characteristic difference, and generate a compensation coefficient according to the actual change characteristic difference; Generate a real-time operation evaluation value for the current module according to the initial operation evaluation value and the corresponding compensation coefficient.

[0012] In some embodiments of the present application, screen out the control parameters to be optimized for the current module and generate an optimization instruction, including: Preset the operation evaluation value threshold for the operation inspection period of the current module; If the real-time operation evaluation value is greater than the operation evaluation value threshold, the current module does not need to be optimized; If the real-time operation evaluation value is less than the operation evaluation value threshold, set the wastewater quality characteristics with the actual wastewater quality characteristic difference greater than the preset water quality characteristic difference threshold or the actual change characteristic difference of the actual wastewater quality characteristics greater than the preset change characteristic difference threshold as the water quality characteristics to be optimized, and calculate the corresponding difference characteristics to be optimized; Determine the historical control parameters associated with the water quality characteristics to be optimized based on the historical wastewater treatment log, and construct a control parameter reference library for the water quality characteristics to be optimized; The control parameter reference library includes the preset difference characteristics corresponding to the water quality characteristics to be optimized, and each preset difference characteristic is associated with a preset regulation amount value of the corresponding associated historical control parameter; Determine the control parameters to be optimized for the current module according to the historical control parameters associated with the water quality characteristics to be optimized, and determine the regulation amount value to be adjusted for the control parameters to be optimized based on the control parameter reference library; Generate an optimization instruction based on the control parameter to be optimized and the quantity value to be regulated, and iteratively train the control parameter prediction model according to the regulated control parameter.

[0013] In some embodiments of the present application, there is also a method for zero discharge of desulfurized wastewater at full load: Construct a first control parameter group, a second control parameter group, and a third control parameter group for the full load of the unit, and use them as training data for neural network training to obtain the corresponding control parameter prediction model; Obtain the real-time load value and input it into the control parameter prediction model to obtain several predicted control parameters, and generate a desulfurized wastewater treatment instruction according to the predicted control parameters; Obtain the real-time monitoring parameters of the wastewater based on the preset monitoring time node, and generate a real-time operation evaluation value for the corresponding module according to the real-time monitoring parameters; Judge whether optimization is needed according to the real-time operation evaluation value. If so, screen out the control parameter to be optimized for the current module and generate an optimization instruction.

[0014] A full-load desulfurized wastewater zero-discharge system and method according to an embodiment of the present application, compared with the prior art, its beneficial effects are as follows: By constructing a control parameter prediction module under the full-load state, combining with the real-time load value, determining the predicted control parameter of the current module and generating a desulfurized wastewater treatment instruction, judging whether optimization is needed according to the real-time operation evaluation value. If so, determining the control parameter to be optimized and generating an optimization instruction, realizing zero discharge of desulfurized wastewater in the desulfurized wastewater system at full load, improving the control efficiency and control accuracy of the zero-discharge system, meeting the wastewater discharge requirements and reducing environmental pollution. Description of the Drawings

[0015] Figure 1 is a schematic diagram of a full-load desulfurized wastewater zero-discharge system in an embodiment of the present application; Figure 2 is a flowchart of a full-load desulfurized wastewater zero-discharge method in an embodiment of the present application. Detailed Embodiments

[0016] The following combines the drawings and embodiments to further describe in detail the specific embodiments of the present application. The following embodiments are used to illustrate the present application, but are not used to limit the scope of the present application.

[0017] In the description of this application, it should be understood that the orientation or positional relationship indicated by terms such as "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing this application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to this application.

[0018] The terms "first" and "second" are only used for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of this application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0019] In the description of this application, it should be noted that unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0020] As Figure 1 shown, a full-load desulfurized wastewater zero-discharge system according to an embodiment of this application includes: An acquisition module, configured to construct a first control parameter group, a second control parameter group, and a third control parameter group for the full load of the unit, and use them as training data for neural network training to obtain a corresponding control parameter prediction model; A generation module, configured to obtain a real-time load value and input it into the control parameter prediction model to obtain a number of predicted control parameters, and generate a desulfurized wastewater treatment instruction according to the predicted control parameters; An evaluation module, configured to obtain real-time monitoring parameters of the wastewater based on a preset monitoring time node, and generate a real-time operation evaluation value for the corresponding module according to the real-time monitoring parameters; An optimization module, configured to determine whether optimization is required according to the real-time operation evaluation value. If so, screen out the control parameters to be optimized for the current module and generate an optimization instruction.

[0021] In this embodiment, the full load of the unit includes high load and low load in the deep adjustment state. In this application, more emphasis is placed on the system control parameters under low load. By constructing a control parameter prediction model for the full load of each module, the normal operation of the wastewater zero-discharge system and the wastewater discharge requirements are achieved, and environmental pollution is reduced.

[0022] In some embodiments of the present application, the first control parameter group includes several first control parameters of the low-temperature flue gas concentration module, and the several first control parameters include the flue gas temperature, flue gas flow rate, wastewater flow rate, and concentrate concentration of the low-temperature flue gas concentration module; The second control parameter group includes several second control parameters of the heavy metal treatment module, and the several second control parameters include the reaction pH value, chemical dosing parameters of the calcium carbonate slurry, reaction temperature, stirring intensity, and reaction time; The third control parameter group includes several third control parameters of the high-temperature bypass flue gas evaporation module, and the several third control parameters include the evaporation temperature of the high-temperature bypass flue gas evaporation module, wastewater atomization particle size, flue gas moisture content, and atomization effect.

[0023] In this embodiment, the low-temperature flue gas concentration module includes a pre-settler, a wastewater tank, a low-temperature flue gas concentration tower, a booster fan, etc. The operation process includes but is not limited to: one way of the desulfurized wastewater enters the pre-settler and then enters the wastewater tank, and the other way directly enters the wastewater tank through a bypass electric valve to adjust the solid content entering the wastewater tank to 1%-2%. The wastewater coming out of the wastewater tank enters the low-temperature flue gas concentration tower. The water side is sprayed above the concentration tower by a circulating pump. The flue gas at 90-110°C after the induced draft fan enters the concentration tower through the booster fan, evaporates a part of the sprayed wastewater, removes the mist, and then returns to the FGD inlet. After being desulfurized by FGD, it is discharged to the atmosphere through the chimney. The wastewater after concentration has a solid content of about 6-8%. This concentration of solid content can increase the seed crystal, and the wastewater is not easy to crystallize on the pipeline.

[0024] In this embodiment, the heavy metal treatment module includes a heavy metal disposal device, a mercury removal device, etc. The operation process includes but is not limited to: the wastewater enters the heavy metal disposal device, and the pH value of the wastewater is adjusted to 5-6 by the calcium carbonate slurry. At the same time, a mercury removal device is set up, that is, by adding limestone, the pH value is adjusted to about 9, and most of the mercury is removed to form a precipitate, which is then filtered and removed through an inclined tube sedimentation tank. The wastewater after heavy metal treatment enters the spray water tank and is pumped into the bypass flue gas evaporator through a pump. The concentrated inlet and outlet flue ducts are made of glass flakes with strong anti-corrosion ability and suitable for humid and strongly acidic environments to ensure that the flue ducts are not corroded.

[0025] In this embodiment, the high-temperature bypass flue gas evaporation module includes an air preheater, a high-temperature bypass flue gas evaporator, a spray water tank, etc. The operation process includes but is not limited to: from the inlet of the air preheater, 5-10% of the high-temperature flue gas with a temperature up to 300-350°C is extracted to the high-temperature bypass flue gas evaporator. The wastewater from the spray water tank is atomized by high-speed rotation and then vaporized by the high-temperature flue gas. After the flue gas returns to the electrostatic precipitator, due to the flue gas differential pressure of the bypass flue gas evaporator being at least 0.6 Kpa, even when the unit load is at the deep peak shaving load of 30% of the rated load, there is sufficient power and flue gas volume to achieve full-load evaporation.

[0026] In some embodiments of the present application, before constructing the first control parameter group, the second control parameter group, and the third control parameter group for the full load of the unit, it further includes: Obtain the historical wastewater treatment log, screen out the preferred wastewater treatment log according to the historical wastewater treatment results, and use the historical treatment duration of each module in each preferred wastewater treatment log as the time reference line; Based on the preset time interval and the historical treatment duration of each module, set the historical acquisition nodes corresponding to each module; Collect the historical unit load and the historical control parameters of the corresponding module according to the historical acquisition nodes, and construct the historical unit load change curve and the historical control parameter change curve corresponding to each module; Pre-divide the full load of the unit into several preset sub-load intervals on average; Mark the historical unit load change curve corresponding to each module according to the boundary load values of each preset sub-load interval to obtain several historical unit load change curve segments, and map each historical unit load change curve segment to the corresponding preset sub-load interval one by one; Analyze the historical control parameter change curve at the same historical acquisition nodes of each historical unit load change curve segment to obtain the historical fluctuation characteristics of each historical control parameter at several historical acquisition nodes of each historical unit load change curve segment; Generate the historical fluctuation evaluation value of the corresponding historical control parameter in the corresponding historical unit load change curve segment according to the historical fluctuation characteristics, and generate the operation influence evaluation value of the preset sub-load interval mapped by the corresponding historical load change curve segment for the corresponding module according to the historical fluctuation evaluation value of each historical control parameter; Generate the operation influence evaluation values of several preset sub-load intervals for each module in turn; Pre-set the first preset operation influence evaluation value interval, the second preset operation influence evaluation value interval, and the third preset operation influence evaluation value interval; Judge whether it is necessary to adjust the corresponding preset sub-load interval according to the relationship between the operation influence evaluation value and the preset operation influence evaluation value interval; When the operation influence evaluation value is within the first preset operation influence evaluation value range, perform similarity analysis on the historical change characteristics of each historical control parameter in the corresponding preset sub-load range and the historical change characteristics of the corresponding historical control parameters in the adjacent preset sub-load range to obtain the similarity; Merge the corresponding preset sub-load range into the adjacent preset sub-load range with the maximum similarity; When the operation influence evaluation value is within the second preset operation influence evaluation value range, do not adjust the preset sub-load range; When the operation influence evaluation value is within the third preset operation influence evaluation value range, re-divide the corresponding preset sub-load range; Generate several adjusted sub-load ranges for each module according to the adjustment result.

[0027] In this embodiment, preferably, the wastewater treatment log refers to the historical wastewater treatment log with high wastewater treatment efficiency and the wastewater discharge meeting the discharge standard.

[0028] In this embodiment, the first preset operation influence evaluation value range < the second preset operation influence evaluation value range < the third preset operation influence evaluation value range. The operation influence evaluation value refers to the influence degree of the corresponding preset sub-load range on the control parameters of the corresponding module. When the operation influence evaluation value is larger, it indicates a greater influence degree, and then the corresponding preset sub-load range should be re-divided, and the re-division node is set according to the actual situation. On the contrary, it indicates a smaller influence degree, and then the corresponding preset sub-load range is merged, so as to realize the accuracy of the division of the adjusted sub-load range for different modules, lay a foundation for the subsequent construction of the control parameter prediction module, and improve the control efficiency and control accuracy of the desulfurized wastewater zero-discharge system.

[0029] In some embodiments of the present application, the operation influence evaluation value includes: The historical fluctuation characteristics include the historical fluctuation degree, historical fluctuation magnitude, and historical fluctuation rate at several historical acquisition nodes in the corresponding historical unit load change curve segment; Compare the historical fluctuation characteristics with the preset fluctuation characteristics, obtain the difference of the historical fluctuation characteristics and quantify it to obtain the first magnitude, the second magnitude, and the third magnitude; Generate a historical fluctuation evaluation value according to the first magnitude, the second magnitude, and the third magnitude; Compare the historical fluctuation evaluation values of multiple historical control parameters in each preset sub-load range of each module with the preset fluctuation evaluation value threshold, screen out the number of historical control parameters with historical fluctuation evaluation values greater than the preset fluctuation evaluation value threshold according to the comparison result, and calculate the historical fluctuation evaluation value difference; Generate the evaluation value of the impact of the corresponding preset sub-load interval on the operation of the corresponding module according to the number of historical control parameters screened out and the difference in the corresponding historical fluctuation evaluation values. The calculation formula of the evaluation value of the operation impact is as follows: ; where Y is the evaluation value of the operation impact, y1 is the conversion coefficient of the operation impact, n1 is the number of historical control parameters screened out, n2 is the total number of historical control parameters of the corresponding module, is the difference in the historical fluctuation evaluation value of the i-th historical control parameter screened out.

[0030] In this embodiment, the first quantity value, the second quantity value, and the third quantity value respectively refer to the degree difference, the quantity value difference, and the volatility difference between the historical fluctuation degree, the historical fluctuation quantity value, and the historical volatility in the historical fluctuation characteristics and the standard fluctuation degree, the standard fluctuation quantity value, and the standard volatility in the standard fluctuation characteristics. When the degree difference, the quantity value difference, and the volatility difference are larger, the corresponding first quantity value, second quantity value, and third quantity value are larger, that is, the historical fluctuation evaluation value of the corresponding historical control parameter is larger, and vice versa.

[0031] In this embodiment, according to the historical fluctuation evaluation value of the historical control parameters in each preset sub-load interval, generate the influence degree of the corresponding preset sub-load interval on the control parameters in the corresponding module, laying a foundation for subsequent determination of the standard acquisition number and construction of the control parameter prediction model, improving the control accuracy and control efficiency of the desulfurized wastewater zero-discharge system under the full-load state, meeting the wastewater discharge standard and reducing environmental pollution.

[0032] In some embodiments of the present application, construct the first control parameter group, the second control parameter group, and the third control parameter group of the unit at full load, and use them as training data for neural network training to obtain the corresponding control parameter prediction model, including: Generate the operation impact ratio of the corresponding adjustment sub-load interval according to the load change quantity value and the operation impact evaluation value corresponding to each adjustment sub-load interval in each module; Preset the first preset operation impact ratio threshold, the second preset operation impact ratio threshold, and the third preset operation impact ratio threshold in advance; When the operation impact ratio is less than the first preset operation impact ratio threshold, set the standard acquisition number of the corresponding adjustment sub-load interval to the fourth preset acquisition number; When the operation impact ratio is between the first preset operation impact ratio threshold and the second preset operation impact ratio threshold, set the standard acquisition number of the corresponding adjustment sub-load interval to the third preset acquisition number; When the operating influence ratio is between the second preset operating influence ratio threshold and the third preset operating influence ratio threshold, the standard acquisition number corresponding to the adjusted sub-load interval is set as the second preset acquisition number; When the operating influence ratio is greater than the third preset operating influence ratio threshold, the standard acquisition number corresponding to the adjusted sub-load interval is set as the first preset acquisition number; According to the standard acquisition number, data acquisition and water quality characteristic acquisition are carried out on each historical control parameter change curve at several historical acquisition nodes in the historical load change curve segment mapped by the adjusted sub-load interval, so as to obtain several first control parameters of the low-temperature flue gas concentration module, several second control parameters of the heavy metal treatment module, several third control parameters of the high-temperature bypass flue gas evaporation module, and the waste water quality characteristics; Among them, there is a mapping relationship between the several first control parameters, several second control parameters, and several third control parameters and the corresponding adjusted sub-load interval of the corresponding module as well as the waste water quality characteristics; Take several adjusted sub-loads and waste water quality characteristics of each module as training input data, and take several first control parameters, several second control parameters, and several third control parameters of each module with a mapping relationship with several adjusted sub-loads as training output data; Perform neural network training according to the training input data and the training output data to obtain a control parameter prediction model.

[0033] In this embodiment, the operating influence ratio = the value of the load change amount / the operating influence evaluation value. When the operating influence ratio is smaller, it means that the value of the load change amount is smaller or the operating influence evaluation value is larger, that is, a larger change in the control parameter caused by a smaller load change, and the standard acquisition number corresponding to the adjusted sub-load interval set is more, and vice versa.

[0034] In this embodiment, the first preset operating influence ratio threshold < the second preset operating influence ratio threshold < the third preset operating influence ratio threshold, and the first preset acquisition number < the second preset acquisition number < the third preset acquisition number < the fourth preset acquisition number.

[0035] In this embodiment, the waste water quality characteristics include heavy metal content, suspended solid concentration, salt content, etc.

[0036] In this embodiment, by determining the standard acquisition number of each adjusted sub-load interval, determining several first control parameters, second control parameters, and third control parameters, and constructing a control parameter prediction model, accurate prediction of the control parameters of the desulfurized waste water zero-discharge system under the full-load state is realized, the control efficiency is improved, the waste water discharge requirements are met, and environmental pollution is reduced.

[0037] In some embodiments of the present application, generating a desulfurized wastewater treatment instruction according to a predictive control parameter includes: Obtaining the real-time load value and real-time wastewater water quality characteristics of the current module, and determining the adjustment sub-load interval where the real-time load value is located; Based on the control parameter prediction model, determining the adjustment sub-load interval where the real-time load value of the current module is located and the predictive control parameter of the real-time wastewater water quality characteristics; Generating a desulfurized wastewater treatment instruction for the corresponding module according to the predictive control parameter of the current module, and controlling the current module according to the desulfurized wastewater treatment instruction.

[0038] In some embodiments of the present application, generating a real-time operation evaluation value for the corresponding module according to real-time monitoring parameters includes: Presetting an operation inspection period for the current module, and setting a number of monitoring time nodes based on the preset time interval and the time length of the operation inspection duration; Obtaining the real-time monitoring parameters of the current module according to the monitoring time nodes, where the real-time monitoring parameters include the actual control parameter of the current module, the actual wastewater water quality characteristics, and the actual change characteristics of the actual wastewater water quality characteristics; Comparing the actual wastewater water quality characteristics with the standard wastewater water quality characteristics of the corresponding module to obtain the actual wastewater water quality characteristic difference, and comparing the actual change characteristics with the standard change characteristics of the standard wastewater water quality characteristics of the corresponding module to obtain the actual change characteristic difference; Generating an initial operation evaluation value according to the actual wastewater water quality characteristic difference, and generating a compensation coefficient according to the actual change characteristic difference; Generating a real-time operation evaluation value for the current module according to the initial operation evaluation value and the corresponding compensation coefficient.

[0039] In this embodiment, the operation inspection period is set according to the average historical treatment duration of the adjustment sub-load interval where the real-time load value of the current module is located, the operation inspection duration refers to 1 / 2 of the average historical treatment duration, and the operation inspection duration is used to test the application effect of the predictive control parameter of the current module.

[0040] In this embodiment, the actual change characteristics include the actual change trend, actual change amount value, and actual change rate. The standard change characteristics for evaluating whether each wastewater water quality characteristic meets the wastewater discharge standard of the current module are such that when the actual change characteristic difference is smaller, the corresponding compensation coefficient is larger, and vice versa. The value range of the compensation coefficient is (0.8, 1.2).

[0041] In this embodiment, the greater the actual wastewater water quality characteristic difference, the smaller the corresponding initial operation evaluation value. When the initial operation evaluation value is smaller and the compensation coefficient is smaller, the corresponding real-time operation evaluation value is smaller, and vice versa.

[0042] In some embodiments of the present application, screening the control parameters to be optimized for the current module and generating an optimization instruction includes: Presetting the threshold value of the operation evaluation value for the operation inspection period of the current module; If the real-time operation evaluation value is greater than the operation evaluation value threshold, the current module does not need to be optimized; If the real-time operation evaluation value is less than the operation evaluation value threshold, set the wastewater quality characteristics with the actual wastewater quality characteristic difference greater than the preset water quality characteristic difference threshold or the actual change characteristic difference of the actual wastewater quality characteristics greater than the preset change characteristic difference threshold as the water quality characteristics to be optimized, and calculate the corresponding difference characteristics to be optimized; Determine the historical control parameters associated with the water quality characteristics to be optimized based on the historical wastewater treatment log, and construct a control parameter reference library for the water quality characteristics to be optimized; The control parameter reference library includes the preset difference characteristics corresponding to the water quality characteristics to be optimized, and each preset difference characteristic is associated with a preset regulation amount value of the corresponding associated historical control parameter; Determine the control parameters to be optimized for the current module according to the historical control parameters associated with the water quality characteristics to be optimized, and determine the regulation amount value of the control parameters to be optimized based on the control parameter reference library; Generate an optimization instruction according to the control parameters to be optimized and the regulation amount value, and perform iterative training on the control parameter prediction model according to the adjusted control parameters.

[0043] In this embodiment, input the difference characteristics to be optimized and the control parameters to be optimized into the control parameter reference library corresponding to the water quality characteristics to be optimized, obtain the similarity between the corresponding difference characteristics to be optimized and the preset difference characteristics, and set the preset regulation amount value of the control parameters to be optimized under the preset difference characteristic with the maximum similarity as the regulation amount value.

[0044] In some embodiments of the present application, as Figure 2 shown, it also includes a full-load desulfurized wastewater zero-discharge method: Step S201: Construct the first control parameter group, the second control parameter group, and the third control parameter group for the full load of the unit, and use them as training data for neural network training to obtain the corresponding control parameter prediction model; Step S202: Obtain the real-time load value and input it into the control parameter prediction model to obtain a number of predicted control parameters, and generate a desulfurized wastewater treatment instruction according to the predicted control parameters; Step S203: Obtain the real-time monitoring parameters of the wastewater based on the preset monitoring time nodes, and generate the real-time operation evaluation value of the corresponding module according to the real-time monitoring parameters; Step S204: Determine whether optimization is required according to the real-time operation evaluation value. If so, screen out the control parameters to be optimized for the current module and generate an optimization instruction.

[0045] The above are only the preferred embodiments of the present application. It should be noted that for those of ordinary skill in the art, several improvements and substitutions can be made without departing from the technical principle of the present application, and these improvements and substitutions should also be regarded as the protection scope of the present application.

Claims

1. A full-load desulfurized wastewater zero-discharge system, characterized in that, Including: A collection module, which is used to construct a first control parameter group, a second control parameter group, and a third control parameter group for the full load of the unit, and use them as training data to train a neural network to obtain a corresponding control parameter prediction model; A generation module, which is used to obtain the real-time load value and input it into the control parameter prediction model to obtain a number of predicted control parameters, and generate a desulfurized wastewater treatment instruction according to the predicted control parameters; An evaluation module, which is used to obtain the real-time monitoring parameters of the wastewater based on the preset monitoring time nodes, and generate a real-time operation evaluation value for the corresponding module according to the real-time monitoring parameters; An optimization module, which is used to judge whether optimization is needed according to the real-time operation evaluation value. If so, screen out the control parameters to be optimized in the current module and generate an optimization instruction.

2. The full-load desulfurized wastewater zero-discharge system according to claim 1, wherein The first control parameter group includes a number of first control parameters of the low-temperature flue gas concentration module, and the number of first control parameters includes the flue gas temperature, flue gas flow rate, wastewater flow rate, and concentrated liquid concentration of the low-temperature flue gas concentration module; The second control parameter group includes a number of second control parameters of the heavy metal treatment module, and the number of second control parameters includes the reaction pH value, the chemical agent dosing parameter of the calcium carbonate slurry, the reaction temperature, the stirring intensity, and the reaction time; The third control parameter group includes a number of third control parameters of the high-temperature bypass flue gas evaporation module, and the number of third control parameters includes the evaporation temperature, the wastewater atomization particle size, the flue gas moisture content, and the atomization effect of the high-temperature bypass flue gas evaporation module.

3. The full-load desulfurized wastewater zero-discharge system according to claim 2, wherein Before constructing the first control parameter group, the second control parameter group, and the third control parameter group for the full load of the unit, it further includes: Obtain the historical wastewater treatment log, screen out the preferred wastewater treatment log according to the historical wastewater treatment results, and use the historical treatment duration of each module in each preferred wastewater treatment log as the time reference line; Set the historical collection nodes of the corresponding modules based on the preset time interval and the historical treatment duration of each module; Collect the historical unit load and the historical control parameters of the corresponding module according to the historical collection nodes, and construct the historical unit load change curve and the historical control parameter change curve corresponding to each module; Pre-divide the full load of the unit into several preset sub-load intervals on average; Mark the historical unit load change curve corresponding to each module according to the boundary load values of each preset sub-load interval to obtain several historical unit load change curve segments, and map each historical unit load change curve segment to the corresponding preset sub-load interval one by one; Analyze the historical control parameter change curves at the same historical collection nodes of each historical unit load change curve segment to obtain the historical fluctuation characteristics of each historical control parameter at several historical collection nodes of each historical unit load change curve segment; Generate a historical fluctuation evaluation value of the corresponding historical control parameter in the corresponding historical unit load change curve segment according to the historical fluctuation characteristics, and generate an operation influence evaluation value of the preset sub-load interval mapped by the corresponding historical load change curve segment for the corresponding module according to the historical fluctuation evaluation value of each historical control parameter; Generate the evaluation values of the operation impacts of several preset sub-load intervals in sequence for each module; Preset the first preset operation impact evaluation value interval, the second preset operation impact evaluation value interval, and the third preset operation impact evaluation value interval in advance; Judge whether it is necessary to adjust the corresponding preset sub-load interval according to the relationship between the operation impact evaluation value and the preset operation impact evaluation value interval; When the operation impact evaluation value is within the first preset operation impact evaluation value interval, perform a similarity analysis on the historical change characteristics of each historical control parameter in the corresponding preset sub-load interval and the historical change characteristics of the corresponding historical control parameters in the adjacent preset sub-load interval to obtain the similarity; Merge the corresponding preset sub-load interval into the adjacent preset sub-load interval with the maximum similarity; When the operation impact evaluation value is within the second preset operation impact evaluation value interval, do not adjust the preset sub-load interval; When the operation impact evaluation value is within the third preset operation impact evaluation value interval, re-divide the corresponding preset sub-load interval; Generate several adjusted sub-load intervals for each module according to the adjustment result.

4. The full-load desulfurized wastewater zero-discharge system according to claim 3, characterized in that, The operation impact evaluation value includes: The historical fluctuation characteristics include the historical fluctuation degree, historical fluctuation magnitude, and historical fluctuation rate of several historical acquisition nodes in the corresponding historical unit load change curve segment; Compare the historical fluctuation characteristics with the preset fluctuation characteristics to obtain the difference of the historical fluctuation characteristics and quantify it to obtain the first value, the second value, and the third value; Generate a historical fluctuation evaluation value according to the first value, the second value, and the third value; Compare the historical fluctuation evaluation values of multiple historical control parameters in each preset sub-load interval of each module with the preset fluctuation evaluation value threshold, screen out the number of historical control parameters whose historical fluctuation evaluation values are greater than the preset fluctuation evaluation value threshold according to the comparison result, and calculate the historical fluctuation evaluation value difference; Generate the operation impact evaluation value of the corresponding preset sub-load interval for the corresponding module according to the number of the screened historical control parameters and the corresponding historical fluctuation evaluation value difference; The calculation formula of the operation impact evaluation value is: ； Among them, Y is the evaluation value of operation impact, y1 is the conversion coefficient of operation impact, n1 is the number of historical control parameters selected, and n2 is the total number of historical control parameters of the corresponding module. is the difference in the historical fluctuation evaluation value of the i-th historical control parameter selected.

5. The full-load desulfurized wastewater zero-discharge system according to claim 4, characterized in that, Construct the first control parameter group, the second control parameter group, and the third control parameter group of the full load of the unit, and use them as training data to perform neural network training to obtain the corresponding control parameter prediction model, including: Generate the operation impact ratio of the corresponding adjusted sub-load interval according to the load change magnitude and the operation impact evaluation value corresponding to each adjusted sub-load interval in each module; Preset the first preset operation impact ratio threshold, the second preset operation impact ratio threshold, and the third preset operation impact ratio threshold in advance; When the operation impact ratio is less than the first preset operation impact ratio threshold, set the standard acquisition number of the corresponding adjusted sub-load interval to the fourth preset acquisition number; When the operation impact ratio is between the first preset operation impact ratio threshold and the second preset operation impact ratio threshold, set the standard acquisition number of the corresponding adjusted sub-load interval to the third preset acquisition number; When the running influence ratio is between the second preset running influence ratio threshold and the third preset running influence ratio threshold, set the standard number of acquisitions for the corresponding adjusted sub-load interval to the second preset number of acquisitions; When the running influence ratio is greater than the third preset running influence ratio threshold, set the standard number of acquisitions for the corresponding adjusted sub-load interval to the first preset number of acquisitions; According to the standard number of acquisitions, collect data for each historical control parameter curve at several historical acquisition nodes in the historical load change curve segment mapped by the adjusted sub-load interval, and collect water quality characteristics, to obtain several first control parameters of the low-temperature flue gas concentration module, several second control parameters of the heavy metal treatment module, several third control parameters of the high-temperature bypass flue gas evaporation module, and the wastewater water quality characteristics; Among them, there is a mapping relationship between the several first control parameters, several second control parameters, and several third control parameters and the corresponding adjusted sub-load intervals of the modules and the wastewater water quality characteristics; Use the several adjusted sub-loads and wastewater water quality characteristics of each module as training input data, and use the several first control parameters, several second control parameters, and several third control parameters of each module with a mapping relationship to the several adjusted sub-loads as training output data; Perform neural network training based on the training input data and training output data to obtain a control parameter prediction model.

6. The full-load desulfurized wastewater zero-discharge system according to claim 5, wherein, Generate a desulfurized wastewater treatment instruction according to the predicted control parameter, including: Obtain the real-time load value and real-time wastewater water quality characteristics of the current module, and determine the adjusted sub-load interval where the real-time load value is located; Based on the control parameter prediction model, determine the predicted control parameters for the adjusted sub-load interval where the real-time load value of the current module is located and the real-time wastewater water quality characteristics; Generate a desulfurized wastewater treatment instruction for the corresponding module according to the predicted control parameter of the current module, and control the current module according to the desulfurized wastewater treatment instruction.

7. The full-load desulfurized wastewater zero-discharge system according to claim 6, characterized in that, Generate a real-time operation evaluation value for the corresponding module according to the real-time monitoring parameter, including: Preset the operation inspection period of the current module in advance, and set several monitoring time nodes based on the preset time interval and the time length of the operation inspection duration; Obtain the real-time monitoring parameters of the current module according to the monitoring time nodes, and the real-time monitoring parameters include the actual control parameter of the current module, the actual wastewater water quality characteristics, and the actual change characteristics of the actual wastewater water quality characteristics; Compare the actual wastewater water quality characteristics with the standard wastewater water quality characteristics of the corresponding module to obtain the actual wastewater water quality characteristic difference, and compare the actual change characteristics with the standard change characteristics of the standard wastewater water quality characteristics of the corresponding module to obtain the actual change characteristic difference; Generate an initial operation evaluation value according to the actual wastewater water quality characteristic difference, and generate a compensation coefficient according to the actual change characteristic difference; Generate a real-time operation evaluation value for the current module according to the initial operation evaluation value and the corresponding compensation coefficient.

8. The full-load desulfurized waste water zero-discharge system according to claim 7, characterized in that Screen out the control parameters to be optimized for the current module and generate an optimization instruction, including: Preset the operation evaluation value threshold for the operation inspection period of the current module in advance; If the real-time operation evaluation value is greater than the operation evaluation value threshold, the current module does not need to be optimized; If the real-time operation evaluation value is less than the operation evaluation value threshold, the wastewater quality characteristics with the actual wastewater quality characteristic difference greater than the preset water quality characteristic difference threshold or the actual change characteristic difference of the actual wastewater quality characteristics greater than the preset change characteristic difference threshold are set as the wastewater quality characteristics to be optimized, and the corresponding difference characteristics to be optimized are calculated; Based on the historical wastewater treatment log, determine the historical control parameters associated with the wastewater quality characteristics to be optimized, and construct a control parameter reference library for the wastewater quality characteristics to be optimized; The control parameter reference library includes the preset difference characteristics corresponding to the wastewater quality characteristics to be optimized, and each preset difference characteristic is associated with a preset regulation quantity value corresponding to the associated historical control parameters; Determine the control parameters to be optimized for the current module according to the historical control parameters associated with the wastewater quality characteristics to be optimized, and determine the regulation quantity value of the control parameters to be optimized based on the control parameter reference library; Generate an optimization instruction according to the control parameters to be optimized and the regulation quantity value, and iteratively train the control parameter prediction model according to the regulated control parameters.

9. A full-load desulfurized wastewater zero-discharge method, characterized in that, Including: Construct the first control parameter group, the second control parameter group and the third control parameter group for the full load of the unit, and use them as training data for neural network training to obtain the corresponding control parameter prediction model; Obtain the real-time load value and input it into the control parameter prediction model to obtain a number of predicted control parameters, and generate a desulfurized wastewater treatment instruction according to the predicted control parameters; Obtain the real-time monitoring parameters of the wastewater based on the preset monitoring time nodes, and generate the real-time operation evaluation value of the corresponding module according to the real-time monitoring parameters; Judge whether optimization is needed according to the real-time operation evaluation value. If so, screen out the control parameters to be optimized for the current module and generate an optimization instruction.

Images