Seawater desulfurization water channel flow control method, storage medium and electronic equipment

Abstract

The invention discloses a seawater desulfurization water channel flow control method, a storage medium and electronic equipment. The control method comprises the steps that the PH value of a water outlet of an aeration tank, the boiler load, the original flue gas sulfur dioxide concentration and water quality parameters of open sea seawater are obtained; constructing a PH spatial distribution matrix according to the PH value and a preset number of PH sensors; the PH value, the boiler load, the original flue gas sulfur dioxide concentration and the water quality parameter serve as input quantities, variance minimization of the PH space distribution matrix serves as a target optimization function, and the orifice opening degree is output; and controlling the opening degree of the orifice of a water outlet of a lower tower water drainage pipeline arranged in the aeration tank according to the opening degree of the orifice. By implementing the device, the water flow of the water outlet of the lower tower water drainage pipeline can be adjusted, so that the PH value of each water outlet is uniform, the resistance of each water channel is hardly influenced, the power consumption of a circulating water pump is reduced, the occupied area is small, and the investment cost is reduced.

Description

Technical Field

[0001] This invention relates to the field of seawater desulfurization technology, and in particular to a method for controlling the flow rate of a seawater desulfurization channel, a storage medium, and an electronic device. Background Technology

[0002] In seawater desulfurization projects, sulfur dioxide in the flue gas inside the absorption tower reacts chemically with alkaline absorbent components in the seawater to generate acidic seawater. The acidic seawater is discharged from the absorption tower into the aeration tank, where it mixes with a large amount of seawater that has not participated in the desulfurization reaction, and a large amount of air is blown in to restore the pH value and dissolved oxygen content of the seawater to the normal levels that allow for discharge.

[0003] However, the seawater pH value at the aeration tank outlet is prone to uneven mixing and pH measurement deviation due to the following reasons: 1. Changes in unit load or coal sulfur content lead to changes in the water volume at the upper tower of the absorption tower, which in turn causes changes in the water flow at each outlet of the lower tower water drainage pipe, resulting in uneven seawater distribution in each flow channel of the aeration tank, ultimately causing uneven mixing of the seawater pH value at the aeration tank outlet; 2. The orifice diameter of the lower tower water drainage pipe outlet is selected according to the design conditions, and the orifice size is a fixed value that cannot be adjusted according to changes in external conditions to control the water flow. Changes in the external sea level cause the back pressure at the lower tower water drainage pipe outlet to deviate from the design value, resulting in changes in the water flow at each outlet, which in turn causes uneven seawater distribution in each flow channel of the aeration tank, ultimately causing uneven mixing of the seawater pH value at the aeration tank outlet; 3. The seawater pH measurement point at the aeration tank outlet is usually a single point measurement. Uneven mixing of the aeration tank effluent will make the single point measurement unrepresentative and have a large deviation.

[0004] Currently, the existing methods to eliminate pH measurement deviations include: 1. Increasing the number of pH sampling points to reduce the influence of local conditions on the measurement results. However, this method can only obtain the average value of the samples in terms of numerical values ​​and cannot fundamentally solve the problem of uneven mixing of drainage and local pH exceeding the standard. 2. Taking turbulence measures to improve the uniformity of drainage mixing. However, due to the large geometric size of the drainage pool and the large drainage volume, and considering the flow resistance problem, there are currently no effective turbulence measures.

[0005] Therefore, there is an urgent need to provide a method for controlling the flow rate of seawater desulfurization channels to solve the technical problems of uneven mixing and measurement deviation of seawater pH value at the aeration tank outlet. Summary of the Invention

[0006] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method for controlling the flow of seawater desulfurization channels, a storage medium, and electronic equipment to solve the technical problems of uneven mixing and measurement deviation of seawater pH value at the aeration tank outlet.

[0007] The technical solution of the present invention provides a method for controlling the flow rate of a seawater desulfurization channel, comprising:

[0008] Obtain the pH value, boiler load, sulfur dioxide concentration in raw flue gas, and water quality parameters of the offshore seawater at the aeration tank outlet;

[0009] A pH spatial distribution matrix is ​​constructed based on the pH value and the preset number of pH sensors;

[0010] Using the pH value, boiler load, sulfur dioxide concentration in the raw flue gas, and water quality parameters as inputs, and minimizing the variance of the pH spatial distribution matrix as the objective optimization function, the orifice opening is output.

[0011] The orifice opening of the lower tower water drainage pipe outlet in the aeration tank is controlled according to the orifice opening.

[0012] In one of the alternative technical solutions, the step of taking the pH value, the boiler load, the sulfur dioxide concentration in the raw flue gas, and the water quality parameters as input quantities, minimizing the variance of the pH spatial distribution matrix as the objective optimization function, and outputting the orifice opening, further includes:

[0013] The orifice opening is optimized using a particle swarm optimization-long short-term memory network algorithm to obtain the target orifice opening.

[0014] In one of the alternative technical solutions, the step of using a particle swarm optimization-long short-term memory network algorithm to optimize the orifice opening and obtain the target orifice opening includes:

[0015] Each particle is set as the orifice opening of a set of the lower tower water drainage pipe outlets;

[0016] The fitness level is calculated based on the pH value;

[0017] Within a preset time period, obtain the historical optimal positions of all the particles;

[0018] The global optimal position of all particles is determined based on the fitness and the historical best position.

[0019] Based on the historical best position, the global best position, and the preset particle swarm optimization parameters, the direction of particle velocity change is determined. The particle swarm optimization parameters include inertia weight and learning factor.

[0020] The optimal position of the target is determined based on the direction of the particle velocity change and the global optimal position.

[0021] The orifice opening corresponding to the optimal target position is obtained as the target orifice opening.

[0022] In one alternative technical solution, the step of determining the global optimal position of all particles based on the fitness and the historical best position further includes:

[0023] Calculate the average swarm fitness of all the particles mentioned;

[0024] Obtain the historical parameter adjustment sequence of the particle swarm optimization parameters;

[0025] The boiler load, the sulfur dioxide concentration in the original flue gas, the water quality parameters, the current iteration number, the average fitness of the particle swarm, the global optimal position, and the historical parameter adjustment sequence are input into a preset long short-term memory network, and the inertia weight adjustment amount and the learning factor adjustment amount are output.

[0026] The inertia weight is calculated based on the historical inertia weight of the previous moment and the inertia weight adjustment amount;

[0027] The learning factor is calculated based on the historical learning factor from the previous moment and the adjustment amount of the learning factor.

[0028] The step of determining the direction of particle velocity change based on the historical best position, the global best position, and preset particle swarm optimization parameters includes:

[0029] The direction of particle velocity change is calculated based on the historical best position, the global best position, the target inertia weight, and the target learning factor.

[0030] In one of the alternative technical solutions, calculating the fitness based on the pH value includes:

[0031] The fitness is calculated using the following formula:

[0032]

[0033] Where f(t) is the fitness at time t, N is the number of PH sensors, and x j Let t be the pH value at time t.

[0034] In one of the alternative technical solutions,

[0035] The step of determining the global optimal position of all particles based on the fitness and the historical optimal position includes:

[0036] The global optimal position is calculated using the following formula:

[0037]

[0038] Among them, G_best t This is the globally optimal position; This refers to the historical optimal position; The fitness value is the fitness value corresponding to the historical best position.

[0039] In one of the alternative technical solutions, determining the direction of particle velocity change based on the historical optimal position, the global optimal position, and preset particle swarm optimization parameters includes:

[0040] The direction of the particle velocity change is calculated using the following formula:

[0041]

[0042] in, The direction of the particle velocity change is given by ω, where ω is the inertial weight, c1 and c2 are the learning factors, and r1 and r2 are constants. Let t be the orifice opening at time t.

[0043] In one optional technical solution, calculating the inertial weight based on the historical inertial weight of the previous moment and the inertial weight adjustment amount includes:

[0044] The inertia weight is calculated using the following formula:

[0045] ω(t+1)=ω(t)+Δω(t)

[0046] Wherein, ω(t+1) is the inertial weight at time t+1, ω(t) is the historical inertial weight at time t, and Δω(t) is the adjustment amount of the inertial weight at time t;

[0047] The step of calculating the learning factor based on the historical learning factor from the previous moment and the adjustment amount of the learning factor includes:

[0048] The learning factor is calculated using the following formula:

[0049]

[0050] Wherein, c1(t+1) and c2(t+1) are the learning factors at time t+1, c1(t) and c2(t) are the historical learning factors at time t, and Δc1(t) and Δc2(t) are the adjustment amounts of the learning factors at time t.

[0051] The present invention also provides a computer-readable storage medium that stores computer instructions, which, when executed by a computer, are used to perform all steps of the seawater desulfurization channel flow control method described above.

[0052] The present invention also provides an electronic device, comprising:

[0053] At least one processor; and,

[0054] A memory communicatively connected to the at least one processor; wherein,

[0055] The memory stores instructions that can be executed by the at least one processor, which enables the at least one processor to perform the seawater desulfurization channel flow control method as described above.

[0056] The above technical solution has the following beneficial effects: By acquiring the pH value, boiler load, sulfur dioxide concentration in the raw flue gas, and water quality parameters of the offshore seawater at the aeration tank outlet, a pH spatial distribution matrix is ​​constructed based on the pH value and the preset number of pH sensors. The pH value, boiler load, sulfur dioxide concentration in the raw flue gas, and water quality parameters are used as input quantities, and the objective optimization function is to minimize the variance of the pH spatial distribution matrix. The orifice opening is output, and the orifice opening of the lower tower water drainage pipe outlet in the aeration tank is controlled according to the orifice opening, thereby adjusting the water flow rate at the lower tower water drainage pipe outlet, making the pH value of each water outlet uniform, having almost no impact on the flow channel resistance, reducing the power consumption of the circulating water pump, requiring less space, and reducing investment costs. Attached Figure Description

[0057] The disclosure of this invention will become more readily understood by referring to the accompanying drawings. It should be understood that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of this invention. In the drawings:

[0058] Figure 1 This is a schematic diagram of the structure of a seawater desulfurization system provided in an embodiment of the present invention;

[0059] Figure 2 for Figure 1 Cross-sectional view;

[0060] Figure 3 This is a schematic diagram of the drainage pipe for the water below the absorption tower.

[0061] Figure 4a for Figure 3 One type of AA sectional view;

[0062] Figure 4b for Figure 3 Another AA section view;

[0063] Figure 4c for Figure 3 Another AA sectional view;

[0064] Figure 5 A flowchart illustrating a seawater desulfurization channel flow control method according to an embodiment of the present invention;

[0065] Figure 6 A flowchart of a seawater desulfurization channel flow control method provided in another embodiment of the present invention;

[0066] Figure 7 This is a schematic diagram of the hardware structure of an electronic device for flow control in a seawater desulfurization channel, provided as an embodiment of the present invention. Detailed Implementation

[0067] The specific embodiments of the present invention will be further described below with reference to the accompanying drawings.

[0068] It is readily understood that, based on the technical solution of this invention, various structural and implementation methods can be interchanged by those skilled in the art without altering the essential spirit of the invention. Therefore, the following detailed embodiments and accompanying drawings are merely illustrative examples of the technical solution of this invention and should not be considered as the entirety of the invention or as limitations or restrictions on the technical solution of the invention.

[0069] The directional terms such as up, down, left, right, front, back, front, back, top, and bottom mentioned or possibly used in this specification are defined relative to the structures shown in the accompanying drawings. They are relative concepts and may therefore vary depending on their location and usage. Therefore, these or other directional terms should not be interpreted as restrictive.

[0070] The seawater desulfurization channel flow control method provided by this invention is mainly applied in seawater desulfurization systems to control the orifice opening of the outlet of the lower tower water drainage pipe in the aeration tank, thereby adjusting the outflow rate and making the pH value of each drainage pipe outlet uniform.

[0071] like Figures 1-4c As shown, the seawater desulfurization system mainly includes an inlet tank 10, an aeration tank 20, and a drainage tank 30. The aeration tank 20 is generally a rectangular pool and is the main site for the seawater desulfurization oxidation reaction. The medium in the aeration tank is seawater. The seawater return head used in the seawater desulfurization system is higher than sea level, and it returns to the sea by gravity. The aeration tank 20 is equipped with a lower tower water drainage pipe 21, which guides the seawater (which has absorbed SO2) from the bottom of the absorption tower to the pipes in the aeration tank 20. These pipes are responsible for discharging the used seawater from the bottom of the absorption tower for subsequent treatment and restoration.

[0072] The drainage pool 30 is typically a rectangular pool. Seawater, after desulfurization and oxidation in the aeration pool 20, flows into the drainage pool 30, which is connected to the sea. The seawater return pressure head used in the seawater desulfurization system is higher than sea level, allowing it to return to the sea by gravity. The desulfurized seawater sequentially passes through the inlet pool 10, aeration pool 20, and drainage pool 30, flowing out through drainage pool 30 and re-entering the sea. The flow direction of the seawater is as follows: Figure 1 The arrow direction is shown.

[0073] The variation in the water volume at the upper tower of the absorption tower leads to variations in the water flow rate at each outlet of the lower tower water drainage pipe, resulting in uneven seawater distribution within the aeration tank's flow channels. This ultimately causes uneven pH mixing of the seawater at the aeration tank's drainage outlet. Therefore, an adjusting device 212 needs to be installed on the lower tower water drainage pipe 21 to regulate the opening of the outlet holes 211. Figures 3-4c As shown, a sealing element 213 is also provided between the regulating device 212 and the lower tower water drainage pipe 21. The sealing element 213 is used to seal the gap between the regulating device 212 and the lower tower water drainage pipe 21 to prevent water leakage. The regulating device 212 uses the following seawater desulfurization channel flow control method to adjust the opening of the outlet hole 211 of the drainage pipe.

[0074] The specific structure of the adjusting device 212 can adopt existing technology, such as... Figures 4a-4c As shown, the adjusting device 212 can be a square slot-shaped structure ( Figure 4a As shown), arc-shaped groove structure ( Figure 4b As shown) and the arc-shaped structure of the flat opening ( Figure 4c As shown in the figure, the specific structure and working principle of the regulating device 211 will not be described in detail here.

[0075] like Figure 5 As shown, an embodiment of the present invention provides a method for controlling the flow rate of a seawater desulfurization channel, comprising:

[0076] Step S501: Obtain the pH value, boiler load, sulfur dioxide concentration in the raw flue gas, and water quality parameters of the offshore seawater at the aeration tank outlet;

[0077] Step S502: Construct a pH spatial distribution matrix based on the pH value and the preset number of pH sensors;

[0078] Step S503: Using the pH value, the boiler load, the sulfur dioxide concentration in the raw flue gas, and the water quality parameters as input quantities, and minimizing the variance of the pH spatial distribution matrix as the objective optimization function, output the orifice opening.

[0079] Step S504: Control the orifice opening of the outlet of the lower tower water drainage pipe set in the aeration tank according to the orifice opening.

[0080] Specifically, firstly, the controller executes step S501 to acquire the pH value of the aeration tank outlet, boiler load, sulfur dioxide concentration in the raw flue gas, and water quality parameters of the offshore seawater, including seawater pH value, seawater temperature, and alkalinity. Among these, for example... Figure 1As shown, the pH value of the aeration tank outlet is obtained in real time by a pH value detector 31 installed in the drainage tank 30;

[0081] Then, step S502 is executed to construct the following PH spatial distribution matrix:

[0082] X = [x1, x2, ..., x N ] T

[0083] Where x1, x2, ..., x N The values ​​measured by each pH sensor are given, where N is the number of pH sensors.

[0084] Next, step S503 is executed, taking pH value, boiler load, raw flue gas sulfur dioxide concentration, and water quality parameters as inputs, and minimizing the variance of the pH spatial distribution matrix as the objective optimization function, outputting the orifice opening. The objective optimization function is as follows:

[0085]

[0086] Finally, step S504 is executed, which controls the orifice opening of the lower tower water drainage pipe outlet according to the orifice opening, thereby adjusting the water flow rate of the lower tower water drainage pipe outlet and making the pH value of each water outlet uniform.

[0087] The seawater desulfurization channel flow control method provided in this embodiment obtains the pH value, boiler load, sulfur dioxide concentration in the raw flue gas, and water quality parameters of the aeration tank outlet, as well as the boiler load, the sulfur dioxide concentration in the raw flue gas, and the water quality parameters of the open sea. Based on the pH value and the preset number of pH sensors, a pH spatial distribution matrix is ​​constructed. The pH value, boiler load, sulfur dioxide concentration in the raw flue gas, and water quality parameters are used as input quantities. The objective optimization function is to minimize the variance of the pH spatial distribution matrix. The orifice opening is output, and the orifice opening of the lower tower water drainage pipe outlet set in the aeration tank is controlled according to the orifice opening. This adjusts the water flow at the lower tower water drainage pipe outlet, making the pH value of each channel outlet uniform, having almost no impact on the flow channel resistance, reducing the power consumption of the circulating water pump, requiring less space, and reducing investment costs.

[0088] In one embodiment, to further improve the accuracy of the orifice opening, step S503 further includes:

[0089] The orifice opening is optimized using the Particle Swarm Optimization-Long Short-Term Memory (PSO-LSTM) algorithm to obtain the target orifice opening.

[0090] like Figure 6As shown, another embodiment of the present invention provides a method for controlling the flow rate of a seawater desulfurization channel, comprising:

[0091] Step S601: Obtain the pH value, boiler load, sulfur dioxide concentration in raw flue gas, and water quality parameters of the offshore seawater at the aeration tank outlet;

[0092] Step S602: Construct a pH spatial distribution matrix based on the pH value and the preset number of pH sensors;

[0093] Step S603: Using the pH value, the boiler load, the sulfur dioxide concentration in the raw flue gas, and the water quality parameters as input quantities, and minimizing the variance of the pH spatial distribution matrix as the objective optimization function, output the orifice opening.

[0094] Step S604: Set each particle as the orifice opening of a set of the lower tower water drainage pipe outlets;

[0095] Step S605: Calculate the fitness based on the pH value;

[0096] Step S606: Within a preset time period, obtain the historical optimal positions of all the particles;

[0097] Step S607: Determine the global optimal position of all particles based on the fitness and the historical optimal position;

[0098] Step S608: Determine the direction of particle velocity change based on the historical optimal position, the global optimal position, and the preset particle swarm optimization parameters, wherein the particle swarm optimization parameters include inertia weight and learning factor;

[0099] Step S609: Determine the optimal position of the target based on the direction of particle velocity change and the global optimal position;

[0100] Step S610: Obtain the orifice opening corresponding to the optimal target position as the target orifice opening;

[0101] Step S611: Control the orifice opening of the lower tower water drainage pipe outlet according to the target orifice opening.

[0102] Specifically, in step S604, the PSO parameters are first initialized, such as setting the inertia weight ω = 0.8, the learning factor c1 = c2 = 1.5, and r1, r2 ∈ [0, 1]. Then, each particle represents a combination K of the orifice openings of the lower tower water drainage pipe outlet. i =[k i1 ,k i2 ,…,k iM M represents the number of water outlets.

[0103] In step S605, the fitness is calculated using the following formula:

[0104]

[0105] Where f(t) is the fitness at time t, N is the number of PH sensors, and x j Let t be the pH value at time t.

[0106] In step S606, the historical best position of particle i is represented as P_best. i =[pbest i1 pbest i2 ,…,pbest iM ], This represents the historical best position of particle i at time t.

[0107] In step S607, the globally optimal position is represented as G_best=[gbest1,gbest2,…,gbest] M ], G_best t This represents the global optimal position of the particle swarm at time t, which is the position corresponding to the minimum fitness value among all the historical optimal positions of all particles at time t.

[0108]

[0109] Among them, G_best t The globally optimal position; This is the best historical position. The fitness value corresponds to the historical best position.

[0110] In step S608, the direction of the particle velocity change is calculated using the following formula:

[0111]

[0112] in, The direction of the particle velocity change is given by ω, where ω is the inertial weight, c1 and c2 are the learning factors, and r1 and r2 are constants. Let t be the orifice opening at time t.

[0113] The seawater desulfurization channel flow control method provided in this embodiment optimizes the orifice opening to obtain a target orifice opening. Based on the target orifice opening, the orifice opening of the lower tower water drainage pipe outlet is controlled, thereby more accurately adjusting the water flow at the lower tower water drainage pipe outlet. This ensures uniform pH values ​​at each channel outlet, further improving the accuracy of the orifice opening. It has almost no impact on the flow channel resistance, reduces the power consumption of the circulating water pump, requires less space, and lowers investment costs.

[0114] In one embodiment, in order to dynamically adjust the PSO parameter so that the PSO parameter can be adaptively adjusted to further improve the accuracy of the orifice opening, step S607 further includes:

[0115] Calculate the average swarm fitness of all the particles mentioned;

[0116] Obtain the historical parameter adjustment sequence of the particle swarm optimization parameters;

[0117] The boiler load, the sulfur dioxide concentration in the original flue gas, the water quality parameters, the current iteration number, the average fitness of the particle swarm, the global optimal position, and the historical parameter adjustment sequence are input into a preset long short-term memory network, and the inertia weight adjustment amount and the learning factor adjustment amount are output.

[0118] The inertia weight is calculated based on the historical inertia weight of the previous moment and the inertia weight adjustment amount;

[0119] The learning factor is calculated based on the historical learning factor from the previous moment and the adjustment amount of the learning factor.

[0120] Step S608 includes:

[0121] The direction of particle velocity change is calculated based on the historical best position, the global best position, the target inertia weight, and the target learning factor.

[0122] Specifically, an LSTM neural network is built to predict the optimal adjustment strategy for PSO parameters using historical iterative data. The LSTM input feature parameters (time series) include:

[0123] Boiler load Q,

[0124] sulfur dioxide concentration in raw flue gas

[0125] The water quality parameters of offshore seawater include pH value, temperature, salinity, and alkalinity (pH, T, S, A). T ),

[0126] Current iteration number t,

[0127] average fitness of particle swarm

[0128] Global optimal fitness f best (t),

[0129] Historical parameter adjustment sequence {ω(t-1),c1(t-1),c2(t-1)},

[0130] Limit k i∈[0, 100%], the overlimit particle is reset to the boundary.

[0131] The target output of the LSTM algorithm is:

[0132] Inertia weight adjustment Δω(t),

[0133] Learning factor adjustment amounts Δc1(t), Δc2(t),

[0134] The specific calculation process of the LSTM algorithm is as follows:

[0135] a) Obtain the input feature parameters of the LSTM algorithm in step S609;

[0136] b) Normalize the parameters using the min-max normalization method. The transformation function is as follows:

[0137] Y = (XX) min ) / (X max -X min )

[0138] c) The normalized data is split, with 80% used for training and 20% for testing.

[0139] d) Construct a 4-layer LSTM neural network. The number of neurons in the input layer matches the number of input feature parameters. The number of neurons in the output layer matches the number of output target parameters. The middle two layers are hidden layers, each with 256 neurons. Each neuron has a forget gate f. t Input gate i t Output gate o t and memory gate c t The basic technical rules for these doors are as follows:

[0140] f t =σ(W f ·[h t-1 ,x t ]+b f )

[0141] The input is: the hidden state h from the previous time step. t-1 and the current input x t .

[0142] i t =σ(W i ·[h t-1 ,x t ]+b i )

[0143]

[0144] h t =ot ·tanh(C t )

[0145]

[0146] Through the above calculation steps, the parameters of the LSTM neural network are determined, and the inertia weight adjustment amount Δω(t), learning factor adjustment amount Δc1(t), and Δc2(t) are output according to the latest input parameters.

[0147] The historical inertia weight ω(t) and the inertia weight adjustment Δω(t) are added together to obtain the inertia weight ω(t+1);

[0148] The historical learning factors c1(r) and c2(t) are added to the learning factor adjustment amounts Δc1(t) and Δc2(t) to obtain the learning factors c1(t+1) and c2(t+1).

[0149] In one embodiment, calculating the inertial weight based on the historical inertial weight of the previous moment and the inertial weight adjustment amount includes:

[0150] The inertia weight is calculated using the following formula:

[0151] ω(t+1)=ω(t)+Δω(t)

[0152] Wherein, ω(t+1) is the inertial weight at time t+1, ω(t) is the historical inertial weight at time t, and Δω(t) is the adjustment amount of the inertial weight at time t;

[0153] The step of calculating the learning factor based on the historical learning factor from the previous moment and the adjustment amount of the learning factor includes:

[0154] The learning factor is calculated using the following formula:

[0155]

[0156] Wherein, c1(t+1) and c2(t+1) are the learning factors at time t+1, c1(t) and c2(t) are the historical learning factors at time t, and Δc1(t) and Δc2(t) are the adjustment amounts of the learning factors at time t.

[0157] One embodiment of the present invention provides a computer-readable storage medium for storing computer instructions, which, when executed by a computer, are used to perform all steps of the seawater desulfurization channel flow control method as described in any of the above method embodiments.

[0158] like Figure 7As shown, a schematic diagram of the hardware structure of an electronic device for flow control in a seawater desulfurization channel according to an embodiment of the present invention is provided, including:

[0159] At least one processor 701; and,

[0160] A memory 702 is communicatively connected to at least one processor 701; wherein,

[0161] The memory 702 stores instructions that can be executed by at least one processor 701, which enables the at least one processor 701 to perform the seawater desulfurization channel flow control method as described in any of the above method embodiments.

[0162] Figure 7 Take the 701 processor as an example.

[0163] The electronic device is preferably a programmable logic controller (PLC).

[0164] The electronic device may also include an input device 703 and an output device 704.

[0165] The processor 701, memory 702, input device 703 and output device 704 can be connected by a bus or other means. The figure shows an example of connection by bus.

[0166] The memory 702, as a non-volatile computer-readable storage medium, can be used to obtain non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the seawater desulfurization channel flow control method in the embodiments of this application, for example, Figures 5-6 The method flow is shown. The processor 701 executes various functional applications and data processing by running non-volatile software programs, instructions, and modules acquired in the memory 702, thereby realizing the seawater desulfurization channel flow control method in the above embodiment.

[0167] The memory 702 may include a program acquisition area and a data acquisition area, wherein the program acquisition area may acquire an operating system and an application program required for at least one function; the data acquisition area may acquire data created based on the use of the seawater desulfurization channel flow control method, etc. Furthermore, the memory 702 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 702 may optionally include memory remotely located relative to the processor 701, and these remote memories may be connected via a network to the apparatus performing the seawater desulfurization channel flow control method. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0168] The input device 703 can receive user clicks and generate signal inputs related to user settings and function control of the seawater desulfurization channel flow control method. The output device 704 may include a display screen or other display device.

[0169] When the one or more modules are accessed in the memory 702 and are run by the one or more processors 701, the seawater desulfurization channel flow control method in any of the above method embodiments is executed.

[0170] The above-described product can perform the methods provided in the embodiments of this application, and has the corresponding functional modules and beneficial effects for performing the methods. Technical details not described in detail in this embodiment can be found in the methods provided in the embodiments of this application.

[0171] The above embodiments are only used to illustrate the technical solutions of the embodiments of the present invention, and are not intended to limit them. Although the embodiments of the present invention have been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for controlling the flow rate of a seawater desulfurization channel, characterized in that, include: Obtain the pH value, boiler load, sulfur dioxide concentration in raw flue gas, and water quality parameters of the offshore seawater at the aeration tank outlet; A pH spatial distribution matrix is ​​constructed based on the pH value and the preset number of pH sensors; Using the pH value, boiler load, sulfur dioxide concentration in the raw flue gas, and water quality parameters as inputs, and minimizing the variance of the pH spatial distribution matrix as the objective optimization function, the orifice opening is output. The orifice opening of the lower tower water drainage pipe outlet in the aeration tank is controlled according to the orifice opening.

2. The seawater desulfurization channel flow control method as described in claim 1, characterized in that, The process involves taking the pH value, boiler load, sulfur dioxide concentration in the raw flue gas, and water quality parameters as inputs, minimizing the variance of the pH spatial distribution matrix as the objective optimization function, and outputting the orifice opening. The process further includes: The orifice opening is optimized using a particle swarm optimization-long short-term memory network algorithm to obtain the target orifice opening.

3. The seawater desulfurization channel flow control method as described in claim 2, characterized in that, The process employs a particle swarm optimization-long short-term memory network algorithm to optimize the orifice opening and obtain the target orifice opening, including: Each particle is set as the orifice opening of a set of the lower tower water drainage pipe outlets; The fitness level is calculated based on the pH value; Within a preset time period, obtain the historical optimal positions of all the particles; The global optimal position of all particles is determined based on the fitness and the historical best position. Based on the historical best position, the global best position, and the preset particle swarm optimization parameters, the direction of particle velocity change is determined. The particle swarm optimization parameters include inertia weight and learning factor. The optimal position of the target is determined based on the direction of the particle velocity change and the global optimal position. The orifice opening corresponding to the optimal target position is obtained as the target orifice opening.

4. The seawater desulfurization channel flow control method as described in claim 3, characterized in that, The process of determining the global optimal position of all particles based on the fitness and the historical optimal position further includes: Calculate the average swarm fitness of all the particles mentioned; Obtain the historical parameter adjustment sequence of the particle swarm optimization parameters; The boiler load, the sulfur dioxide concentration in the original flue gas, the water quality parameters, the current iteration number, the average fitness of the particle swarm, the global optimal position, and the historical parameter adjustment sequence are input into a preset long short-term memory network, and the inertia weight adjustment amount and the learning factor adjustment amount are output. The inertia weight is calculated based on the historical inertia weight of the previous moment and the inertia weight adjustment amount; The learning factor is calculated based on the historical learning factor from the previous moment and the adjustment amount of the learning factor. The step of determining the direction of particle velocity change based on the historical best position, the global best position, and preset particle swarm optimization parameters includes: The direction of particle velocity change is calculated based on the historical best position, the global best position, the target inertia weight, and the target learning factor.

5. The seawater desulfurization channel flow control method as described in claim 3, characterized in that, The calculation of fitness based on the pH value includes: The fitness is calculated using the following formula: Where f(t) is the fitness at time t, N is the number of PH sensors, and x j Let t be the pH value at time t.

6. The seawater desulfurization channel flow control method as described in claim 5, characterized in that, The step of determining the global optimal position of all particles based on the fitness and the historical optimal position includes: The global optimal position is calculated using the following formula: Among them, G_best t This is the globally optimal position; This refers to the historical optimal position; The fitness value is the fitness value corresponding to the historical best position.

7. The seawater desulfurization channel flow control method as described in claim 6, characterized in that, The step of determining the direction of particle velocity change based on the historical best position, the global best position, and preset particle swarm optimization parameters includes: The direction of the particle velocity change is calculated using the following formula: in, The direction of the particle velocity change is given by ω, where ω is the inertial weight, c1 and c2 are the learning factors, and r1 and r2 are constants. Let t be the orifice opening at time t.

8. The seawater desulfurization channel flow control method as described in claim 4, characterized in that, The step of calculating the inertia weight based on the historical inertia weight of the previous moment and the inertia weight adjustment amount includes: The inertia weight is calculated using the following formula: ω(t+1)=ω(t)+Δω(t) Wherein, ω(t+1) is the inertial weight at time t+1, ω(t) is the historical inertial weight at time t, and Δω(t) is the adjustment amount of the inertial weight at time t; The step of calculating the learning factor based on the historical learning factor from the previous moment and the adjustment amount of the learning factor includes: The learning factor is calculated using the following formula: Wherein, c1(t+1) and c2(t+1) are the learning factors at time t+1, c1(t) and c2(t) are the historical learning factors at time t, and Δc1(t) and Δc2(t) are the adjustment amounts of the learning factors at time t.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a computer, are used to perform all steps of the seawater desulfurization channel flow control method as described in any one of claims 1-8.

10. An electronic device, characterized in that, include: At least one processor; as well as, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the seawater desulfurization channel flow control method as described in any one of claims 1-8.

Images