CN114967780B - Desulfurization system pH value control method and system based on predictive control - Google Patents
Desulfurization system pH value control method and system based on predictive control Download PDFInfo
- Publication number
- CN114967780B CN114967780B CN202210672456.7A CN202210672456A CN114967780B CN 114967780 B CN114967780 B CN 114967780B CN 202210672456 A CN202210672456 A CN 202210672456A CN 114967780 B CN114967780 B CN 114967780B
- Authority
- CN
- China
- Prior art keywords
- value
- deltau
- control
- limestone slurry
- supply valve
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000006477 desulfuration reaction Methods 0.000 title claims abstract description 55
- 230000023556 desulfurization Effects 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title claims abstract description 32
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims abstract description 21
- 239000003546 flue gas Substances 0.000 claims abstract description 21
- 239000002002 slurry Substances 0.000 claims description 44
- 235000019738 Limestone Nutrition 0.000 claims description 39
- 239000006028 limestone Substances 0.000 claims description 39
- 238000012937 correction Methods 0.000 claims description 24
- 238000013528 artificial neural network Methods 0.000 claims description 11
- 238000005457 optimization Methods 0.000 claims description 11
- 238000005096 rolling process Methods 0.000 claims description 11
- 230000003009 desulfurizing effect Effects 0.000 claims description 10
- 239000000779 smoke Substances 0.000 claims description 9
- 238000013135 deep learning Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 7
- 230000001276 controlling effect Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000002401 inhibitory effect Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 235000008733 Citrus aurantifolia Nutrition 0.000 description 1
- 235000011941 Tilia x europaea Nutrition 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000004571 lime Substances 0.000 description 1
- 238000005312 nonlinear dynamic Methods 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D21/00—Control of chemical or physico-chemical variables, e.g. pH value
- G05D21/02—Control of chemical or physico-chemical variables, e.g. pH value characterised by the use of electric means
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Treating Waste Gases (AREA)
Abstract
The invention relates to the technical field of wet flue gas desulfurization, in particular to a pH value control method and system of a desulfurization system based on predictive control. By the method, the tracking accuracy of the pH value of the desulfurization system can be ensured when the unit is operated in a large-scale variable load mode, fluctuation of the pH value is reduced, and safe, economical and stable operation of the wet flue gas desulfurization system of the thermal power unit is realized.
Description
Technical Field
The invention relates to the technical field of wet flue gas desulfurization, in particular to a desulfurization system pH value control method and system based on predictive control.
Background
During the fourteen-five planning period, the construction of a clean, low-carbon, safe and efficient energy system and the construction of a novel power system taking new energy as a main body are development trends of the energy power field in a long period of time in the future. In the novel power system, the grid connection of new energy sources requires that the thermal power generating unit should have higher operation flexibility. The flue gas desulfurization system is one of important systems in a thermal power generating unit, and has the main tasks of desulfurizing flue gas generated in a boiler, reducing pollutant emission and keeping various operation parameters in a reasonable range. Wherein, the pH value of the slurry is one of the most important operation parameters in the desulfurization system, and accurate control of the pH value is beneficial to ensuring safe, economical and stable operation of the unit. At present, when the unit stably operates under rated load, the control effect of the pH value control system is good, but when the unit operates under variable load in a large range, the nonlinearity and the large hysteresis characteristic of the desulfurization system are obvious, so that the pH value cannot be accurately controlled.
Therefore, there is a need for a desulfurization system pH control method and system based on predictive control to improve the control accuracy of the desulfurization system pH, so as to adapt to the large-scale variable load operation of the unit, thereby ensuring the safe, economical and stable operation of the unit.
Disclosure of Invention
The invention provides a method and a system for controlling the pH value of a desulfurization system based on predictive control, which are used for solving the problem that the pH value cannot be accurately controlled due to obvious nonlinearity and large hysteresis characteristics of the desulfurization system when a unit is operated in a large-range variable load mode.
In order to achieve the above object, a first aspect of the present invention provides a method for controlling pH of a desulfurization system based on predictive control, the method comprising:
acquiring a pH value and a pH value set value, and calculating an expected track of the pH value;
according to the influence of the unit load on the pH value, a data driving deep learning method is adopted to construct a nonlinear prediction model of the pH value controlled object;
performing feedback correction based on a prediction output of the nonlinear prediction model;
and performing rolling optimization based on the expected track of the pH value and the predicted output of the system.
Preferably, the desired trajectory of the pH value is:
wherein N is p To predict the time domain, y r (k+i) is a desired trajectory based on the k time, and α is a softening coefficient (0.ltoreq.α)Less than or equal to 1), r (k) is a pH value set value at the moment k, and y (k) is a system output at the moment k.
Preferably, the nonlinear prediction model is:
y m (k)＝f(E(k-1),c(k-1),q(k-1),ρ(k-1),u(k-1),y(k-1))；
wherein y is m The predicted value of the pH value is that y is the pH value, u is the opening of a limestone slurry supply valve, E is the unit load, and c is the flue gas SO at the inlet of the desulfurizing tower 2 The concentration q is the smoke amount, the concentration of rho limestone slurry and f (·) represent the nonlinear mapping relation of the neural network.
Preferably, the feedback correction is:
y p (k+i)＝y m (k+i)+h(y(k)-y m (k))(i＝1,2,…,N p )；
wherein y is p And h is a feedback correction coefficient for the prediction output of the system.
Preferably, the scrolling is optimized as:
wherein N is c To control the time domain, q i For the error weighting coefficient, r j To control the weighting coefficient, deltau is the opening increment of the limestone slurry supply valve, u max 、u min Respectively the maximum value and the minimum value of the opening degree of the limestone slurry supply valve, delta u max 、Δu min Respectively, the maximum value and the minimum value of the opening increment of the limestone slurry supply valve, and DeltaU (k) = [ Deltau (k), deltau (k+1), …, deltau (k+N) c -1)] T Is the optimal control sequence to be solved.
In a second aspect, the present invention provides a desulfurization system pH control system based on predictive control, the system comprising:
the pH value expected track module is used for acquiring a pH value and a pH value set value and calculating an expected track of the pH value;
the nonlinear prediction model module is used for constructing a nonlinear prediction model of the pH controlled object by adopting a data driving deep learning method according to the influence of the unit load on the pH value;
the feedback correction module is used for carrying out feedback correction based on the prediction output of the nonlinear prediction model;
and the rolling optimization module is used for conducting rolling optimization based on the expected track of the pH value and the predicted output of the system.
Preferably, the desired trajectory of the pH value is:
wherein N is p To predict the time domain, y r (k+i) is a desired trajectory based on the time k, α is a softening coefficient (0.ltoreq.α.ltoreq.1), r (k) is a pH value set value at the time k, and y (k) is a system output at the time k.
Preferably, the nonlinear prediction model is:
y m (k)＝f(E(k-1),c(k-1),q(k-1),ρ(k-1),u(k-1),y(k-1))；
wherein y is m The predicted value of the pH value is that y is the pH value, u is the opening of a limestone slurry supply valve, E is the unit load, and c is the flue gas SO at the inlet of the desulfurizing tower 2 The concentration q is the smoke amount, the concentration of rho limestone slurry and f (·) represent the nonlinear mapping relation of the neural network.
Preferably, the feedback correction is:
y p (k+i)＝y m (k+i)+h(y(k)-y m (k))(i＝1,2,…,N p )；
wherein y is p And h is a feedback correction coefficient for the prediction output of the system.
Preferably, the scrolling is optimized as:
wherein N is c To control the time domain, q i For the error weighting coefficient, r j For controlling the weighting factor, deltau is the opening of the limestone slurry feed valveIncrement u max 、u min Respectively the maximum value and the minimum value of the opening degree of the limestone slurry supply valve, delta u max 、Δu min Respectively, the maximum value and the minimum value of the opening increment of the limestone slurry supply valve, and DeltaU (k) = [ Deltau (k), deltau (k+1), …, deltau (k+N) c -1)] T Is the optimal control sequence to be solved.
According to the technical scheme, the pH value control method and the pH value control system for the desulfurization system based on predictive control are used for inhibiting disturbance through the pH value control method for the desulfurization system based on predictive control, so that the pH value of the wet flue gas desulfurization system is controlled in real time, the pH value of the desulfurization system is ensured to be stabilized at a set value when the load of a unit is changed in a large range, the tracking precision of the pH value of the desulfurization system is ensured when the unit is operated in a large range in a variable load mode, and fluctuation of the pH value is reduced, so that safe, economical and stable operation of the wet flue gas desulfurization system of the thermal power unit is realized.
Meanwhile, aiming at the nonlinear dynamic characteristics of the thermal power generating unit desulfurization system in variable load operation, a nonlinear prediction model of the pH value controlled object is constructed by adopting a data driving deep learning method, so that the control precision is effectively improved.
Drawings
FIG. 1 is a flow chart of a method of controlling pH of a desulfurization system based on predictive control;
FIG. 2 is a schematic diagram of the architecture of a desulfurization system pH control system based on predictive control;
FIG. 3 is a block diagram of a system for controlling pH of a desulfurization system based on predictive control;
FIG. 4 is a diagram of a network structure of a pH predicted GRU.
Detailed Description
The following describes the detailed implementation of the embodiments of the present invention with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the invention, are not intended to limit the invention.
The first aspect of the present invention provides a method for controlling a pH value of a desulfurization system based on predictive control, as shown in fig. 1 to 4, the method for controlling a pH value of a desulfurization system based on predictive control comprising the steps of:
s1, acquiring a pH value and a pH value set value, and calculating an expected track of the pH value;
specifically, the desired trace of the pH value in step S1 is:
wherein N is p To predict the time domain, y r (k+i) is a desired trajectory based on the time k, α is a softening coefficient (0.ltoreq.α.ltoreq.1), r (k) is a pH set value at the time k, and y (k) is a system output at the time k, that is, a pH value.
S2, constructing a nonlinear prediction model of the pH value controlled object by adopting a data driving deep learning method according to the influence of the unit load on the pH value;
specifically, the nonlinear prediction model in step S2 is:
y m (k)＝f(E(k-1),c(k-1),q(k-1),ρ(k-1),u(k-1),y(k-1))；
wherein y is m The predicted value of the pH value is that y is the pH value, u is the opening of a limestone slurry supply valve, E is the unit load, and c is the flue gas SO at the inlet of the desulfurizing tower 2 The concentration q is the smoke amount, the concentration of rho limestone slurry and f (·) represent the nonlinear mapping relation of the neural network.
S3, performing feedback correction based on the prediction output of the nonlinear prediction model;
specifically, the feedback correction in step S3 is:
y p (k+i)＝y m (k+i)+h(y(k)-y m (k))(i＝1,2,…,N p )；
wherein y is p And h is a feedback correction coefficient for the prediction output of the system.
S4, performing rolling optimization on the expected track based on the pH value and the system prediction output.
Specifically, the scrolling in step S4 is optimized as:
wherein N is c To control the time domain, q i For the error weighting coefficient, r j To control the weighting coefficient, deltau is the opening increment of the limestone slurry supply valve, u max 、u min Respectively the maximum value and the minimum value of the opening degree of the limestone slurry supply valve, delta u max 、Δu min Respectively, the maximum value and the minimum value of the opening increment of the limestone slurry supply valve, and DeltaU (k) = [ Deltau (k), deltau (k+1), …, deltau (k+N) c -1)] T The method is an optimal control sequence which needs to be solved, namely an optimal solution.
According to the technical scheme, the pH value control method and the pH value control system for the desulfurization system based on predictive control are used for inhibiting disturbance through the pH value control method for the desulfurization system based on predictive control, so that the pH value of the wet flue gas desulfurization system is controlled in real time, the pH value of the desulfurization system is ensured to be stabilized at a set value when the load of a unit is changed in a large range, the tracking precision of the pH value of the desulfurization system is ensured when the unit is operated in a large range in a variable load mode, and fluctuation of the pH value is reduced, so that safe, economical and stable operation of the wet flue gas desulfurization system of the thermal power unit is realized.
The second aspect of the present invention also provides a desulfurization system pH control system based on predictive control, as shown in fig. 2 to 4, the system comprising:
the pH value expected track module is used for acquiring a pH value and a pH value set value and calculating an expected track of the pH value;
the nonlinear prediction model module is used for constructing a nonlinear prediction model of the pH controlled object by adopting a data driving deep learning method according to the influence of the unit load on the pH value;
the feedback correction module is used for carrying out feedback correction based on the prediction output of the nonlinear prediction model;
and the rolling optimization module is used for conducting rolling optimization based on the expected track of the pH value and the predicted output of the system.
In the embodiment of the invention, the core of the pH value control system of the desulfurization system based on predictive control is an MPC controller.
According to a preferred embodiment of the invention, the desired trajectory of the pH value is:
wherein N is p To predict the time domain, y r (k+i) is a desired trajectory based on the time k, α is a softening coefficient (0.ltoreq.α.ltoreq.1), r (k) is a pH set value at the time k, and y (k) is a system output at the time k, that is, a pH value.
According to a preferred embodiment of the present invention, the nonlinear predictive model is:
y m (k)＝f(E(k-1),c(k-1),q(k-1),ρ(k-1),u(k-1),y(k-1))；
wherein y is m The predicted value of the pH value is that y is the pH value, u is the opening of a limestone slurry supply valve, E is the unit load, and c is the flue gas SO at the inlet of the desulfurizing tower 2 The concentration q is the smoke amount, the concentration of rho limestone slurry and f (·) represent the nonlinear mapping relation of the neural network.
According to a preferred embodiment of the invention, the feedback correction is:
y p (k+i)＝y m (k+i)+h(y(k)-y m (k))(i＝1,2,…,N p )；
wherein y is p And h is a feedback correction coefficient for the prediction output of the system.
According to a preferred embodiment of the invention, the scrolling is optimised:
wherein N is c To control the time domain, q i For the error weighting coefficient, r j To control the weighting coefficient, deltau is the opening increment of the limestone slurry supply valve, u max 、u min Respectively the maximum value and the minimum value of the opening degree of the limestone slurry supply valve, delta u max 、Δu min Lime respectivelyDan Jiangye the maximum and minimum valve opening increments, Δu (k) = [ Δu (k), Δu (k+1), …, Δu (k+n) c -1)] T The method is an optimal control sequence which needs to be solved, namely an optimal solution.
By utilizing the method and the system for controlling the pH value of the desulfurization system based on predictive control, which are provided by the scheme of the invention, the tracking precision of the pH value of the desulfurization system can be ensured when the unit is operated in a large-scale variable load mode, and the fluctuation of the pH value is reduced, so that the safe, economical and stable operation of the wet flue gas desulfurization system of the thermal power unit is realized. Specific examples of the method for controlling the pH of the desulfurization system by predictive control will be described below.
Example 1
As shown in fig. 1-4, at time k, a pH value and a pH value set value are obtained, and an expected trajectory of the pH value is calculated, where the expected trajectory of the pH value is:
wherein N is p To predict the time domain, y r (k+i) is a desired trajectory based on the time k, α is a softening coefficient (0.ltoreq.α.ltoreq.1), r (k) is a pH set value at the time k, and y (k) is a system output at the time k, that is, a pH value.
According to a large amount of historical operation data of a thermal power generating unit desulfurization system, a gate control cyclic neural network (GRU) is adopted to establish a nonlinear prediction model of the pH value control system. According to the influence of the unit load on the pH value, when the unit lifts the load, the change of the smoke amount entering the desulfurizing tower is larger, so that the pH value of the desulfurizing tower slurry is influenced, and therefore the unit load and the smoke amount are added as disturbance variables when a predictive model of a pH value controlled object is constructed. In the desulfurization process, the pH value of the slurry is generally regulated by regulating the limestone slurry supply flow, and the limestone slurry supply flow is combined with flue gas SO at the inlet of the desulfurization tower through the opening of a limestone slurry supply valve 2 The concentration and the limestone slurry concentration are adjusted. Selecting a unit load E (k-1) at the last moment and inlet flue gas SO 2 Concentration c (k-1), flue gas flow q (k-1), limestone slurry density ρ (k-1), slurry supply valve opening, slurryThe pH value u (k-1) y (k-1) is taken as the input of the neural network, the slurry pH value y (k) at the current moment is taken as the output of the neural network, and the network structure is shown in figure 4. And selecting 70% of the running data as training set data, using the rest as test set data, normalizing the data set, and training a neural network by using the normalized data to obtain a nonlinear prediction model of the pH value control system. Meanwhile, root Mean Square Error (RMSE) is selected as a model evaluation index, and the smaller the RMSE is, the better the built model performance is. The nonlinear prediction model is as follows:
y m (k)＝f(E(k-1),c(k-1),q(k-1),ρ(k-1),u(k-1),y(k-1))
wherein y is m The predicted value of the pH value is that y is the pH value, u is the opening of a limestone slurry supply valve, E is the unit load, and c is the flue gas SO at the inlet of the desulfurizing tower 2 The concentration q is the smoke amount, ρ is the limestone slurry concentration, and f (·) represents the nonlinear mapping relation of the GRU neural network.
Based on the nonlinear predictive model, calculating a predicted value y of the pH value at the current moment m (k) Performing multi-step prediction to obtain a multi-step predicted value y of the pH value m (k+i) and then performing feedback correction through the system output, calculating a system predicted output, said feedback correction being:
y p (k+i)＝y m (k+i)+h(y(k)-y m (k))(i＝1,2,…,N p )
wherein y is p And h is a feedback correction coefficient for the prediction output of the system.
In order to minimize the error between the system output pH and the pH setpoint while avoiding dramatic incremental changes in control during control, an optimized objective function is selected as follows. Performing rolling optimization based on the expected trajectory of the pH value and a system prediction output, wherein the rolling optimization is as follows:
s.t.
wherein N is c To control the time domain, q i For the error weighting coefficient, r j To control the weighting coefficient, deltau is the opening increment of the limestone slurry supply valve, u max 、u min Respectively the maximum value and the minimum value of the opening degree of the limestone slurry supply valve, delta u max 、Δu min Respectively, the maximum value and the minimum value of the opening increment of the limestone slurry supply valve, and DeltaU (k) = [ Deltau (k), deltau (k+1), …, deltau (k+N) c -1)] T The method is an optimal control sequence which needs to be solved, namely an optimal solution.
The control variables of the system are calculated as follows:
u(k)＝u(k-1)+Δu(k)
the control variable is acted on the desulfurization system of the thermal power generating unit, so that the pH value of the desulfurization system can quickly track the pH value set value.
And repeating the steps at the time k+1.
The pH value control method of the desulfurization system based on predictive control can enable the desulfurization system of the thermal power unit to be well adapted to large-range variable load operation of the unit, reduce fluctuation of operation parameters of the desulfurization system and ensure safe, economical and stable operation of the unit.
The pH value control method and system for the desulfurization system based on predictive control can ensure the tracking accuracy of the pH value of the desulfurization system during large-scale variable load operation of the unit, reduce the fluctuation of the pH value and realize the safe, economical and stable operation of the wet flue gas desulfurization system of the thermal power unit.
The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited thereto. Within the scope of the technical idea of the invention, a plurality of simple variants can be made to the technical proposal of the invention, and in order to avoid unnecessary repetition, the invention does not need to be additionally described for various possible combinations. Such simple variations and combinations are likewise to be regarded as being within the scope of the present disclosure.
Claims (2)
1. The desulfurization system pH value control method based on predictive control is characterized by comprising the following steps:
acquiring a pH value and a pH value set value, and calculating an expected track of the pH value;
according to the influence of the unit load on the pH value, a data driving deep learning method is adopted to construct a nonlinear prediction model of the pH value controlled object;
performing feedback correction based on a prediction output of the nonlinear prediction model;
performing rolling optimization based on the expected track of the pH value and the predicted output of the system;
the desired trace of the pH is:
wherein N is p To predict the time domain, y r (k+i) is an expected track based on the moment k, alpha is a softening coefficient (alpha is more than or equal to 0 and less than or equal to 1), r (k) is a pH value set value at the moment k, and y (k) is a system output at the moment k;
the nonlinear prediction model is as follows:
y m (k)＝f(E(k-1),c(k-1),q(k-1),ρ(k-1),u(k-1),y(k-1))；
wherein y is m The predicted value of the pH value is that y is the pH value, u is the opening of a limestone slurry supply valve, E is the unit load, and c is the flue gas SO at the inlet of the desulfurizing tower 2 The concentration q is the smoke amount, the concentration of rho limestone slurry and f (·) represent the nonlinear mapping relation of the neural network;
the feedback correction is:
y p (k+i)＝y m (k+i)+h(y(k)-y m (k)) (i＝1,2,…,N p )；
wherein y is p H is a feedback correction coefficient for system prediction output;
the scrolling is optimized as:
wherein N is c To control the time domain, q i For the error weighting coefficient, r j To control the weighting coefficient, deltau is the opening increment of the limestone slurry supply valve, u max 、u min Respectively the maximum value and the minimum value of the opening degree of the limestone slurry supply valve, delta u max 、Δu min Respectively, the maximum value and the minimum value of the opening increment of the limestone slurry supply valve, and DeltaU (k) = [ Deltau (k), deltau (k+1), …, deltau (k+N) c -1)] T Is the optimal control sequence to be solved.
2. The utility model provides a desulfurization system pH value control system based on predictive control which characterized in that, desulfurization system pH value control system based on predictive control includes:
the pH value expected track module is used for acquiring a pH value and a pH value set value and calculating an expected track of the pH value;
the nonlinear prediction model module is used for constructing a nonlinear prediction model of the pH controlled object by adopting a data driving deep learning method according to the influence of the unit load on the pH value;
the feedback correction module is used for carrying out feedback correction based on the prediction output of the nonlinear prediction model;
the rolling optimization module is used for conducting rolling optimization based on the expected track of the pH value and the predicted output of the system;
the desired trace of the pH is:
wherein N is p To predict the time domain, y r (k+i) is an expected track based on the moment k, alpha is a softening coefficient (alpha is more than or equal to 0 and less than or equal to 1), r (k) is a pH value set value at the moment k, and y (k) is a system output at the moment k;
the nonlinear prediction model is as follows:
y m (k)＝f(E(k-1),c(k-1),q(k-1),ρ(k-1),u(k-1),y(k-1))；
wherein y is m The predicted value of the pH value is that y is the pH value, u is the opening of a limestone slurry supply valve, E is the unit load, and c is the flue gas SO at the inlet of the desulfurizing tower 2 The concentration q is the smoke amount, the concentration of rho limestone slurry and f (·) represent the nonlinear mapping relation of the neural network;
the feedback correction is:
y p (k+i)＝y m (k+i)+h(y(k)-y m (k)) (i＝1,2,…,N p )；
wherein y is p H is a feedback correction coefficient for system prediction output;
the scrolling is optimized as:
wherein N is c To control the time domain, q i For the error weighting coefficient, r j To control the weighting coefficient, deltau is the opening increment of the limestone slurry supply valve, u max 、u min Respectively the maximum value and the minimum value of the opening degree of the limestone slurry supply valve, delta u max 、Δu min Respectively, the maximum value and the minimum value of the opening increment of the limestone slurry supply valve, and DeltaU (k) = [ Deltau (k), deltau (k+1), …, deltau (k+N) c -1)] T Is the optimal control sequence to be solved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210672456.7A CN114967780B (en) | 2022-06-14 | 2022-06-14 | Desulfurization system pH value control method and system based on predictive control |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210672456.7A CN114967780B (en) | 2022-06-14 | 2022-06-14 | Desulfurization system pH value control method and system based on predictive control |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114967780A CN114967780A (en) | 2022-08-30 |
| CN114967780B true CN114967780B (en) | 2024-01-12 |
Family
ID=82963500
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210672456.7A Active CN114967780B (en) | 2022-06-14 | 2022-06-14 | Desulfurization system pH value control method and system based on predictive control |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114967780B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07116455A (en) * | 1993-10-22 | 1995-05-09 | Kawasaki Heavy Ind Ltd | Wet exhaust gas desulfurization device and its control method |
| CN1605959A (en) * | 2004-11-04 | 2005-04-13 | 浙江大学 | Nonlinear model predictive control method based on support vector machine for groove type reactor |
| CN103955751A (en) * | 2014-04-11 | 2014-07-30 | 国家电网公司 | Method for predicting multi-element nonlinear limestone-gypsum wet desulphurization efficiency |
| CN107168055A (en) * | 2017-05-15 | 2017-09-15 | 东南大学 | A kind of ammonia process of desulfurization optimal control method based on umlti-variable finite elements |
| CN108845501A (en) * | 2018-09-11 | 2018-11-20 | 东北大学 | A kind of blast-melted quality adaptation optimal control method based on Lazy learning |
| CN111045326A (en) * | 2019-10-22 | 2020-04-21 | 杭州安脉盛智能技术有限公司 | Tobacco shred drying process moisture prediction control method and system based on recurrent neural network |
| CN112044243A (en) * | 2020-08-05 | 2020-12-08 | 华能国际电力股份有限公司上安电厂 | Automatic control system and method for emission indexes of thermal power generating unit desulfurization device |
| CN112742187A (en) * | 2020-12-10 | 2021-05-04 | 山西漳山发电有限责任公司 | Method and device for controlling pH value in desulfurization system |
| CN113900379A (en) * | 2021-11-02 | 2022-01-07 | 南京工业大学 | Neural network-based predictive control algorithm |
| CN114035430A (en) * | 2021-09-30 | 2022-02-11 | 湖北华电襄阳发电有限公司 | Desulfurization system pH value control system and method based on predictive control |
-
2022
- 2022-06-14 CN CN202210672456.7A patent/CN114967780B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07116455A (en) * | 1993-10-22 | 1995-05-09 | Kawasaki Heavy Ind Ltd | Wet exhaust gas desulfurization device and its control method |
| CN1605959A (en) * | 2004-11-04 | 2005-04-13 | 浙江大学 | Nonlinear model predictive control method based on support vector machine for groove type reactor |
| CN103955751A (en) * | 2014-04-11 | 2014-07-30 | 国家电网公司 | Method for predicting multi-element nonlinear limestone-gypsum wet desulphurization efficiency |
| CN107168055A (en) * | 2017-05-15 | 2017-09-15 | 东南大学 | A kind of ammonia process of desulfurization optimal control method based on umlti-variable finite elements |
| CN108845501A (en) * | 2018-09-11 | 2018-11-20 | 东北大学 | A kind of blast-melted quality adaptation optimal control method based on Lazy learning |
| CN111045326A (en) * | 2019-10-22 | 2020-04-21 | 杭州安脉盛智能技术有限公司 | Tobacco shred drying process moisture prediction control method and system based on recurrent neural network |
| CN112044243A (en) * | 2020-08-05 | 2020-12-08 | 华能国际电力股份有限公司上安电厂 | Automatic control system and method for emission indexes of thermal power generating unit desulfurization device |
| CN112742187A (en) * | 2020-12-10 | 2021-05-04 | 山西漳山发电有限责任公司 | Method and device for controlling pH value in desulfurization system |
| CN114035430A (en) * | 2021-09-30 | 2022-02-11 | 湖北华电襄阳发电有限公司 | Desulfurization system pH value control system and method based on predictive control |
| CN113900379A (en) * | 2021-11-02 | 2022-01-07 | 南京工业大学 | Neural network-based predictive control algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114967780A (en) | 2022-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109062053B (en) | Denitration ammonia injection control method based on multivariate correction | |
| CN105629738B (en) | SCR flue gas denitrification systems control method and equipment | |
| CN104826492B (en) | Improvement method for selective catalytic reduction flue gas denitrification and ammonia injection control system | |
| CN112580250A (en) | Thermal power generating unit denitration system based on deep learning and optimization control method | |
| US9747544B2 (en) | Method and system for wastewater treatment based on dissolved oxygen control by fuzzy neural network | |
| CN112661259A (en) | Self-adaptive control method and system for aeration process | |
| CN109634315B (en) | Method and device for controlling pH value of slurry | |
| CN111562744B (en) | Boiler combustion implicit generalized predictive control method based on PSO algorithm | |
| CN104696952B (en) | Fluidized bed boiler air input capacity control method based on model online identification | |
| CN112742187A (en) | Method and device for controlling pH value in desulfurization system | |
| CN114336673B (en) | Wind-storage combined power station primary frequency modulation control strategy based on model predictive control | |
| CN111552175A (en) | Overall optimization scheduling and rapid variable load control method for supercritical coal-fired power plant-carbon capture system after chemical adsorption combustion | |
| CN111598308B (en) | Method for solving combination optimization of slurry circulating pump based on regression and double PSO algorithm | |
| CN107561944A (en) | A kind of denitrating system adaptive prediction control method based on Laguerre model | |
| CN114967780B (en) | Desulfurization system pH value control method and system based on predictive control | |
| Han et al. | Fuzzy super-twisting sliding mode control for municipal wastewater nitrification process | |
| CN111450694B (en) | Desulfurization system industrial controller based on multi-objective optimization and control method | |
| CN114053865A (en) | Generalized predictive control method suitable for SCR denitration control system of coal-fired boiler | |
| Chi et al. | Fuzzy dynamic matrix predictive control of ammonia injection quantityin SCR denitration systems | |
| CN113741182A (en) | Sewage treatment process control method based on generalized value iteration | |
| Guo et al. | Application of DMC algorithm on pH control of WFGD system | |
| Dong et al. | Optimal Control of pH Value in Wet Flue Gas Desulfurization Process Based on Model Predictive Control | |
| Zhong et al. | Control strategies for the air supply system in PEMFC | |
| Nascu et al. | Improving Activated Sludge Wastewater Treatment Process Efficiency Using Predictive Control | |
| Wang et al. | Design and Application of DHP Controller Based on Online Leaky Echo State Network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |