CN113341716A - Large-scale coal-fired power plant CO based on artificial intelligence2Optimal scheduling method for trapping system - Google Patents
Large-scale coal-fired power plant CO based on artificial intelligence2Optimal scheduling method for trapping system Download PDFInfo
- Publication number
- CN113341716A CN113341716A CN202110646133.6A CN202110646133A CN113341716A CN 113341716 A CN113341716 A CN 113341716A CN 202110646133 A CN202110646133 A CN 202110646133A CN 113341716 A CN113341716 A CN 113341716A
- Authority
- CN
- China
- Prior art keywords
- coal
- fired power
- power plant
- trapping
- max
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Feedback Control In General (AREA)
Abstract
The invention is suitable for the technical field of thermal process optimization scheduling, and provides an artificial intelligence-based large-scale coal-fired power plant CO2The optimal scheduling method of the trapping system comprises the following steps: large-scale coal-fired power plant CO is constructed by utilizing artificial intelligence methods such as Deep Belief Network (DBN)2Capturing system data to drive a steady-state model; considering CO of large coal-fired power plant2Generated energy and CO of gathering system unit2Emission and operation costs, and a target function capable of fully reflecting the economic indexes and the operation constraints of the whole system is constructed; according to the related information such as the electricity price and the carbon price, the efficient real-time solution of the objective function is realized by using a Bayesian Optimization (BO). The invention can give consideration to CO of coal-fired power station2The operation requirements of the capture system on economy, safety and environmental protection are met, an optimal scheduling mode which meets the lowest total operation cost is found, and CO of a large coal-fired power plant is realized2The trapping system is operated optimally.
Description
Technical Field
The invention belongs to the technical field of thermal process optimization scheduling, and particularly relates to artificial intelligence-based large-scale coal-fired power plant CO2And (4) a capture system optimization scheduling method.
Background
For CO, in order to realize the ambitious goal of' 2030C peak reaching and 2060C neutralization2The main greenhouse gases are collected and the CO of the industrial system is reduced2Emissions are currently of importanceThe technical means of (1). A coal-fired thermal power generating unit is CO in China2The most prominent source of emissions, national CO of 20182The total emission is about 9.48Gt, and 77% is from coal-fired thermal power units and other coal-fired processes. Due to the energy structure of China, the coal-fired thermal power generating unit is the main body of energy production at present and in a period of time in the future. Therefore, the coal-fired power generation unit is subjected to CO2Trapping is of great significance.
Currently, post-combustion CO based on chemical absorption by solvents such as ethanolamine2The capture is one of the most mature and commercially popularized technologies in all carbon capture technologies, and is successfully applied to more than ten tested devices in China. However, coal-fired thermal power generating unit and post-combustion CO2The trapping system has a strong coupling effect. On one hand, with the vigorous popularization of new energy technology, the coal-fired thermal power generating unit needs to carry out deep peak regulation to maintain the balance of supply and demand of a power grid, and the peak regulation process of the thermal power generating unit can cause corresponding change of flue gas parameters, which can affect the operation of a downstream carbon capture system; on the other hand, post-combustion CO2A large amount of heat is consumed for solvent regeneration of the trapping system, and a steam turbine of the thermal power generating unit is used for extracting and stripping a heat supply source, so that the generated energy of the thermal power generating unit is reduced, and the thermal efficiency of the unit is influenced. In conclusion, the coal-fired thermal power generating unit and the CO after combustion2The operation modes of the trapping system affect and conflict with each other. In order to maximize the benefit of the whole system, the operation requirement of the whole system needs to be comprehensively considered, and the CO of the coal-fired power plant is realized on the premise of ensuring the constraint condition of the system2And capturing the optimized scheduling of the whole system.
According to the current research situation at home and abroad, the CO is combusted for the coal-fired power station2The research on the optimal scheduling of the trapping system is relatively less, and the existing method does not consider the CO of the coal-fired power plant2The complex nature of the capture system makes it difficult to achieve optimal operation of the overall system. The invention utilizes artificial intelligence to establish CO of coal-fired power station2The optimal scheduling system of the trapping system overcomes the defects of a plurality of system operating variables, complex process characteristics and large optimal scheduling calculation amount, can solve the optimal given value of the main controlled variable of the system in the scheduling period on line in real time, and is suitable for industrial application.
Disclosure of Invention
The invention provides a large-scale coal-fired power plant CO based on artificial intelligence2An optimal scheduling method for a trapping system aims to solve the problems.
The invention is realized in such a way that the invention provides a large-scale coal-fired power plant CO based on artificial intelligence2The optimal scheduling method of the trapping system comprises the following steps:
selecting main steam pressure, an intermediate point enthalpy value, unit generating capacity, a capturing rate, reboiler temperature and CO2The output is large-scale coal-fired power station CO2Controlled variable y of trapping system(k)Selecting corresponding control variables u of coal supply amount, water supply flow, main steam valve opening, barren liquor flow and reboiler steam extraction flow(k)；
Step two, under the condition of open loop, simultaneously changing the coal feeding amount, the water feeding flow, the opening of a main steam valve, the flow of a barren solution and the steam extraction flow of a reboiler, and acquiring steady-state input and output data of the system under the operating conditions of different generated energy and capture rates;
thirdly, normalizing the input data and the output data, and constructing a CO (carbon dioxide) of the coal-fired power plant containing three layers of Restricted Boltzmann Mechanisms (RBMs) by utilizing functions of pretrainDBN (star) and trainnDBN (star) in MATLAB2The capture system DBN steady-state model,
wherein, the coal-fired power plant CO2The capture system DBN steady state model function is in the form: y (k) ═ fDBN(u(k))，y(k)Is the value of the controlled variable collected at the current moment, u(k)For the collected value of the control variable at the current moment, fDBN(. h) is a functional form of the DBN model;
step four, considering the generating capacity and CO of the unit2Emission, running cost and system constraint factors, and the construction can reflect CO of the coal-fired power plant2An objective function of the system operation cost and a weight coefficient corresponding to the objective function are collected,
wherein, the coal-fired power plant CO2The objective function of the operational cost of the capture system is
The coal-fired power plant CO2The objective function of the operation cost of the trapping system meets a series of constraints;
step five, setting an optimized time domain NiAnd a scheduling period Ts；
Setting related parameters of a BO solver, including an acquisition function, the number of initial evaluation points and cycle period parameters;
solving the performance index (1) by using a BO solver, and solving the minimum optimized control variable u meeting the performance index (1) under the system constraint condition(k)；
Step eight, utilizing CO of coal-fired power station2The collection system DBN steady-state model solves the input into the control variable u(k)Given value y of the optimal output variableref(k)；
Step nine, outputting the optimal set value yref(k)Realizing CO of coal-fired power plant2And trapping the optimized scheduling of the system, and then repeatedly executing the steps seven to nine in each optimized time domain.
Preferably, in the step one: command by fuel amount (u)1) Water supply flow (u)2) Main steam valve opening (u)3) Lean solution flow (u)4) And the flow rate of extracted steam (u)5) Is a main control variable u of the system(k)At the main steam pressure (y)1) Intermediate point enthalpy value (y)2) Turbine power (y)3) Collecting ratio (y)4) Reboiler temperature (y)5) And CO2Yield (y)6) Is the main controlled variable y of the system(k)To control the variable u(k)Taking the historical sampling value of (a) as input, and taking the controlled variable y as input(k)As an output.
Preferably, in step two: the output data can cover the main operation interval of 40% -95% of capture rate and 300MW-660MW unit power generation.
Preferably, in step three: the number of the units of the three layers of limited Boltzmann machines is respectively 100, 100 and 50.
Preferably, in step four: the coal-fired power plant CO2The objective function of the capture system operating cost satisfies a series of constraints:
yj＝fDBN(uj),j＝1,2,…,5 (2)
umin≤uj≤umax,j＝1,2,...,5 (3)
y1,i≤y1，max,i＝1,2,...,Ni (4)
y4,min≤y4,i≤y4,max,i＝1,2,...,Ni (5)
y5,min≤y5,i≤y5,max,i＝1,2,...,Ni (6)
wherein N isiRepresenting an optimized time domain; alpha is alpha1,iTo alpha4,iRespectively are weight coefficients corresponding to the performance indexes; u. ofminAnd umaxRespectively an amplitude lower limit constraint and an amplitude upper limit constraint of the input variable; y is1，maxIs the main steam pressure (y)1) An upper limit constraint of (d); y is4,minAnd y4,maxRespectively, the trapping rate (y)4) Lower and upper limit constraints; y is5,minAnd y5,maxRespectively reboiler temperature (y)5) Lower and upper limit constraints; y is6,minAnd y6,maxAre each CO2Yield (y)6) Lower and upper bounds on the total amount in the optimization time domain;
J1,ito J4,iRespectively large coal-fired power station CO2The specific expression of an objective function related to unit operation safety and operation economy in the trapping system is as follows:
J1,i＝|y3,i-Euld| (8)
J2,i＝u1,i (9)
J3,i＝(1-y4,i) (10)
J4,i＝y4,i (11)
in the formula, J1,iIndicating the load tracking error of the thermal power generating unit, J2,iRepresenting the amount of fuel consumed during operation of the unit, J3,iIndicating CO emission2Penalty of, J4,iRepresenting the cost of operation and maintenance of the PCC system, EuldIs an AGC load command.
Preferably, in step four: the weight coefficients corresponding to the objective function in formula (1) are respectively:
α1,i＝0.3Cgrid,i (12)
α2,i＝3.6Cfuel,i (13)
α4,i＝0.215qg,iCO&M,i (15)
in the formula, Cgrid,iRepresenting the power price (USD/MWh) of the internet at the current moment; cfuel，iIndicating the fuel quantity price (USD/ton) at the current moment. Meanwhile, the service power consumption and the throttling heat loss of the thermal power generating unit can be converted into the fuel consumption; q. q.sg,iRepresenting the mass flow of flue gas (kg/s),
for the current moment CO2Price of emissions (USD/ton); cO&M,iThe cost of operating and maintaining (USD/ton) for the individual carbon capture systems.
Preferably, in step seven: the BO solver utilizes a BO algorithm to solve the performance index (I), wherein the BO algorithm is realized through a bayesopt function in MATLAB
Preferably, large coal-fired power plant CO2The trapping system comprises five main units, namely a boiler, a steam turbine, a generator, an absorption tower and a separation tower; the main variables include: fuel quantity command (u)1) Water supply flow (u)2) Main steam valve opening (u)3) Lean solution flow (u)4) And the flow rate of extracted steam (u)5) Main steamingSteam pressure (y)1) Intermediate point enthalpy value (y)2) Turbine power (y)3) Collecting ratio (y)4) Reboiler temperature (y)5) And CO2Yield (y)6)。
Compared with the prior art, the invention has the beneficial effects that: the invention relates to a large-scale coal-fired power plant CO based on artificial intelligence2Optimal scheduling method for trapping system, and building CO of coal-fired power plant by using DBN2A steady state data model of a capture system, which takes the generated energy and CO of the unit into consideration2Emission and CO of coal-fired power plant2The operation cost of the trapping system is used for establishing a system economic index, the optimal control variable set value meeting system constraints is solved by using a BO algorithm according to information such as real-time carbon price and electricity price, and CO of the coal-fired power station is realized2The optimal scheduling of the trapping system can give consideration to the CO of the coal-fired power station2The operation requirements of the capture system on economy, safety and environmental protection are met, an optimal scheduling mode which meets the lowest total operation cost is found, and CO of a large coal-fired power plant is realized2The trapping system is operated optimally.
Drawings
FIG. 1 shows an artificial intelligence-based CO (carbon monoxide) of a coal-fired power plant2And (4) capturing a system optimization scheduling method block diagram.
FIG. 2 shows CO of a large coal-fired power plant2A capture system flow diagram.
Fig. 3 is a trend chart of the load command and the power price on the internet.
FIG. 4 shows CO of coal-fired power plant2Time-by-time cost comparison of capture systems before and after optimization.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention provides a technical scheme that: coal-fired power plant CO based on artificial intelligence2The trapping system optimal scheduling method is realized by a system as shown in FIG. 1, and the system comprises: BO solutionCoal-fired power plant CO decomposing device2Capture system objective function and coal-fired power plant CO2A capture system DBN steady-state model;
the BO solver utilizes a Bayesian algorithm to quickly solve the objective function;
CO of coal-fired power plant2The capture system objective function considers the electricity price, the carbon price, the system operation cost and the input and output variable constraints and can describe the CO of the coal-fired power plant2Capturing the total running cost of the system;
CO of coal-fired power plant2DBN steady-state model of capture system and CO of coal-fired power plant2Input control variable u of trapping system objective function module(k)And outputting the controlled variable y(k)And gives the optimal output variable given value yref(k)。
As shown in FIG. 2, the CO of a large coal-fired power plant2A capture system, comprising: main units such as a boiler, a steam turbine, a generator, an absorption tower, a separation tower and the like; the main variables include: fuel quantity command (u)1) Water supply flow (u)2) Main steam valve opening (u)3) Lean solution flow (u)4) And the flow rate of extracted steam (u)5) Main steam pressure (y)1) Intermediate point enthalpy value (y)2) Turbine power (y)3) Collecting ratio (y)4) Reboiler temperature (y)5) And CO2Yield (y)6)。
Coal-fired power plant CO based on artificial intelligence2The optimal scheduling method of the trapping system comprises the following steps:
selecting main steam pressure, an intermediate point enthalpy value, unit generating capacity, a capturing rate, reboiler temperature and CO2The output is large-scale coal-fired power station CO2Controlled variable y of trapping system(k)Selecting corresponding control variables u of coal supply amount, water supply flow, main steam valve opening, barren liquor flow and reboiler steam extraction flow(k)；
Step two, setting a sampling period Ts30 seconds. Under the condition of open loop, the coal supply quantity, the water supply flow, the opening of a main steam valve, the flow of barren liquor and the steam extraction flow of a reboiler are simultaneously changed to obtain different quantitiesThe method comprises the following steps that stable input and output data of a system under operating conditions such as generating capacity and trapping rate are input and output, and the output data can cover main operating intervals such as 40% -95% of trapping rate and 300MW-660MW unit generating capacity;
thirdly, carrying out normalization preprocessing on the input data and the output data, and constructing the CO of the coal-fired power plant containing the three layers of Bernoulli-Bernoulli restricted Boltzmann machines by utilizing functions prerainDBN () and trainDBN () in MATLAB2Capture system DBN steady state model. The number of units of each layer of limited Boltzmann machine is respectively 100, 100 and 50, the learning rate is 0.5, and the DBN model is as follows: y (k) ═ fDBN(u(k))；
Step four, considering the generating capacity and CO of the unit2The construction of the factors such as emission, operation cost and system constraint can reflect the CO of the coal-fired power station2Objective function of capture system operating cost:
and satisfies the following constraints:
yj＝fDBN(uj),j＝1,2,...,5 (2)
umin≤uj≤umax,j＝1,2,...,5 (3)
y1,i≤y1，max,i＝1,2,...,Ni (4)
y4,min≤y4,i≤y4,max,i＝1,2,...,Ni (5)
y5,min≤y5,i≤y5,max,i＝1,2,...,Ni (6)
wherein the constraint conditions are respectively set as: u. ofmin＝[20；200；0.4；100；30]T；umax＝[80；600；1；600；250]T；y1,max＝26；y4,min＝50％；y4,max＝90％；y5,min＝383；y5,max＝393；y6,min＝1000；y6,max＝1200；
J in the above formula (1)1,iTo J4,iRespectively large coal-fired power station CO2The specific expression of an objective function related to unit operation safety and operation economy in the trapping system is as follows:
J1,i＝|y3,i-Euld| (8)
J2,i＝u1,i (9)
J3,i＝(1-y4,i) (10)
J4,i＝y4,i (11)
in the formula, J1,iIndicating the load tracking error of the thermal power generating unit, J2,iRepresenting the amount of fuel consumed during operation of the unit, J3,iIndicating CO emission2Penalty of, J4,iRepresenting the cost of operation and maintenance of the PCC system, EuldFor the AGC load command, the variation trend of the AGC load command is shown in fig. 3.
Constructing weight coefficients corresponding to the objective function in the formula (1), wherein the weight coefficients are respectively as follows:
α1,i＝0.3Cgrid,i (12)
α2,i＝3.6Cfuel,i (13)
α4,i＝0.215qg,iCO&M,i (15)
in the formula, the power price C of the networkgrid,iThe (USD/MWh) trend is shown in FIG. 3; fuel quantity price C at presentfuel，i91.4 USD/ton; flue gas mass flow qg,i＝3.8756u1+264.2507 (kg/s); current time CO2Discharge price
Is 50 USD/ton; carbon only capture systemSystem operation and maintenance costs CO&M,i4.862 USD/ton;
step five, setting an optimized time domain Ni＝12；
Setting related parameters of a BO solver, wherein the acquisition function is 'robustness-of-improvement', the number of initial evaluation points is 4, and the cycle period is 100;
solving the performance index (I) by using a BO solver, and solving the minimum optimized control variable u meeting the performance index (I) under the system constraint condition(k)；
Step eight, utilizing CO of coal-fired power station2The collection system DBN steady-state model is solved with the input of u(k)Given value y of the optimal output variableref(k)；
Step nine, outputting the optimal set value yref(k)Realizing CO of coal-fired power plant2And trapping the optimized scheduling of the system, and then repeatedly executing the steps seven to nine in each optimized time domain.
CO2Discharge price
Respectively to 10USD/ton, 50USD/ton and 150USD/ton, and coal-fired power station CO2The hourly cost of the collection system before and after the optimization scheduling is shown in fig. 4 (the upper half lines distributed from bottom to top correspond to the carbon values 10USD/ton, 50USD/ton, and 150USD/ton after the optimization, and the lower half lines distributed from bottom to top correspond to the carbon values 10USD/ton, 50USD/ton, and 150USD/ton before the optimization), and it is apparent that the hourly cost after the system optimization is greatly reduced.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (8)
1. Large-scale coal-fired power plant CO based on artificial intelligence2The optimal scheduling method of the trapping system is characterized by comprising the following steps: the method comprises the following steps:
selecting main steam pressure, an intermediate point enthalpy value, unit generating capacity, a capturing rate, reboiler temperature and CO2The output is large-scale coal-fired power station CO2Controlled variable y of trapping system(k)Selecting corresponding control variables u of coal supply amount, water supply flow, main steam valve opening, barren liquor flow and reboiler steam extraction flow(k)；
Step two, under the condition of open loop, simultaneously changing the coal feeding amount, the water feeding flow, the opening of a main steam valve, the flow of a barren solution and the steam extraction flow of a reboiler, and acquiring steady-state input and output data of the system under the operating conditions of different generated energy and capture rates;
thirdly, normalizing the input data and the output data, and constructing a CO (carbon dioxide) of the coal-fired power plant containing three layers of limited Boltzmann Machines (RBMs) by utilizing functions of pretrainDBN (star) and trainnDBN (star) in MATLAB2The capture system DBN steady-state model,
wherein, the coal-fired power plant CO2The capture system DBN steady state model function is in the form: y (k) ═ fDBN(u(k))，y(k)Is the value of the controlled variable collected at the current moment, u(k)For the collected value of the control variable at the current moment, fDBN(. h) is a functional form of the DBN model;
step four, considering the generating capacity and CO of the unit2Emission, running cost and system constraint factors, and the construction can reflect CO of the coal-fired power plant2An objective function of the system operation cost and a weight coefficient corresponding to the objective function are collected,
wherein, the coal-fired power plant CO2The objective function of the operational cost of the capture system is
The coal-fired power plant CO2The objective function of the operation cost of the trapping system meets a series of constraints;
step five, setting an optimized time domain NiAnd a scheduling period Ts；
Setting related parameters of a BO solver, including an acquisition function, the number of initial evaluation points and cycle period parameters;
solving the performance index (1) by using a BO solver, and solving the minimum optimized control variable u (k) meeting the performance index (1) under the system constraint condition;
step eight, utilizing CO of coal-fired power station2The collection system DBN steady-state model solves the input into the control variable u(k)Given value y of the optimal output variableref(k)；
Step nine, outputting the optimal set value yref(k) Realizing CO of coal-fired power plant2And trapping the optimized scheduling of the system, and then repeatedly executing the steps seven to nine in each optimized time domain.
2. The large-scale coal-fired power plant CO based on artificial intelligence of claim 12The optimal scheduling method of the trapping system is characterized by comprising the following steps: in the first step: command by fuel amount (u)1) Water supply flow (u)2) Main steam valve opening (u)3) Lean solution flow (u)4) And the flow rate of extracted steam (u)5) Is a main control variable u of the system(k)At the main steam pressure (y)1) Intermediate point enthalpy value (y)2) Turbine power (y)3) Collecting ratio (y)4) Reboiler temperature (y)5) And CO2Yield (y)6) Is the main controlled variable y of the system(k)To control the variable u(k)Taking the historical sampling value of (a) as input, and taking the controlled variable y as input(k)As an output.
3. The large-scale coal-fired power plant CO based on artificial intelligence of claim 12The optimal scheduling method of the trapping system is characterized by comprising the following steps: in the second step: the output data can cover the main operation interval of 40% -95% of capture rate and 300MW-660MW unit power generation.
4. The large-scale coal-fired power plant CO based on artificial intelligence of claim 12Optimal scheduling method for trapping system, and program thereofIs characterized in that: in the third step: the number of the units of the three layers of limited Boltzmann machines is respectively 100, 100 and 50.
5. The large-scale coal-fired power plant CO based on artificial intelligence of claim 12The optimal scheduling method of the trapping system is characterized by comprising the following steps: in the fourth step: the coal-fired power plant CO2The objective function of the capture system operating cost satisfies a series of constraints:
yj＝fDBN(uj),j＝1,2,...,5 (2)
umin≤uj≤umax,j＝1,2,…,5 (3)
y1,i≤y1，max,i＝1,2,…,Ni (4)
y4,min≤y4,i≤y4,max,i＝1,2,...,Ni (5)
y5,min≤y5,i≤y5,max,i＝1,2,...,Ni (6)
wherein N isiRepresenting an optimized time domain; alpha is alpha1,iTo alpha4,iRespectively are weight coefficients corresponding to the performance indexes; u. ofminAnd umaxRespectively an amplitude lower limit constraint and an amplitude upper limit constraint of the input variable; y is1，maxIs the main steam pressure (y)1) An upper limit constraint of (d); y is4,minAnd y4,maxRespectively, the trapping rate (y)4) Lower and upper limit constraints; y is5,minAnd y5,maxRespectively reboiler temperature (y)5) Lower and upper limit constraints; y is6,minAnd y6,maxAre each CO2Yield (y)6) Lower and upper bounds on the total amount in the optimization time domain;
J1,ito J4,iRespectively large coal-fired power station CO2Objective function relating to unit operation safety and operation economy in a capture system, and specific details thereofThe expression is as follows:
J1,i＝|y3,i-Euld| (8)
J2,i＝u1,i (9)
J3,i＝(1-y4,i) (10)
J4,i＝y4,i (11)
in the formula, J1,iIndicating the load tracking error of the thermal power generating unit, J2,iRepresenting the amount of fuel consumed during operation of the unit, J3,iIndicating CO emission2Penalty of, J4,iRepresenting the cost of operation and maintenance of the PCC system, EuldIs an AGC load command.
6. The large-scale coal-fired power plant CO based on artificial intelligence of claim 52The optimal scheduling method of the trapping system is characterized by comprising the following steps: in the fourth step: the weight coefficients corresponding to the objective function in formula (1) are respectively:
α1,i＝0.3Cgrid,i (12)
α2,i＝3.6Cfuel,i (13)
α4,i＝0.215qg,iCO&M,i (15)
in the formula, Cgrid,iRepresenting the power price (USD/MWh) of the internet at the current moment; cfuel，iRepresenting the fuel quantity price (USD/ton) at the current moment, and simultaneously converting the service power consumption and the throttling heat loss of the thermal power unit into the fuel quantity consumption; q. q.sg,iRepresenting the mass flow of flue gas (kg/s),
for the current moment CO2Price of emissions (USD/ton); cO&M,iThe cost of operating and maintaining (USD/ton) for the individual carbon capture systems.
7. The large-scale coal-fired power plant CO based on artificial intelligence of claim 12The optimal scheduling method of the trapping system is characterized by comprising the following steps: step seven: the BO solver solves the performance index (I) by using a BO algorithm, wherein the BO algorithm is realized by a bayesopt function in MATLAB.
8. The large-scale coal-fired power plant CO based on artificial intelligence of claim 22The optimal scheduling method of the trapping system is characterized by comprising the following steps: CO of large coal-fired power station2The trapping system comprises five main units, namely a boiler, a steam turbine, a generator, an absorption tower and a separation tower; the main variables include: fuel quantity command (u)1) Water supply flow (u)2) Main steam valve opening (u)3) Lean solution flow (u)4) And the flow rate of extracted steam (u)5) Main steam pressure (y)1) Intermediate point enthalpy value (y)2) Turbine power (y)3) Collecting ratio (y)4) Reboiler temperature (y)5) And CO2Yield (y)6)。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110646133.6A CN113341716B (en) | 2021-06-10 | 2021-06-10 | Large-scale coal-fired power plant CO based on artificial intelligence 2 Optimized scheduling method for trapping system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110646133.6A CN113341716B (en) | 2021-06-10 | 2021-06-10 | Large-scale coal-fired power plant CO based on artificial intelligence 2 Optimized scheduling method for trapping system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113341716A true CN113341716A (en) | 2021-09-03 |
| CN113341716B CN113341716B (en) | 2023-08-04 |
Family
ID=77476167
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110646133.6A Active CN113341716B (en) | 2021-06-10 | 2021-06-10 | Large-scale coal-fired power plant CO based on artificial intelligence 2 Optimized scheduling method for trapping system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113341716B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114819341A (en) * | 2022-04-25 | 2022-07-29 | 东南大学 | Multi-time scale control perception scheduling method of coal-fired power plant coupling carbon capture system |
| CN114819341B (en) * | 2022-04-25 | 2024-07-09 | 东南大学 | Multi-time scale control sensing scheduling method for coal-fired power plant coupling carbon capture system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011150462A1 (en) * | 2010-06-02 | 2011-12-08 | Co2Crc Technologies Pty Ltd | Optimising objectives of a plant and a carbon dioxide capture facility |
| CN110764419A (en) * | 2019-11-15 | 2020-02-07 | 江苏方天电力技术有限公司 | CO of large coal-fired power station2Capture global scheduling and predictive control system and method |
| CN112633560A (en) * | 2020-12-11 | 2021-04-09 | 西安交通大学 | Power station optimal scheduling method containing coal-fired cogeneration unit |
-
2021
- 2021-06-10 CN CN202110646133.6A patent/CN113341716B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011150462A1 (en) * | 2010-06-02 | 2011-12-08 | Co2Crc Technologies Pty Ltd | Optimising objectives of a plant and a carbon dioxide capture facility |
| CN110764419A (en) * | 2019-11-15 | 2020-02-07 | 江苏方天电力技术有限公司 | CO of large coal-fired power station2Capture global scheduling and predictive control system and method |
| CN112633560A (en) * | 2020-12-11 | 2021-04-09 | 西安交通大学 | Power station optimal scheduling method containing coal-fired cogeneration unit |
Non-Patent Citations (2)
| Title |
|---|
| XIAO WU等: "Solvent-based post-combustion CO2 capture for power plants: A critical review and perspective on dynamic modelling, system identification, process control and flexible operation", 《APPLIED ENERGY》 * |
| 田牧等: "燃煤电站锅炉二氧化碳捕集封存技术经济性分析", 《锅炉技术》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114819341A (en) * | 2022-04-25 | 2022-07-29 | 东南大学 | Multi-time scale control perception scheduling method of coal-fired power plant coupling carbon capture system |
| CN114819341B (en) * | 2022-04-25 | 2024-07-09 | 东南大学 | Multi-time scale control sensing scheduling method for coal-fired power plant coupling carbon capture system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113341716B (en) | 2023-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | The mutual benefits of renewables and carbon capture: Achieved by an artificial intelligent scheduling strategy | |
| CN107482688B (en) | Scheduling optimization method for carbon capture virtual power plant | |
| CN110764419B (en) | CO of large coal-fired power plant2Capture global scheduling and predictive control system and method | |
| CN111552175B (en) | Overall optimization scheduling and rapid variable load control method for supercritical coal-fired power plant-carbon capture system after chemical adsorption combustion | |
| Xi et al. | Artificial intelligent based energy scheduling of steel mill gas utilization system towards carbon neutrality | |
| CN104166877A (en) | Microgrid optimization operation method based on improved binary system particle swarm optimization algorithm | |
| CN113237081A (en) | Zero-carbon-emission green hydrogen alcoholization, preparation and storage combined upgrading and transformation system for coal-fired thermal power generating unit | |
| Alabi et al. | Automated deep reinforcement learning for real-time scheduling strategy of multi-energy system integrated with post-carbon and direct-air carbon captured system | |
| CN108958031B (en) | Post combustion CO2Coordinated prediction control method for trapping coal-fired power generation system | |
| Fan et al. | Exergy analysis and dynamic control of chemical looping combustion for power generation system | |
| AU2021105749A4 (en) | Method for designing and modeling integrated energy system for realizing carbon cycle | |
| Zhang et al. | Modeling and optimization of integrated energy system for renewable power penetration considering carbon and pollutant reduction systems | |
| CN201962264U (en) | System for producing natural gas by wind, power and coal | |
| Chen et al. | Multi-timescale capacity configuration optimization of energy storage equipment in power plant-carbon capture system | |
| CN114282828A (en) | Carbon circulation system and application thereof | |
| CN108508748B (en) | Effective operation control method for photo-thermal auxiliary combustion post-CO 2 capture system | |
| CN117709644A (en) | Comprehensive energy system low-carbon optimal scheduling method based on asynchronous deep reinforcement learning | |
| CN113341716B (en) | Large-scale coal-fired power plant CO based on artificial intelligence 2 Optimized scheduling method for trapping system | |
| CN113221325A (en) | Multi-source energy storage type regional comprehensive energy low-carbon operation optimization method considering electricity to gas | |
| Hildebrand et al. | Optimization of carbon capture percentage for technical and economic impact of near-term CCS implementation at coal-fired power plants | |
| CN114000979A (en) | Electric water-hydrogen-methanol multi-generation energy source island and method | |
| CN113972662A (en) | Integrated energy production unit and method | |
| CN206917687U (en) | One kind coupling thermal power generation and CO2Zero carbon polygenerations systeme of conversion | |
| CN113988367A (en) | Random optimization scheduling method of wind-solar-thermal storage coupling carbon capture and utilization system | |
| FU et al. | A Integrated System of The Coal-Fired Unit With CO2 Capture to Produce Methanol |
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 |