CN113887827B - Coal blending and burning optimization decision method based on real-time carbon emission monitoring of thermal power generating unit - Google Patents
Coal blending and burning optimization decision method based on real-time carbon emission monitoring of thermal power generating unit Download PDFInfo
- Publication number
- CN113887827B CN113887827B CN202111240635.5A CN202111240635A CN113887827B CN 113887827 B CN113887827 B CN 113887827B CN 202111240635 A CN202111240635 A CN 202111240635A CN 113887827 B CN113887827 B CN 113887827B
- Authority
- CN
- China
- Prior art keywords
- coal
- carbon emission
- unit
- thermal power
- carbon
- 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
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 174
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 171
- 239000003245 coal Substances 0.000 title claims abstract description 127
- 238000002156 mixing Methods 0.000 title claims abstract description 88
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000005457 optimization Methods 0.000 title claims abstract description 33
- 238000012544 monitoring process Methods 0.000 title claims abstract description 25
- 238000013528 artificial neural network Methods 0.000 claims abstract description 22
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 230000006870 function Effects 0.000 claims description 34
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000002485 combustion reaction Methods 0.000 claims description 11
- 238000010248 power generation Methods 0.000 claims description 11
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 claims description 10
- 239000003546 flue gas Substances 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 10
- 229910002092 carbon dioxide Inorganic materials 0.000 claims description 9
- 239000001569 carbon dioxide Substances 0.000 claims description 9
- 230000005284 excitation Effects 0.000 claims description 9
- 210000002569 neuron Anatomy 0.000 claims description 9
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 claims description 7
- 229910052717 sulfur Inorganic materials 0.000 claims description 7
- 239000011593 sulfur Substances 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 claims description 3
- 239000007789 gas Substances 0.000 claims description 3
- 238000012821 model calculation Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 239000000779 smoke Substances 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims 1
- 230000007613 environmental effect Effects 0.000 description 3
- 238000010304 firing Methods 0.000 description 3
- 238000010438 heat treatment Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- -1 and in recent years Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- 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
- Y02P90/80—Management or planning
- Y02P90/84—Greenhouse gas [GHG] management systems
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Software Systems (AREA)
- Tourism & Hospitality (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- General Business, Economics & Management (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a coal blending and burning optimization decision method based on real-time carbon emission monitoring of a thermal power generating unit, which comprises the steps of collecting real-time carbon emission data of the thermal power generating unit, predicting the current day carbon emission of the thermal power generating unit, constructing a neural network algorithm, collecting real-time carbon price of a carbon emission right trade market, storing and classifying the collected real-time carbon emission data of the thermal power generating unit, predicting the current day carbon emission data of the thermal power generating unit and the current carbon price of the carbon emission right trade market, updating in real time, optimizing the classified data through the neural network algorithm, obtaining an optimization result, and carrying out a coal blending and burning scheme of the thermal power generating unit through the optimization result. The method can easily obtain the optimal coal blending and coal blending combination by combining the implementation emission data of the thermal power plant and the real-time carbon transaction price, and can ensure that enterprises obtain the maximum comprehensive benefit, save a large amount of energy and save a large amount of cost.
Description
Technical Field
The invention relates to the technical field of environmental protection monitoring of coal-fired power plants, in particular to a coal blending and burning optimization decision-making method based on real-time carbon emission monitoring of a thermal power unit.
Background
At present, the electric power production mainly uses coal, and in recent years, coal is wasted due to the contradiction between electricity and coal supply and demand, so that the coal quality of most coal-fired thermal power plants is unstable, the coal consumption of a generator set is increased, the power generation efficiency is reduced, the pollutant emission exceeds standard, and the like, and the safety, civilization, economy and environmental protection operation of the set are affected.
In addition, after the thermal power plant participates in carbon transaction, excessive carbon emission will generate cost. The thermal power plant uses the fire coal with different coal qualities to generate different economic effects and environmental effects. The coal with poor coal quality has lower cost, but can lead to the reduction of boiler efficiency and the increase of power generation coal consumption rate; the high-quality coal can improve the boiler efficiency and reduce the power generation coal consumption rate although the cost is higher.
Blending coal is an important measure for reducing cost and improving efficiency and improving core competitiveness of power generation enterprises, and is an effective method for solving the problems of shortage of unit coal and poor running performance due to variable coal types.
The invention establishes a blending and burning optimization decision method of the thermal power unit coal blending by considering the quality and carbon emission of various fuels and combining the real-time monitoring data of carbon emission and the real-time carbon transaction price.
Disclosure of Invention
The invention provides a coal blending and burning optimization decision method based on real-time carbon emission monitoring of a thermal power generating unit.
In order to solve the problems, the technical scheme adopted by the invention is as follows:
The coal blending and burning optimization decision method based on the real-time carbon emission monitoring of the thermal power generating unit comprises the following steps:
step one: collecting real-time carbon emission data of the coal-fired thermal power unit;
step two: predicting the carbon emission of the coal-fired thermal power unit on the same day;
Step three: constructing a neural network algorithm;
Step four: collecting real-time data of carbon prices of the carbon emission right trading market;
step five: storing, classifying and updating the collected real-time carbon emission data of the coal-fired thermal power generating unit, the carbon emission data of the predicted coal-fired thermal power generating unit on the same day and the real-time data of the carbon price of the carbon emission right trading market in real time;
step six: optimizing the classified data through a neural network algorithm, and obtaining an optimization result;
step seven: and carrying out a coal blending and burning scheme of the coal-fired thermal power generating unit through the optimized result.
Further, in the first step, the method for collecting the real-time carbon emission data of the coal-fired thermal power unit comprises the following steps:
Data is gathered from a flue gas emission stack of a coal-fired thermal power unit, comprising: the volume concentration of CO 2 gas analyzed by carbon dioxide analysis equipment is adopted, and the calculation formula of the carbon emission concentration is as follows:
wherein: x is a CO 2 concentration conversion value, and the unit is mg/Nm 3; c is the measured value of CO 2 concentration, unit ppm; m is the molecular weight of CO 2; t is the temperature of the clean flue gas, and the unit is DEG C; p is the net smoke pressure, unit Pa;
The calculation formula of the carbon emission amount is:
Wherein: mc is the accumulated emission of CO 2 in the time T, and the unit is T; x is a CO 2 concentration conversion value, and the unit is mg/Nm 3; f is the flow rate of the clean flue gas, and the unit is Nm 3/h;
calculating the carbon emission amount in one day according to the above method;
Obtaining the carbon emission amount of N days based on the carbon emission monitoring data of N days: e i, i is the i th day of observation, and the value of N is not less than 50.
Further, in the method for collecting real-time carbon emission data of the coal-fired thermal power unit, for all coal types of the thermal power plant, a physicochemical experiment is performed on randomly collected samples to collect coal data, wherein the data comprises heat values u i of each coal type, a unit of GJ/t, a carbon dioxide emission factor CC i, a unit of tCO 2/GJ, a sulfur content S i, a moisture H i index, a daily usage amount X i, a unit of t and a unit price index Q i, and a unit of yuan/t.
Further, in the third step, the building a neural network algorithm specifically includes:
Parameters of different coal types and the consumption of a certain day are input, and the carbon emission of the coal-fired thermal power unit in the same day is predicted:
and (3) establishing a model:
The neural network model consists of an input layer, a hidden layer and an output layer, and adopts an S-shaped transfer function:
Inverse error function:
and (3) network structure design:
The input layer is formed by adding 5 layers of input layers to different types of coals in use, heat values, carbon dioxide emission factors, carbon content in unit heat value and sulfur content, wherein each more type of coals participate in blending and burning, and the number of hidden layers is set as follows:
m is the number of input layers, n is the number of output layers, a is a constant, and a is more than or equal to 1 and less than or equal to 10;
The output layer is carbon emission;
model implementation:
The S-shaped tangent function tansig is adopted as the excitation function of the hidden layer neuron, the output of the network is normalized to the range of [ -1,1], so that the prediction model selects the S-shaped logarithmic function tansig as the excitation function of the output layer neuron;
The training sample data is normalized and then is input into a network, a network hidden layer and an output layer excitation function are adopted as tansig and logsig functions respectively, a network training function is traingdx, a network performance function is mse, the hidden layer neuron number, the network parameter, the expected network iteration number error and the learning rate are set, then the training network is started, the input parameters and the input amount of various coals are normalized before the input is started, and finally the obtained value is between [ -1,1], so that in order to restore the previous value, a postmnmx () function is adopted for processing, and the carbon emission C is obtained, wherein the unit is t.
Further, in the fourth step, the method for collecting the real-time data of the carbon price of the carbon emission right trading market is as follows:
calculating the daily carbon emission cost of the coal-fired thermal power unit, and acquiring the carbon price of the past 1 day on a carbon transaction platform by a device for acquiring real-time data of the carbon price of a national carbon emission right transaction market;
case one: the carbon emission quota of the thermal power generating unit is K, the unit is t, the thermal power generating unit is used up, namely, the carbon emission quota K is less than or equal to 0, and the carbon emission cost is obtained by multiplying the emission amount by the carbon price;
And a second case: the carbon emission quota K of the thermal power generating unit is not used up and is more than 0, and the carbon emission cost is obtained by multiplying the emission quantity by the average unit carbon emission cost in the previous performance period;
The calculation formula of the carbon emission cost comprises the following steps:
the carbon emission cost is P, the unit is a unit, if the thermal power unit is in a case one, the formula (1) is substituted, P c1 is the current carbon price, the unit is a unit/t, if the thermal power unit is in a case two, the formula (2) is substituted, and P c2 is the average unit carbon emission cost of the previous caterpillar period, and the unit is a unit/t.
Further, in the sixth step, the specific method for optimizing the classified data through the neural network algorithm and obtaining the optimization result is as follows:
given an initial coal blending and burning state, the carbon emission generated by different blending and burning modes is obtained by a neural network algorithm, the carbon emission generated by power generation of a thermal power generating unit, the carbon emission cost is changed, the coal blending and burning state is changed, the proportion of different coal types is exhausted, all the possibilities are exhausted, then the maximum benefit is taken, and the optimization goal is that:
maxw = power generation benefit-carbon emission cost-coal purchase cost
Constraint conditions:
Si＜Smax
Hi＜Hmax；
i is the generation gain, the unit is yuan, P is the carbon emission cost, X i is the consumption of coal blending and coal blending, the unit is t, Q i is the corresponding coal purchase price, the unit is yuan/t, CAL min is the daily minimum combustion heat productivity of the thermal generator set, and the unit is GJ;
the using amount X i of the coal blended and burned coal is taken as a decision variable, the optimal blending and burned number of each coal variety is obtained through model calculation, the coal variety combination is carried out, the blending and burned state of the coal is changed, the optimization model is repeatedly executed, the maximum comprehensive benefit of all the blending and burned states is obtained, and the corresponding decision variable gives the blending and burned result of the coal.
Further, in the seventh step, the coal blending and burning scheme of the coal-fired thermal power generating unit is performed through the optimized result, and the method specifically comprises the following steps:
Under the aim of the optimized result to display the maximum comprehensive benefit, the method is used for the coal blending and burning scheme of the coal-fired thermal power generating unit in the next day, the scheme is conducted to a coal blending control device to realize the coal blending and burning function, the optimized result in the next day is used as an initial state of the optimization in the third day, the coal blending proportion and the carbon emission monitoring result in the next day are incorporated into the neural network algorithm, and data are updated.
Compared with the prior art, the invention has the following beneficial effects:
The invention establishes the coal blending and burning optimizing decision-making method of the thermal power unit based on the coal blending and burning optimizing decision-making method of the thermal power unit for monitoring the real-time carbon emission, combines the implementation emission data of the thermal power plant and the real-time carbon transaction price, can easily obtain the method of the optimal coal blending and burning coal combination, and can lead enterprises to obtain the maximum comprehensive benefit, save a large amount of energy sources and save a large amount of cost.
Drawings
Fig. 1 is a flow chart of a coal blending and burning optimization decision method based on real-time carbon emission monitoring of a thermal power generating unit.
Detailed Description
The present invention will be described below in conjunction with specific embodiments, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functionality throughout.
Referring to fig. 1, fig. 1 is a flowchart of a coal blending and burning optimization decision method based on real-time carbon emission monitoring of a thermal power generating unit.
The coal blending and burning optimization decision method based on the real-time carbon emission monitoring of the thermal power generating unit comprises the following steps:
step one: collecting real-time carbon emission data of the coal-fired thermal power unit;
The method for collecting the real-time carbon emission data of the coal-fired thermal power unit comprises the following steps:
Data is gathered from a flue gas emission stack of a coal-fired thermal power unit, comprising: the volume concentration of CO 2 gas analyzed by carbon dioxide analysis equipment is adopted, and the calculation formula of the carbon emission concentration is as follows:
wherein: x is a CO 2 concentration conversion value, and the unit is mg/Nm 3; c is the measured value of CO 2 concentration, unit ppm; m is the molecular weight of CO 2; t is the temperature of the clean flue gas, and the unit is DEG C; p is the net smoke pressure, unit Pa;
The calculation formula of the carbon emission amount is:
Wherein: mc is the accumulated emission of CO 2 in the time T, and the unit is T; x is a CO 2 concentration conversion value, and the unit is mg/Nm 3; f is the flow rate of the clean flue gas, and the unit is Nm 3/h;
calculating the carbon emission amount in one day according to the above method;
Obtaining the carbon emission amount of N days based on the carbon emission monitoring data of N days: e i, i is the i th day of observation, and the value of N is not less than 50.
Step two: predicting the carbon emission of the coal-fired thermal power unit on the same day;
According to the method for collecting the real-time carbon emission data of the coal-fired thermal power unit, all coal types of the thermal power plant are required to be subjected to physical and chemical experiment collection, and the coal data are obtained by randomly collecting samples, wherein the samples comprise the heat value u i of each coal type, the unit of GJ/t, the carbon dioxide emission factor CC i, the unit of tCO 2/GJ, the sulfur content S i, the moisture H i index, the daily dosage X i, the unit of t and the unit of unit price index Q i, and the unit of yuan/t.
Step three: constructing a neural network algorithm;
The method comprises the following steps:
Parameters of different coal types and the consumption of a certain day are input, and the carbon emission of the coal-fired thermal power unit in the same day is predicted:
and (3) establishing a model:
The neural network model consists of an input layer, a hidden layer and an output layer, and adopts an S-shaped transfer function:
Inverse error function:
and (3) network structure design:
The input layer is formed by adding 5 layers of input layers to different types of coals in use, heat values, carbon dioxide emission factors, carbon content in unit heat value and sulfur content, wherein each more type of coals participate in blending and burning, and the number of hidden layers is set as follows:
m is the number of input layers, n is the number of output layers, a is a constant, and a is more than or equal to 1 and less than or equal to 10;
The output layer is carbon emission;
model implementation:
The S-shaped tangent function tansig is adopted as the excitation function of the hidden layer neuron, the output of the network is normalized to the range of [ -1,1], so that the prediction model selects the S-shaped logarithmic function tansig as the excitation function of the output layer neuron;
The training sample data is normalized and then is input into a network, a network hidden layer and an output layer excitation function are adopted as tansig and logsig functions respectively, a network training function is traingdx, a network performance function is mse, the hidden layer neuron number, the network parameter, the expected network iteration number error and the learning rate are set, then the training network is started, the input parameters and the input amount of various coals are normalized before the input is started, and finally the obtained value is between [ -1,1], so that in order to restore the previous value, a postmnmx () function is adopted for processing, and the carbon emission C is obtained, wherein the unit is t.
Step four: collecting real-time data of carbon prices of the carbon emission right trading market;
The method for collecting the real-time data of the carbon price of the carbon emission right trading market comprises the following steps:
calculating the daily carbon emission cost of the coal-fired thermal power unit, and acquiring the carbon price of the past 1 day on a carbon transaction platform by a device for acquiring real-time data of the carbon price of a national carbon emission right transaction market;
case one: the carbon emission quota of the thermal power generating unit is K, the unit is t, the thermal power generating unit is used up, namely, the carbon emission quota K is less than or equal to 0, and the carbon emission cost is obtained by multiplying the emission amount by the carbon price;
And a second case: the carbon emission quota K of the thermal power generating unit is not used up and is more than 0, and the carbon emission cost is obtained by multiplying the emission quantity by the average unit carbon emission cost in the previous performance period;
The calculation formula of the carbon emission cost comprises the following steps:
the carbon emission cost is P, the unit is a unit, if the thermal power unit is in a case one, the formula (1) is substituted, P c1 is the current carbon price, the unit is a unit/t, if the thermal power unit is in a case two, the formula (2) is substituted, and P c2 is the average unit carbon emission cost of the previous caterpillar period, and the unit is a unit/t.
Step five: and storing, classifying and updating the collected real-time carbon emission data of the coal-fired thermal power generating unit, the carbon emission data of the predicted coal-fired thermal power generating unit on the same day and the real-time data of the carbon price of the carbon emission right trading market in real time.
Step six: optimizing the classified data through a neural network algorithm, and obtaining an optimization result;
The specific method for optimizing the classified data through the neural network algorithm and obtaining the optimized result is as follows:
given an initial coal blending and burning state, the carbon emission generated by different blending and burning modes is obtained by a neural network algorithm, the carbon emission generated by power generation of a thermal power generating unit, the carbon emission cost is changed, the coal blending and burning state is changed, the proportion of different coal types is exhausted, all the possibilities are exhausted, then the maximum benefit is taken, and the optimization goal is that:
maxw = power generation benefit-carbon emission cost-coal purchase cost
Constraint conditions:
Si＜Smax
Hi＜Hmax；
i is the generation gain, the unit is yuan, P is the carbon emission cost, X i is the consumption of coal blending and coal blending, the unit is t, Q i is the corresponding coal purchase price, the unit is yuan/t, CAL min is the daily minimum combustion heat productivity of the thermal generator set, and the unit is GJ;
the using amount X i of the coal blended and burned coal is taken as a decision variable, the optimal blending and burned number of each coal variety is obtained through model calculation, the coal variety combination is carried out, the blending and burned state of the coal is changed, the optimization model is repeatedly executed, the maximum comprehensive benefit of all the blending and burned states is obtained, and the corresponding decision variable gives the blending and burned result of the coal.
Step seven: carrying out a coal blending and burning scheme of the coal-fired thermal power generating unit through an optimized result;
The method comprises the following steps:
Under the aim of the optimized result to display the maximum comprehensive benefit, the method is used for the coal blending and burning scheme of the coal-fired thermal power generating unit in the next day, the scheme is conducted to a coal blending control device to realize the coal blending and burning function, the optimized result in the next day is used as an initial state of the optimization in the third day, the coal blending proportion and the carbon emission monitoring result in the next day are incorporated into the neural network algorithm, and data are updated.
Examples:
According to the device for collecting the real-time carbon emission data of the coal-fired thermal power unit, the thermal power plant collects related data from a flue gas emission chimney of the coal-fired thermal power unit and the coal blending and burning optimization decision method based on the real-time carbon emission monitoring of the thermal power unit, and monitors and obtains the carbon emission of the thermal power plant, the type and the amount of coal used by the thermal power plant and the corresponding related chemical and physical data in the first 14 days aiming at all coal types of the thermal power plant. As shown in table 1.
TABLE 1 carbon emission and coal consumption parameter index for the first 14 days of thermal power plant
The type and the amount of coal used in the thermal power plant on the fifteenth day and corresponding relevant chemical and physical data. As shown in table 2.
Table 2 fifteenth day coal usage data for thermal power plant
| Variety of coal | Heating value (GJ/t) | Carbon content per unit heating value (tC/GJ) | Sulfur content (%) | Unit price (Yuan/t) |
| 1 | 31.44 | 0.00290 | 0.79 | 1650 |
| 2 | 21.03 | 0.00263 | 1.67 | 1050 |
| 3 | 13.22 | 0.00236 | 2.17 | 750 |
And on the premise of not exceeding the cost threshold value of the thermal power plant and ensuring the power generation capacity, determining a plurality of blending ratio, wherein the blending ratio to be selected is shown in table 3.
TABLE 3 blending ratio of coal to be selected
| Proportion 1 | Proportion 2 | Proportion 3 | Proportion 4 | Proportion 5 | Proportion 6 | Proportion 7 | Proportion 8 | |
| Coal 1 | 2600 | 2400 | 2800 | 2400 | 2200 | 2400 | 3200 | 2600 |
| Coal 2 | 2200 | 2000 | 2000 | 2200 | 2400 | 2400 | 1800 | 2000 |
| Coal 3 | 1200 | 1600 | 1200 | 1400 | 1200 | 1200 | 1000 | 1400 |
At this point the thermal unit has run out of carbon emission allowance. And carrying out a real-time data acquisition device according to the carbon price of the national carbon emission right trading market, and acquiring the carbon price of the past 1 day as 50 yuan/t on a carbon trading platform. The previous day of the thermal power plant has the benefit of 800 ten thousand yuan. The lowest combustion heating value of the thermal generator set per day is 131380GJ.
The data in tables 1,2 and 3 are output through a neural network algorithm to obtain carbon emission data of different coal blending and blending combustion thermal power plants. Since the weights and thresholds initialized by the neural network algorithm during calculation are random, the results are different each time, and for this phenomenon, we perform 5 times of neural network calculation for each pre-selected firing ratio, and the results are shown in table 4.
Table 4: carbon emission of each combustion ratio
The comprehensive benefits obtained from each of the firing ratios were obtained from the average carbon emissions, and the results are shown in Table 5.
TABLE 5 comprehensive benefits from each firing rate
| Proportion 1 | Proportion 2 | Proportion 3 | Proportion 4 | Proportion 5 | Proportion 6 | Proportion 7 | Proportion 8 | |
| Comprehensive benefit (Yuan) | 430008 | 663357 | 307851 | 604288 | 870462 | 538366 | 3294 | 478312 |
As can be seen from Table 5, the maximum gain is 5, namely 2400t, 2400t and 1200t are used as the blending ratio of the blending coal 1, the blending coal 2 and the blending coal 3 on the fifteenth day, and the comprehensive gain is estimated to be 870462 yuan. The heat productivity of complete combustion is 141792GJ, which is larger than the minimum required heat productivity of the thermal power generating unit and meets the requirements. And outputting the blending coal blending combustion proportion 5 to a blending coal control device to realize the blending coal blending combustion function.
Compared with the prior art, the invention has the following beneficial effects:
The invention establishes the coal blending and burning optimizing decision-making method of the thermal power unit based on the coal blending and burning optimizing decision-making method of the thermal power unit for monitoring the real-time carbon emission, combines the implementation emission data of the thermal power plant and the real-time carbon transaction price, can easily obtain the method of the optimal coal blending and burning coal combination, and can lead enterprises to obtain the maximum comprehensive benefit, save a large amount of energy sources and save a large amount of cost.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (5)
1. The coal blending and burning optimization decision-making method based on the real-time carbon emission monitoring of the thermal power generating unit is characterized by comprising the following steps of:
step one: collecting real-time carbon emission data of the coal-fired thermal power unit;
step two: predicting the carbon emission of the coal-fired thermal power unit on the same day;
Step three: constructing a neural network algorithm;
Step four: collecting real-time data of carbon prices of the carbon emission right trading market;
step five: storing, classifying and updating the collected real-time carbon emission data of the coal-fired thermal power generating unit, the carbon emission data of the predicted coal-fired thermal power generating unit on the same day and the real-time data of the carbon price of the carbon emission right trading market in real time;
step six: optimizing the classified data through a neural network algorithm, and obtaining an optimization result;
Step seven: carrying out a coal blending and burning scheme of the coal-fired thermal power generating unit through an optimized result;
In the third step, the neural network algorithm is constructed, specifically as follows:
Parameters of different coal types and the consumption of a certain day are input, and the carbon emission of the coal-fired thermal power unit in the same day is predicted:
and (3) establishing a model:
The neural network model consists of an input layer, a hidden layer and an output layer, and adopts an S-shaped transfer function:
Inverse error function:
and (3) network structure design:
The input layer is formed by adding 5 layers of input layers to different types of coals in use, heat values, carbon dioxide emission factors, carbon content in unit heat value and sulfur content, wherein each more type of coals participate in blending and burning, and the number of hidden layers is set as follows:
m is the number of input layers, n is the number of output layers, a is a constant, and a is more than or equal to 1 and less than or equal to 10
The output layer is carbon emission;
model implementation:
the S-shaped tangent function tansig is adopted as the excitation function of the hidden layer neuron, the output of the network is normalized to the range of [ -1,1], so that the prediction model selects the S-shaped logarithmic function tansig as the excitation function of the output layer neuron;
Normalizing training sample data and inputting the normalized training sample data into a network, adopting a network hidden layer and an output layer excitation function as tansig and logsig functions respectively, adopting a network training function as traingdx, adopting a network performance function as mse, setting hidden layer neuron number, network parameters, expected network iteration number errors and learning rate, then starting training the network, and carrying out normalization processing on parameters and the dosage of various input coals before starting input, wherein the finally obtained value is a value between [ -1,1], so that in order to restore the previous value, adopting a postmnmx () function for processing to obtain carbon emission C with the unit of t;
in the sixth step, the specific method for optimizing the classified data through the neural network algorithm and obtaining the optimization result is as follows:
given an initial coal blending and burning state, the carbon emission generated by different blending and burning modes is obtained by a neural network algorithm, the carbon emission generated by power generation of a thermal power generating unit, the carbon emission cost is changed, the coal blending and burning state is changed, the proportion of different coal types is exhausted, all the possibilities are exhausted, then the maximum benefit is taken, and the optimization goal is that:
maxw = power generation benefit-carbon emission cost-coal purchase cost
Constraint conditions:
Si＜Smax
Hi＜Hmax
I is the generation gain, the unit is yuan, P is the carbon emission cost, X i is the consumption of coal blending and coal blending, the unit is t, Q i is the corresponding coal purchase price, the unit is yuan/t, CAL min is the daily minimum combustion heat productivity of the thermal generator set, and the unit is GJ;
the using amount X i of the coal blended and burned coal is taken as a decision variable, the optimal blending and burned number of each coal variety is obtained through model calculation, the coal variety combination is carried out, the blending and burned state of the coal is changed, the optimization model is repeatedly executed, the maximum comprehensive benefit of all the blending and burned states is obtained, and the corresponding decision variable gives the blending and burned result of the coal.
2. The coal blending and burning optimization decision method based on real-time carbon emission monitoring of the thermal power generating unit according to claim 1, wherein in the first step, the method for collecting real-time carbon emission data of the coal-fired thermal power generating unit is as follows:
Data is gathered from a flue gas emission stack of a coal-fired thermal power unit, comprising: the volume concentration of CO 2 gas analyzed by carbon dioxide analysis equipment is adopted, and the calculation formula of the carbon emission concentration is as follows:
wherein: x is a CO 2 concentration conversion value, and the unit is mg/Nm 3; c is the measured value of CO 2 concentration, unit ppm; m is the molecular weight of CO 2; t is the temperature of the clean flue gas, and the unit is DEG C; p is the net smoke pressure, unit Pa;
The calculation formula of the carbon emission amount is:
Wherein: mc is the accumulated emission of CO 2 in the time T, and the unit is T; x is a CO 2 concentration conversion value, and the unit is mg/Nm 3; f is the flow rate of the clean flue gas, and the unit is Nm 3/h;
calculating the carbon emission amount in one day according to the above method;
obtaining the carbon emission amount of N days based on the carbon emission monitoring data of N days: e i, i is the i th day of observation, and the value of N is not less than 50.
3. The coal blending and burning optimization decision method based on the real-time carbon emission monitoring of the thermal power generating unit according to claim 2 is characterized in that in the method for collecting the real-time carbon emission data of the coal-fired thermal power generating unit, physicochemical experiment collection needs to be carried out on all coal types of the thermal power generating unit, wherein the coal data comprises the heat value u i of each coal type, the carbon dioxide emission factor CC i, the unit of tCO 2/GJ, the sulfur content S i and the moisture H i index, the daily consumption X i, the unit of t and the unit of unit price index Q i and the unit of yuan/t.
4. The coal blending and burning optimization decision method based on real-time carbon emission monitoring of the thermal power generating unit according to claim 1, wherein in the fourth step, the method for collecting real-time data of carbon price of the carbon emission right trading market is as follows:
calculating the daily carbon emission cost of the coal-fired thermal power unit, and acquiring the carbon price of the past 1 day on a carbon transaction platform by a device for acquiring real-time data of the carbon price of a national carbon emission right transaction market;
Case one: the carbon emission quota of the thermal power generating unit is K, the unit is t, the thermal power generating unit is used up, namely, the carbon emission quota K is less than or equal to 0, and the carbon emission cost is obtained by multiplying the emission amount by the carbon price;
And a second case: the carbon emission quota K of the thermal power generating unit is not used up and is more than 0, and the carbon emission cost is obtained by multiplying the emission quantity by the average unit carbon emission cost in the previous performance period;
The calculation formula of the carbon emission cost comprises the following steps:
the carbon emission cost is P, the unit is a unit, if the thermal power unit is in a case one, the formula (1) is substituted, P c1 is the current carbon price, the unit is a unit/t, if the thermal power unit is in a case two, the formula (2) is substituted, and P c2 is the average unit carbon emission cost of the previous caterpillar period, and the unit is a unit/t.
5. The coal blending and combustion optimization decision-making method and device based on real-time carbon emission monitoring of the thermal power generating unit according to claim 1, wherein in the seventh step, the coal blending and combustion scheme of the coal-fired thermal power generating unit is performed through the optimization result, and the method is specifically as follows:
Under the aim of the optimized result to display the maximum comprehensive benefit, the method is used for the coal blending and burning scheme of the coal-fired thermal power generating unit in the next day, the scheme is conducted to a coal blending control device to realize the coal blending and burning function, the optimized result in the next day is used as an initial state of the optimization in the third day, the coal blending proportion and the carbon emission monitoring result in the next day are incorporated into the neural network algorithm, and data are updated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111240635.5A CN113887827B (en) | 2021-10-25 | 2021-10-25 | Coal blending and burning optimization decision method based on real-time carbon emission monitoring of thermal power generating unit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111240635.5A CN113887827B (en) | 2021-10-25 | 2021-10-25 | Coal blending and burning optimization decision method based on real-time carbon emission monitoring of thermal power generating unit |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113887827A CN113887827A (en) | 2022-01-04 |
| CN113887827B true CN113887827B (en) | 2024-06-14 |
Family
ID=79013575
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111240635.5A Active CN113887827B (en) | 2021-10-25 | 2021-10-25 | Coal blending and burning optimization decision method based on real-time carbon emission monitoring of thermal power generating unit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113887827B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115115473B (en) * | 2022-07-19 | 2023-05-12 | 东南大学溧阳研究院 | BP neural network-based carbon emission quantitative calculation method for diesel generator set |
| CN115509126B (en) * | 2022-08-06 | 2023-10-20 | 福建华电福瑞能源发展有限公司福建分公司 | Mixed coal blending combustion method based on big data and deep mining technology |
| CN115222153B (en) * | 2022-08-30 | 2023-11-07 | 华能靖远热电有限公司 | Low-carbon scheduling optimizing method and system for thermal power enterprises |
| CN115564314A (en) * | 2022-11-24 | 2023-01-03 | 安徽蓝海之光科技有限公司 | Regional carbon emission intelligent measurement system based on low-carbon energy consumption optimization cooperation |
| CN116305769B (en) * | 2022-12-30 | 2024-03-29 | 数字双碳科技(合肥)有限公司 | Carbon emission data-based blending combustion proportion optimization method |
| CN117010728B (en) * | 2023-10-07 | 2024-01-02 | 华北电力大学 | Comprehensive power generation cost optimization method for thermal power enterprises |
| CN117745097B (en) * | 2023-12-22 | 2024-06-18 | 山东淄矿物产有限公司 | Management method of coal blending type self-management warehouse and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109325682A (en) * | 2018-09-18 | 2019-02-12 | 中国电力科学研究院有限公司 | A kind of fired power generating unit generation capacity allocation method considering carbon transaction cost |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109886471A (en) * | 2019-01-22 | 2019-06-14 | 中国大唐集团科学技术研究院有限公司火力发电技术研究院 | Fired power generating unit load distribution method based on neural network and intelligent optimization algorithm |
| US11398000B2 (en) * | 2019-05-20 | 2022-07-26 | Singularity Energy, Inc. | Methods and systems for machine-learning for prediction of grid carbon emissions |
| CN111091230A (en) * | 2019-11-20 | 2020-05-01 | 国电浙能宁东发电有限公司 | Scientific coal blending co-combustion system based on coal full-value chain management of coal-fired power plant |
| KR102271070B1 (en) * | 2020-03-31 | 2021-06-29 | 조선대학교산학협력단 | Method and apparatus for determining mixed coal combination |
| CN112682810B (en) * | 2020-12-28 | 2022-12-16 | 国电电力邯郸东郊热电有限责任公司 | Coal yard fire coal control system and method |
-
2021
- 2021-10-25 CN CN202111240635.5A patent/CN113887827B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109325682A (en) * | 2018-09-18 | 2019-02-12 | 中国电力科学研究院有限公司 | A kind of fired power generating unit generation capacity allocation method considering carbon transaction cost |
Non-Patent Citations (1)
| Title |
|---|
| 基于数字化平台的配煤掺烧优化方法;黄忠明;印琪民;付轩熠;韩万里;;上海电机学院学报;20190425(02);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113887827A (en) | 2022-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113887827B (en) | Coal blending and burning optimization decision method based on real-time carbon emission monitoring of thermal power generating unit | |
| Sun et al. | Capacity planning and optimization for integrated energy system in industrial park considering environmental externalities | |
| CN109345012B (en) | Park energy Internet operation optimization method based on comprehensive evaluation indexes | |
| CN110738530A (en) | user side-oriented electric energy substitution comprehensive benefit analysis method | |
| CN105870976B (en) | A kind of low-carbon dispatching method and device based on energy environment efficiency | |
| CN104613468A (en) | Circulating fluidized bedboiler combustion optimizing control method based on fuzzy adaptive inference | |
| CN103729691B (en) | Multi-target coal distribution method based on uniform design | |
| CN112907074B (en) | Comprehensive energy system user oriented energy efficiency sensitive index detection method and system | |
| CN115660918A (en) | Industrial park carbon emission calculation and prediction method | |
| CN111668878A (en) | Optimal configuration method and system for renewable micro-energy network | |
| CN110826868A (en) | Multi-energy coordination optimization operation evaluation method | |
| CN104751373A (en) | Environmental economic dispatching method considering polluted gas emission risk | |
| CN116542370A (en) | Park low-carbon economic operation method considering carbon capture and carbon transaction | |
| CN111553608A (en) | Benefit evaluation method for urban distribution network comprehensive energy system | |
| CN106056307A (en) | Electric power replacement technology comprehensive benefit assessment method based on comprehensive weighting method | |
| CN111949936A (en) | Method and system for evaluating comprehensive energy system of suburb | |
| Liu et al. | Planning mechanism design and benefit analysis of electric energy substitution: A case study of tobacco industry in Yunnan province, China | |
| CN115719180A (en) | Method for analyzing carbon reduction key influence factors of industrial park | |
| CN114912825A (en) | Carbon neutralization comprehensive evaluation method based on sparse logarithm principal component analysis | |
| CN113240330A (en) | Multi-dimensional value evaluation method and scheduling strategy for demand side virtual power plant | |
| CN112653180A (en) | Wind-fire-storage combined system environment economic dispatching method and system | |
| CN114958395B (en) | Waste heat utilization method and system for biomass carbonization furnace | |
| CN115496336A (en) | Thermal power generating unit benefit evaluation method under peak regulation auxiliary service market mechanism | |
| Jiang et al. | An integrated energy system evaluation method based on FAHP-EWM-TOPSIS | |
| CN117391734B (en) | Power generation cost prediction method based on support vector machine regression model |
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 |