Carbon emission reduction supervision method based on artificial intelligence

Abstract

The invention discloses a carbon emission reduction supervision method based on artificial intelligence, and relates to the field of data analysis, and the main scheme is that the total carbon emission X is calculated according to the actual fuel carbon emission XA, the steam turbine carbon emission XB, the auxiliary equipment carbon emission XC and the transport vehicle carbon emission XD, the carbon emission condition can be comprehensively and systematically evaluated from the overall operation perspective of a power generation enterprise, and the carbon emission reduction supervision method can be applied to the power generation enterprise. The problem that the accuracy of carbon emission calculation is reduced due to the fact that collected data are single, the influence of boiler combustion equipment on carbon emission is ignored and carbon emission generated by other power generation equipment is ignored at the same time is solved, whether the carbon emission meets the standard or not is judged according to the total carbon emission X and the carbon emission upper limit value YG, different supervision methods are selected according to the judgment result, and the accuracy of carbon emission calculation is improved. The condition that carbon emission of part of links reaches the standard and other links exceed the standard is avoided, supervision judgment is more accurate and effective, and meanwhile reasonable allocation of supervision resources and accurate implementation of supervision measures are facilitated.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a carbon emission reduction supervision method based on artificial intelligence. Background Art

[0002] In the field of thermal power generation, supervision of carbon emission reductions in thermal power plants based on artificial intelligence can improve the accuracy of carbon emission monitoring and accounting, and improve the equipment operation efficiency and energy utilization rate of thermal power plants.

[0003] The traditional working principle of carbon emission reduction supervision on thermal power plants is: use fuel flow sensors to collect the hourly coal input, calculate carbon emissions based on the coal input, and use carbon emissions to determine whether the carbon emission intensity of the thermal power generation company exceeds the limit set by the local environmental protection department.

[0004] The existing technology still has the following shortcomings: the collected data is single, ignoring the impact of boiler combustion equipment on carbon emissions, and ignoring the carbon emissions generated by other power generation equipment, resulting in reduced accuracy in calculating carbon emissions. Summary of the invention

[0005] 1. Technical issues to be resolved In view of the shortcomings of the prior art, the present invention provides a carbon emission reduction supervision method based on artificial intelligence, which calculates the total carbon emissions X according to the actual fuel carbon emissions XA, turbine carbon emissions XB, auxiliary equipment carbon emissions XC and transport vehicle carbon emissions XD, and judges the carbon emission level according to the total carbon emissions X and the carbon emission level threshold set, thereby solving the problem of single data collection, ignoring the impact of boiler combustion equipment on carbon emissions, and ignoring the carbon emissions generated by other power generation equipment, resulting in reduced accuracy in calculating carbon emissions.

[0006] (II) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: a carbon emission reduction supervision method based on artificial intelligence, comprising the following steps: Collect fuel data, boiler combustion equipment data, environmental data, fan data, steam turbine data, auxiliary equipment data, transportation vehicle data and carbon emission upper limit value YG of thermal power plants; The theoretical fuel carbon emissions WA are calculated based on the fuel data; the furnace temperature uniformity coefficient KA and the equipment efficiency coefficient KB are calculated based on the boiler combustion equipment data; the air density correction value KC is calculated based on the environmental data; the fan efficiency influence value KD is calculated based on the air density correction value KC and the fan data; the actual fuel carbon emissions XA are calculated based on the furnace temperature uniformity coefficient KA, the equipment efficiency coefficient KB, the fan efficiency influence value KD, the fuel carbon emissions WA and the boiler combustion equipment data; the turbine carbon emissions XB are calculated based on the turbine data; the auxiliary equipment correction value KE is calculated based on the auxiliary equipment datad , according to the auxiliary equipment data, auxiliary equipment correction value KE d Calculate the carbon emissions of auxiliary equipment XC based on the carbon emission factor of power generation MC; calculate the carbon emissions of transport vehicles XD based on the transport vehicle data; Calculate the total carbon emissions X based on the actual fuel carbon emissions XA, turbine carbon emissions XB, auxiliary equipment carbon emissions XC and transport vehicle carbon emissions XD; determine whether the carbon emissions meet the standards based on the total carbon emissions X and the carbon emissions upper limit YG, and select different supervision methods based on the judgment results.

[0007] In the preferred embodiment of the above-mentioned carbon emission reduction supervision method based on artificial intelligence: the method for calculating the theoretical fuel carbon emission WA is: Fuel data includes coal consumption AA m and coal carbon content AB m ; The theoretical fuel carbon emissions WA are calculated based on the fuel data according to the following formula:

[0008] Among them, AA m is the consumption of the mth type of coal, m is the serial number corresponding to different types of coal, and its value is [m, n]; n is the total number of types of coal, and its value is a positive integer; AB m is the carbon content of the mth type of coal.

[0009] In the preferred embodiment of the carbon emission reduction supervision method based on artificial intelligence, the method for calculating the furnace temperature uniformity coefficient KA and the equipment efficiency coefficient KB is: Boiler combustion equipment data including boiler furnace temperature CA a , equipment usage time CB, equipment service life CC and equipment maintenance frequency score CD; According to the boiler furnace temperature CA a The calculation formula of furnace temperature uniformity coefficient KA is as follows:

[0010] Among them, CA a is the temperature value of the ath sampling position in the boiler furnace, a is the serial number corresponding to different sampling positions in the boiler furnace, and its value is [1, b]; b is the total number of different sampling positions in the boiler furnace, and its value is a positive integer; The equipment efficiency coefficient KB is calculated based on the equipment usage time CB, equipment service life CC and equipment maintenance frequency score CD, based on the formula:

[0011] in, is the weight coefficient of the equipment life index, ranging from 0.3 to 0.7; is the weight coefficient for the equipment maintenance frequency score, ranging from 0.3 to 0.7; and .

[0012] In the above preferred embodiment of the carbon emission reduction supervision method based on artificial intelligence: the method for calculating the fan efficiency impact value KD is: Environmental data include reference altitude FA and actual altitude FB; The air density correction value KC is calculated based on the environmental data according to the following formula:

[0013] in, is the gas adiabatic index; Fan data include inlet static pressure EA, outlet static pressure EB, inlet temperature EC, inlet air volume EF and actual fan efficiency EH; The fan efficiency impact value KD is calculated based on the air density correction value KC and fan data, and the formula is: .

[0014] In the preferred embodiment of the above-mentioned carbon emission reduction supervision method based on artificial intelligence: the method for calculating the actual fuel carbon emission XA is: The boiler combustion equipment data also includes the actual combustion pressure value CE and the theoretical combustion pressure value CF; The actual fuel carbon emission XA is calculated based on the furnace temperature uniformity coefficient KA, equipment efficiency coefficient KB, fan efficiency influence value KD, actual combustion pressure value CE, theoretical combustion pressure value CF and fuel carbon emission WA, and the formula is: .

[0015] In the preferred embodiment of the carbon emission reduction supervision method based on artificial intelligence, the method for calculating the carbon emission XB of the steam turbine is: Steam turbine data include steam turbine power consumption MA, operating time MB, power generation carbon emission factor MC, input steam heat MD, torque ME and speed MF; The carbon emission of the steam turbine XB is calculated based on the steam turbine data according to the following formula: .

[0016] In the preferred embodiment of the above-mentioned carbon emission reduction supervision method based on artificial intelligence: the method for calculating the carbon emission XC of the auxiliary equipment is: Auxiliary equipment data includes auxiliary equipment power consumption DB d , Runtime DC d, actual load DD d , Rated load DE d and maintenance frequency score DF d ; According to the actual load DD d , Rated load DE d and maintenance frequency score DF d Calculation of auxiliary equipment correction value KE d , the formula based on is:

[0017] Among them, KE d is the auxiliary equipment correction value of the dth auxiliary equipment; DD d is the actual load of the dth auxiliary equipment; DE d is the rated load of the dth auxiliary equipment; DF d Score the maintenance frequency of the dth auxiliary equipment; According to the power consumption DB of the auxiliary equipment d , Runtime DC d , auxiliary equipment correction value KE and power generation carbon emission factor MC are used to calculate auxiliary equipment carbon emissions XC, based on the following formula:

[0018] Among them, DB d is the power consumption of the dth auxiliary device, d is the serial number corresponding to different auxiliary devices, and its value is [1, f]; f is the total number of auxiliary devices, and its value is a positive integer; DC d is the operating time of the dth auxiliary device.

[0019] In the preferred embodiment of the above-mentioned carbon emission reduction supervision method based on artificial intelligence: the method for calculating the carbon emission XD of the transport vehicle is: Transport vehicle data including fuel consumption LA h and fuel carbon emission factor LB h ; The carbon emissions of transport vehicles XD are calculated based on the transport vehicle data, and the formula is:

[0020] Among them, LA h is the fuel consumption of the h-th transport vehicle, h is the serial number corresponding to different transport vehicles, and its value is [1, i]; i is the total number of transport vehicles, and its value is a positive integer; LB h is the fuel carbon emission factor of the hth transport vehicle.

[0021] In the preferred embodiment of the above-mentioned carbon emission reduction supervision method based on artificial intelligence: the method for calculating the total carbon emission X is: The total carbon emissions X are calculated based on the actual fuel carbon emissions XA, turbine carbon emissions XB, auxiliary equipment carbon emissions XC and transportation vehicle carbon emissions XD. The formula is: .

[0022] In the preferred embodiment of the above-mentioned carbon emission reduction supervision method based on artificial intelligence: the method for judging whether the carbon emission meets the standard is: The total carbon emissions X and the upper limit of carbon emissions YG are used to determine whether the carbon emissions meet the standards. The standards are:

[0023] When the criteria are met, select supervision method 1; When the standards are not met, select supervision method two.

[0024] (III) Beneficial effects The present invention provides a carbon emission reduction supervision method based on artificial intelligence, which has the following beneficial effects: (1) By collecting the fuel data, boiler combustion equipment data, environmental data, fan data, steam turbine data, auxiliary equipment data, and transportation vehicle data of thermal power plants, carbon emissions can be comprehensively calculated from multiple aspects to more comprehensively reflect the carbon emissions of thermal power plants.

[0025] (2) Calculating the actual fuel carbon emissions XA based on the furnace temperature uniformity coefficient KA, equipment efficiency coefficient KB, fan efficiency impact value KD, fuel carbon emissions WA and boiler combustion equipment data can obtain more accurate carbon emission assessment results and provide a basis for formulating effective carbon emission reduction strategies. Calculating the turbine carbon emissions XB based on the turbine data can accurately determine the carbon emissions of the turbine during operation and better allocate emission reduction tasks and responsibilities. Based on the auxiliary equipment data and auxiliary equipment correction value KE d Calculating the carbon emissions XC of auxiliary equipment based on the carbon emission factor MC for power generation can help operators gain a deeper understanding of the impact of auxiliary equipment on carbon emissions, and help companies rationally allocate resources for equipment upgrades and renovations. Calculating the carbon emissions XD of transport vehicles based on transport vehicle data can help companies understand the carbon emissions of different vehicles under different working conditions, and then optimize vehicle scheduling plans, give priority to low-carbon emission vehicles to perform transportation tasks, and improve operational efficiency.

[0026] (3) The total carbon emissions X are calculated based on the actual fuel carbon emissions XA, turbine carbon emissions XB, auxiliary equipment carbon emissions XC and transport vehicle carbon emissions XD. This can comprehensively and systematically evaluate the carbon emissions from the overall operation perspective of the power generation enterprise, solving the problem of single data collection, ignoring the impact of boiler combustion equipment on carbon emissions, and ignoring the carbon emissions generated by other power generation equipment, which leads to reduced accuracy in calculating carbon emissions. Judging whether the carbon emissions meet the standards based on the total carbon emissions X and the upper limit of carbon emissions YG and selecting different regulatory methods based on the judgment results can help avoid the situation where the carbon emissions of some links meet the standards while covering up the exceeding of the standards in other links, making regulatory judgments more accurate and effective, and at the same time conducive to the rational allocation of regulatory resources and the precise implementation of regulatory measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A schematic diagram of the working steps of a carbon emission reduction supervision method based on artificial intelligence of the present invention; Figure 2 A schematic diagram of the steps of calculating the actual fuel carbon emission XA in a carbon emission reduction supervision method based on artificial intelligence of the present invention; Figure 3 The present invention is a schematic diagram of the steps of calculating the carbon emissions XC of auxiliary equipment in a carbon emission reduction supervision method based on artificial intelligence. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] See also Figure 1-3 The present invention provides a carbon emission reduction supervision method based on artificial intelligence, comprising the following steps: Step 1: Collect the fuel data, boiler combustion equipment data, environmental data, fan data, turbine data, auxiliary equipment data, transportation vehicle data and the carbon emission upper limit value YG stipulated by the environmental protection department of the thermal power plant.

[0030] Combined with the content of step 1: By collecting the fuel data, boiler combustion equipment data, environmental data, fan data, turbine data, auxiliary equipment data, and transportation vehicle data of thermal power plants, it is possible to comprehensively calculate carbon emissions from multiple aspects and more comprehensively reflect the carbon emissions of thermal power plants.

[0031] Step 2: Calculate the theoretical fuel carbon emissions WA based on the fuel data, calculate the furnace temperature uniformity coefficient KA and the equipment efficiency coefficient KB based on the boiler combustion equipment data, calculate the air density correction value KC based on the environmental data, calculate the fan efficiency influence value KD based on the air density correction value KC and the fan data, calculate the actual fuel carbon emissions XA based on the furnace temperature uniformity coefficient KA, the equipment efficiency coefficient KB, the fan efficiency influence value KD, the fuel carbon emissions WA and the boiler combustion equipment data; calculate the turbine carbon emissions XB based on the turbine data; calculate the auxiliary equipment correction value KE based on the auxiliary equipment data d , according to the auxiliary equipment data, auxiliary equipment correction value KE d The carbon emissions of auxiliary equipment XC are calculated based on the carbon emission factor of power generation MC; the carbon emissions of transport vehicles XD are calculated based on the transport vehicle data.

[0032] Step 2 includes the following steps: Step 201: The method for calculating the theoretical fuel carbon emission WA is: Fuel data includes coal consumption AA m and coal carbon content AB m .

[0033] It should be noted that coal consumption AA m It refers to the mass or volume of various types of coal used in the process of thermal power generation, such as anthracite, bituminous coal, lignite, etc. The method of obtaining it is: a belt scale will be installed on the conveyor belt, which can measure the coal flow through the belt in real time, and obtain the coal consumption by integrating the flow over time. m It refers to the mass fraction of carbon element in each type of coal. It is the key factor that determines the carbon emissions when coal is burned. It can be obtained by referring to the coal quality inspection report.

[0034] The theoretical fuel carbon emissions WA are calculated based on the fuel data according to the following formula:

[0035] Among them, AA m is the consumption of the mth type of coal, m is the serial number corresponding to different types of coal, and its value is [m, n]; n is the total number of types of coal, and its value is a positive integer; AB m is the carbon content of the mth type of coal.

[0036] It should be noted that the operating principle of this formula is: According to the chemical reaction equation of carbon combustion to generate carbon dioxide, the amount of carbon dioxide generated by each gram of carbon combustion is Grams, further multiplied by the actual coal consumption, to obtain the theoretical fuel carbon emissions WA.

[0037] Step 202: The method for calculating the furnace temperature uniformity coefficient KA and the equipment efficiency coefficient KB is: Boiler combustion equipment data including boiler furnace temperature CA a , equipment usage time CB, equipment service life CC and equipment maintenance frequency score CD.

[0038] It should be noted that the boiler furnace temperature CA a It refers to the temperature reached when the fuel is burned in the furnace area inside the boiler. It is a key parameter reflecting the combustion status of the boiler. It is obtained by installing thermocouples at different positions in the furnace. Equipment use time CB refers to the time from the start of operation of the boiler equipment to the current moment, reflecting the degree of equipment aging. The way to obtain it is: by querying the boiler's operation log, operation record and other documents, obtain the start time and stop time of the equipment, calculate the difference between the equipment's stop time and start time each time and accumulate them, and obtain the equipment use time CB. Equipment service life CC refers to the expected time from the start of operation of the boiler equipment to the inability to continue normal use due to performance degradation, frequent failures, and excessive maintenance costs. It is obtained by consulting the product manual. Equipment maintenance frequency score CD is a quantitative evaluation of the frequency of boiler equipment maintenance, reflecting the reliability and operation stability of the equipment. The way to obtain it is: by consulting the maintenance record archive of the boiler equipment, the number of equipment maintenance in the past year is counted. When the number is less than 2 times, the equipment maintenance frequency score CD is 1 point, when the number is between 2 and 5 times, the equipment maintenance frequency score CD is 3 points, and when the number is greater than 5 times, the equipment maintenance frequency score CD is 5 points.

[0039] According to the boiler furnace temperature CA a The calculation formula of furnace temperature uniformity coefficient KA is as follows:

[0040] Among them, CA a is the temperature value of the ath sampling position in the boiler furnace, a is the serial number corresponding to different sampling positions in the boiler furnace, and its value is [1, b]; b is the total number of different sampling positions in the boiler furnace, and its value is a positive integer.

[0041] It should be noted that this formula measures the uniformity of temperature distribution in the boiler furnace by calculating the standard deviation of temperature values ​​at different positions in the boiler furnace. The higher the standard deviation, the more uneven the temperature distribution and the smaller the furnace temperature uniformity coefficient KA.

[0042] The equipment efficiency coefficient KB is calculated based on the equipment usage time CB, equipment service life CC and equipment maintenance frequency score CD, based on the formula:

[0043] in, is the weight coefficient of the equipment life index, ranging from 0.3 to 0.7, and is determined according to the importance of the equipment life index to the equipment efficiency coefficient KB; is the weight coefficient of the equipment maintenance frequency score CD, which is between 0.3 and 0.7 and is determined according to the importance of the equipment maintenance frequency score CD to the equipment efficiency coefficient KB; and .

[0044] It should be noted that this formula measures the aging degree of the equipment by calculating the ratio of the equipment usage time CB to the equipment service life CC, and comprehensively considers the equipment aging degree and the equipment maintenance frequency score CD through a weighted method to obtain the equipment efficiency coefficient KB.

[0045] Step 203: The method for calculating the fan efficiency impact value KD is: The environmental data includes a reference altitude FA and an actual altitude FB.

[0046] It should be noted that the reference altitude FA refers to the benchmark altitude used to compare and measure changes in meteorological elements such as air pressure, temperature, and humidity. In this solution, the altitude of the mean sea level is set to 0 meters as the reference altitude FA. The actual altitude FB refers to the vertical height of the location of the thermal power plant relative to the mean sea level, which can be measured by GPS equipment.

[0047] The air density correction value KC is calculated based on the environmental data according to the following formula:

[0048] in, is the gas adiabatic index, for air, Take 1.4; It should be noted that this formula is based on the principle that the air pressure drops by 10 kPa for every 1000 m increase in altitude. The air pressure correction coefficient of the altitude where the thermal power plant is located is calculated. At the same time, based on the principle that altitude affects air pressure and then affects air density, the gas adiabatic index is introduced to obtain the air density correction value KC.

[0049] The fan data includes inlet static pressure EA, outlet static pressure EB, inlet temperature EC, inlet air volume EF and actual fan efficiency EH.

[0050] It should be noted that the inlet static pressure EA refers to the static pressure value of the air at the inlet of the fan, which reflects the pressure state when the fan inhales air. Static pressure refers to the pressure between air molecules when the dynamic pressure generated by air flow is not considered. The inlet static pressure EA is measured and obtained by installing a static pressure sensor at the inlet of the fan. The outlet static pressure EB refers to the static pressure value of the air at the outlet of the fan, which reflects the static pressure energy of the air at the outlet after the fan does work on the air. It is measured and obtained by installing a static pressure sensor at the outlet of the fan. The inlet temperature EC refers to the temperature of the air entering the fan. The air temperature will affect the density and viscosity of the air, and thus affect the performance of the fan. The inlet temperature EC is measured and obtained by installing a thermocouple or a thermistor thermometer at the inlet of the fan. The inlet air volume EF refers to the volume of air entering the fan per unit time, reflecting the ventilation and conveying capacity of the fan. The method of obtaining it is: put the air volume hood at the inlet of the fan. There are multiple wind speed sensors inside the air volume hood, which can measure the wind speed at different positions. The control system of the air volume hood will automatically process the wind speed data measured by each sensor, calculate the average wind speed, and then further calculate the product of the cross-sectional area of ​​the hood and the average wind speed as the inlet air volume EF. The actual fan efficiency EH refers to the ratio of the actual useful work output of the fan to the input power, reflecting the effectiveness of the fan in converting the input electrical energy or mechanical energy into air kinetic energy and pressure energy. The method of obtaining it is: use a power meter to measure the input electrical power of the fan, calculate the output useful work according to the formula EF×(EB-EA), and calculate the ratio of the output useful work to the input electrical power as the actual fan efficiency EH.

[0051] The fan efficiency impact value KD is calculated based on the air density correction value KC and fan data, and the formula is:

[0052] It should be noted that the operating principle of this formula is: is the fan efficiency under ideal gas conditions. By calculating the ratio of the fan efficiency under ideal gas conditions to the actual fan efficiency EH, the fan ventilation efficiency is obtained. Meanwhile, considering the influence of air density, the fan efficiency influence value KD is obtained.

[0053] Step 204: The method for calculating the actual fuel carbon emission XA is: The boiler combustion equipment data also includes an actual combustion pressure value CE and a theoretical combustion pressure value CF.

[0054] It should be noted that the actual combustion pressure value CE refers to the actual pressure generated in the combustion chamber during the operation of the boiler combustion equipment. It is measured by installing a pressure sensor in the boiler combustion chamber and is measured in Pascals. The theoretical combustion pressure value CF is the pressure value that should be reached in the combustion chamber based on theoretical calculations such as the type and quantity of fuel and the stoichiometric relationship of combustion. It is an important reference indicator for evaluating whether the actual combustion process is close to the ideal state. It is determined based on the chemical reaction equation of fuel combustion and the ideal gas state equation. The specific calculation formula is: Theoretical combustion pressure value CF = (coal mass × 12 / coal carbon content × ideal gas constant × boiler combustion chamber temperature) / combustion chamber volume, where the ideal gas constant is 8.314 joules per mole Kelvin.

[0055] The actual fuel carbon emission XA is calculated based on the furnace temperature uniformity coefficient KA, equipment efficiency coefficient KB, fan efficiency influence value KD, actual combustion pressure value CE, theoretical combustion pressure value CF and fuel carbon emission WA, and the formula is:

[0056] It should be noted that the operating principle of this formula is: the more uniform the furnace temperature, the higher the efficiency of the boiler combustion equipment, the higher the fan efficiency, the closer the actual combustion pressure value is to the ideal state, the more conducive it is to achieving complete combustion of the fuel, and the less indirect increase in carbon emissions. This formula adjusts the fuel carbon emissions WA through the furnace temperature uniformity, equipment efficiency, fan efficiency and actual combustion pressure to obtain the actual fuel carbon emissions XA.

[0057] Step 205: The method for calculating the carbon emission XB of the steam turbine is: The steam turbine data include steam turbine power consumption MA, operating time MB, power generation carbon emission factor MC, input steam heat MD, torque ME and speed MF.

[0058] It should be noted that the turbine power consumption MA refers to the additional energy consumed by the turbine during operation to ensure its normal operation. The method of obtaining it is: install an electric meter on the power supply line of the turbine auxiliary equipment, and calculate the difference between the readings of the electric meter at the beginning and end of the operation to obtain the turbine power consumption MA, in kilowatt-hours. The operating time MB refers to the time from the start of operation to the stop of operation of the turbine. The method of obtaining it is: obtain the time of each start and stop of the turbine through the operation record system of the turbine, calculate the difference between the two and accumulate them to obtain the operating time MB. The power generation carbon emission factor MC is used to measure the carbon emission level corresponding to the unit of electricity consumption. It is a key parameter for the calculation of electricity carbon emissions. It is determined by referring to the carbon emission factor data released by the Ministry of Ecology and Environment, the National Bureau of Statistics and other institutions, and the unit is kg of carbon dioxide / kilowatt-hour. The input steam heat MD refers to the heat carried by the steam entering the steam turbine. It is obtained by: obtaining the temperature value TA and pressure value PA of the steam entering the steam turbine through the temperature sensor and pressure sensor installed at the inlet of the steam pipe, consulting the steam property table, obtaining the enthalpy value HA of the steam at the temperature value TA and pressure value PA, obtaining the steam flow rate MA through the steam flow meter, and calculating the input steam heat MD according to the formula HA×MA. Torque ME refers to the torque on the turbine shaft, which is directly measured by the torque sensor installed on the turbine shaft, and the unit is Newton•meter. Speed ​​MF refers to the number of rotations of the turbine rotor per minute, which is directly measured by the speed sensor installed on the turbine shaft, and the unit is revolutions per minute.

[0059] The carbon emission of the steam turbine XB is calculated based on the steam turbine data according to the following formula:

[0060] It should be noted that the operating principle of this formula is: is the carbon emission theoretically produced by the steam turbine in the steam power link, is the thermal efficiency of the steam turbine. By considering the influence of thermal efficiency on carbon emissions, the carbon emissions of the steam turbine XB are obtained.

[0061] Step 206: The method for calculating the carbon emission XC of the auxiliary equipment is: Auxiliary equipment data includes auxiliary equipment power consumption DB d , Runtime DC d , actual load DD d , Rated load DE d and maintenance frequency score DF d .

[0062] It should be noted that the power consumption DB of the auxiliary equipment dRefers to the electric energy consumed per unit time by auxiliary equipment other than steam power during operation, reflecting the speed at which the equipment consumes energy. It is measured and obtained through a power meter installed on the power supply line of the auxiliary equipment. The auxiliary equipment includes boiler combustion equipment, powder making equipment, oil system equipment, and dust removal equipment. d It is the time that the auxiliary equipment experiences from starting to stopping, including the cumulative time of various states such as normal operation, no-load operation, and standby. It is an important indicator to measure the degree of equipment use and working life. The equipment control system obtains the start time and stop time of each equipment, calculates the difference between the two and accumulates them to get the running time DC d . Actual load DD d Refers to the actual workload of the auxiliary equipment during operation, reflecting the actual working intensity and operating status of the equipment. The method of obtaining it is: using a voltmeter and an ammeter to measure the actual voltage and current values ​​of the auxiliary equipment, and calculating the product of the actual voltage and current values ​​as the actual load DD d , in watts. Rated load DE d It is the maximum load value that the auxiliary equipment must be designed and manufactured to operate safely and stably. It is an important parameter for the normal operation of the equipment. It can be obtained by referring to the product manual, technical specification sheet or equipment nameplate of the equipment. The unit is watt. Maintenance Frequency Score DF d It is a quantitative evaluation of the maintenance of auxiliary equipment, reflecting the maintenance degree and reliability of the equipment. The method of obtaining it is: by checking the maintenance records, the number of maintenance times of the auxiliary equipment in a month is obtained. When the number is 0, the maintenance frequency score DF d 1 point, when the number is 1 to 2, the maintenance frequency score DF d 3 points. When the number is greater than 2, the maintenance frequency score DF d is 5 points.

[0063] According to the actual load DD d , Rated load DE d and maintenance frequency score DF d Calculation of auxiliary equipment correction value KE d , the formula based on is:

[0064] Among them, KE d is the auxiliary equipment correction value of the dth auxiliary equipment; DD d is the actual load of the dth auxiliary equipment; DE d is the rated load of the dth auxiliary equipment; DF d Score the maintenance frequency of the dth auxiliary equipment.

[0065] It should be noted that this formula obtains the auxiliary equipment correction value KE by comprehensively considering the actual load rate and maintenance times of the auxiliary equipment. d .

[0066] According to the power consumption DB of the auxiliary equipment d , Runtime DC d , auxiliary equipment correction value KE and power generation carbon emission factor MC are used to calculate auxiliary equipment carbon emissions XC, based on the following formula:

[0067] Among them, DB d is the power consumption of the dth auxiliary device, d is the serial number corresponding to different auxiliary devices, and its value is [1, f]; f is the total number of auxiliary devices, and its value is a positive integer; DC d is the operating time of the dth auxiliary device.

[0068] It should be noted that the operating principle of this formula is: is the theoretical carbon emission of the auxiliary equipment, which is adjusted by the auxiliary equipment correction value KE to obtain the auxiliary equipment carbon emission XC.

[0069] Step 207: The method for calculating the carbon emission XD of the transport vehicle is: Transport vehicle data including fuel consumption LA h and fuel carbon emission factor LB h .

[0070] It should be noted that the fuel consumption LA h Refers to the amount of fuel consumed by a transport vehicle during operation, measured in liters, and is obtained by calculating the difference between the fuel gauge readings before and after the transport journey. h It refers to the carbon dioxide emissions generated by the complete combustion of unit mass or unit volume of fuel. It is a key parameter for evaluating the carbon emission level of vehicles. It is determined by referring to the carbon emission factor data released by the Ministry of Ecology and Environment, the National Bureau of Statistics or the Chinese Academy of Environmental Sciences. When the fuel is gasoline, the fuel carbon emission factor LB h When the fuel is diesel, the fuel carbon emission factor LB is 2.3 kg CO2 / L. h It is 2.6 kg of carbon dioxide per liter.

[0071] The carbon emissions of transport vehicles XD are calculated based on the transport vehicle data, and the formula is:

[0072] Among them, LA his the fuel consumption of the h-th transport vehicle, h is the serial number corresponding to different transport vehicles, and its value is [1, i]; i is the total number of transport vehicles, and its value is a positive integer; LB h is the fuel carbon emission factor of the hth transport vehicle.

[0073] It should be noted that this formula obtains the carbon emissions of transport vehicles XD by accumulating the carbon emissions of each transport vehicle.

[0074] Combined with the contents of step 201 to step 207: According to the furnace temperature uniformity coefficient KA, equipment efficiency coefficient KB, fan efficiency impact value KD, fuel carbon emissions WA and boiler combustion equipment data, the actual fuel carbon emissions XA can be calculated to obtain more accurate carbon emission assessment results, providing a basis for formulating effective carbon emission reduction strategies. Based on the turbine data, the carbon emissions of the turbine XB can be calculated to accurately determine the carbon emissions of the turbine during operation, and better allocate emission reduction tasks and responsibilities. According to the auxiliary equipment data and the auxiliary equipment correction value KE d Calculating the carbon emissions XC of auxiliary equipment based on the carbon emission factor MC for power generation can help operators gain a deeper understanding of the impact of auxiliary equipment on carbon emissions, and help companies rationally allocate resources for equipment upgrades and renovations. Calculating the carbon emissions XD of transport vehicles based on transport vehicle data can help companies understand the carbon emissions of different vehicles under different working conditions, and then optimize vehicle scheduling plans, give priority to low-carbon emission vehicles to perform transportation tasks, and improve operational efficiency.

[0075] Step 3: Calculate the total carbon emissions X based on the actual fuel carbon emissions XA, turbine carbon emissions XB, auxiliary equipment carbon emissions XC and transport vehicle carbon emissions XD; determine whether the carbon emissions meet the standards based on the total carbon emissions X and the carbon emissions upper limit YG, and select different supervision methods based on the judgment results.

[0076] Step 301: The method for calculating the total carbon emissions X is: The total carbon emissions X are calculated based on the actual fuel carbon emissions XA, turbine carbon emissions XB, auxiliary equipment carbon emissions XC and transportation vehicle carbon emissions XD. The formula is:

[0077] It should be noted that this formula obtains the total carbon emissions X by adding the carbon emissions from fuel production and the carbon emissions generated by different equipment.

[0078] Step 302: The method for determining whether the carbon emissions meet the standards is: The total carbon emissions X and the upper limit of carbon emissions YG are used to determine whether the carbon emissions meet the standards. The standards are:

[0079] Among them, the carbon emission upper limit value YG refers to the maximum upper limit value of greenhouse gas emissions that the enterprise is allowed to emit in the current region and time period. The environmental protection department will formulate a carbon emission quota allocation plan based on national carbon emission control targets, regional economic development conditions, industry characteristics and other factors. Enterprises can obtain the carbon emission upper limit value YG of their own by reviewing relevant documents, such as the "National Carbon Emission Trading Power Generation Industry Quota Total and Allocation Plan for 2023 and 2024".

[0080] When the standards are met, the first supervision method is selected, which is: thermal power plants are required to submit carbon emission reports to the regulatory authorities at prescribed time intervals, such as monthly, quarterly or annually. At the same time, the main production equipment of thermal power plants, such as boilers, steam turbines, generators, etc., are inspected to check whether the equipment is in good operating condition and whether there are abnormal conditions that affect carbon emissions. If the thermal power plants are found to have falsified carbon emission data, failed to install or operate monitoring equipment as required, and failed to implement emission reduction measures during the supervision process, the regulatory authorities will impose severe penalties in accordance with the law, including fines, orders to rectify within a time limit, restrictions on production, and revocation of pollution discharge permits.

[0081] When the standards are not met, the second supervision method is selected, which is specifically: restricting the production activities of thermal power plants, such as requiring them to reduce the operating time of units and reduce the power generation load, in order to control carbon emissions. At the same time, thermal power plants are required to formulate and implement emission reduction plans, clarify emission reduction targets, measures and timetables, such as accelerating energy-saving and emission reduction transformation, improving energy utilization efficiency, and increasing the proportion of clean energy use. Law enforcement personnel will inspect the preparation and implementation of enterprise data quality control plans through on-site visits and data review, inspect the operation management and calibration of metering equipment, the storage and traceability of data sources, and the standardization of coal sample collection, preparation, and retention, etc., to urge enterprises to ensure that the data is true, accurate, and complete, and prevent misjudgment of carbon emissions due to data problems.

[0082] Combined with the contents of step 301 to step 302: The total carbon emissions X are calculated based on the actual fuel carbon emissions XA, turbine carbon emissions XB, auxiliary equipment carbon emissions XC and transport vehicle carbon emissions XD. This can comprehensively and systematically evaluate carbon emissions from the overall operation perspective of the power generation enterprise, solve the problem of single data collection, ignoring the impact of boiler combustion equipment on carbon emissions, and ignoring the carbon emissions generated by other power generation equipment, resulting in reduced accuracy in calculating carbon emissions. Judging whether carbon emissions meet the standards based on the total carbon emissions X and the upper limit of carbon emissions YG and selecting different regulatory methods based on the judgment results can help avoid the situation where carbon emissions in some links meet the standards while exceeding the standards in other links, making regulatory judgments more accurate and effective, and at the same time conducive to the rational allocation of regulatory resources and the precise implementation of regulatory measures.

[0083] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware or in combination with computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0084] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0085] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A carbon emission reduction supervision method based on artificial intelligence, characterized by: The following steps are involved: Collect fuel data, boiler combustion equipment data, environmental data, fan data, steam turbine data, auxiliary equipment data, transportation vehicle data and carbon emission upper limit value YG of thermal power plants; The theoretical fuel carbon emissions WA are calculated based on the fuel data; the furnace temperature uniformity coefficient KA and the equipment efficiency coefficient KB are calculated based on the boiler combustion equipment data; the air density correction value KC is calculated based on the environmental data; the fan efficiency influence value KD is calculated based on the air density correction value KC and the fan data; the actual fuel carbon emissions XA are calculated based on the furnace temperature uniformity coefficient KA, the equipment efficiency coefficient KB, the fan efficiency influence value KD, the fuel carbon emissions WA and the boiler combustion equipment data; the turbine carbon emissions XB are calculated based on the turbine data; the auxiliary equipment correction value KE is calculated based on the auxiliary equipment data d , according to the auxiliary equipment data, auxiliary equipment correction value KE d and the power generation carbon emission factor MC to calculate the auxiliary equipment carbon emission XC; Calculate the carbon emissions of transport vehicles XD based on transport vehicle data; Calculate the total carbon emissions X based on the actual fuel carbon emissions XA, turbine carbon emissions XB, auxiliary equipment carbon emissions XC and transport vehicle carbon emissions XD; determine whether the carbon emissions meet the standards based on the total carbon emissions X and the carbon emissions upper limit YG, and select different supervision methods based on the judgment results.

2. According to claim 1, a carbon emission reduction supervision method based on artificial intelligence is characterized in that: The method for calculating the theoretical fuel carbon emissions WA is: Fuel data includes coal consumption AA m and coal carbon content AB m ; The theoretical fuel carbon emissions WA are calculated based on the fuel data according to the following formula: Among them, AA m is the consumption of the mth type of coal, m is the serial number corresponding to different types of coal, and its value is [m, n]; n is the total number of types of coal, and its value is a positive integer; AB m is the carbon content of the mth type of coal.

3. The method for monitoring carbon emission reduction based on artificial intelligence according to claim 2 is characterized in that: The method for calculating the furnace temperature uniformity coefficient KA and the equipment efficiency coefficient KB is: Boiler combustion equipment data including boiler furnace temperature CA a , equipment usage time CB, equipment service life CC and equipment maintenance frequency score CD; According to the boiler furnace temperature CA a The calculation of furnace temperature uniformity coefficient KA is based on the following formula: Among them, CA a is the temperature value of the ath sampling position in the boiler furnace, a is the serial number corresponding to different sampling positions in the boiler furnace, and its value is [1, b]; b is the total number of different sampling positions in the boiler furnace, and its value is a positive integer; The equipment efficiency coefficient KB is calculated based on the equipment usage time CB, equipment service life CC and equipment maintenance frequency score CD, based on the formula: in, is the weight coefficient of the equipment life index, ranging from 0.3 to 0.7; is the weight coefficient for the equipment maintenance frequency score, ranging from 0.3 to 0.7; and .

4. The method for monitoring carbon emission reduction based on artificial intelligence according to claim 3 is characterized in that: The method for calculating the fan efficiency impact value KD is: Environmental data include reference altitude FA and actual altitude FB; The air density correction value KC is calculated based on the environmental data according to the following formula: in, is the gas adiabatic index; Fan data include inlet static pressure EA, outlet static pressure EB, inlet temperature EC, inlet air volume EF and actual fan efficiency EH; The fan efficiency impact value KD is calculated based on the air density correction value KC and fan data, and the formula is: 。 5. The method for monitoring carbon emission reduction based on artificial intelligence according to claim 4 is characterized in that: The method for calculating the actual fuel carbon emissions XA is: The boiler combustion equipment data also includes the actual combustion pressure value CE and the theoretical combustion pressure value CF; The actual fuel carbon emission XA is calculated based on the furnace temperature uniformity coefficient KA, equipment efficiency coefficient KB, fan efficiency influence value KD, actual combustion pressure value CE, theoretical combustion pressure value CF and fuel carbon emission WA. The formula is: 。 6. The method for monitoring carbon emission reduction based on artificial intelligence according to claim 5 is characterized in that: The method for calculating the carbon emissions XB of steam turbine is: Steam turbine data include steam turbine power consumption MA, operating time MB, power generation carbon emission factor MC, input steam heat MD, torque ME and speed MF; The carbon emission of the steam turbine XB is calculated based on the steam turbine data according to the following formula: 。 7. The method for monitoring carbon emission reduction based on artificial intelligence according to claim 6 is characterized in that: The method for calculating the carbon emissions XC of auxiliary equipment is: Auxiliary equipment data includes auxiliary equipment power consumption DB d , Runtime DC d , actual load DD d , Rated load DE d and maintenance frequency score DF d ; According to the actual load DD d , Rated load DE d and maintenance frequency score DF d Calculation of auxiliary equipment correction value KE d , the formula based on is: Among them, KE d is the auxiliary equipment correction value of the dth auxiliary equipment; DD d is the actual load of the dth auxiliary equipment; DE d is the rated load of the dth auxiliary equipment; DF d Score the maintenance frequency of the dth auxiliary equipment; According to the power consumption DB of the auxiliary equipment d , Runtime DC d , auxiliary equipment correction value KE and power generation carbon emission factor MC are used to calculate auxiliary equipment carbon emissions XC, based on the following formula: Among them, DB d is the power consumption of the dth auxiliary device, d is the serial number corresponding to different auxiliary devices, and its value is [1, f]; f is the total number of auxiliary devices, and its value is a positive integer; DC d is the operating time of the dth auxiliary device.

8. The method for monitoring carbon emission reduction based on artificial intelligence according to claim 7 is characterized in that: The method for calculating the carbon emissions XD of transport vehicles is: Transport vehicle data including fuel consumption LA h and fuel carbon emission factor LB h ; The carbon emissions of transport vehicles XD are calculated based on the transport vehicle data, and the formula is: Among them, LA h is the fuel consumption of the h-th transport vehicle, h is the serial number corresponding to different transport vehicles, and its value is [1, i]; i is the total number of transport vehicles, and its value is a positive integer; LB h is the fuel carbon emission factor of the hth transport vehicle.

9. The method for monitoring carbon emission reduction based on artificial intelligence according to claim 8 is characterized in that: The method for calculating the total carbon emissions X is: The total carbon emissions X are calculated based on the actual fuel carbon emissions XA, turbine carbon emissions XB, auxiliary equipment carbon emissions XC and transportation vehicle carbon emissions XD. The formula is: 。 10. The method for monitoring carbon emission reduction based on artificial intelligence according to claim 9 is characterized in that: The method to determine whether carbon emissions meet the standards is: The total carbon emissions X and the upper limit of carbon emissions YG are used to determine whether the carbon emissions meet the standards. The standards are: When the criteria are met, select supervision method 1; When the standards are not met, select supervision method two.

Images