阅读说明：本技术 一种碳排放强度测量方法、设备及介质 (Carbon emission intensity measuring method, equipment and medium ) 是由 卢建刚 李波 林玥廷 于 2021-08-03 设计创作，主要内容包括：本发明公开了一种碳排放强度测量方法、设备及介质,该方法包括：根据实时获取的锅炉热效率与汽轮机热耗率,确定燃烧CO-(2)排放强度值；结合预设的脱硫CO-(2)排放强度值与所述燃烧CO-(2)排放强度值,计算CO-(2)排放强度值；将所述CO-(2)排放强度值输入预设的BP神经网络训练,构建改进的BP神经网络；将实时获取的煤质参数、运行参数及煤耗参数输入所述改进的BP神经网络,获取实时碳排放强度值。本发明实时获取运行数据确定燃烧CO-(2)排放强度值,并结合预设的改进BP神经网络进行训练,获取实时碳排放强度值,提高碳排放强度测量的准确度。(The invention discloses a method, equipment and a medium for measuring carbon emission intensity, wherein the method comprises the following steps: determining combustion CO according to the boiler heat efficiency and the steam turbine heat consumption rate acquired in real time 2 A discharge intensity value; combined with pre-set desulphurised CO 2 Emission intensity value and the combustion CO 2 Emission intensity value, calculating CO 2 A discharge intensity value; introducing the CO into a reaction vessel 2 Inputting the emission intensity value into a preset BP neural network for training, and constructing an improved BP neural network; and inputting the coal quality parameters, the operation parameters and the coal consumption parameters which are obtained in real time into the improved BP neural network to obtain a real-time carbon emission intensity value. The invention obtains operation data in real time to determine combustion CO 2 And the emission intensity value is trained by combining a preset improved BP neural network, so that a real-time carbon emission intensity value is obtained, and the accuracy of carbon emission intensity measurement is improved.)

1. A carbon emission intensity measurement method, characterized by comprising:

determining combustion CO according to the boiler heat efficiency and the steam turbine heat consumption rate acquired in real time₂A discharge intensity value;

combined with pre-set desulphurised CO₂Emission intensity value and the combustion CO₂Emission intensity value, calculating CO₂A discharge intensity value;

introducing the CO into a reaction vessel₂Inputting the emission intensity value into a preset BP neural network for training, and constructing an improved BP neural network;

and inputting the coal quality parameters, the operation parameters and the coal consumption parameters which are obtained in real time into the improved BP neural network to obtain a real-time carbon emission intensity value.

2. The carbon emission intensity measuring method according to claim 1, further comprising, before the obtaining of the boiler thermal efficiency and the turbine thermal efficiency in real time, the steps of:

real-time acquisition of heat loss of exhaust smokeValue q₂Incomplete combustion heat loss value q of combustible gas₃Solid incomplete combustion heat loss value q₄Boiler heat dissipation loss value q₅And physical heat loss value q of ash₆；

Calculating the thermal efficiency eta of the boiler according to the following formula_g；

η_g＝100-(q₂+q₃+q₄+q₅+q₆)。

3. The carbon emission intensity measuring method according to claim 2, further comprising, before the obtaining of the boiler thermal efficiency and the turbine thermal efficiency in real time, the steps of:

real-time acquisition of the enthalpy h of the main steam entering the turbine_msFlow G of hot reheat steam into the steam turbine_rhrEnthalpy h of hot reheat steam of a steam turbine_rhrHigh pressure cylinder exhaust flow G_rhlEnthalpy h of cold reheat steam of steam turbine_rhlMake-up water flow G_maEnthalpy of make-up water h_maFinal feed rate G_fwFinal feed water enthalpy h_fwFlow G of superheated desuperheated water_ssReheat desuperheating water flow G_rsEnthalpy of superheated desuperheated water h_ssAnd enthalpy of reheated desuperheated water h_rs；

Calculating the heat consumption Q of the steam turbine according to the following formula₀；

Q₀＝G₀×h_ms+G_rhr×h_rhr-G_rhl×h_rhl+G_ma×h_ma-G_fw×h_fw-G_ss×h_ss-G_rs×h_rs；

Incorporating said steam turbine heat consumption Q₀Determining the heat consumption rate q of the steam turbine together with the electric load W of the generator;

calculating the heat rate q of the steam turbine according to the following formula;

q＝Q₀/(1000*W)。

4. the method of claim 3, wherein the carbon emission intensity is measuredCharacterised in that the determination of combustion CO₂Emission intensity values, in particular:

obtaining coal consumption B and carbon content C of coal as fired_arSolid incomplete combustion heat loss value q₄Receiving base calorific value Q of actual coal as fired in power plant_arAnd a molar mass conversion factor R;

calculating the combustion CO according to the following formula₂Emission intensity value W₁；

B＝b_f*W*1000*29.307/Q_ar；

In the formula, b_fIndicating standard coal consumption rate, eta, of electricity generation_gExpressing the thermal efficiency, eta, of the boiler_gdAnd q represents the heat consumption rate of the steam turbine.

5. The carbon emission intensity measurement method of claim 4, wherein the calculating CO is performed₂Emission intensity values, in particular:

according to the inlet flue gas SO of the desulphurization device₂Flow rate S₁With flue gas SO from the outlet of the desulfurizer₂Flow rate S₂Determining the predetermined desulfurized CO₂Emission intensity value W₂；

Combining the predetermined desulfurized CO₂Emission intensity value W₂With said combustion CO₂Emission intensity value W₁Calculating the CO according to the following formula₂Emission intensity value W₀；

W₂＝(S₁-S₂)*44/64；

W₀＝W₁+W₂。

6. The method of measuring carbon emission intensity according to claim 5, wherein the modified BP neural network is constructed by:

introducing the CO into a reaction vessel₂Emission intensity value W₀Inputting a preset BP neural network for training, acquiring a mapping relation between the number of input nodes and the number of output nodes, and constructing the improved BP neural network, wherein the optimal number of hidden layer neurons in the improved BP neural network is determined according to an empirical formula.

7. The method of claim 6, wherein the determining the optimal number of hidden layer neurons in the modified BP neural network according to an empirical formula comprises:

determining an empirical formula:

n₁＝log₂n；

in the formula, k represents the number of samples, n₁Representing the number of neurons in the hidden layer, n representing the number of input units, m representing the number of output units, a representing [1,10 ]]A constant between;

and determining the optimal number of hidden layer neurons as 20 according to the empirical formula.

8. The carbon emission intensity measurement method according to claim 7,

the coal quality parameters comprise a moisture parameter, an ash parameter, a volatile component parameter and a low calorific value;

the operation parameters comprise main steam flow, main steam temperature, hot reheat steam flow, hot reheat steam temperature and high-pressure cylinder exhaust steamFlow, final feed flow, superheated desuperheating water, reheated desuperheating water flow, flue gas temperature, and flue gas SO at outlet of desulfurizing device₂Flow and inlet flue gas SO of desulfurization device₂Flow rate;

the coal consumption parameters comprise coal feeding amount and load parameters.

9. A computer terminal device, comprising:

one or more processors;

a memory coupled to the processor for storing one or more programs;

when executed by the one or more processors, cause the one or more processors to implement the carbon emission intensity measurement method of any one of claims 1 to 8.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the carbon emission intensity measurement method according to any one of claims 1 to 8.

Technical Field

The invention relates to the technical field of thermal measurement, in particular to a method, equipment and medium for measuring carbon emission intensity.

Background

As the first major country of global carbon emission, China accurately monitors the carbon emission generated by coal-fired power plants, not only is a basic basis for implementing low-carbon planning and operation, but also has a fundamental role in widely trading carbon emission rights and finally realizing low-carbon emission of the coal-fired power plants, and has important practical significance in researching a carbon emission calculation method of a thermal power plant, wherein the method meets the international greenhouse gas list compilation specification and also meets the domestic data conditions.

At present, the emission of carbon dioxide is measured on line in real time by monitoring the emission amount and emission density of waste gas of a thermal power plant, monitoring the content of carbon dioxide in flue gas by various carbon dioxide analyzers and using a certain correction means. Due to the complexity of the boiler flue structure, the carbon dioxide emission intensity measured at each point in the flue has a certain difference, and the correct selection of the measuring point has great influence on the measuring result and the control effect. According to field experience, for boiler combustion control of a power station, one measuring point is far from enough, a general boiler operation optimization control system requires more than three measuring points, each measuring point is provided with two symmetrically-installed carbon dioxide analyzers, and finally carbon dioxide emission data of the power station is obtained. A method for calculating carbon emission, namely an emission coefficient method, is provided in a guidance manual issued by an international Panel on commercial Change (IPCC) of the united nations, and carbon dioxide emission of a coal-fired power plant is obtained by multiplying energy consumption and an emission coefficient.

Disclosure of Invention

The invention aims to provide a method, equipment and a medium for measuring carbon emission intensity, so as to solve the problem of large calculation deviation of the carbon emission intensity at present.

In order to achieve the above object, the present invention provides a method for measuring carbon emission intensity, comprising:

determining combustion CO according to the boiler heat efficiency and the steam turbine heat consumption rate acquired in real time₂A discharge intensity value;

combined with pre-set desulphurised CO₂Emission intensity value and the combustion CO₂Emission intensity value, calculating CO₂A discharge intensity value;

introducing the CO into a reaction vessel₂Inputting the emission intensity value into a preset BP neural network for training, and constructing an improved BP neural network;

and inputting the coal quality parameters, the operation parameters and the coal consumption parameters which are obtained in real time into the improved BP neural network to obtain a real-time carbon emission intensity value.

Preferably, before the obtaining of the boiler thermal efficiency and the turbine thermal efficiency in real time, the method further comprises:

obtaining the heat loss value q of exhaust smoke in real time₂Incomplete combustion heat loss value q of combustible gas₃Solid incomplete combustion heat loss value q₄Boiler heat dissipation loss value q₅And physical heat loss value q of ash₆；

Calculating the thermal efficiency eta of the boiler according to the following formula_g；

η_g＝100-(q₂+q₃+q₄+q₅+q₆)。

Preferably, before the obtaining of the boiler thermal efficiency and the turbine thermal efficiency in real time, the method further comprises:

real-time acquisition of the enthalpy h of the main steam entering the turbine_msFlow G of hot reheat steam into the steam turbine_rhrEnthalpy h of hot reheat steam of a steam turbine_rhrHigh pressure cylinder exhaust flow G_rhlEnthalpy h of cold reheat steam of steam turbine_rhlMake-up water flow G_maEnthalpy of make-up water h_maFinal feed rate G_fwFinal feed water enthalpy h_fwTo passFlow rate of hot desuperheated water G_ssReheat desuperheating water flow G_rsEnthalpy of superheated desuperheated water h_ssAnd enthalpy of reheated desuperheated water h_rs；

Calculating the heat consumption Q of the steam turbine according to the following formula₀；

Q₀＝G₀×h_ms+G_rhr×h_rhr-G_rhl×h_rhl+G_ma×h_ma-G_fw×h_fw-G_ss×h_ss-G_rs×h_rs；

Incorporating said steam turbine heat consumption Q₀Determining the heat consumption rate q of the steam turbine together with the electric load W of the generator;

calculating the heat rate q of the steam turbine according to the following formula;

q＝Q₀/(1000*W)。

preferably, the determining combustion CO₂Emission intensity values, in particular:

obtaining coal consumption B and carbon content C of coal as fired_arSolid incomplete combustion heat loss value q₄Receiving base calorific value Q of actual coal as fired in power plant_arAnd a molar mass conversion factor R;

calculating the combustion CO according to the following formula₂Emission intensity value W₁；

B＝b_f*W*1000*29.307/Q_ar；

In the formula, b_fIndicating standard coal consumption rate, eta, of electricity generation_gExpressing the thermal efficiency, eta, of the boiler_gdAnd q represents the heat consumption rate of the steam turbine.

Preferably, said calculating CO₂Emission intensity values, in particular:

according to the inlet flue gas SO of the desulphurization device₂Flow rate S₁With flue gas SO from the outlet of the desulfurizer₂Flow rate S₂Determining the predetermined desulfurized CO₂Emission intensity value W₂；

Combining the predetermined desulfurized CO₂Emission intensity value W₂With said combustion CO₂Emission intensity value W₁Calculating the CO according to the following formula₂Emission intensity value W₀；

W₂＝(S₁-S₂)*44/64；

W₀＝W₁+W₂。

Preferably, the constructing of the improved BP neural network specifically comprises:

introducing the CO into a reaction vessel₂Emission intensity value W₀Inputting a preset BP neural network for training, acquiring a mapping relation between the number of input nodes and the number of output nodes, and constructing the improved BP neural network, wherein the optimal number of hidden layer neurons in the improved BP neural network is determined according to an empirical formula.

Preferably, the determining the optimal number of hidden layer neurons in the modified BP neural network according to an empirical formula includes:

determining an empirical formula:

n₁＝log₂n；

in the formula, k represents the number of samples, n₁Representing the number of neurons in the hidden layer, n representing the number of input units, m representing the number of output units, a representing [1,10 ]]A constant between;

and determining the optimal number of hidden layer neurons as 20 according to the empirical formula.

Preferably, the coal quality parameters comprise a moisture parameter, an ash parameter, a volatile matter parameter and a low calorific value;

the operation parameters comprise main steam flow, main steam temperature, hot reheat steam flow, hot reheat steam temperature, high-pressure cylinder exhaust flow, final supply flow, superheated desuperheating water, reheated desuperheating water flow, exhaust gas temperature and desulfurization device outlet flue gas SO₂Flow and inlet flue gas SO of desulfurization device₂Flow rate;

the coal consumption parameters comprise coal feeding amount and load parameters.

The present invention also provides a terminal device, including:

one or more processors;

a memory coupled to the processor for storing one or more programs;

when executed by the one or more processors, cause the one or more processors to implement the carbon emission intensity measurement method of any one of the above.

The present invention also provides a computer-readable storage medium having stored thereon a computer program for execution by a processor to implement the carbon emission intensity measurement method as defined in any one of the above.

Compared with the prior art, the invention has the beneficial effects that:

according to the boiler thermal efficiency and the steam turbine thermal efficiency obtained in real time, the method determines the CO combustion₂Emission intensity values in combination with desulphurised CO₂Emission intensity value and the combustion CO₂Emission intensity value, calculating CO₂Emission intensity value of the CO₂The emission intensity value is input into a preset BP neural network for training, an improved BP neural network is constructed, a real-time carbon emission intensity value is obtained, and the efficiency and the accuracy of real-time evaluation and calculation of the carbon emission intensity of the unit are improved.

Drawings

In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a schematic flow chart of a method for measuring carbon emission intensity according to an embodiment of the present invention;

FIG. 2 is a schematic flow chart of a method for measuring carbon emission intensity according to another embodiment of the present invention;

FIG. 3 is a topology structure diagram of a BP neural network according to another embodiment of the present invention;

FIG. 4 is a graph of three transfer functions provided by an embodiment of the present invention;

fig. 5 is a schematic structural view of a carbon emission intensity measuring apparatus according to another embodiment of the present invention;

fig. 6 is a schematic structural view of a carbon emission intensity measuring apparatus according to still another embodiment of the present invention;

fig. 7 is a schematic structural diagram of a computer terminal device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be understood that the step numbers used herein are for convenience of description only and are not intended as limitations on the order in which the steps are performed.

It is to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

The terms "comprises" and "comprising" indicate the presence of the described features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.

The term "and/or" refers to and includes any and all possible combinations of one or more of the associated listed items.

Referring to fig. 1, an embodiment of the present invention provides a method for measuring carbon emission intensity, including the following steps:

s101: determining combustion CO according to the boiler heat efficiency and the steam turbine heat consumption rate acquired in real time₂Emission intensity value.

Specifically, under the condition that the unit working condition is unstable, the parameter changes rapidly, and the system input and output heat is unbalanced, so that a coal consumption calculated value has a larger deviation from an actual value, and the currently calculated coal consumption value cannot reflect the real coal consumption condition, so that the calculated carbon emission intensity value of the training model needs to be screened for stable working condition judgment.

Taking a unit as an example, referring to test regulations, selecting important initial and final parameters as determination indexes to determine whether the unit working condition is stable, respectively determining whether the change magnitude (change value: difference between maximum value and minimum value, change rate: difference between maximum value and minimum value/value of current determination time) of the indexes within a plurality of time before and after a certain time exceeds a set range, and when any index value in the indexes exceeds the set range at a certain time, determining that the unit at the certain time is in an unstable state, wherein the coal consumption data is not included in relevant statistics. Taking the load factor index as an example, the specific determination process is as follows (the load factor determination period is 10 minutes, and the set range is such that the absolute value of the change does not exceed 3%).

Judging whether the time value of the load rate index 2015-8-18: 00:00 exceeds a set range, acquiring data values 5 minutes before and after the time point 2015-8-18: 00:00, namely, all values of 2015-7-3123: 55:00 to 2015-8-18: 05:00, acquiring the maximum and minimum values of the data, comparing to judge whether the difference between the maximum value and the minimum value exceeds 3%, and determining that the unit state is in a stable state at the time point 2015-8-18: 00:00 when the judgment results of all the indexes are normal at the time point.

The judgment process of other indexes is similar to the above, and the judgment indexes and the setting of the range value of the currently used stable working condition are as follows:

1) the change value of the exhaust gas temperature before and after 10 minutes is not more than 10 ℃.

2) The change value of the exhaust oxygen amount before and after 10 minutes is not more than 2 percent.

3) The change value of the load factor before and after 5 minutes is not more than 1.5%, and the change value before and after 10 minutes is not more than 3% (this is done to avoid unidirectional change of the start-up and shut-down process parameters. ).

4) The change rate of the main steam flow (real time point) before and after 5 minutes is not more than 1.5 percent.

5) The change value of the main steam pressure before and after 5 minutes is not more than 0.6 MPa.

6) The change value of the main steam temperature before and after 5 minutes is not more than 5 ℃.

7) The change value of the reheated steam temperature before and after 5 minutes is not more than 5 ℃.

According to the heat loss value q of the exhaust smoke₂Incomplete combustion heat loss value q of combustible gas₃Solid incomplete combustion heat loss value q₄Boiler heat dissipation loss value q₅And physical heat loss value q of ash₆Determining the boiler thermal efficiency η_gThe following are:

η_g＝100-(q₂+q₃+q₄+q₅+q₆)。

according to the enthalpy h of the main steam entering the turbine_msFlow G of hot reheat steam into the steam turbine_rhrEnthalpy h of hot reheat steam of a steam turbine_rhrHigh pressure cylinder exhaust flow G_rhlEnthalpy h of cold reheat steam of steam turbine_rhlMake-up water flow G_maEnthalpy of make-up water h_maFinal feed rate G_fwFinal feed water enthalpy h_fwFlow G of superheated desuperheated water_ssReheat desuperheating water flowG_rsEnthalpy of superheated desuperheated water h_ssAnd enthalpy of reheated desuperheated water h_rsDetermining heat consumption Q of the steam turbine₀The following are:

Q₀＝G₀×h_ms+G_rhr×h_rhr-G_rhl×h_rhl+G_ma×h_ma-G_fw×h_fw-G_ss×h_ss-G_rs×h_rs；

combined heat consumption Q of steam turbine₀And determining the heat consumption rate q of the steam turbine together with the electric load W of the generator as follows:

q＝Q₀/(1000*W)。

according to the coal consumption B and the carbon content C of the coal as fired_arSolid incomplete combustion heat loss value q₄Receiving base calorific value Q of actual coal as fired in power plant_arAnd determining the combustion CO by the molar mass conversion factor R₂Emission intensity value W₁The following are:

B＝b_f*W*1000*29.307/Q_ar；

in the formula, b_fIndicating standard coal consumption rate, eta, of electricity generation_gExpressing the thermal efficiency, eta, of the boiler_gdThe power generation coal consumption efficiency is shown, q is the heat consumption rate of the steam turbine, 29.307 is 1/1000 of 29.307KJ/Kg of the calorific value of target coal, 32700KJ/Kg is the calorific value of complete combustion per kilogram of carbon, and the molar mass conversion coefficient R is 44/12.

The above equations are integrated as follows:

s102: knotCombined with predetermined desulfurized CO₂Emission intensity value and the combustion CO₂Emission intensity value, calculating CO₂Emission intensity value.

Specifically, since part of the coal powder is in sufficient contact with oxygen, carbon in the unburned coal powder cannot be completely combusted, and the unburned coal powder is directly discharged out of the furnace in solid forms such as ash, fly ash and the like, so that the loss of the carbon element is subtracted when the carbon dioxide emission generated by combustion in the coal-fired power plant is calculated.

CaCO for desulfurization₃CO produced₂The amount of SO removed can be calculated according to the desulfurization amount and known from the chemical reaction equation₂With CO produced₂The amounts of the two substances are the same, and the CO discharged by desulfurization can be obtained by multiplying a molar mass coefficient₂Quantity W₂According to the inlet flue gas SO of the desulfurizer₂Flow rate S₁With flue gas SO from the outlet of the desulfurizer₂Flow rate S₂Determination of desulfurized CO₂Emission intensity value W₂Combined with combustion of CO₂Emission intensity value W₁Obtaining CO₂Emission intensity value W₀The following are:

W₂＝(S₁-S₂)*44/64；

W₀＝W₁+W₂。

s103: introducing the CO into a reaction vessel₂And inputting the emission intensity value into a preset BP neural network for training to construct an improved BP neural network.

Referring to fig. 2 and 3, in particular, the BP neural network is a multi-layer feedforward neural network, and the main features of the network are signal forward transmission and error backward propagation. In forward transmission, an input signal is processed layer by layer from an input layer through a hidden layer until reaching an output layer, and the neuron state of each layer only affects the neuron state of the next layer. If the expected output cannot be obtained by the output layer, the backward propagation is carried out, and the network weight and the threshold are adjusted according to the prediction error, so that the predicted output of the BP neural network continuously approaches the expected output. X₁,X₂,...,X_nIs the input value of the BP neural network, Y₁,Y₂,...,Y_mIs BP spiritPredicted values over the network, W_ijAnd W_jkFor the weight of the BP neural network, the BP neural network can be regarded as a nonlinear function, the network input value and the predicted value are respectively an independent variable and a dependent variable of the function, and when the number of input nodes is n and the number of output nodes is m, the BP neural network expresses the function mapping relation from n independent variables to m dependent variables.

Referring to fig. 4, the activation function is a function running on a neuron of the artificial neural network, and is responsible for mapping the input of the neuron to the output, sometimes called a transfer function, and if the activation function is not used, the output of each layer is a linear function of the input of the upper layer, and the output is a linear combination of the inputs no matter how many layers the neural network has, which is the most primitive perceptron. The use of activation functions introduces nonlinear factors into the neurons, so that the neural network can arbitrarily approximate any nonlinear function, and thus the neural network can be applied to numerous nonlinear models. There are many transfer functions of the BP network, and three common transfer functions are a Log-sigmoid type function, a tan-sigmod type function, and a purelin type function, as follows:

characteristics of Log-sigmoid type functions from the figure, it can be seen that the input values take any values and are meaningful, no limitation exists, but the output values of the functions are all between 0 and 1, and the expression is as follows:

the tan-sigmmod type function is characterized in that as can be seen from the figure, any value of an input value is meaningful, no limitation exists, but all output values of the function are between-1 and 1, and the expression is as follows:

the purelin type function is a linear function, and input and output values can take any values, so that no limitation exists.

Because the fluctuation of the carbon emission input data causes the method of the error, the invention adopts an improved BP neural network model, namely does not adopt the traditional transfer function model, but adopts a form of reducing the product of cosine function and natural exponential function of the fluctuation, the activation function of the improved BP neural network is as follows:

the invention adopts a 3-layer BP network structure, and determines the output layer parameters, the input layer parameters and the number of hidden layers in the following way.

Output layer parameters: carbon emission intensity.

Inputting layer parameters: are arguments that affect the output parameters. First, the parameters introduced in the above calculation process generally affect the intensity of carbon emissions, specifically the coal quality: moisture, ash content, volatile matter, low level calorific capacity, operating parameter includes: main steam flow, main steam temperature, hot reheat steam flow, hot reheat steam temperature, high pressure cylinder exhaust steam flow, final feed flow, superheated desuperheating water, reheated desuperheating water flow, exhaust gas temperature, and flue gas SO at the outlet of a desulfurizer₂Flue gas SO at inlet of flow and desulfurization device₂Flow, and coal consumption parameters for correction calculation: coal feeding amount and load.

Number of hidden layers: when the three-layer BP network prediction model is designed, the number of the hidden layer neurons is determined to be somewhat complex, if the number of the hidden layer neuron nodes is too small, the network is difficult to effectively recognize training samples, the training difficulty is increased, meanwhile, the fault tolerance of the network is reduced, if the number of the hidden layer neuron nodes is too large, the number of iterations of the network is increased, the learning time is too long, and the input beyond the training samples cannot be recognized, when the neural network is specifically designed, the number of the hidden layer neurons is obtained by preliminarily calculating according to an empirical formula, then the number of the hidden layer neurons is converted, the best training results of the networks with different numbers of the hidden layers are selected to determine the best number of the hidden layer neurons, and the empirical formula for determining the number of the hidden layer neurons is three:

n₁＝log₂n；

in the formula, k represents the number of samples, n₁Representing the number of hidden layer neurons, n representing the number of input cells, m representing the number of output cells, a representing [1,10 ]]The optimal number of hidden layer neurons is determined to be 20 according to an empirical formula.

S104: and inputting the coal quality parameters, the operation parameters and the coal consumption parameters which are obtained in real time into the improved BP neural network to obtain a real-time carbon emission intensity value.

Specifically, the input layer parameters obtained in real time are input into an improved BP neural network to obtain a real-time carbon emission intensity value, wherein the input layer parameters specifically include coal quality: moisture parameter, ash content parameter, volatile matter parameter and low level calorific value, the operating parameter includes: main steam flow, main steam temperature, hot reheat steam flow, hot reheat steam temperature, high pressure cylinder exhaust steam flow, final feed flow, superheated desuperheating water, reheated desuperheating water flow, exhaust gas temperature, and flue gas SO at the outlet of a desulfurizer₂Flow and inlet flue gas SO of desulfurization device₂Flow, and coal consumption parameters for correction calculation: coal feed amount and load parameters.

The invention obtains the boiler heat efficiency and the steam turbine heat consumption rate in real time to determine the combustion CO₂The emission intensity value is obtained by calculating the carbon emission intensity of the unit in real time by adopting the coal quality and operation data, so that the accumulated error generated in the monitoring process of the traditional carbon dioxide emission monitoring method is effectively eliminated.

Referring to fig. 5 and 6, in an embodiment, the present invention further provides a carbon emission intensity measuring device, which includes a device housing 1, a data acquisition port 2, an AT89S51 single chip microcomputer 3, an alarm unit 4, a display unit 5, a data output interface 6 and a power switch 7, a parallel comparison digital-to-analog converter is disposed inside the device, the data acquisition port 2 on the device housing 1 is connected with the parallel comparison digital-to-analog converter, the parallel comparison digital-to-analog converter is further connected with the AT89S51 single chip microcomputer 3, the alarm unit 4, the display unit 5 and the data output interface 6 are respectively connected with the AT89S51 single chip microcomputer 3, the AT89S51 single chip microcomputer 3 is connected with a working power supply, the data acquisition port 2 is respectively connected with a data acquisition device and a coal quality testing instrument on site, the parallel comparison digital-to analog converter is used for converting a continuous analog signal of the instrument on site into a discrete digital signal which can be identified by the single chip microcomputer, the following were used:

the conversion of the analog signal into a data signal (AD conversion) goes through 4 steps:

1) sampling

During a/D conversion, a sampling circuit is generally used in order to keep the input signal constant, keeping the value at the start of the conversion. The start-up transition is actually to turn on the sampling switch to perform sampling.

2) Holding

During the A/D conversion, after the sampling of the sampling circuit, the switch is turned off after a period of time, and the sampling circuit enters the holding mode, so that the A/D conversion is really started.

3) Quantization

The analog-to-digital conversion is used for converting collected information which cannot be identified by a digital system into an identifiable result, the digital system only has two states of 0 and 1, the analog quantity has a plurality of states, the ADC is used for dividing the analog quantity into a plurality of small quantities to form the digital quantity so as to be identified by the digital system, and therefore the quantization is used for representing the analog quantity more accurately by the digital quantity.

The storage unit is arranged in the device, and is provided with an algorithm program of a BP artificial neural network model trained offline and used for collecting coal quality signals, operation parameter signals and SO (sulfur dioxide) of the outlet flue gas of the desulfurization device₂Flow signal and inlet flue gas SO of desulfurizing device₂Flow signal meterAnd calculating the carbon emission intensity value, wherein the display unit 5 is used for displaying the measured carbon emission intensity data on site, and the data output interface 6 is used for transmitting the measured data to the remote control station.

Referring to fig. 7, an embodiment of the present invention provides a terminal device, including:

one or more processors;

a memory coupled to the processor for storing one or more programs;

when executed by the one or more processors, cause the one or more processors to implement the carbon emission intensity measurement method as described above.

The processor is used for controlling the overall operation of the computer terminal equipment so as to complete all or part of the steps of the carbon emission intensity measuring method. The memory is used to store various types of data to support the operation at the computer terminal device, which data may include, for example, instructions for any application or method operating on the computer terminal device, as well as application-related data. The Memory may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk.

In an exemplary embodiment, the computer terminal Device may be implemented by one or more Application Specific 1 integrated circuits (AS 1C), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components, and is configured to perform the above carbon emission intensity measuring method and achieve the same technical effects AS the above method.

In another exemplary embodiment, there is also provided a computer readable storage medium comprising program instructions which, when executed by a processor, implement the steps of the carbon emission intensity measurement method in any one of the above embodiments. For example, the computer readable storage medium may be the above-described memory including program instructions executable by the processor of the computer terminal device to perform the above-described carbon emission intensity measurement method and achieve the technical effects consistent with the above-described method.

While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.