KR102337026B1 - Apparatus for treating exhaust gas comprising nitrogen oxide in thermal power plant and Method for treating exhaust gas comprising nitrogen oxide in thermal power plant - Google Patents

Abstract

An apparatus and a method for treating exhaust gas containing a nitrogen oxide in a thermal power plant are provided. The apparatus for treating exhaust gas includes a reducing agent injection unit, a reducing agent transfer unit, a data learning module, a concentration prediction module, and a process control module, and the method for treating exhaust gas includes (a) a learning-derivation step, (b) a learning-prediction step, and (c) a target-control step. According to the present invention, it is possible to actively handle nitrogen oxides, which have different emission patterns over time, by more effectively applying different types of reducing agents.

Description

Apparatus for treating exhaust gas comprising nitrogen oxide in thermal power plant and Method for treating exhaust gas comprising nitrogen oxide in thermal power plant

The present invention relates to a treatment apparatus and a treatment method for treating the nitrogen oxide-containing flue gas emitted from a thermal power plant, and more particularly, a treatment device capable of more effectively treating the nitrogen oxide-containing flue gas of a thermal power plant based on artificial intelligence and It's about processing.

A technology for treating the nitrogen oxide-containing flue gas emitted from thermal power plants is being developed. Among them, a technique for more effectively treating an exhaust gas containing nitrogen oxides by applying a hydrocarbon-based reducing agent and an ammonia-based reducing agent is also known (refer to Korean Patent Publication No. 10-2159082). This technology was able to treat nitrogen oxides in flue gas emitted from thermal power plants by applying different types of reducing agents.

However, depending on the operating state of the gas turbine, especially in the low-load operation state, the emission pattern of nitrogen oxides changed rapidly over time, which made it difficult to respond.

Therefore, it is necessary to develop a technology that can actively respond to nitrogen oxides, which have different emission patterns over time, by effectively applying different types of reducing agents.

Republic of Korea Patent Publication No. 10-2159082, (2020. 09. 23), Specification

One problem to be solved by the present invention is an apparatus for treating nitrogen oxide-containing flue gas of a thermal power plant that can effectively treat nitrogen oxides, which change in emission patterns over time, by more effectively applying different types of reducing agents based on artificial intelligence is to provide

In addition, another problem to be solved by the present invention is based on artificial intelligence, by applying different types of reducing agents more effectively, containing nitrogen oxides of thermal power plants that can effectively treat nitrogen oxides that change over time in emission patterns To provide an exhaust gas treatment method.

The technical problems of the present invention are not limited to the problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description.

The nitrogen oxide-containing flue gas treatment apparatus of a thermal power plant according to the present invention comprises: a reducing agent injection unit formed between a gas turbine and a denitration catalyst; a reducing agent transfer unit for transferring the reducing agent to the reducing agent injection unit; a data learning module that receives the correlation between the operation data of the previously collected sample gas turbine and the exhaust gas composition data, and learns it by an artificial intelligence learning algorithm to derive influence factors affecting the nitrogen oxide concentration in the exhaust gas; The artificial intelligence learning algorithm receives the measured value of the change in the influencing factor measured in real time during the operation of the gas turbine and the change in the nitrogen oxide concentration in the exhaust gas accordingly, and the correlation over time between the influencing factor and the nitrogen oxide concentration a concentration prediction module for estimating the concentration of nitrogen oxides in the exhaust gas at a second point in time that has elapsed from the first point in time during gas turbine operation by learning by; and obtaining a calculated reducing agent injection amount corresponding to the nitrogen oxide concentration in the exhaust gas at the second time point predicted by the concentration prediction module, and controlling the reducing agent transfer unit from the first time point, through the reducing agent injection unit at the second time point and a process control module for matching the amount of the injected reducing agent with the calculated reducing agent injection amount, wherein the nitrogen oxide includes nitrogen monoxide and nitrogen dioxide, and the reducing agent includes a hydrocarbon-based reducing agent and an ammonia-based reducing agent.

The sample gas turbine may include a gas turbine in which a sample denitration catalyst is positioned at a rear end thereof, and a sample reducing agent injection unit is formed between the sample gas turbine and the sample denitration catalyst.

The artificial intelligence learning algorithm of the data learning module and the concentration prediction module includes an artificial neural network algorithm in which at least one hidden layer composed of a plurality of computation nodes is formed between an input layer and an output layer, and the artificial neural network algorithm of the concentration prediction module comprises: , it may include a recurrent neural network algorithm that outputs an operation result in which time dependence of input variables is considered.

The artificial intelligence learning algorithm of the concentration prediction module may include at least one selected from an artificial neural network algorithm, a reinforcement learning algorithm, a supervised learning algorithm, and an unsupervised learning algorithm.

The calculated reducing agent injection amount may be obtained by calculating the required amount of the hydrocarbon-based reducing agent in association with nitrogen dioxide included in nitrogen oxides in the exhaust gas at the second time point predicted by the concentration prediction module.

The calculated value of the reducing agent injection amount, the amount corresponding to 0.5 equivalent of nitrogen dioxide contained in the nitrogen oxide in the exhaust gas at the second time point predicted by the concentration prediction module can be obtained by setting the maximum amount of the hydrocarbon-based reducing agent.

The maximum amount of the hydrocarbon-based reducing agent can be calculated by applying Equation 1 or Equation 1-1 below.

[Equation 1]

In the above formula, Q _e1 is the amount of hydrocarbon-based reducing agent (kg/hr), Q is the amount of exhaust gas (Nm ³ /hr.dry), NO _2i is nitrogen dioxide concentration (ppm), MW is the reducing agent molecular weight, P is the reducing agent purity (%) , NSR is the reducing agent standard equivalent ratio (0.5).

[Equation 1-1]

In the above formula, Q _e1 is the amount of hydrocarbon-based reducing agent (kg/hr), Q is the amount of exhaust gas (Nm ³ /hr. dry), NO _2i is nitrogen dioxide concentration (ppm), O _2A is the actual oxygen concentration (%, dry), O _2R is the standard oxygen concentration (%, dry), MW is the reducing agent molecular weight, P is the reducing agent purity (%), and NSR is the reducing agent standard equivalent ratio (0.5).

The calculated reducing agent injection amount may be obtained by setting the amount corresponding to 1 equivalent of nitrogen oxide in the exhaust gas at the second time point predicted by the concentration prediction module as the maximum amount of the ammonia-based reducing agent.

The maximum amount of the ammonia-based reducing agent can be calculated by applying Equation 2 or Equation 2-1 below.

[Equation 2]

In the above formula, Q _e2 is the amount of ammonia-based reducing agent (kg/hr), Q is the amount of exhaust gas (Nm ³ /hr. dry), NOx _i is the nitrogen oxide concentration (ppm), NOx _o is the nitrogen oxide target concentration (ppm), M is the design margin (margin, less than 20% of NOxi), MW is the molecular weight of the reducing agent, P is the reducing agent purity (%), and NSR is the reducing agent standard equivalent ratio (1).

[Equation 2-1]

In the above formula, Q _e2 is the amount of ammonia-based reducing agent (kg/hr), Q is the amount of exhaust gas (Nm ³ /hr. dry), NOx _i is the nitrogen oxide concentration (ppm), NOx _o is the nitrogen oxide target concentration (ppm), M is the design margin (margin, value less than 20% of NOxi), O _2A is the actual oxygen concentration (%, dry), O _2R is the standard oxygen concentration (%, dry), MW is the reducing agent molecular weight, and P is the reducing agent purity ( %), NSR is the reducing agent standard equivalent ratio (1).

The calculated value of the reducing agent injection amount is set as the maximum amount of the hydrocarbon-based reducing agent an amount corresponding to 0.5 equivalent of nitrogen dioxide contained in nitrogen oxide in the exhaust gas at the second time point predicted by the concentration prediction module, and the concentration prediction module is It can be obtained by setting the predicted amount corresponding to 1 equivalent of nitrogen oxide in the exhaust gas at the second time point as the maximum amount of the ammonia-based reducing agent.

The maximum amount of the hydrocarbon-based reducing agent may be calculated by applying Equation 1 or Equation 1-1, and the maximum amount of the ammonia-based reducing agent may be calculated by applying Equation 2 or Equation 2-1.

The operation data includes at least one selected from a combustion condition, a load amount, and an amount of exhaust gas of the sample gas turbine, the combustion condition includes at least one selected from an internal combustion condition and an external air condition, and the internal combustion condition is an amount of combustor (or number of burners), air fuel cost, combustion temperature, combustion pressure, furnace temperature, and at least one selected from furnace pressure, wherein the sample gas turbine includes at least one selected from the gas turbine and other gas turbines can do.

The operation data may include at least one selected from an exhaust gas temperature and an exhaust gas flow rate between the sample gas turbine and the sample denitration catalyst at the rear end of the sample gas turbine.

The exhaust gas composition data may include flue gas composition data between the sample gas turbine and the sample denitration catalyst at the rear end of the sample gas turbine.

Between the gas turbine and the denitration catalyst, a measuring unit for measuring at least one selected from an exhaust gas temperature, an exhaust gas flow rate, and an exhaust gas composition may be further included.

It may further include an additional reducing agent injection unit disposed between the denitration catalyst and the reducing agent injection unit.

The process control module automatically diagnoses an abnormal state in the exhaust gas flow path including the gas turbine before or after supply of the reducing agent, and when an abnormal state is found, the reducing agent transfer unit, and the facility of a thermal power plant including the gas turbine It is possible to perform a control to automatically resolve the abnormal state by operating at least one controllable facility among them.

The abnormal state may include a reducing agent excess state determined from the reducing agent concentration in the exhaust gas flow path.

The method for treating exhaust gas containing nitrogen oxides of thermal power plants according to the present invention comprises: (a) a computer learns the correlation between the operation data of a sample gas turbine and the composition data of the collected sample gas by an artificial intelligence learning algorithm, and the nitrogen oxide in the exhaust gas a learning-derivation step of deriving an influencing factor affecting the concentration; (b) The computer learns the correlation with time of the change in the influence factor measured in real time during gas turbine operation and the change in the nitrogen oxide concentration in the exhaust gas according to the artificial intelligence learning algorithm, and the first in operation of the gas turbine a learning-prediction step of predicting the concentration of nitrogen oxides in the exhaust gas at a second time point at which time has elapsed; and (c) obtaining a calculated reducing agent injection amount corresponding to the nitrogen oxide concentration in the exhaust gas at the second point in time predicted in step (b), and controlling the transfer process of the reducing agent from the first point in time to control the exhaust gas at the second time point a target-control step of matching the amount of the reducing agent injected into the furnace with the calculated value of the reducing agent injection amount, wherein a denitration catalyst is located at the rear end of the gas turbine, and a reducing agent injection part is formed between the gas turbine and the denitration catalyst, The nitrogen oxide includes nitrogen monoxide and nitrogen dioxide, and the reducing agent includes a hydrocarbon-based reducing agent and an ammonia-based reducing agent.

The sample gas turbine may have a sample denitration catalyst positioned at a rear end thereof, and a sample reducing agent injection unit may be formed between the sample gas turbine and the sample denitration catalyst.

The artificial intelligence learning algorithm of steps (a) and (b) includes an artificial neural network algorithm in which at least one hidden layer composed of a plurality of computation nodes is formed between an input layer and an output layer, and in the step (b), the artificial neural network The algorithm may include a recurrent neural network algorithm that outputs an operation result in which time dependence of input variables is considered.

The artificial intelligence learning algorithm of step (b) may include at least one selected from an artificial neural network algorithm, a reinforcement learning algorithm, a supervised learning algorithm, and an unsupervised learning algorithm.

The operation data includes at least one selected from a combustion condition, a load amount, and an amount of exhaust gas of the sample gas turbine, the combustion condition includes at least one selected from an internal combustion condition and an external air condition, and the internal combustion condition is an amount of combustor (or number of burners), air fuel cost, combustion temperature, combustion pressure, furnace temperature, and at least one selected from furnace pressure, wherein the sample gas turbine includes at least one selected from the gas turbine and other gas turbines can do.

The operation data may include at least one selected from an exhaust gas temperature and an exhaust gas flow rate between the sample gas turbine and the sample denitration catalyst at the rear end of the sample gas turbine.

The exhaust gas composition data may include flue gas composition data between the sample gas turbine and the sample denitration catalyst at the rear end of the sample gas turbine.

The influencing factor of step (a) may be derived as a part of the operation data according to the sensitivity of the change to change the concentration of nitrogen oxide in the exhaust gas.

In the step (c), the calculated value of the reducing agent injection amount is linked to the nitrogen dioxide contained in the nitrogen oxides in the exhaust gas at the second time point predicted in the step (b). It can be obtained by calculating the required amount of the hydrocarbon-based reducing agent. have.

The calculated value of the reducing agent injection amount can be obtained by setting the amount corresponding to 0.5 equivalent of nitrogen dioxide contained in the nitrogen oxide in the exhaust gas at the second time point predicted in step (b) as the maximum amount of the hydrocarbon-based reducing agent.

The maximum amount of the hydrocarbon-based reducing agent can be calculated by applying Equation 1 or Equation 1-1 below.

[Equation 1]

In the above formula, Q _e1 is the amount of hydrocarbon-based reducing agent (kg/hr), Q is the amount of exhaust gas (Nm ³ /hr.dry), NO _2i is nitrogen dioxide concentration (ppm), MW is the reducing agent molecular weight, P is the reducing agent purity (%) , NSR is the reducing agent standard equivalent ratio (0.5).

[Equation 1-1]

In the above formula, Q _e1 is the amount of hydrocarbon-based reducing agent (kg/hr), Q is the amount of exhaust gas (Nm ³ /hr. dry), NO _2i is nitrogen dioxide concentration (ppm), O _2A is the actual oxygen concentration (%, dry), O _2R is the standard oxygen concentration (%, dry), MW is the reducing agent molecular weight, P is the reducing agent purity (%), and NSR is the reducing agent standard equivalent ratio (0.5).

The calculated value of the reducing agent injection amount may be obtained by setting the amount corresponding to 1 equivalent of nitrogen oxide in the exhaust gas at the second time point predicted in step (b) as the maximum amount of the ammonia-based reducing agent.

The maximum amount of the ammonia-based reducing agent can be calculated by applying Equation 2 or Equation 2-1 below.

[Equation 2]

In the above formula, Q _e2 is the amount of ammonia-based reducing agent (kg/hr), Q is the amount of exhaust gas (Nm ³ /hr. dry), NOx _i is the nitrogen oxide concentration (ppm), NOx _o is the nitrogen oxide target concentration (ppm), M is the design margin (margin, less than 20% of NOxi), MW is the molecular weight of the reducing agent, P is the reducing agent purity (%), and NSR is the reducing agent standard equivalent ratio (1).

[Equation 2-1]

In the above formula, Q _e2 is the amount of ammonia-based reducing agent (kg/hr), Q is the amount of exhaust gas (Nm ³ /hr. dry), NOx _i is the nitrogen oxide concentration (ppm), NOx _o is the nitrogen oxide target concentration (ppm), M is the design margin (margin, value less than 20% of NOxi), O _2A is the actual oxygen concentration (%, dry), O _2R is the standard oxygen concentration (%, dry), MW is the reducing agent molecular weight, and P is the reducing agent purity ( %), NSR is the reducing agent standard equivalent ratio (1).

The calculated value of the reducing agent injection amount is set as the maximum amount of the hydrocarbon-based reducing agent in an amount corresponding to 0.5 equivalents of nitrogen dioxide contained in nitrogen oxides in the exhaust gas at the second time point predicted in step (b), and (b) It can be obtained by setting the amount corresponding to 1 equivalent of nitrogen oxide in the exhaust gas at the second time point predicted in the step as the maximum amount of the ammonia-based reducing agent.

The maximum amount of the hydrocarbon-based reducing agent may be calculated by applying Equation 1 or Equation 1-1, and the maximum amount of the ammonia-based reducing agent may be calculated by applying Equation 2 or Equation 2-1.

The step (c) is, before or after supply of the reducing agent, automatically diagnosing an abnormal state in the flue gas flow path including the gas turbine with a computer, and when an abnormal state is found, at least one of the computer control system and the transfer process It may include a detailed step including the step of automatically resolving the abnormal state by controlling any one.

The step of automatically resolving the abnormal state may include the process of controlling the concentration of the reducing agent in the exhaust gas flow path including the gas turbine to remove the risk of explosion and fire due to the excess of the reducing agent.

According to the present invention, by more effectively applying different series of reducing agents, it is possible to actively treat nitrogen oxides, which have different emission patterns over time.

1 is a view showing a nitrogen oxide-containing exhaust gas treatment apparatus of a thermal power plant according to an embodiment of the present invention.
2 is a block diagram for explaining a nitrogen oxide-containing exhaust gas treatment apparatus of a thermal power plant according to an embodiment of the present invention.
3 is a diagram conceptually illustrating an example of a learning algorithm applicable to the data learning module and the concentration prediction module of FIG. 1 .
4 is a flowchart illustrating a method for treating a nitrogen oxide-containing exhaust gas of a thermal power plant according to an embodiment of the present invention.
5 is a view showing a time table showing the processing process related to the prediction of the pollutant concentration and the supply of the reducing agent over time, and a graph showing the fluctuation of the supply amount of the reducing agent according thereto.

Advantages and features of the present invention and methods for achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but can be implemented in various different forms, and only these embodiments allow the disclosure of the present invention to be complete and common knowledge in the art to which the present invention pertains. It is provided to fully inform the possessor of the scope of the invention, and the present invention is only defined by the claims. Like reference numerals refer to like elements throughout.

In the present specification, nitrogen oxide means a compound consisting of nitrogen and oxygen or a mixture thereof, and includes nitrogen monoxide, nitrogen dioxide, dinitrogen monoxide, dinitrogen trioxide, dinitrogen tetraoxide, and/or dinitrogen pentoxide .

Hereinafter, with reference to FIGS. 1 to 5 , a nitrogen oxide-containing flue gas treatment device (hereinafter, may be referred to as a ‘treatment device’ or ‘exhaust gas treatment device’) of a thermal power plant according to an embodiment of the present invention and a thermal power plant The nitrogen oxide-containing flue gas treatment method (hereinafter, may be referred to as a 'treatment method' or a 'exhaust gas treatment method') will be described in detail.

1 is a view showing an exhaust gas treatment apparatus of a thermal power plant according to an embodiment of the present invention, Figure 2 is a block diagram for explaining the exhaust gas treatment apparatus of a thermal power plant according to an embodiment of the present invention.

As shown in Figures 1 and 2, an embodiment of the processing device 1 of the present invention is a reducing agent injection unit 500, a reducing agent transfer unit 400, a data learning module 100, a concentration prediction module 200, and a process control module 300 .

The reducing agent injection unit 500 is formed between the gas turbine 10 and the denitration catalyst 22, and the reducing agent injected through the reducing agent injection unit 500 includes two heterogeneous reducing agents. The two heterogeneous reducing agents are a hydrocarbon-based reducing agent and an ammonia-based reducing agent. As nitrogen dioxide in the flue gas is reduced to nitrogen monoxide by the hydrocarbon-based reducing agent, the nitrogen dioxide content in the flue gas is reduced, and the exhaust gas is passed through a denitration catalyst together with the ammonia-based reducing agent, so that the denitration reaction proceeds. By the denitrification reaction, nitrogen oxides can be finally reduced to nitrogen and treated. As such, since the nitrogen dioxide content in the flue gas is reduced by the hydrocarbon-based reducing agent, yellowing caused by nitrogen dioxide can be suppressed, and the denitration reaction mainly performed by the ammonia-based reducing agent and the denitration catalyst can be effectively performed. In addition, nitrogen oxide, particularly nitrogen dioxide, has a high content in the exhaust gas at the initial stage of gas turbine start-up, and its variability with time is large. One embodiment of the present invention is by organically applying the reducing agent transfer unit 400, the data learning module 100, the concentration prediction module 200, and the process control module 300 together with the reducing agent injection unit 500, the It can easily respond to volatility such as That is, the data learning module 100 derives an influencing factor affecting the nitrogen oxide concentration in the exhaust gas, and the concentration prediction module 200 predicts the nitrogen oxide concentration at a future time from the derived influencing factor, and the process control module ( 300) not only obtains the calculated value of the reducing agent injection amount corresponding to the predicted value, but also controls the reducing agent transfer unit 400 in consideration of the time difference so that the reducing agent in the amount corresponding to the calculated value is injected through the reducing agent injection unit 500 , it is possible to not only predict the fluctuating nitrogen oxide concentration in advance, but also to deal with it preemptively. In particular, one embodiment of the present invention is not only applied to the two heterogeneous reducing agents discussed above, but also by preemptively applying such a reducing agent, the exhaust gas containing nitrogen oxides including nitrogen monoxide and nitrogen dioxide together more effectively can be processed Hereinafter, each configuration will be described in more detail.

The hydrocarbon-based reducing agent may be one or more selected from hydrocarbons and sugars having one or more hydroxyl (OH) groups in one molecule. A more preferred hydrocarbon-based reducing agent may be, for example, at least one selected from ethanol, ethylene glycol, glycerin, sugar, and fructose.

The ammonia-based reducing agent may be one or more selected from ammonia, urea, or a precursor thereof.

Such a reducing agent may be injected into the exhaust gas through a reducing agent injection unit in a state in which a single substance or two or more substances are mixed, regardless of liquid or gaseous phase.

The denitration catalyst is not limited as long as it can reduce nitrogen oxide to nitrogen by selective catalytic reduction (SCR). For example, it may include an ammonia-SCR reaction catalyst (eg, a metal oxide catalyst containing vanadium, etc.), and may be manufactured by a known method such as an ion exchange method or a dry impregnation method or may be commercially available. In addition, the denitration catalyst may be a dual function catalyst to which an oxidation catalyst function is added. In this case, the dual function catalyst to which the oxidation catalyst function is added means a catalyst to which an oxidation catalyst function is added in addition to the denitration catalyst function, and is not limited to the form or type of the catalyst, for example, the dual function catalyst is one catalyst support It may be that the catalyst component responsible for the denitrification function and the catalyst component responsible for the oxidation function exist together. Preferably, the catalyst component responsible for the denitration function may be located in front of the catalyst component responsible for the oxidation function. In this case, the catalyst component responsible for the denitration function may be a vanadium oxide catalyst component having a reducing ability, The catalyst component responsible for the may be a noble metal-based catalyst component. In this case, the noble metal may be platinum, palladium, silver, or the like. With such a dual function catalyst, THC and ammonia slip can also be suppressed, and more effective exhaust gas treatment is possible in terms of pressure difference. The denitration catalyst 22 is not limited as long as it is disposed at the rear end of the reducing agent injection unit 500, but preferably may be disposed at a position where the exhaust gas temperature can reach 200°C to 500°C. This is because the catalytic reaction can proceed more effectively in such a temperature range. The denitration catalyst 22 may be disposed between a plurality of heat exchange modules 21 spaced apart from each other in the duct 20 . Although the plurality of heat exchange modules is illustrated as being separated from each other, in reality, they may be connected to each other.

The reducing agent injection unit 500 is not limited as long as the reducing agent can be injected into the duct 20 between the gas turbine 10 and the denitration catalyst 22, but may be a nozzle or a grid. In addition, the reducing agent injection unit 500 may be one or plural. Each reducing agent injection unit may be formed for each type of reducing agent, and two reducing agents may be supplied to one or a plurality of reducing agent injection units in a mixed state. In addition, an additional reducing agent injection unit 550 in addition to the reducing agent injection unit 500 may be added. The additional reducing agent injection unit 550 may be disposed between the reducing agent injection unit 500 and the denitration catalyst 22 . An ammonia-based reducing agent and/or a hydrocarbon-based reducing agent may be injected through the additional reducing agent injection unit 550 , and a reducing agent of a different type may be injected. By such an additional reducing agent injection unit 550, it is possible to supplement the insufficient reducing agent, it is possible to more smoothly process nitrogen oxides according to the operating conditions.

In addition, the reducing agent injection unit 500 is not limited as long as it is formed between the gas turbine 10 and the denitration catalyst 22, but preferably the exhaust gas temperature is 200 ° C to 500 ° C, more preferably 300 ° C to 500 ° C It can be formed at a position that can reach °C. This is because nitrogen dioxide can be more easily reduced to nitrogen monoxide by a reducing agent, preferably a hydrocarbon-based reducing agent, in such a temperature range.

The reducing agent transfer unit 400 may be formed as a reducing agent supply facility for transferring the reducing agent to the reducing agent injection unit 500 . The reducing agent transport unit 400 may be connected to the reducing agent storage units 600 and 650 such as the reducing agent tank in which the reducing agent is stored. As shown, the reducing agent storage unit is made up of a plurality, and a hydrocarbon-based reducing agent and an ammonia-based reducing agent may be stored in each. The reducing agent (B) is transferred from the reducing agent storage unit (600, 650) to the reducing agent injection unit (500) through the reducing agent conveying unit (400), and is injected into the duct (20) from the reducing agent injection unit (500). Therefore, it is mixed with the exhaust gas (A) flowing inside the duct 20 can be removed by reducing the nitrogen oxides in the exhaust gas. The reducing agent may be transferred to the additional reducing agent injection unit 550 by the reducing agent transfer unit 400, and the reducing agent may be transferred by a separate additional reducing agent transfer unit (not shown).

The reducing agent transfer unit 400 may be composed of various facilities for transferring the reducing agent (B) from the reducing agent storage units 600 and 650 to the reducing agent injection unit 500, and these facilities include pipes, valves, pumps, etc. Various equipment may be installed. The pipe may be formed in one or a plurality, and a plurality of pipes may be connected to each other to form a relatively complicated transport path. In addition, other facilities may be additionally disposed. For this reason, it takes time for the reducing agent to reach the reducing agent injection unit 500 through the reducing agent conveying unit 400, and this may be referred to as the required time of the reducing agent conveying process. The reducing agent transfer unit 400 may be formed in various ways depending on the implementation of the device, and accordingly, the required time of the transfer process may also vary. Therefore, in the prior art, even if the reducing agent injection instruction is given to the actual reducing agent transfer unit 400, until the reducing agent is actually injected by the amount according to the instruction, a time difference occurs at least as much as the required time of the transfer process. It was difficult. In the present invention, since the concentration prediction module 200 can predict the concentration of nitrogen oxides in the exhaust gas at the first time point during operation of the gas turbine 10 and at the second time point that has elapsed than that, the required time is reduced even if there is a required time for the transfer process. Through the considered control, it is possible to control so that the correct amount of the reducing agent is injected according to the predicted time point (ie, the second time point).

Hereinafter, in addition to the concentration prediction module, a data learning module and a process control module will be described. The data learning module, the concentration prediction module, and the process control module may include program modules installed in one or more computers. The data learning module 100, the concentration prediction module 200, and the process control module 300 may include one or a plurality of operation programs capable of performing each operation, and are a type of software in which related programs are combined. It may be formed or may be formed in a form including hardware storing the same together with such software. If necessary, each module may also include a central arithmetic unit capable of driving an arithmetic program. Thus, for example, each module may be implemented on independent hardware having a different independent central processing unit, software, and a memory device storing the same (in such case, each module can be viewed as constituting an independent computer), It is also possible that at least two modules of each module share a part of hardware such as a central processing unit (in such a case, it can be considered that at least two modules are formed in one computer). As described above, the data learning module 100 , the concentration prediction module 200 , and the process control module 300 can be operably implemented using a computer in various forms. The data learning module 100, the concentration prediction module 200, and the process control module 300 may operate at different times, but since the operation times may overlap with each other, the process is not limited according to the time sequence in the present invention. For example, each module may perform concurrently with each other at the same time.

The data learning module 100 receives the correlation between the previously collected operation data of the sample gas turbine and the composition data of the exhaust gas associated therewith, and learns by an artificial intelligence learning algorithm (eg, a machine by an artificial intelligence learning algorithm). -Learning method) to derive influence factors that affect the concentration of nitrogen oxides in the exhaust gas. The data learning module 100 may include one or a plurality of operation programs capable of performing such operations. Data such as operation data and flue gas composition data of the previously collected sample gas turbine may be included in the database. The sample gas turbine may include a gas turbine in which a sample denitration catalyst is positioned at a rear end thereof, and a sample reducing agent injection unit is formed between the sample gas turbine and the sample denitration catalyst. As described above, by applying a gas turbine having a reducing agent injection part and a denitration catalyst located at the rear end of the gas turbine included in the exhaust gas processing apparatus according to an embodiment of the present invention as a sample gas turbine, the operation data and the exhaust gas composition data obtained therefrom are It can be used as learning data in a state with less noise.

In addition, in the present specification, components such as a database and a module may be connected to each other by wire and/or wirelessly. It goes without saying that wired and/or wireless may be commercially available, such as a modem, or manufactured by a common technique. In addition, it goes without saying that the database and/or the program may be physically integrated into the device itself and may also be included in the cloud. The data learning module 100 may perform the learning-derivation step (refer to S100 of FIG. 4 ) of the exhaust gas processing method to be described later.

The concentration prediction module 200 receives the measured value of the change in the influencing factor measured in real time during the operation of the gas turbine and the change in the nitrogen oxide concentration in the exhaust gas accordingly, and the correlation of the influencing factor and the nitrogen oxide concentration over time. By learning by an artificial intelligence learning algorithm, for example, by a machine-learning method by an artificial intelligence learning algorithm, the concentration of nitrogen oxides in the exhaust gas at the first time point while the gas turbine 10 is being operated and at the second time point elapsed therefrom predict The concentration prediction module 200 may receive the measured value of the change in the influence factor measured in real time and the change in the nitrogen oxide concentration in the exhaust gas according to the real-time data as real-time data to predict the nitrogen oxide concentration at the second time point. At this time, between the gas turbine and the denitration catalyst, real-time data may be obtained through the measuring unit 25 that measures one or more selected from the flue gas temperature, the flue gas flow rate, and the flue gas composition. In particular, the data measured by the measuring unit 25 can directly grasp the state of the space in which the reducing agent injection unit 500 is located, which is effective in predicting the concentration of nitrogen oxides. The concentration prediction module 200 may also include one or a plurality of calculation programs capable of performing such calculations. The concentration prediction module 200 may perform the learning-prediction step (refer to S200 of FIG. 4 ) of the exhaust gas processing method to be described later.

Hereinafter, the artificial intelligence learning algorithm of the data learning module 100 and the concentration prediction module 200 will be described in more detail with reference to FIG. 3 . 3 is a diagram conceptually illustrating an example of a learning algorithm applicable to the data learning module and the concentration prediction module of FIG. 1 .

Data learning module 100 and a concentration prediction module 200, artificial intelligence learning algorithm, such as a plurality between the input layer and the output layer as shown in FIG compute nodes artificial hidden layer of at least one formed consisting of (H _n) Including an artificial neural network (ANN) algorithm, in particular, the artificial neural network algorithm of the concentration prediction module 200 is a recurrent neural network (RNN) algorithm that outputs an operation result in which the time dependence of input variables is considered. may include For example, in the artificial neural network algorithm, nodes of each layer may be weighted functions, and as shown in the figure, artificial neurons are configured in a network form, and calculations by synthesizing them may be performed according to the algorithm. Accordingly, data is input to the nodes (I _n ) of the input layer, passes through a plurality of nodes formed in the hidden layer _{, and propagates to the nodes (O n} ) of the output layer, so that it can be calculated. In this process, the weights of the nodes may be updated by back propagation or the like to optimize the results. From the result of this operation, modeling in which various correlations between input data such as nonlinear correlation are shown, for example, can be modeled. For example, an artificial neural network that performs a desired type of operation by appropriately adjusting or selecting each node or a function for synthesizing nodes or processing a result of a node can be configured. Therefore, for example, in the case of the data learning module 100, it can be configured to learn data with an artificial neural network capable of deriving a correlation between the nitrogen oxide concentration and operation data in the exhaust gas from the previously collected operation data and exhaust gas composition data, and from this As part of the operation data, it is possible to derive the influencing factors affecting the nitrogen oxide concentration in the exhaust gas.

Although not shown, one or a plurality of hidden layers may be formed, and the number of neurons may be enlarged by increasing the hidden layer. In the case of having a plurality of hidden layers, for example, it may be composed of a deep neural network (DNN), and machine-learning by deep learning is performed therefrom, so that a non-linear correlation may be more appropriately identified. In addition to this, for example, it is possible to output the operation result in which the time dependence of the input variables is considered in a method such as recursively calculating the output of the node in the hidden state in the hidden layer according to the time order. For example, a recurrent neural network (RNN) configured to circulate within the hidden layer while the direction of the operation is directed from the input layer to the output layer may be configured. In the case of the concentration prediction module 200, since it is a configuration that derives a time-dependent relationship of real-time measured data, such a cyclic neural network algorithm may be more suitable. It is possible to more appropriately derive their correlation with time from the measured values of the concentration change. As such, it is possible to form a learning algorithm of the data learning module 100 and the concentration prediction module 200 to enable operation by the artificial neural network algorithm.

However, it is not necessary to be limited in this way, and if necessary, it is possible to selectively/additionally apply other artificial intelligence learning algorithms. For example, in the case of the concentration prediction module 200, another learning method that can be predicted by learning can be considered, and as such a learning method, for example, a reinforcement learning algorithm applying the concept of reinforcement through a reward to the learning process or , a supervised learning algorithm of the concept of training with data with answers, and an unsupervised learning algorithm of a concept of training through classification through clustering of data without an answer can be used. These algorithms, for example, can be applied as an artificial intelligence learning algorithm through deep learning, whereby the artificial intelligence learning algorithm of the concentration prediction module 200 is the aforementioned artificial neural network algorithm, reinforcement learning algorithm, supervised learning algorithm, and unsupervised learning algorithm. It may include at least one selected from among the learning algorithms. The data learning module 100 and the concentration prediction module 200 may each include one or a plurality of operation programs implemented by such an artificial intelligence learning algorithm, and in the case of the concentration prediction module 200, learning from such operation programs and predictions can be made together. Alternatively, if necessary, a computation program for deriving a correlation between data by an artificial intelligence learning algorithm and another computation program for repeatedly performing prediction by applying a result derived by an artificial intelligence learning algorithm may be included together. In this way, the data learning module 100 that derives the above-mentioned influence factors by applying the learning method based on artificial intelligence in this way and the first time point during gas turbine operation to predict the pollutant concentration at the second time point when time has elapsed It is possible to configure the concentration prediction module 200 .

The driving data and the flue gas composition data learned by the data learning module 100 may include the following data in more detail. The operation data may include combustion conditions, a load amount, and/or an amount of exhaust gas of the above-described sample gas turbine, and may further include an exhaust gas temperature. The operating data may include at least one selected from the temperature of the exhaust gas between the sample gas turbine and the sample denitration catalyst, and the flow rate of the exhaust gas. This is because the operation data in a specific space is suitable for predicting the change of nitrogen oxides with time in the space in which the reducing agent of the device according to an embodiment of the present invention is injected. In order to collect such operation data, a measuring unit capable of measuring one or more selected from the flue gas temperature and the flue gas flow rate may be positioned between the sample gas turbine and the sample denitration catalyst. The measuring unit may include a thermometer, a flow meter, and/or a flow meter. Combustion conditions may include internal combustion conditions and external air conditions. Such operation data is closely related to the concentration of contaminants such as nitrogen oxides present in the exhaust gas, and is found in the process of the present invention, and it seems that more accurate prediction is possible by using such operation data. More specifically, the internal combustion conditions described above may include, for example, details such as the number of combustors (or the number of burners), air fuel cost, combustion temperature, combustion pressure, furnace temperature, and furnace pressure, and the load amount is The output of the sample gas turbine may be included. In addition, the outdoor conditions may include contents related to the combustion environment such as temperature and humidity at the time the corresponding operation data is generated. At this time, the combustor quantity means including the burner quantity, and the air fuel ratio means including the air quantity and the fuel quantity. The flue gas composition data includes the constituents of substances and the concentrations of each constituent in the flue gas generated from the sample gas turbine operated according to the time at which the corresponding operation data is generated. include all Examples of pollutants include nitrogen oxides and carbon monoxide. Examples of non-polluting substances include oxygen and water in the form of water vapor. As described above, the sample gas turbine is a gas turbine currently being considered (a gas turbine that is actually operated, the gas turbine in the learning-prediction step (S200) described above) and other gas turbines (eg, different types of gas turbines). pseudo-gas turbine) and may include at least one selected from among them. Such exhaust gas composition data may preferably be flue gas composition data between the sample gas turbine and the sample denitration catalyst. This is because the exhaust gas composition data in such a specific space is suitable for predicting the nitrogen oxide change with time in the space in which the reducing agent of the device according to an embodiment of the present invention is injected. In order to collect such exhaust gas composition data, a gas measuring unit may be formed between the sample gas turbine and the sample denitration catalyst. The gas measuring unit may include a particle measuring sensor, a gas measuring sensor, and/or a moisture measuring meter. Also, a gas measuring unit may be formed between the gas turbine and the denitration catalyst.

These driving data and flue gas composition data are learned by the artificial intelligence learning algorithm as described above (e.g., learning by the machine-learning method by the artificial intelligence learning algorithm), and accordingly, the influencing factors affecting the nitrogen oxide concentration in the flue gas is derived For example, the influencing factor may be derived as a part of the above-described operation data according to the sensitivity of the change in the nitrogen oxide concentration in the exhaust gas. The influencing factor may consist of any one or a plurality of detailed contents constituting the driving data, and the specific contents may vary depending on the situation. For example, at least one of a load amount in the operation data and a quantity of combustors (or a quantity of burners) among internal combustion conditions, air fuel cost, combustion temperature, combustion pressure, furnace temperature, and furnace pressure may be derived as an influence factor. However, since this is an example, there may be more or fewer influencing factors depending on the situation, and it is possible to more accurately predict the nitrogen oxide concentration in the flue gas from the measured values of such influencing factors. If this is described in relation to the exhaust gas treatment method to be described later, the influencing factor of (a) step (S100) can be derived as a part of the operation data according to the sensitivity of the change to change the nitrogen oxide concentration in the exhaust gas, and such (a) Nitrogen oxides of which the influencing factors of the stage change the concentration include nitrogen monoxide and nitrogen dioxide. That is, by learning the correlation between the real-time change of the derived influencing factor and the resulting change in the nitrogen oxide concentration in the exhaust gas by the machine-learning method using the artificial intelligence learning algorithm as described above, it is possible to derive a predicted value of the nitrogen oxide concentration at a future time. have. For example, influencing factors that sensitively affect changes in the concentration of nitrogen monoxide and nitrogen dioxide among nitrogen oxides in the flue gas are derived, and the time-dependent correlation between the changes in the influencing factors and changes in the concentrations of nitrogen monoxide and nitrogen dioxide is evaluated using the concentration prediction module ( 200), it is possible to predict the concentrations of nitrogen monoxide and nitrogen dioxide in the exhaust gas at the first point in time during gas turbine operation, and at the second time point in which the time has elapsed.

The process control module 300 obtains the calculated value of the reducing agent injection amount corresponding to the nitrogen oxide concentration in the exhaust gas of the second time point predicted by the concentration prediction module 200, and controls the reducing agent transfer unit 400 from the first time point, the second At this point, the control is performed to match the amount of the reducing agent injected into the exhaust gas through the reducing agent injection unit 500 with the calculated value of the reducing agent injection amount. The process control module 300 may be connected to the data learning module 100 and the concentration prediction module 200, and may be formed to enable data exchange with them. The process control module 300 can control the operation of the reducing agent transfer unit 400 by transmitting a control signal to the reducing agent transfer unit 400, and is connected to the gas turbine 10, the duct 20, the stack 30, and the like, as will be described later. The control system 40 may also be configured to be capable of transmitting a control signal. The process control module 300 may be formed to include one or a plurality of operation programs similar to the data learning module 100 or the concentration prediction module 200, and may be configured as an independent computer device, or the data learning module 100 And it is possible to be configured to be integrated into a computer device such as at least one of the concentration prediction module 200. In particular, the calculation program of the process control module 300 may be equipped with a function of calculating the reducing agent injection amount corresponding to the predicted nitrogen oxide concentration at the second time point. In addition, another arithmetic program for performing an operation related to control for controlling various facilities constituting the reducing agent transfer unit 400 may be configured together. The process control module 300 may perform a target-control step (refer to S300 of FIG. 4 ) of an exhaust gas treatment method to be described later.

As described above, the data learning module 100 derives an influencing factor affecting the nitrogen oxide concentration, and the concentration prediction module 200 uses the derived influencing factor to determine the nitrogen oxide concentration at the second point in the future. to predict, and to control the reducing agent transfer unit 400 with the process control module 300 so that the reducing agent corresponding to the nitrogen oxide concentration at the second time point is injected through the reducing agent injection unit 500 . In this way, together with the reducing agent injection unit 500 for injecting two types of heterogeneous reducing agents, the reducing agent transfer unit 400, the data learning module 100, the concentration prediction module 200, and the process control module 300 organically By applying it, it is possible to preemptively respond to nitrogen oxides that fluctuate with time.

In addition, the process control module 300 automatically diagnoses an abnormal state in the exhaust gas flow path including the gas turbine 10 before or after supply of the reducing agent, and when an abnormal state is found, the reducing agent transfer unit 400, and the gas turbine 10 ), by operating at least one controllable facility among the facilities of the thermal power plant including In particular, the abnormal state may include an excessive reducing agent state determined from the reducing agent concentration in the flue gas flow path, and therefore, automatically eliminating the risk of explosion due to excessive reducing agent through the control of the process control module 300 through inspection It is possible. In addition, the abnormal state may include a state in which the exhaust gas treatment performance such as denitrification performance is excessively reduced or the concentration of by-products according to the exhaust gas treatment is excessively increased, and at least one controllable facility among the facilities of the thermal power plant. It can be controlled to automatically resolve this abnormal state by operating the . For example, it is possible to monitor the concentration of the reducing agent by arranging a concentration sensor in the flue gas flow path. In addition, it is possible to monitor whether an abnormal condition occurs in the flue gas flow path by arranging a temperature sensor, a pressure sensor, etc. in combination. When an abnormal state is found, the process control module 300 may stop supplying the reducing agent even in the reducing agent transport process, and may perform a control operation to immediately resolve the abnormal state before or after the supply of the reducing agent is made. Such a control operation is, for example, controlled by the control system 40 (which may be formed to operate the facilities of the thermal power plant) connected to the gas turbine 10, the duct 20, the stack 30, etc. as shown in FIG. 2 . It can be executed by transmitting a signal or by transmitting a control signal to the reducing agent transfer unit 400, and the reducing agent supply can be executed after the reducing agent concentration is lower than the appropriate state by the control operation. In addition, the process control module 300 collects information through various sensors or monitor devices disposed in the thermal power plant to have a problem with the gas turbine 10, a problem with fluid flow in the duct 20, or a reducing agent injection unit (500), it is possible to control to detect and solve various abnormal conditions, such as there is a problem in the reducing agent transfer unit 400, etc. If necessary, an alarm or the like can be activated to inform the operator of a problem, and if the problem is not resolved immediately, the process may be temporarily stopped. Controls for resolving the abnormal state will be described in more detail in the exhaust gas treatment method to be described later.

Hereinafter, with reference to the configuration of such an exhaust gas processing apparatus and FIG. 4, an exhaust gas processing method of a thermal power plant according to an embodiment of the present invention will be described in detail. 4 is a flowchart illustrating a method for treating exhaust gas of a thermal power plant according to an embodiment of the present invention.

Referring to FIG. 4 , the exhaust gas treatment method according to the present invention includes processes for predicting and corresponding processes of changing the concentration of nitrogen oxides through data learning. The present invention learns pre-collected data and actual data by an artificial intelligence learning algorithm, and predicts changes in nitrogen oxide concentration, etc. in exhaust gas in advance. Prediction is made with excellent accuracy by reflecting the collected data and real-time data at the time of gas turbine operation in a complex way, and through this, it is possible to effectively perform control tailored to the future point in time after a certain time has elapsed from the present point. That is, when performing a process to reduce and remove nitrogen oxides with a reducing agent, predict how the nitrogen oxide concentration in the flue gas will change from the current information, and control using the time interval from the current point to the predicted time. can be supplied more accurately. Through this, it is possible not only to effectively deal with the case where nitrogen oxides fluctuate over time, but also to solve the problem of the actual supply amount of the reducing agent fluctuating with time lag due to the transfer process of the reducing agent, etc.

The exhaust gas treatment method of the present invention is specifically configured as follows. As shown in FIG. 4 , the exhaust gas processing method includes (a) a learning-derivation step, (b) a learning-prediction step, and (c) a target-control step. (a) In the learning-derivation step, the computer learns the correlation between the operation data of the sample gas turbine and the exhaust gas composition data collected previously by an artificial intelligence learning algorithm, and derives the influencing factors affecting the nitrogen oxide concentration in the exhaust gas. step (S100). (b) In the learning-prediction step, the computer learns the correlation over time of the influencing factor measured in real time during gas turbine operation and the resultant change in nitrogen oxide concentration in the exhaust gas by an artificial intelligence learning algorithm, At the first time point, it is a step of predicting the nitrogen oxide concentration in the exhaust gas at the second time point in which time has elapsed (S200). (c) The target-control step obtains the calculated reducing agent injection amount corresponding to the nitrogen oxide concentration in the exhaust gas at the second time point predicted in step (b) (ie, S200), and controls the reducing agent transport process from the first time point. , is a step of matching the amount of the reducing agent injected into the exhaust gas at the second time point with the calculated value of the reducing agent injection amount (S300). The target-control step can also be performed by a computer, and various machine-learning learning algorithms including artificial neural network algorithms can be used for the learning-derivation step and the learning-prediction step of the AI learning algorithm. Hereinafter, the main points of each step will be described in more detail.

The learning-derivation step ( S100 ) may be a step of materializing the correlation between the operation of the gas turbine of the thermal power plant and the change in the composition (same meaning as components, properties, etc.) of the exhaust gas according to the artificial intelligence learning method. For example, data related to the operation of a gas turbine in a thermal power plant are independent variables, and data representing the composition of the flue gas related thereto are made a dependent variable, so that a causal relationship between the two can be determined. The correlation between various types of accumulated data and related flue gas composition data can be found with high accuracy through a self-learning process such as machine-learning. This is a process of determining the organic correlation of data analyzed by an artificial intelligence learning algorithm, not the result obtained by simply assuming linearity between data, as in the conventional linear regression analysis, according to the result derived through repeated self-learning, Through this, it is possible to find out with higher reliability the factors affecting the nitrogen oxide concentration in the exhaust gas among gas turbine operation data. These influencing factors may be derived as a part of the operation data according to the sensitivity of the change to change the nitrogen oxide concentration in the exhaust gas, for example, and may be derived one or more. For example, when operation data consists of various types of data including combustion conditions, load amounts, flue gas amounts, and/or flue gas temperatures, among them, combustion conditions or loads, or a part of detailed conditions constituting the combustion conditions, etc. As a part of this operation data, it can be derived as an influencing factor, and one or more pollutants in the flue gas whose concentration is sensitively changed according to the change of the influencing factor may appear. For example, nitrogen oxides in the flue gas whose concentration is changed by the influencing factor include nitrogen monoxide and nitrogen dioxide, and it is possible to effectively respond by predicting the change in the concentration of nitrogen oxides from the change in the influencing factor. Therefore, the present invention is effective for denitrification treatment.

In this learning-derivation step (S100), learning is performed on the operation data and the exhaust gas composition data of the previously collected sample gas turbine. In this case, the sample gas turbine may be a gas turbine actually operated in the learning-prediction step to be described later, or may be another gas turbine. That is, the exhaust gas treatment method of the present invention can extensively learn the correlation between the operating conditions of various gas turbines used in a thermal power plant and the composition of the exhaust gas generated accordingly, and through this, an influence factor that gives more sensitive and accurate results is derived. can do. In other words, data of various gas turbines previously collected can be used to derive influence factors that give more sensitive and accurate prediction results. That is, the sample gas turbine includes at least one selected from among a plurality of gas turbines including the gas turbine operated in the learning-prediction step (S200) and another gas turbine (eg, a heterogeneous pseudo-gas turbine). It can be included, and influence factors can be derived by learning the operation data and flue gas composition data of such sample gas turbines. Depending on the situation, the amount of data that can be learned increases as the operation data of several gas turbines are considered, but noise may also occur. A sample gas turbine can be established within the range of pseudo-gas turbines having substantial similarity to The pseudo-gas turbine may be, for example, determined to be within the learning range because it is similar in structure, specifications, and performance among other types of gas turbines that are not exactly the same model as the currently considered gas turbine. Since the learning range may vary depending on the situation, the range of the pseudo-gas turbine may be adjusted accordingly. In this way, by selecting a sample gas turbine from among various gas turbines including the currently considered gas turbine and other gas turbines, and learning the collected operation data of the sample gas turbine(s), it provides more sensitive and accurate prediction results. influence factors can be derived. The sample gas turbine may include a gas turbine in which a sample denitration catalyst is positioned at a rear end thereof, and a sample reducing agent injection unit is formed between the sample gas turbine and the sample denitration catalyst. As described above, by applying a gas turbine having a reducing agent injection part and a denitration catalyst located at the rear end of the gas turbine included in the exhaust gas processing apparatus according to an embodiment of the present invention as a sample gas turbine, the operation data and the exhaust gas composition data obtained therefrom are It can be used as data in a state with less noise, and the amount of processed data can be avoided from becoming excessively large. A reduction in the amount of data is particularly desirable in terms of device efficiency.

The computer of the learning-derivation step (S100) may be implemented in various forms. This is the same in the learning-prediction step (S200) and the target-control step (S300), which will be described later, and the implementation method or form of a computer capable of performing each of these steps is not specifically limited. For example, each step of the exhaust gas treatment method may be performed on one physically integrated computer, or may be performed on an independent computer separate from each other. For example, each step can be performed through a kind of program module that includes one or a plurality of operation programs. Various types of devices formed may be computers. Therefore, it is not necessary to be limited by the name of a computer, and for example, a control device such as a PLC (Programmed Logic Controller) may be substantially within the scope of the computer of the present invention. By utilizing such a computer device, it is possible to configure an exhaust gas processing apparatus capable of performing the exhaust gas processing method of the present invention. A specific embodiment of the exhaust gas treatment apparatus is as described above.

The learning-derived step ( S100 ) may be performed before the gas turbine actually starts operating. That is, the above-mentioned influencing factors can be derived first by learning the correlation between the operation data of the sample gas turbine and the composition data of the related flue gas collected before the operation of the gas turbine by the machine-learning method, and then Based on real-time data learning, it is possible to more accurately predict the concentration of nitrogen oxides.

Thereafter, the learning-prediction step (S200) is performed. The learning-prediction phase proceeds when the actual gas turbine is operated. In the learning-prediction step (S200), the computer analyzes the time-dependent correlation of the change in the influencing factor measured in real time during gas turbine operation and the consequent change in the nitrogen oxide concentration in the exhaust gas in a machine-learning method using an artificial intelligence learning algorithm. It learns and predicts the concentration of nitrogen oxides in the exhaust gas at the first time point during gas turbine operation and at the second time point when the time has elapsed. That is, the influence factor derived earlier in the learning-prediction step (S200) is applied to the analysis of the actual gas turbine operation situation, and the correlation of the influence factor change on the change in the nitrogen oxide concentration in the exhaust gas is identified in real time. At this time, the machine-learning method learning by the artificial intelligence learning algorithm is performed on the computer, and through this, in particular, the time-dependent correlation of the change in the influencing factor that fluctuates in real time and the change in the nitrogen oxide concentration in the exhaust gas is learned and measured. Depending on the value of the influencing factor, it is possible to predict what the nitrogen oxide concentration will have in the future. For example, the correlation between the influencing factor and the nitrogen oxide concentration can be identified as a time-dependent relationship. It is possible to predict the nitrogen oxide concentration in the flue-gas.

In this learning-prediction step (S200), real-time measured data is learned, not pre-collected data. The data measured in real time includes the change value of the influencing factor measured in real time, which is the time-dependent values of the above-mentioned influencing factor derived as a part of the currently considered operation data of the gas turbine, and the change value thereof, and The nitrogen oxide concentration in the flue gas and its fluctuation value may be included. For example, these data may also include time information in which the measurement time or data generation time is recorded during real-time measurement, and the change with time between each data (that is, the influencing factor and the resulting nitrogen oxide concentration) from this time information relationships can be learned. In this way, the measured values that change in real time are quickly learned through an artificial intelligence learning algorithm to derive the correlation of the change over time in the nitrogen oxide concentration according to the change of the influencing factor, and from this, the first point in time, the second point in the future The concentration of nitrogen oxides in the exhaust gas at time 2 can be predicted. At this time, the artificial intelligence learning algorithm can use, for example, a recurrent neural network algorithm that outputs a calculation result in consideration of the time dependence of the input data, and derives the result of learning the correlation between time-varying data more correctly from this. It can accurately predict the nitrogen oxide concentration.

That is, the present invention is formed to be able to derive and predict results that are difficult to derive conventionally by applying a machine-learning method based on artificial intelligence to at least two different steps. Data can be learned repeatedly in a computer in a short time through an artificial intelligence learning algorithm, and the learning algorithm is configured to utilize an artificial neural network in which a plurality of computational nodes are interrelated. can Therefore, it is possible to closely grasp correlations that were difficult to easily identify with conventional analysis methods, and it is possible to derive influence factors that more sensitively affect the concentration of pollutants and effectively use them for analysis. In addition, based on the analysis of these influencing factors, it is possible to predict with higher accuracy how the nitrogen oxide concentration will fluctuate with time, and to perform the control based on the prediction more conveniently.

Thereafter, the target-control step (S300) is performed. In the target-control step, the calculated value of the reducing agent injection amount corresponding to the nitrogen oxide concentration in the exhaust gas at the future point in time predicted in the learning-prediction step (S200), that is, the second time point is obtained, and the reducing agent transport process is controlled from the first point At the second point in time, control is performed to match the amount of reducing agent injected into the exhaust gas with the calculated value of the reducing agent injection amount. That is, the reducing agent injection amount that can solve this is calculated according to the predicted contaminant concentration at the second time point, which is the future point from the first time point. It is possible to match the injection amount of the reducing agent injected into the exhaust gas at the second time point with the calculated value of the reducing agent injection amount. This includes, for example, the concept of time difference control in consideration of the time required for the reducing agent transport process, and is particularly effective because it is possible even when the concentration of the exhaust gas is changed rather than fixed. That is, through the analysis based on the above-described artificial intelligence learning method, for example, the nitrogen oxide concentration after the required time has elapsed can be predicted with high accuracy, and the reducing agent injection amount according to the prediction time while repeatedly predicting the nitrogen oxide concentration at a future time point It is possible to repeat the time difference control to adjust Therefore, even nitrogen oxides with varying concentrations can be accurately and precisely treated by prediction.

In this target-control step (S300), the first time point may be a time point during gas turbine operation, and the second time point may be a time elapsed longer than that, and the first time point may be a future time point. The interval between the first time point and the second time point may vary, and this may be intentionally changed according to circumstances. For example, it may have an interval of minutes, but it is also possible to increase or decrease the interval as needed. For example, the interval between the first time point and the second time point may be adjusted with a wider time interval than that in consideration of the time required for the above-described reducing agent transfer process, and the required time may be gradually reduced by controlling the transfer process as described below. While changing, the interval between the first time point and the second time point may be adjusted as needed. Also, the time interval between the first time point and the second time point may be variously adjusted in a different manner. Specific details related to the target-control step, such as the first time point and the second time point, the calculation method of the reducing agent injection amount, and the reducing agent transfer process, will also be described later in more detail.

Through these steps, the exhaust gas treatment method of the present invention predicts the nitrogen oxide concentration value of the future time from the value of the influencing factor at the present time point, and can supply a reducing agent capable of accurately treating the nitrogen oxides at the predicted time point. When the relationship between the change in the influence factor and the change in the concentration of nitrogen oxide is derived through artificial intelligence-based learning, it is possible to continuously predict the concentration of nitrogen oxide in the future after a certain period of time while continuously monitoring the change in the influencing factor. In addition, through repeated learning, the correlation between the change in the influence factor and the change in the nitrogen oxide concentration can be gradually increased, and it is possible to continuously improve the accuracy of the control process while the control process is in progress. In this way, while predicting the nitrogen oxide concentration in the exhaust gas during gas turbine operation, it is possible to control the supply of the reducing agent so that the predicted nitrogen oxide is more accurately removed.

Hereinafter, with reference to FIG. 5, the prediction of the nitrogen oxide concentration and the supply of the reducing agent will be described in more detail.

Figure 5 is a time table showing the processing process related to the prediction of the pollutant concentration and the supply of the reducing agent over time [Fig. It is a drawing showing together.

In conjunction with FIG. 5, the description will proceed with reference to FIGS. 1 to 4 . Although not shown on the time table, the above-described learning-derivation step (refer to S100 in FIG. 4) may be performed by the data analysis module (refer to 100 in FIG. 1), which starts operation of the gas turbine (refer to 10 in FIG. 1) It may proceed in advance before the time point T _{0 .} As described above, the computer learns the correlation between the operation data of the previously collected sample gas turbine and the composition data of the associated flue gas by the artificial intelligence learning algorithm (eg, learning by the machine-learning method by the artificial intelligence learning algorithm) ) to derive the factors affecting the nitrogen oxide concentration in the exhaust gas. At this time, for example, this process may be performed in the above-described data learning module 100 in the computer, and information on the derived influence factors is provided by the concentration prediction module (see 200 in FIG. 1 ) and the process control module (see 300 in FIG. 1 ). can be transmitted, etc.

After the gas turbine 10 starts to operate, the above-described learning-prediction step (refer to S200 of FIG. 4 ) proceeds. That is, the learning-prediction step is performed based on the data measured in real time after _{the operation start time (T 0 ) of the gas turbine 10 .} That is, as described above, the computer learns the correlation over time of the change in the influencing factor measured in real time during the operation of the gas turbine 10 and the change in the nitrogen oxide concentration in the exhaust gas according to it by the artificial intelligence learning algorithm (e.g., The concentration of nitrogen oxides in the exhaust gas is predicted _{at the first time point (T 1} ) during gas turbine operation by learning by machine-learning method by artificial intelligence learning algorithm), and at the second time point (T _{2 ) that has elapsed more than that.} At this time, for example, this process may be performed in the above-described concentration prediction module 200 in the computer, and the derived concentration prediction value may be transmitted to the process control module 300 .

As described above, the influencing factor may be derived as a part of the driving data, and the type or number of the influencing factor may vary depending on the situation as described above. In addition, nitrogen oxides in the flue gas to which these influence factors change the concentration include nitrogen monoxide and nitrogen dioxide, and other nitrogen oxides may also be included. However, below, a more detailed explanation related to the reducing agent supply process is provided by assuming a situation in which the influencing factors correlated with nitrogen monoxide and nitrogen dioxide are derived and the concentrations of nitrogen monoxide and nitrogen dioxide are predicted through the learning-prediction step.

The learning process of the learning-prediction stage may be started with operation of the gas turbine 10 , and the learning process may be continued while actual data is supplied and appropriate data is provided. This can be adjusted, and as described above, when the concentration prediction module 200 is formed of a plurality of calculation programs, the learning process is performed while the process related to the prediction of the concentration of nitrogen oxides in the exhaust gas can be performed in parallel. Since the influencing factor is derived as a part of the operation data as described above, real-time measured values and change values of the influencing factor can be provided through various facilities or sensors in the thermal power plant that can collect the operation data of the gas turbine 10 in operation. have. Since the exhaust gas (A) is _{continuously generated from the starting point of operation (T 0} ) of the gas turbine 10 to the ending point of operation (T _x ), the main exhaust gas flow path in the thermal power plant is the duct (refer to 20 in FIG. 1) and the stack. (See 30 of FIG. 1) It is possible to receive a real-time measured value and change value of the nitrogen oxide concentration in the exhaust gas through a concentration sensor disposed on the back. That is, on the other hand, the process of predicting the nitrogen oxide concentration of the future time from the updated result while receiving the measured value of the influencing factor and the measured value of the nitrogen oxide concentration in the exhaust gas provided in real time and proceeding with the learning by the aforementioned machine learning can

For better understanding, only one set of the first time point (T ₁ ) and the second time point (T ₂ ) is shown on the timetable, but these sets are repeatedly generated with a lag according to the iterative prediction of the concentration prediction module 200 . can be Accordingly, the control operation of the process control module 300 to be described later is also repeatedly performed accordingly, and it is possible to continuously perform control according to the nitrogen oxide concentration at a future time point.

The time interval between the first time point (T _{1 ), which is a time when prediction is performed, and the second time point (T 2} ), which is a prediction time of the future that has elapsed more than that, may be adjusted as needed, but preferably, the time interval is at least It may be 20 seconds, more preferably 40 seconds to 5 minutes, even more preferably 40 seconds to 3 minutes. Such a time interval is more preferable in terms of predictability and processing efficiency according to prediction. Separately from the above steps, the nitrogen oxide concentration predicted at the second time point (T ₂ ) can be repeatedly compared with the actual value measured at that time point, and the validity of the correlation derived from the concentration prediction module 200 through this It is also possible to determine For example, the correlation over time between the influencing factor and the nitrogen oxide concentration derived by the concentration prediction module 200 can be determined to be valid only when the predicted value agrees with the actual value by at least 80%, for example, the degree of agreement is higher than that If it is low, you can stop predicting and continue learning. The learning-prediction phase is not formal and can take many different forms. The time interval between the first time point (T ₁ ) and the second time point (T ₂ ) is preferably set to be larger than the required time of the transfer process shown in the above-described reducing agent transfer unit (see 400 of FIG. 1 ). When the operation of the reducing agent transfer unit 400 is adjusted according to the control of the process control module 300 to change the required time of the transfer process, the time between the first time point (T ₁ ) and the second time point (T ₂ ) You can also change the spacing.

The target-control step may be performed from _{the first time point (T 1} ) at which the nitrogen oxide concentration in the exhaust gas is predicted. As described above, the target-control step (see S300 of FIG. 4 _{) calculates the reducing agent injection amount (Q e} ) corresponding to the nitrogen oxide concentration in the exhaust gas _{at the second time point (T 2} ) predicted in the learning-prediction step, and the first By controlling the transfer process of the reducing agent from the time point (T ₁ ), the amount of the reducing agent injected into the exhaust gas along the transfer process is matched with the calculated value of the reducing agent injection amount (Q _{e ) at the second time point (T 2 ).} This may be performed, for example, by the process control module 300 formed on the computer, and the process control module 300 considers both the _{calculated reducing agent injection amount (Q e} ) and the predicted time (T _{2 ) reducing agent transfer unit 400} ) to control the operation.

At this time, as described above, before or after the supply of the reducing agent, the process of automatically diagnosing and resolving the abnormal state may be performed first or together. That is, the target-control step includes the steps of automatically diagnosing an abnormal condition in the exhaust gas flow path including the gas turbine 10 with a computer before or after supplying the reducing agent as described above, and when an abnormal condition is found, a computer control system and It may include a detailed step including the step of automatically resolving the abnormal state by controlling at least any one of the reducing agent transfer process. In this case, the step of automatically resolving the abnormal state may include a process of controlling the concentration of the reducing agent in the exhaust gas flow path including the gas turbine 10 to remove the risk of explosion and fire due to the excess of the reducing agent. This operation may be made, for example, at the beginning of the first time point (T ₁ ) when the control of the reducing agent transfer process is started.

For example, the process of removing the risk of explosion and fire due to the excess of the reducing agent is performed by controlling the reducing agent transport process when at least one of the temperature and pressure of the reducing agent transport path exceeds 20% at the normal temperature and normal pressure. After removing the risk of explosion and fire by rapidly reducing or stopping the injection amount of the reducing agent, it can be performed by restarting the injection of the reducing agent. During the process of removing the risk of explosion and fire as described above, for example, the reducing agent transport conditions (for example, increasing the reducing agent injection amount, etc.) and/or the operating conditions of the gas turbine 10 (controlling the concentration of by-products such as ammonia) change of operating conditions, etc.) may be ignored.

In addition, the step of automatically resolving the abnormal state may include, for example, adjusting the contact ratio between the reducing agent and the exhaust gas by adjusting at least one of the flow rate and pressure of the reducing agent injected into the exhaust gas flow path. For example, a change in at least one of the reducing agent flow rate and pressure measured with a measuring device (eg, it may include a flow rate and/or a pressure sensor) formed on one side of the reducing agent injection unit 500, etc. , the reducing agent according to the flue gas amount change (can be found through calculation from the flow rate and/or temperature change, etc.) By controlling at least one of the flow rate and pressure of the , it is possible to adjust the contact molar ratio between the reducing agent and the exhaust gas to have an appropriate value throughout the injection region. Through this, as described above, it is possible to solve abnormal conditions such as excessively lowering of flue gas treatment performance such as denitrification performance or excessively increasing concentration of by-products due to flue gas treatment.

_{The process control module 300 calculates the reducing agent injection amount (Q e} ) corresponding to the predicted concentration of the second time point (T ₂ ) as described above, and controls the reducing agent transfer process to control the amount of the reducing agent injected into the exhaust gas. Match at time point T _{2 .} That is, the reducing agent is controlled so that the reducing agent is injected in an amount accurately calculated according to the predicted value, rather than simply arbitrarily injecting the reducing agent. The calculated reducing agent injection amount (Qe) is calculated _{according to the predicted nitrogen oxide concentration at the second time point (T 2} ), and is calculated as an amount capable of resolving the pollutant at the predicted time point. As described above, assuming that the predicted nitrogen oxide concentrations are nitrogen monoxide and nitrogen dioxide, this will be described in more detail as follows.

The nitrogen oxide concentration predicted in the learning-prediction step (S200) includes nitrogen monoxide and nitrogen dioxide, and the calculated value of the reducing agent injection amount (Qe) obtained in the target-control step (S300) is the second time point (T ₂ ) Prediction It can be obtained by calculating the required amount of a hydrocarbon-based reducing agent by interlocking with nitrogen dioxide contained in nitrogen oxides. At this time, it can be obtained by setting an amount corresponding to 0.5 equivalents of nitrogen dioxide contained in nitrogen oxides in the exhaust gas at the second time point (T _{2 ) as the maximum amount of the hydrocarbon-based reducing agent.} That is, by allowing the hydrocarbon-based reducing agent to reduce 1/2 of the maximum nitrogen dioxide to nitrogen monoxide, the content of nitrogen dioxide in the exhaust gas can be reduced, and the NO ₂ /NO ratio in the exhaust gas can be set to 1 or less. Therefore, it is possible to suppress yellow smoke caused by nitrogen dioxide, and it is possible _{to make a NO 2} /NO ratio suitable for the denitrification reaction by the ammonia-based reducing agent and the denitrification catalyst.

In addition, it can be obtained by setting an amount corresponding to 1 equivalent of nitrogen oxide in the exhaust gas at the second time point (T _{2 ) as the maximum amount of the ammonia-based reducing agent. Since the NO 2} /NO ratio is adjusted suitable for denitration by catalytic reaction by the hydrocarbon-based reducing agent, the ammonia-based reducing agent reduces nitrogen oxides even when the amount corresponding to one equivalent of nitrogen oxide is set to the maximum regardless of the nitrogen dioxide concentration. can be sufficiently reduced.

By setting the maximum amount of the hydrocarbon-based reducing agent and the ammonia-based reducing agent as described above, the amount of the reducing agent used is reduced, yellow smoke is suppressed, and denitration by catalytic reaction can occur effectively.

Specifically, the maximum amount of the reducing agent can be obtained by applying a standard equivalent ratio (NSR: Normalized stoichiometric ratio) of the reducing agent. For example, the maximum amount of the hydrocarbon-based reducing agent may be calculated by applying Equation 1 or Equation 1-1. Equation 1-1 is a modification of Equation 1, and is an expression reflecting the standard oxygen concentration correction. That is, Equation 1 represents the formula for calculating the reducing agent injection amount without the standard oxygen concentration correction. By applying Equation 1 or Equation 1-1 as described above, the reducing agent injection amount is calculated regardless of the presence or absence of oxygen correction can do. At this time, _{of course, NO 2i} in Equation 1-1 represents the concentration in which the standard oxygen concentration correction is reflected. In other words, NO _2i in Equation 1 represents a concentration based on an actual value to which standard oxygen concentration correction is not reflected, but NO _2i in Equation 1-1 is actually a standard oxygen concentration correction coefficient {m = (21) -Standard oxygen concentration)/(21-actual oxygen concentration)} shows the concentration based on the multiplied value. _{NO 2i} in Equation 1-1 is expressed not to be complicated as follows, but may be expressed in the same way as _{NO 2i (std) if necessary.}

[Equation 1]

In the above formula, Q _e1 is the amount of hydrocarbon-based reducing agent (kg/hr), Q is the amount of exhaust gas (Nm ³ /hr. dry), NO _2i is nitrogen dioxide concentration (ppm), MW is the reducing agent molecular weight, P is the reducing agent purity (%) , NSR is the reducing agent standard equivalent ratio (0.5).

[Equation 1-1]

In the above formula, Q _e1 is the amount of hydrocarbon-based reducing agent (kg/hr), Q is the amount of exhaust gas (Nm ³ /hr. dry), NO _2i is nitrogen dioxide concentration (ppm), O _2A is the actual oxygen concentration (%, dry), O _2R is the standard oxygen concentration (%, dry), MW is the reducing agent molecular weight, P is the reducing agent purity (%), and NSR is the reducing agent standard equivalent ratio (0.5).

In this case, the amount of exhaust gas and the actual oxygen concentration may be a value at the first time point or a value at the second time point predicted therefrom. Since the change in the amount of exhaust gas and oxygen concentration with time is not relatively large compared to pollutants such as nitrogen oxides, the value at the first time point may be used, and the predicted value predicted in the same way as the pollutant concentration prediction of the present invention can also be used For example, in steps (a) and (b), instead of 'influencing factors affecting nitrogen oxide concentration in exhaust gas', 'influencing factors affecting oxygen concentration in exhaust gas' were applied, and The oxygen concentration can be predicted. In addition, in step (a), 'operating data and flue gas amount other than exhaust gas amount' is applied instead of 'operation data and flue gas composition data', and in steps (a) and (b), 'influence of nitrogen oxide concentration in exhaust gas' It is also possible to predict the amount of exhaust gas at the second point in time by applying the 'influencing factor on the exhaust gas quantity' instead of the 'influencing factor'.

The standard oxygen concentration may have different values depending on the pollutant and the emission facility, and may be the value described in the 'Permissible Emission Standards for Air Pollutants' under the Enforcement Regulations of the Air Conservation Act of Korea.

In addition, the maximum amount of the ammonia-based reducing agent can be calculated by applying Equation 2 or Equation 2-1. Equation 2-1 is a modification of Equation 2 and reflects the standard oxygen concentration correction. In other words, Equation 2 represents a formula for calculating the reducing agent injection amount while omitting the standard oxygen concentration correction. can be calculated. At this time, of course, NOxi, NOxo, and M in Equation 2-1 represent concentrations in which standard oxygen concentration correction is reflected. That is, NOxi, NOxo, and M in Equation 2 represent concentrations based on the measured values to which standard oxygen concentration correction is not reflected, but NOxi, NOxo, and M in Equation 1-1 are actually measured values with standard oxygen concentration correction coefficients It represents the concentration based on the value multiplied by {m=(21-standard oxygen concentration)/(21-actual oxygen concentration)}. NOxi, NOxo, and M in Equation 2-1 are briefly expressed so as not to complicate the expressions as follows, but may be expressed in the same way as NOxi(std), NOxo(std), M(std), respectively, if necessary. there is also

[Equation 2]

In the above formula, Q _e2 is the amount of ammonia-based reducing agent (kg/hr), Q is the amount of exhaust gas (Nm ³ /hr. dry), NOx _i is the nitrogen oxide concentration (ppm), NOx _o is the nitrogen oxide target concentration (ppm), M is the design margin (margin, less than 20% of NOxi), MW is the molecular weight of the reducing agent, P is the reducing agent purity (%), and NSR is the reducing agent standard equivalent ratio (1).

[Equation 2-1]

In the above formula, Q _e2 is the amount of ammonia-based reducing agent (kg/hr), Q is the amount of exhaust gas (Nm ³ /hr. dry), NOx _i is the nitrogen oxide concentration (ppm), NOx _o is the nitrogen oxide target concentration (ppm), M is the design margin (margin, value less than 20% of NOxi), O _2A is the actual oxygen concentration (%, dry), O _2R is the standard oxygen concentration (%, dry), MW is the reducing agent molecular weight, and P is the reducing agent purity ( %), NSR is the reducing agent standard equivalent ratio (1).

At this time, the amount of exhaust gas, the actual oxygen concentration, and the standard oxygen concentration are the same as in Equation 1 or Equation 1-1, and the nitrogen oxide target concentration represents a value lower than the nitrogen oxide concentration, and may be determined in consideration of the nitrogen oxide treatment rate .

As a result, the maximum value of the reducing agent injection amount (Qe) can be calculated by Equation (3).

[Equation 3]

Qe=Qe ₁ +Qe ₂

In the above formula, Q _e is the reducing agent injection amount (kg/hr), Q _e1 is the hydrocarbon-based reducing agent amount calculated by Equation 1 or Equation 1-1 (kg/hr), Q _e2 is Equation 2 or Equation 2 It is the amount of ammonia-based reducing agent (kg/hr) calculated by -1.

By varying the amount of each reducing agent according to the predicted nitrogen oxide or nitrogen dioxide concentration with such a maximum value as a limit, it is possible to easily treat flue gases with fluctuating nitrogen monoxide and nitrogen dioxide contents.

_{In the end, a more accurate amount of reducing agent is sprayed at the predicted second time point (T 2} ) by applying an equation that can determine the injection amount according to the predicted change in nitrogen oxide and nitrogen dioxide concentrations and the type of reducing agent to remove nitrogen oxides in the exhaust gas. It is possible.

The reducing agent injection amount (Q _e ) calculated in this way is to remove the nitrogen oxides at the second time point (T ₂ ), which has elapsed time than the first time point (T _{1 ) at which the prediction is advanced.} The transfer process of the reducing agent is controlled from _{the first time point (T 1} ) in advance in consideration of the time difference due to the time required or the transfer process. The process control module 300, for example, transmits a control signal on the reducing agent transfer unit 400 described above to change the opening degree of the pipeline or the transfer route of the reducing agent moving along the pipeline, and through this, the transfer process You can check and adjust the required time. Through this, the amount of the reducing agent injected from the reducing agent injection unit (see 500 in FIG. 1) to the duct (see 20 in FIG. 1) through which the exhaust gas A flows can be adjusted with a time difference, and the target time is set to the second By controlling to match the time point (T ₂ ), the amount of the reducing agent injected into the exhaust gas along the transfer process as shown in FIG. 5 at the second time point (T ₂ ) can be matched with the calculated value of the reducing agent injection amount (Q _{e ).} Therefore, if you actually know only the actual measured value of the influencing factor at the first time point (T _{1 ), predict the nitrogen oxide concentration at the second time point (T 2} ), which has elapsed more than that, and accurately calculate the reducing agent injection amount (Qe). A suitable process may be performed at a second time point (T _{2 ) after the time.} Although the concentration of nitrogen oxides can be changed, it is possible to more accurately predict how the concentration will change from the influencing factors by deriving more sensitive influencing factors based on the aforementioned artificial intelligence learning and more accurately discriminating the correlation between the influencing factors and nitrogen oxides. As a result, it is possible to more actively respond to nitrogen oxides, whose emission patterns change with time. In addition, since the reducing agent is sprayed in an accurately calculated amount according to the predicted concentration, it is possible to minimize risk factors such as excessive reducing agent. As described above, it is possible to effectively treat the nitrogen oxide-containing flue gas of a thermal power plant by using the present invention.

<Experimental Example 1> Nitrogen oxide treatment experiment using two types of reducing agents

The nitrogen oxide treatment experiment was carried out by setting an amount corresponding to 0.5 equivalent of nitrogen dioxide in the exhaust gas as the maximum amount of hydrocarbon-based reducing agent, and an amount corresponding to 1 equivalent of nitrogen oxide in the exhaust gas as the maximum amount of ammonia-based reducing agent.

Specifically, for the simulated exhaust gas under the following conditions, a reducing agent (ethanol, ammonia) in an amount calculated by applying Equations 1 to 3 was injected into a selective catalytic reduction device equipped with a denitration catalyst to treat nitrogen oxides. At this time, 15% dry, 46, 100% wt, and 0.5 were applied to standard oxygen concentration, reducing agent molecular weight, reducing agent purity, and NSR in Equation 1-1, respectively. In Equation 2-1, 3ppmvd, 0.4ppmvd, 15% dry, 17, 100% wt, and 1 were applied for nitrogen oxide target concentration, design margin, standard oxygen concentration, reducing agent molecular weight, reducing agent purity, and NSR, respectively. The nitrogen oxide treatment rate was obtained by dividing the difference in nitrogen oxide content before and after treatment by the nitrogen oxide content before treatment and multiplying by 100. As a result, the nitrogen oxide treatment rate was 98%. In addition, the measured values of hydrocarbon compounds and ammonia measured at the rear end of the denitration catalyst during the experiment were 0.5 ppm or less, respectively.

O Exhaust gas conditions

Flue gas volume 9,000 Nm ³ /hr, dry

Nitrogen oxide inlet concentration 61 ppmvd (standard oxygen concentration correction standard)

Nitrogen dioxide inlet concentration 39 ppmvd (standard oxygen concentration correction standard)

Actual oxygen concentration 15%, dry (Base gas N ₂ )

O Reductant injection amount calculation process

Qe=Qe ₁ +Qe ₂

=0.76 kg/hr

From this result, the amount corresponding to 0.5 equivalent of nitrogen dioxide contained in nitrogen oxide in the exhaust gas is set as the maximum amount of the hydrocarbon-based reducing agent, and the amount corresponding to 1 equivalent of nitrogen oxide in the exhaust gas is set as the maximum amount of the ammonia-based reducing agent. It can be seen that by applying the obtained value as the maximum amount of the reducing agent, it is possible to effectively treat nitrogen oxides, and the concern about the excess of the reducing agent can be avoided. In particular, according to the present invention, reducing agents of different series are appropriately applied not only in terms of quantity, but also in terms of time, by being preemptively applied in terms of time, more actively treating the flue gas with a rapidly changing nitrogen oxide concentration know you can do it.

Although the embodiments of the present invention have been described above with reference to the accompanying drawings, those of ordinary skill in the art to which the present invention pertains can realize that the present invention can be embodied in other specific forms without changing the technical spirit or essential features. you will be able to understand Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

1: Nitrogen oxide-containing flue gas treatment device of thermal power plant 10: Gas turbine
20: duct 21: heat exchange module
22: denitration catalyst 30: stack
40: control system 100: data learning module
200: concentration prediction module 300: process control module
400: reducing agent transfer unit 500: reducing agent injection unit
550: additional reducing agent injection unit 600, 650: reducing agent storage unit
A: flue gas B: reducing agent

Claims (13)

a reducing agent injection unit formed between the gas turbine and the denitration catalyst;
a reducing agent transfer unit for transferring the reducing agent to the reducing agent injection unit;
a data learning module that receives the correlation between the operation data of the previously collected sample gas turbine and the exhaust gas composition data, and learns it by an artificial intelligence learning algorithm to derive influence factors affecting the nitrogen oxide concentration in the exhaust gas;
The artificial intelligence learning algorithm receives the measured value of the change in the influencing factor measured in real time during the operation of the gas turbine and the change in the nitrogen oxide concentration in the exhaust gas accordingly, and the correlation over time between the influencing factor and the nitrogen oxide concentration a concentration prediction module for estimating the concentration of nitrogen oxides in the exhaust gas at a second point in time that has elapsed from the first point in time during gas turbine operation by learning by; and
Obtain the calculated reducing agent injection amount corresponding to the nitrogen oxide concentration in the exhaust gas at the second time point predicted by the concentration prediction module, control the reducing agent transfer unit from the first time point, and inject through the reducing agent injection unit at the second time point A process control module for matching the amount of reducing agent to be injected with the calculated value of the reducing agent injection,
The nitrogen oxides include nitrogen monoxide and nitrogen dioxide,
The reducing agent includes a hydrocarbon-based reducing agent and an ammonia-based reducing agent,
The calculated value of the reducing agent injection amount is obtained by setting the amount corresponding to 0.5 equivalent of nitrogen dioxide included in the nitrogen oxide in the exhaust gas at the second time point predicted by the concentration prediction module as the maximum amount of the hydrocarbon-based reducing agent, and the hydrocarbon-based reducing agent The maximum amount of the reducing agent is a nitrogen oxide-containing flue gas treatment device of a thermal power plant calculated by applying the following Equation 1 or Equation 1-1.
[Equation 1]

In the above formula, Q _e1 is the amount of hydrocarbon-based reducing agent (kg/hr), Q is the amount of exhaust gas (Nm ³ /hr.dry), NO _2i is nitrogen dioxide concentration (ppm), MW is the reducing agent molecular weight, P is the reducing agent purity (%) , NSR is the reducing agent standard equivalent ratio (0.5).
[Equation 1-1]

In the above formula, Q _e1 is the amount of hydrocarbon-based reducing agent (kg/hr), Q is the amount of exhaust gas (Nm ³ /hr. dry), NO _2i is nitrogen dioxide concentration (ppm), O _2A is the actual oxygen concentration (%, dry), O _2R is the standard oxygen concentration (%, dry), MW is the reducing agent molecular weight, P is the reducing agent purity (%), and NSR is the reducing agent standard equivalent ratio (0.5). delete delete According to claim 1, wherein the artificial intelligence learning algorithm of the data learning module and the concentration prediction module comprises an artificial neural network algorithm in which at least one hidden layer consisting of a plurality of computation nodes is formed between the input layer and the output layer, the concentration prediction module The artificial neural network algorithm of, a nitrogen oxide-containing exhaust gas processing apparatus of a thermal power plant including a cyclic neural network algorithm that outputs a calculation result in consideration of the time dependence of input variables. The apparatus of claim 1, wherein the operation data comprises at least one selected from the group consisting of an exhaust gas temperature between the sample gas turbine and a sample denitration catalyst at the rear end of the sample gas turbine, and an exhaust gas flow rate. The apparatus of claim 1, wherein the exhaust gas composition data includes exhaust gas composition data between the sample gas turbine and the sample denitration catalyst at the rear end of the sample gas turbine. According to claim 1, Between the gas turbine and the denitration catalyst, flue gas temperature, flue gas flow rate, and flue gas treatment apparatus of a thermal power plant containing nitrogen oxides further comprising a measuring unit for measuring at least one selected from the composition of the flue gas. According to claim 1, wherein the nitrogen oxide-containing flue gas treatment apparatus of a thermal power plant further comprising an additional reducing agent injection part disposed between the denitration catalyst and the reducing agent injection part. According to claim 1, wherein the process control module, before or after supply of the reducing agent, automatically diagnoses an abnormal state in the exhaust gas flow path including the gas turbine, and when an abnormal state is found, the reducing agent transfer unit, and the gas turbine A nitrogen oxide-containing flue gas treatment device of a thermal power plant that automatically eliminates the abnormal condition by operating at least one controllable facility among the facilities of the thermal power plant, including: (a) a learning-derivation step in which the computer learns the correlation between the operation data of the previously collected sample gas turbine and the exhaust gas composition data by an artificial intelligence learning algorithm, and derives the influencing factors affecting the nitrogen oxide concentration in the exhaust gas;
(b) The computer learns the correlation with time of the change in the influence factor measured in real time during gas turbine operation and the change in the nitrogen oxide concentration in the exhaust gas according to the artificial intelligence learning algorithm, and the first in operation of the gas turbine a learning-prediction step of predicting the concentration of nitrogen oxides in the exhaust gas at a second time point at which time has elapsed; and
(c) obtain a calculated value of reducing agent injection corresponding to the nitrogen oxide concentration in the exhaust gas at the second point in time predicted in step (b), and control the transfer process of the reducing agent from the first time point to the exhaust gas at the second time point a target-control step of matching the amount of the injected reducing agent with the calculated value of the reducing agent injection amount;
The gas turbine has a denitration catalyst located at its rear end,
A reducing agent injection part is formed between the gas turbine and the denitration catalyst,
The nitrogen oxides include nitrogen monoxide and nitrogen dioxide,
The reducing agent includes a hydrocarbon-based reducing agent and an ammonia-based reducing agent,
In the step (c), the calculated value of the reducing agent injection amount is the amount corresponding to 0.5 equivalent of nitrogen dioxide contained in the nitrogen oxides in the exhaust gas at the second time point predicted in the step (b) as the maximum amount of the hydrocarbon-based reducing agent. Obtained by setting, the maximum amount of the hydrocarbon-based reducing agent is a nitrogen oxide-containing flue gas treatment method of a thermal power plant calculated by applying Equation 1 or Equation 1-1 below.
[Equation 1]

In the above formula, Q _e1 is the amount of hydrocarbon-based reducing agent (kg/hr), Q is the amount of exhaust gas (Nm ³ /hr. dry), NO _2i is nitrogen dioxide concentration (ppm), MW is the reducing agent molecular weight, P is the reducing agent purity (%) , NSR is the reducing agent standard equivalent ratio (0.5).
[Equation 1-1]

In the above formula, Q _e1 is the amount of hydrocarbon-based reducing agent (kg/hr), Q is the amount of exhaust gas (Nm ³ /hr. dry), NO _2i is nitrogen dioxide concentration (ppm), O _2A is the actual oxygen concentration (%, dry), O _2R is the standard oxygen concentration (%, dry), MW is the reducing agent molecular weight, P is the reducing agent purity (%), and NSR is the reducing agent standard equivalent ratio (0.5). delete delete 11. The method of claim 10, wherein the step (c) comprises the steps of: automatically diagnosing an abnormal state in the exhaust gas flow path including the gas turbine by a computer before or after supplying the reducing agent; and a detailed step comprising the step of automatically resolving the abnormal state by controlling at least one of the transfer processes.

Images