JP6673800B2 - Exhaust gas control apparatus and exhaust gas control method for gasification and melting furnace plant - Google Patents

Description

  The present invention relates to an exhaust gas control device and an exhaust gas control method for suppressing generation of NOx gas in a gasification and melting furnace plant.

  In a waste treatment plant, it is required to suppress the emission of regulated gases such as CO and NOx. Conventionally, a feedback control system based on a PID has been applied to operation control of a waste treatment plant. Patent Document 1 discloses an operation in which an optimum control target value is selected from correlation information between a predetermined waste quality and a control target value using feedback information of a process value acquired during operation of the plant, and operation is performed. A method as an input is disclosed. In the method described in Patent Literature 1, the quality of waste is estimated in advance from process information, and the emission of exhaust gas is suppressed by controlling the plant using operating conditions corresponding to the quality of the waste.

JP 2000-18549 A

  By the way, in a process where the combustion fluctuation is relatively steep such as in a gasification and melting furnace plant, the combustion state is rapidly destabilized irrespective of only the change in the waste quality, and as a result, the emission of regulated substances suddenly increases. There are cases. However, the method described in Patent Literature 1 cannot sufficiently cope with a sudden change in combustion state in a plant, and may not be able to sufficiently suppress emission of regulated substances.

  In some cases, the operator manually operates the control system so that the emission of regulated substances does not exceed the regulation value.However, since the emission of regulated substances depends on the skill of the operator, A low operator may exceed the regulation value. There is also a problem that the burden on the operator is large.

  The present invention has been made in view of such circumstances, and a main object of the present invention is to provide an exhaust gas control apparatus and an exhaust gas control method for a gasification and melting furnace plant that can suppress the emission of NOx gas without depending on the skill of an operator. Is to provide.

In order to solve the above-mentioned problem, an exhaust gas control device of a gasification and melting furnace plant according to one embodiment of the present invention is provided with a gasification furnace for incinerating waste, and the gasification furnace is connected to the gasification furnace. An exhaust gas control apparatus for a gasification and melting furnace plant having a gasification and melting furnace including a melting furnace for melting coal produced by the furnace, comprising: an air ratio in the melting furnace; and an oxygen gas at an inlet side of the melting furnace. Data acquisition means for acquiring the flow rate of the _two gases and the temperature in the gasification and melting furnace, and based on the air ratio, the flow rate of the O ₂ gas, and the temperature acquired by the data acquisition means, Predicting means for predicting the emission of high-concentration NOx gas from the gasification and melting furnace plant, and controlling the concentration of the NOx gas when the emission of high-concentration NOx gas is predicted by the prediction means. Dissolution Comprising setting means for setting an amount of air to flow into the furnace, the.

  In this aspect, the melting furnace has a narrowed portion having a smaller cross-sectional area than other portions, and the temperature is the temperature of the gasification furnace outlet, the temperature of the melting furnace top, and the temperature of the narrowed portion. May be included.

  Further, in the above aspect, the prediction unit may further include the high-concentration NOx based on at least one of a control target value of the NOx concentration contained in the exhaust gas and a main steam flow rate of a boiler communicating with the melting furnace. It may be configured to predict gas emissions.

  Further, in the above aspect, the melting furnace includes a primary combustion chamber that is generated in the gasification furnace and burns a part of a pyrolysis gas flowing from the gasification furnace, and a heat that is not burned in the primary combustion chamber. A secondary combustion chamber for burning the cracked gas, wherein the predicting means includes an exhaust gas flow rate of the gasification / melting furnace plant, an exhaust gas temperature in the secondary combustion chamber, and a temperature in a wind box connected to the gasification furnace. The high-concentration NOx gas, further based on at least one of a temperature, an exhaust gas temperature in a vertical flue provided downstream of the secondary combustion chamber, and a temperature of a sand layer provided in the gasification furnace. May be configured to predict the emission of wastewater.

Further, in the above aspect, the exhaust gas control device may include a prediction rule including a condition including the air ratio, the flow rate of the O ₂ gas, and the temperature, and a result indicating whether or not the high-concentration NOx gas is discharged. Generating means for generating the air ratio, the flow rate of the O ₂ gas, the temperature, and the actual value of the concentration of the NOx gas in the exhaust gas. The predicting means includes: It may be configured to predict the emission of the high-concentration NOx gas using a prediction rule.

  Further, in the above aspect, the generation unit may be configured to generate the prediction rule by decision tree learning.

In the above aspect, the exhaust gas control device further includes an identification unit that identifies a reaction time TR of NOx in the gasification and melting furnace plant based on the actual value of the air ratio and the concentration of NOx gas in the exhaust gas. The generation unit has the condition including the air ratio, the flow rate of the O ₂ gas, and the temperature at time t, and the result indicating whether or not the high-concentration NOx gas is discharged at time t + TR. It may be configured to generate a prediction rule.

  In the above aspect, the prediction unit predicts the emission of the high-concentration NOx gas using a first prediction rule that is the prediction rule whose result indicates that the high-concentration NOx gas is discharged. The setting means is configured to use the second prediction rule, which is the prediction rule indicating that there is no emission of the high-concentration NOx gas, to set the amount of air to flow into the melting furnace. May be set.

Further, in the above aspect, the setting unit acquires the air ratio, the flow rate of the O ₂ gas, and the representative value of the temperature actual value that meet the conditions of the second prediction rule, and The representative value closest to the current value including the specified air ratio, the flow rate of the O ₂ gas, and the temperature is specified, and based on the specified representative value, the amount of air to be flown into the melting furnace is set. May be configured.

In the above aspect, the setting means may include a plurality of coordinates of the representative value when each item of the condition including the air ratio, the flow rate of the O ₂ gas, and the temperature is a coordinate axis, and the current value May be configured to specify a representative value closest to the current value based on a distance from the coordinates.

  Further, in the above aspect, the setting means clusters the plurality of representative values in a coordinate space defined by the coordinate axes, and based on a distance between barycentric coordinates of the obtained plurality of clusters and coordinates of the current value. Identifying the cluster closest to the current value, and calculating the representative value closest to the current value based on the distance between the coordinates of the plurality of representative values included in the identified cluster and the coordinates of the current value. It may be configured to specify.

Further, in the above aspect, the melting furnace includes a primary combustion chamber that is generated in the gasification furnace and burns a part of a pyrolysis gas flowing from the gasification furnace, and a heat that is not burned in the primary combustion chamber. A secondary combustion chamber for burning the cracked gas, wherein the setting means is configured to supply the primary air to the primary combustion chamber based on the flow rate of the O ₂ gas included in the specified closest representative value. May be set, and the secondary air amount supplied to the secondary combustion chamber may be set based on the primary air amount and the air ratio included in the closest representative value.

In addition, an exhaust gas control method for a gasification and melting furnace plant according to another aspect of the present invention includes a gasification furnace for incinerating waste, and a coal content that is communicated with the gasification furnace and generates coal by the gasification furnace. An exhaust gas control method for a gasification and melting furnace plant having a gasification and melting furnace including a melting furnace for melting, wherein an air ratio in the melting furnace, a flow rate of O ₂ gas at an inlet side of the melting furnace, and Obtaining the temperature in the gasification and melting furnace; and discharging the high-concentration NOx gas from the gasification and melting furnace plant based on the obtained air ratio, the flow rate of the O ₂ gas, and the temperature. And setting the amount of air to flow into the melting furnace so as to suppress the concentration of the NOx gas when the emission of high-concentration NOx gas is predicted.

  ADVANTAGE OF THE INVENTION According to the exhaust gas control apparatus and the exhaust gas control method of the gasification melting furnace plant according to the present invention, the emission amount of NOx gas can be suppressed without depending on the skill of the operator.

FIG. 1 is a schematic diagram showing a schematic configuration of a gasification and melting furnace plant. FIG. 1 is a block diagram showing a configuration of an exhaust gas control device according to an embodiment. 5 is a flowchart showing a procedure of an operation of the exhaust gas control device according to the embodiment. 9 is a flowchart illustrating a procedure of a prediction rule generation process. 4 is a graph showing a melting furnace air ratio and a NOx concentration in exhaust gas during a certain period. 9 is a flowchart illustrating a procedure of a NOx reaction time identification process. 9 is a flowchart illustrating a procedure of a learning data creation process. 9 is a flowchart illustrating a procedure of a prediction rule generation process. 9 is a flowchart illustrating a procedure of a prediction rule selection process. FIG. 3 is a conceptual diagram for explaining a target value vector. 9 is a flowchart (first half) illustrating a procedure of a target value vector creation process. 10 is a flowchart (second half) illustrating a procedure of a target value vector creation process. The conceptual diagram showing the composition of the 1st prediction rule in a prediction rule database. 9 is a flowchart illustrating a procedure of a high concentration NOx emission prediction process. 9 is a flowchart (first half) illustrating a procedure of a control operation determination process. 10 is a flowchart (second half) illustrating a procedure of a control operation determination process.

  Hereinafter, preferred embodiments of the present invention will be described with reference to the drawings. Each of the embodiments described below exemplifies a method and an apparatus for embodying the technical idea of the present invention, and the technical idea of the present invention is not limited to the following. Absent. Various changes can be made to the technical idea of the present invention within the technical scope described in the claims.

<Structure of gasification and melting furnace plant>
FIG. 1 is a schematic diagram showing a schematic configuration of a gasification and melting furnace plant. The gasification and melting furnace plant 10 according to the present embodiment includes a gasification and melting furnace 15 including a gasification furnace 20 and a melting furnace 30. The gasification and melting furnace plant 10 includes a waste pit 40 for storing waste, and waste discharged from a waste collection vehicle 41 is stored in the waste pit 40. A garbage crane 42 is provided in the garbage pit 40. The garbage crane 42 grasps the waste stored in the garbage pit 40 and rises to take out the garbage from the garbage pit 40 by a fixed amount.

  A dust hopper 50 is provided next to the waste pit 40. The garbage crane 42 throws the waste material pulled up from the garbage pit 40 into the dust hopper 50. The dust hopper 50 includes a crusher (not shown) and crushes the input waste. A dust conveyor 51, which is a belt conveyor, is provided below the dust hopper 50, and crushed waste is supplied to the dust conveyor 51 by a fixed amount. The dust conveyer 51 conveys the waste and puts it into the gasification furnace 20.

  The gasification furnace 20 is provided with a fluidized bed 21 made of fluidized particles (eg, sand) at the bottom. A wind box 22 is provided at the lower portion of the fluidized bed 21. When forced air is introduced into the wind box 22 by a blower (not shown), fluidized air is ejected upward, and the fluidized particles of the fluidized bed 21 and the feeding conveyor are fed. The waste supplied by 51 is fluidized and stirred. In this gasification furnace 20, in order to recover metals such as iron and aluminum in an unoxidized state, the fluidized bed temperature (sand bed temperature) of the fluidized particles in the fluidized bed 21 is about 500 which is lower than the melting point of aluminum (600 ° C.). It is operated to reach 600 ° C. The waste is thermally decomposed in a reducing atmosphere having an air ratio of about 0.2 to 0.3 in the fluidized bed 21 to become a pyrolysis gas (combustible gas) and an unburned solid (char, ash, etc.). . A flow path 23 communicating with the melting furnace 30 is provided at the furnace top of the gasification furnace 20, and the pyrolysis gas and unburned solids are supplied to the melting furnace 30 through the flow path.

  The melting furnace 30 burns the pyrolysis gas and the unburned solids generated in the gasification furnace 20 at a high temperature of about 1300 to 1400 ° C. The flow path 23 is provided with a primary air supply port 24 for supplying combustion air, and is connected to an oxygen enrichment device 25. The primary air supply port 24 is provided with a primary air supply device 26, and the combustion air supplied from the primary air supply device 26 and the oxygen supplied from the oxygen enrichment device 25 are mixed, 30. In the melting furnace 30, a portion communicating with the flow path 23 is a primary combustion chamber 31, and the supplied combustion air is strongly swirled as indicated by an arrow in the drawing. In the primary combustion chamber 31, a part of the pyrolysis gas flowing from the gasification furnace is burned. A melting furnace auxiliary burner 35 is provided at the top of the primary combustion chamber 31 to assist combustion of the pyrolysis gas. Further, the melting furnace 30 has a narrowed portion 36 having a smaller cross-sectional area than other portions at the lower end of the primary combustion chamber 31, and has a secondary combustion chamber 32 at a stage subsequent to the narrowed portion 36. A secondary air supply port 33 is provided in the secondary combustion chamber 32, and a secondary air supply device 34 is connected to the secondary air supply port 33. The secondary combustion chamber 32 is supplied with combustion air from a secondary air supply device 34. In the secondary combustion chamber 32, the unburned pyrolysis gas is burned at high temperature by the combustion air. The ash melts, producing slag and decomposing dioxins. The molten slag is used as a useful resource by being collected outside the furnace from a slag downstream port 37 provided in a lower part of the melting furnace 30.

  The boiler 60 is attached to the melting furnace 30 and recovers heat generated in the gasification and melting process. The boiler 60 evaporates water using heat generated in the gasification and melting process, and drives a steam turbine and a generator (not shown) to generate electric power. An exhaust chimney 70 is connected to the melting furnace 30. Between the melting furnace 30 and the chimney 70, a gas cooling device (not shown), an exhaust gas treatment device (eg, a bag filter), a denitration device, and an induction blower are installed, which cool and remove dust generated by the melting furnace 30. Send it to the chimney 70. Here, a gasification and melting furnace plant provided with a boiler is described, but a gasification and melting furnace plant without a boiler may be used.

Various sensors are provided in the gasification and melting furnace plant 10 as described above. The wind box 22 has a wind box thermometer 71 for measuring the temperature inside the wind box 22 (hereinafter, referred to as “wind box temperature”), and a flow rate of the pressurized air introduced into the wind box 22 (hereinafter, “push-in”). A forced air flow meter 72 for measuring the air flow rate) and a sand layer thermometer 73 for measuring the sand layer temperature are provided. A gasifier outlet thermometer 74 for measuring the temperature of the outlet portion (hereinafter referred to as “gasifier outlet temperature”) is provided at the outlet of the gasifier 20. The primary air supply port 24 is provided with a primary air flow meter 75 for measuring the flow rate of air flowing through the flow path 23 (hereinafter, referred to as “primary air”). An O ₂ flow meter 76 for measuring the flow rate of O ₂ gas supplied from the oxygen enrichment device 25 (hereinafter, referred to as “supplied O ₂ flow rate”) is provided. At the top of the primary combustion chamber 31, a melting furnace temperature thermometer 77 for measuring the temperature of the portion (hereinafter, referred to as "melting furnace temperature") and air supplied from the melting furnace auxiliary burner 35 are provided. And an auxiliary burner air flow meter 78 for measuring the flow rate (hereinafter, referred to as “auxiliary burner air flow rate”). In addition, the throttle portion 36 of the melting furnace 30 is provided with a throttle portion thermometer 79 for measuring the temperature at the throttle portion 36 (hereinafter, referred to as “throttle portion temperature”). The secondary air supply port 33 is provided with a secondary air flow meter 80 for measuring a flow rate of combustion air (hereinafter, referred to as “secondary air”) supplied from the secondary air supply device 34. The secondary combustion chamber 32 is provided with a secondary combustion chamber exhaust gas thermometer 81 for measuring the exhaust gas temperature of the secondary combustion chamber 32 (hereinafter, referred to as “secondary combustion chamber exhaust gas temperature”). The boiler 60 has a main steam flow meter 82 for measuring the flow rate of main steam and a temperature of exhaust gas passing through a vertical flue of the boiler 60 (hereinafter, referred to as “vertical flue exhaust gas temperature”). Vertical flue exhaust gas thermometer 83 is provided. At the connection between the melting furnace 30 and the boiler 60, there is provided an O ₂ concentration meter 86 for measuring the oxygen concentration of the portion (hereinafter referred to as “secondary combustion chamber outlet O ₂ concentration”). In the equipment without the boiler 60 as described above, a thermometer is provided on the vertical flue provided downstream of the secondary combustion chamber 32, and the exhaust gas passing through the vertical flue measured by the thermometer is measured. The temperature can be used as the vertical flue gas temperature. Further, in the boiler 60 is not equipment, the O ₂ concentration meter provided at the outlet of the melting furnace 30, the O ₂ concentration measured by the O ₂ concentration meter, it can be used as a secondary combustion chamber outlet O ₂ concentration. An exhaust gas flow meter 84 for measuring the flow rate of the exhaust gas is provided in a flow path from the melting furnace 30 to the chimney 70, and a NOx concentration meter 85 for measuring the NOx concentration in the exhaust gas is provided in the chimney 70. Is provided.

The gasification and melting furnace plant 10 is connected to an exhaust gas control device 100 (see FIG. 2). Emission control device 100, the above windbox thermometer 71, forced air flow meter 72, sand thermometer 73, gasifier outlet temperature gauge 74, the primary air flow meter 75, _{O 2} flow meter 76, the melting furnace furnace top temperature Meter 77, auxiliary burner air flow meter 78, throttle section thermometer 79, secondary air flow meter 80, secondary combustion chamber exhaust gas thermometer 81, main steam flow meter 82, vertical flue exhaust gas thermometer 83, exhaust gas flow meter 84 , NOx concentration meter 85, and is connected to the O ₂ concentration meter 86, so as to receive these output data. Further, the exhaust gas control device 100 is connected to the primary air supply device 26 and the secondary air supply device 34. The exhaust gas control device 100 drives the primary air supply device 26 and the secondary air supply device 34 based on the output data of these sensors, and performs feedback control of the state of the exhaust gas (combustion state) of the gasification and melting furnace plant 10. .

<Configuration of exhaust gas control device>
Next, the configuration of the exhaust gas control device according to the present embodiment will be described. FIG. 2 is a block diagram illustrating a configuration of the exhaust gas control device according to the present embodiment. The exhaust gas control device 100 is realized by the computer 200. As shown in FIG. 2, the computer 200 includes a main body 300, an input unit 400, and a display unit 500. The main body 300 includes a CPU 301, a ROM 302, a RAM 303, a reading device 304, a hard disk 305, an input / output interface 306, and an image output interface 307. The image output interface 307 is connected by a bus.

  The CPU 301 executes the computer program loaded on the RAM 303. When the CPU 301 executes the exhaust gas control program 310, which is a computer program for exhaust gas control, the computer 200 functions as the exhaust gas control device 100.

  The ROM 302 is configured by a mask ROM, a PROM, an EPROM, an EEPROM, or the like, and stores a computer program executed by the CPU 301, data used for the computer program, and the like.

  The RAM 303 is configured by an SRAM, a DRAM, or the like. The RAM 303 is used to read the exhaust gas control program 310 recorded on the hard disk 305. The RAM 303 is used as a work area of the CPU 301 when the CPU 301 executes a computer program.

  The hard disk 305 has installed therein various computer programs to be executed by the CPU 301, such as an operating system and application programs, and data used for executing the computer programs. The exhaust gas control program 310 is also installed on the hard disk 305.

  The hard disk 305 also includes a performance database (performance DB) 320 for storing data output from each of the above-described sensors, a learning database (learning DB) 330 for storing learning data used for machine learning, and machine learning. A rule temporary storage database (rule temporary storage DB) 340 for temporarily storing the generated prediction rules, a prediction rule database (prediction rule DB) 350 for storing prediction rules used for exhaust gas control, and an evaluation of the prediction rules And an operation condition database (operation condition DB) 370 for storing data used for determining the supply amounts of the primary and secondary air.

The input / output interface 306 includes, for example, a serial interface such as USB, IEEE1394, or RS-232C, a parallel interface such as SCSI, IDE, or IEEE1284, and an analog interface including a D / A converter and an A / D converter. It is configured. An input unit 400 including a keyboard and a mouse is connected to the input / output interface 306, and a user can input data to the computer 200 by using the input unit 400. Further, the input-output interface 306, windbox thermometer 71 described above, forced air flow meter 72, sand thermometer 73, gasifier outlet temperature gauge 74, the primary air flow meter 75, _{O 2} flow meter 76, the melting furnace Furnace top thermometer 77, auxiliary burner air flow meter 78, throttle thermometer 79, secondary air flow meter 80, secondary combustion chamber exhaust gas thermometer 81, main steam flow meter 82, vertical flue exhaust gas thermometer 83, exhaust gas flow meter 84, NOx concentration meter 85, and the O ₂ concentration meter 86 is connected, and is configured to receive the output data from these sensors. Furthermore, the primary air supply device 26 and the secondary air supply device 34 are connected to the input / output interface 306, and control signals can be transmitted to these.

  The image output interface 307 is connected to the display unit 500 constituted by an LCD, a CRT, or the like, and outputs a video signal corresponding to the image data provided from the CPU 301 to the display unit 500. The display unit 500 displays an image (screen) according to the input video signal.

<Operation of exhaust gas control device>
Next, the operation of the exhaust gas control device 100 will be described. FIG. 3 is a flowchart showing a procedure of an operation of the exhaust gas control device 100 according to the present embodiment. The exhaust gas control device 100 performs a normal control process of the gasification and melting furnace plant 10 (hereinafter, referred to as a “normal control process”). This normal control processing is PID control based on output data from various sensors, and thereby keeps the state of the exhaust gas, that is, the combustion state constant.

但し、上式の「全空気流量」は、一次空気流量、二次空気流量、押込空気流量、及び補助バーナ空気流量の総和である。また、「一次側空気流量」は、全空気流量から二次空気流量を差し引いた値、即ち、溶融炉３０の入口より上流側の空気量の合計である。この前処理により、溶融炉空気比、一次側Ｏ_２流量、風箱温度、押込空気量、砂層温度、排ガス流量、ガス化炉出口温度、一次空気流量、供給Ｏ_２流量、溶融炉炉頂温度、補助バーナ空気流量、絞部温度、二次空気流量、二次燃焼室排ガス温度、主蒸気流量、二次燃焼室出口Ｏ_２濃度、垂直煙道排ガス温度、ＮＯｘ濃度のそれぞれ（以下、「運転データ」という）が取得される。その後、ＣＰＵ３０１は、取得された運転データを実績ＤＢ３２０に保存する（ステップＳ１０３）。 During the execution of the normal control, the exhaust gas control device 100 receives the data output from each of the sensors (step S101). The CPU 301 executes preprocessing such as noise elimination and smoothing on the output data (step S102). In the preprocessing, the air ratio in the melting furnace 30 (hereinafter, referred to as “melting furnace air ratio”) is expressed by the formula ( According to 1), the flow rate of the O ₂ gas at the inlet side of the melting furnace 30 (hereinafter, referred to as “primary O ₂ flow rate”) is generated according to Equation (2). Here, the inlet side of the melting furnace 30 refers to the opening of the flow path 23 in the melting furnace 30 and its vicinity, and includes the melting furnace auxiliary burner 35. In other words, the primary O ₂ flow rate is the sum of the flow rate of O ₂ gas supplied to the melting furnace 30, the flow rate of O ₂ gas supplied to the melting furnace 30 from the melting furnace auxiliary burner 35 from the flow passage 23 .

However, the “total air flow rate” in the above equation is the sum of the primary air flow rate, the secondary air flow rate, the forced air flow rate, and the auxiliary burner air flow rate. The “primary air flow rate” is a value obtained by subtracting the secondary air flow rate from the total air flow rate, that is, the sum of the air flows upstream from the inlet of the melting furnace 30. This pretreatment melting furnace air ratio, primary O ₂ flow, windbox temperature, forced air quantity, sand temperature, exhaust gas flow rate, the gasifier exit temperature, primary air flow rate, supply O ₂ flow rate, melting furnaces top temperature auxiliary burner air flow rate, diaphragm unit temperature, secondary air flow rate, secondary combustion chamber exhaust gas temperature, the main steam flow rate, secondary combustion chamber outlet O ₂ concentration, the vertical flue gas temperature, each of the NOx concentration (hereinafter, "operation Data). After that, the CPU 301 stores the obtained operation data in the performance DB 320 (step S103).

  Next, the CPU 301 refers to the prediction rule DB 350 and determines whether a prediction rule is stored (step S104). When the prediction rule is not stored in the prediction rule DB 350 (NO in step S104), the CPU 301 executes a prediction rule generation process (step S105).

  FIG. 4 is a flowchart illustrating the procedure of the prediction rule generation process. In the prediction rule generation processing, the CPU 301 first reads out operation data from the performance DB 320 (step S201). Next, the CPU 301 executes a NOx reaction time identification process (step S202).

  In the exhaust gas control device 100 according to the present embodiment, exhaust gas control is performed so as to suppress the emission of high-concentration NOx gas from the gasification and melting furnace plant 10. Therefore, emission of high-concentration NOx is predicted. For that purpose, it is necessary to consider the reaction time of NOx in the gasification and melting furnace plant 10. The NOx reaction time depends on the time required for the analysis in the NOx concentration meter 85 and the dead time of the process depending on the configuration of the gasification and melting furnace plant 10, and therefore differs from plant to plant. Therefore, it is necessary to identify the reaction time based on the actual data obtained from the plant.

  FIG. 5 is a graph showing the melting furnace air ratio and the NOx concentration upstream of the denitration apparatus during a certain period. The NOx concentration upstream of the denitration device refers to the NOx concentration upstream of the denitration device provided between the melting furnace 30 and the chimney 70. In FIG. 5, the horizontal axis represents time, and the vertical axis represents the melting furnace air ratio and the NOx concentration level. It is known that the NOx concentration discharged from the melting furnace 30 has a strong correlation with the melting furnace air ratio. That is, the NOx concentration value increases after the reaction time TR has elapsed since the melting furnace air ratio showed a high value. In this graph, the melting furnace air ratio increases about 100 seconds after the start of observation, and then the NOx concentration value sharply increases from about 50 ppm to 200 ppm after the reaction time TR (about 75 seconds). In view of such knowledge, in the NOx reaction time identification processing, the NOx reaction time is exploratively determined using the correlation coefficient between the melting furnace air ratio and the NOx concentration.

  Hereinafter, the procedure of the NOx reaction time identification processing will be described. FIG. 6 is a flowchart showing the procedure of the NOx reaction time identification process. First, the CPU 301 sets the time parameter t1 to “0” for initialization (step S301), and sets the time index t2 to “0” for initialization (step S302).

  Next, the CPU 301 reads the melting furnace air ratio at time t2 from the performance DB 320 (step S303), and reads the NOx concentration value at time t2 + t1 (step S304). Further, the CPU 301 combines the obtained data of the melting furnace air ratio at time t2 and the data of the NOx concentration value at time t2 + t1 to generate a data set (step S305).

  The CPU 301 determines whether or not the time t2 has reached the predetermined maximum value T2 (step S306). If the time t2 is less than the maximum value T2 (NO in step S306), the CPU 301 increments the time t2 (step S307). ), The process returns to step S302. On the other hand, if the time t2 has reached the maximum value T2 (YES in step S306), the CPU 301 calculates a correlation coefficient between the melting furnace air ratio and the NOx concentration from the plurality of generated data sets (step S308). ).

  Next, the CPU 301 determines whether or not the time t1 has reached a predetermined maximum value T1 (step S309). If the time t1 is less than the maximum value T1 (NO in step S309), the CPU 301 increments the time t1. (Step S310), the process returns to step S301. On the other hand, if the time t1 has reached the maximum value T1 (YES in step S309), the CPU 301 specifies t1 at which the correlation coefficient becomes maximum, and determines this as the reaction time TR (step S311). That is, the CPU 301 changes t1 in a range from 0 to T1, and sets t1 at which the correlation coefficient becomes maximum in the range as the reaction time TR. After that, the CPU 301 ends the NOx reaction time identification processing.

  FIG. 4 is referred to again. When the NOx reaction time identification process ends, the CPU 301 executes a learning data creation process using the acquired operation data (step S203).

  FIG. 7 is a flowchart illustrating the procedure of the learning data creation process. In the learning data creation processing, learning data for machine learning a prediction rule for emission prediction of high concentration NOx is created. The learning data includes input data and output data.

  The CPU 301 initializes the time index t (step S401). Next, the CPU 301 creates input data at time t based on the operation data at time t (step S402). Further, the CPU 301 acquires the NOx concentration value at the time t + TR from the result DB 320 (step S403).

  The CPU 301 determines whether or not the obtained NOx concentration value is equal to or more than a predetermined threshold value C1 (see FIG. 5) (step S404). If it is equal to or more than C1 (YES in step S404), the output data at time t Is determined to be “1” (step S405), and if it is less than C1 (NO in step S404), the output data at time t is determined to be “0” (step S406).

  Next, the CPU 301 combines the obtained input data and output data to create learning data (step S407), and stores it in the learning DB 330. Further, the CPU 301 determines whether or not the time t has reached the predetermined maximum value T (step S408). If the time t is less than the maximum value T (NO in step S408), the CPU 301 increments the time t (step S408). (S409), the process returns to step S402. On the other hand, if time t has reached maximum value T (YES in step S408), CPU 301 ends the learning data creation process.

  FIG. 4 is referred to again. When the learning data creation process ends, the CPU 301 executes an evaluation data creation process (step S204). The evaluation data is data used to select a highly accurate rule from the prediction rules, and has the same data format as the learning data. The evaluation data creation process is the same as the learning data creation process, and a description thereof will be omitted. However, in the evaluation data creation process, only data different from the learning data is created as evaluation data and stored in the evaluation DB 360 instead of the learning DB 330.

  Next, the CPU 301 executes a prediction rule generation process (step S205). FIG. 8 is a flowchart illustrating the procedure of the prediction rule generation process. First, the CPU 301 initializes the index m of the learning data set (step S501). Here, the learning data set indicates that the output data includes emission of high-concentration NOx gas, that is, the learning data whose output data is “1” and that the output data indicates that high-concentration NOx gas is not emitted, This is a data set that includes the learning data of “0” at a predetermined ratio (hereinafter, referred to as “data ratio”). Here, a plurality of learning data sets having different data ratios are defined. For example, the data ratio in a certain learning data set is “1” (that is, the ratio of the learning data of “1” to the learning data of “0” is 1: 1), and the other learning data set is one. Is "2" (that is, the ratio of the learning data whose output data is "1" to the learning data whose "0" is 1: 2).

  Next, the CPU 301 initializes the data ratio index 1 (step S502). The data ratio is defined as a function R (l). For example, four values of R (1) = 1, R (2) = 2, R (3) = 5, and R (4) = 10 are set in advance. ing.

  Next, the CPU 301 acquires a predetermined number of learning data whose output data is “1” from the learning DB 330 (step S503). Further, the CPU 301 acquires learning data whose output data is “0” from the learning DB 330 by the number according to the data ratio R (l) (step S504). For example, when l = 1, learning data whose output data is “0” is obtained by the same number as the learning data whose output data is “1”, and when l = 1, learning data whose output data is “1” is obtained. Learning data whose output data is "0" is obtained by the number of times five times the data.

Next, the CPU 301 generates a prediction rule by decision tree learning using the acquired learning data set (step S505). Known learning algorithms, such as ID3, C4.5, and CART, can be used for the learning using the decision tree. The generated prediction rule, melting furnace air ratio of the operating data, the primary O ₂ flow, windbox temperature, sand temperature gasification furnace outlet temperature, melting furnace furnace top temperature, diaphragm unit temperature, secondary combustion chamber Exhaust gas temperature, main steam flow rate, exhaust gas flow rate, vertical flue gas temperature, and control target value of NOx concentration in exhaust gas (hereinafter referred to as "input variables"). This is an IF-THEN rule having a result indicating presence / absence. For example, conditions "are the melting furnace air ratio threshold A1 or more and is the primary O ₂ flow rate threshold value F1 or more and gasifier outlet temperature threshold value T1 or more" is, the result is "1 ( High concentration NOx gas is discharged).

  The CPU 301 determines whether or not the index 1 has reached a predetermined maximum value L (step S506), and if l is less than the maximum value L (NO in step S506), increments l (step S507). The process returns to step S503. On the other hand, if 1 has reached the maximum value L (YES in step S506), the CPU 301 determines whether or not the index m has reached a predetermined maximum value M (step S508), and m has reached the maximum value M. If less than (NO in step S508), m is incremented (step S509), and the process returns to step S502. If m has reached the maximum value M (YES in step S508), CPU 301 ends the prediction rule generation processing.

  FIG. 4 is referred to again. When the prediction rule generation process ends, the CPU 301 stores the generated prediction rule in the rule temporary storage DB 340 (step S206), and executes a prediction rule selection process (step S207). FIG. 9 is a flowchart illustrating the procedure of the prediction rule selection process. First, the CPU 301 initializes the index i of the prediction rule and the counter c (i) (step S601), and initializes the index j of the evaluation data (step S602).

  Next, the CPU 301 applies the prediction rule i to the evaluation data j and evaluates the prediction rule i (step S603). When the evaluation result is “match”, that is, when the prediction rule i matches the evaluation data j (YES in step S604), the CPU 301 increments the counter c (i) (step S605), and proceeds to step S606. Move. On the other hand, when the evaluation result is “unsuitable”, that is, when the prediction rule i does not match the evaluation data j (NO in step S604), the CPU 301 proceeds to the process in step S606.

The CPU 301 determines whether or not the index j has reached a predetermined maximum value J (step S606). If j is less than the maximum value J (NO in step S606), j is incremented (step S607). The process returns to step S603. On the other hand, when j has reached the maximum value J (YES in step S606), the CPU 301 calculates the support and the reliability (step S608). Here, the support is given by equation (3), and the reliability is given by equation (4).
Support = the number of evaluation data conforming to the prediction rule / the total number of evaluation data J (3)
Reliability = the number of evaluation data conforming to the prediction rule / the number of evaluation data classified into the prediction rule (4)
However, the number of evaluation data that conforms to the prediction rule is given as a counting result of the counter c (i). Further, “evaluation data classified into prediction rules” refers to evaluation data whose input data matches the conditions of the prediction rules. That is, the “evaluation data classified into the prediction rule” includes not only evaluation data whose output data matches the result of the prediction rule, but also evaluation data that does not match.

  The CPU 301 determines whether or not the index i has reached a predetermined maximum value I (step S609). If i is less than the maximum value I (NO in step S609), i is incremented (step S610). The process returns to step S602. On the other hand, when i has reached the maximum value I (YES in step S609), the CPU 301 uses a prediction rule in which each of the support level and the reliability level is equal to or higher than a predetermined threshold value for predicting high-concentration NOx emission. The prediction rule is selected (step S611), and the prediction rule is stored in the rule temporary storage DB 340, and the prediction rule selection process ends.

  FIG. 4 is referred to again. When the prediction rule selection process ends, the CPU 301 executes a target value vector creation process (step S208). The target value vector is information used for acquiring an operation amount (a set value of the primary and secondary air supply amounts) for suppressing the emission of the high-concentration NOx gas. The prediction rule includes a first prediction rule indicating that the result is “1”, that is, “there is high-concentration NOx gas emission”, and a result that is “0”, that is, “no high-concentration NOx gas emission”. And the second prediction rule shown in FIG. In the exhaust gas control apparatus 100 according to the present embodiment, the emission of high-concentration NOx gas is predicted using the first prediction rule, and the supply amounts of the primary and secondary air are set using the second prediction rule. decide. The target value vector is a representative value (specifically, an average value) of the actual values of past driving data that conforms to the second prediction rule, and is created for each second prediction rule.

FIG. 10 is a conceptual diagram for explaining a target value vector. The vertical axis of FIG. 10 is a coordinate axis of one variable (hereinafter, referred to as “first input variable”) included in the operation data, and the horizontal axis is another variable (hereinafter, “second input variable”). Coordinate axes. Here, although the two variables in order to simplify the explanation, in the present embodiment, the melting furnace air ratio, primary O ₂ flow, windbox temperature, sand temperature gasification furnace outlet temperature, melting furnaces Twelve variables including the top temperature, the auxiliary burner air flow rate, the throttle section temperature, the secondary combustion chamber exhaust gas temperature, the main steam flow rate, the exhaust gas flow rate, and the vertical flue exhaust gas temperature are included in the operation data. Further, 13 variables obtained by adding the control target value of the NOx concentration to these 12 variables are used for creating the target value vector. The target value vector is obtained by averaging a plurality of actual values matching one second prediction rule for each input variable. That is, the target value vector, melting furnace air ratio, primary O ₂ flow, windbox temperature, sand temperature gasification furnace outlet temperature, melting furnace furnace top temperature, auxiliary burner air flow rate, diaphragm unit temperature, secondary combustion The average values of the room exhaust gas temperature, the main steam flow rate, the vertical flue exhaust gas temperature, the exhaust gas flow rate, and the control target value of the NOx concentration are included. Such a target value vector is created for each second prediction rule. Therefore, as shown in FIG. 10, the target value vector is distributed in a coordinate space defined by each input variable.

  Each target value vector corresponds to the second prediction rule. That is, the value of the input variable included in the target value vector reflects the state of the gasification and melting furnace plant 10 when the high-concentration NOx gas is not discharged. Therefore, in the present embodiment, when the emission of the high-concentration NOx gas is predicted, the supply amounts of the primary and secondary air are set so that the operation data is close to the target value vector. Reduce emissions. Here, the emission of high-concentration NOx gas can be suppressed by bringing the operation data closer to any target value vector, but the NOx emission characteristics have a longer time constant and a steep The operation change becomes a disturbance and returns to worsen the combustion state. Therefore, it is desired that the NOx emission amount be controlled to a desired state with as few operations as possible from the current operation state. If the target value vector as the control target is significantly different from the current value of the input variable, it takes time to converge some input variables (input variables that cannot be directly operated such as temperature). Therefore, in the present embodiment, the target value vector closest to the current value of the operation data (hereinafter, referred to as “nearest neighbor target value vector”) is selected as the control target. Distance search is performed for searching for the nearest neighbor target value vector.

  Further, when the prediction rule is complicated, the number of target value vectors increases, and therefore, when the distance evaluation with all the target value vectors is performed, the calculation cost increases. Therefore, in the present embodiment, the target value vector is clustered, and the cluster closest to the current value of the input variable (hereinafter, referred to as “nearest neighbor cluster”) is identified from the distance evaluation of each cluster from the position of the center of gravity. The target value vectors included in the neighboring clusters are each evaluated for a distance from the current value, and the nearest target value vector is specified. Thereby, the calculation cost required for searching for the nearest target value vector can be suppressed.

  In the target value vector creation processing, the above-described target value vector is created, and a plurality of target value vectors are clustered. FIGS. 11A and 11B are flowcharts showing the procedure of the target value vector creation processing. First, the CPU 301 initializes the index i of the second prediction rule (step S701), and initializes the index j of the evaluation data (step S702).

  Next, the CPU 301 applies the second prediction rule i to the evaluation data j, and evaluates the second prediction rule i (step S703). When the evaluation result is “match”, that is, when the second prediction rule i matches the evaluation data j (YES in step S704), the CPU 301 temporarily stores the evaluation data j in the RAM 303 or the hard disk 305 (step S705). ) And the process moves to step S706. On the other hand, when the evaluation result is “nonconforming”, that is, when the second prediction rule i does not match the evaluation data j (NO in step S704), the CPU 301 proceeds to the process in step S706.

  The CPU 301 determines whether or not the index j has reached a predetermined maximum value J (step S706). If j is less than the maximum value J (NO in step S706), j is incremented (step S707). The process returns to step S703. By repeatedly executing the processing of steps S703 to S707, evaluation data that matches the second prediction rule is searched from a plurality of evaluation data. Here, the second prediction rule that does not match all the evaluation data is discarded.

  On the other hand, if j has reached the maximum value J (YES in step S706), CPU 301 averages the temporarily stored evaluation data for each input variable, and obtains a data set of the obtained average value in the second prediction. The target value vector of the rule i is stored in the hard disk 305 (step S708).

  Next, the CPU 301 determines whether or not the index i has reached the predetermined maximum value I (step S709). If i is less than the maximum value I (NO in step S709), i is incremented (step S710). ), And returns the process to step S702. On the other hand, if i has reached the maximum value I (YES in step S709), CPU 301 shifts the processing to step S711.

但し、ｚ_ｉは、標準化された目標値ベクトルの各入力変数の値を、ｘ_ｉは、標準化前の目標値ベクトルの各入力変数の値をそれぞれ示している。 The target value vector has a different unit and a different value scale for each input variable such as an air ratio, a temperature and a flow rate. Therefore, in the present embodiment, the target value vector is standardized. The use of such a standardized target value vector facilitates clustering processing and distance evaluation. The CPU 301 calculates an average value μ and a standard deviation σ for each input variable of the target value vector (step S711), and uses the calculated average value μ and standard deviation σ to standardize each target value vector according to the following equation. (Step S712).

Here, z _i indicates the value of each input variable of the standardized target value vector, and x _i indicates the value of each input variable of the target value vector before standardization.

  Next, the CPU 301 clusters the obtained plurality of standardized target value vectors (step S713). For clustering, a known clustering method such as a k-means method, a shortest distance method, a longest distance method, a group averaging method, a war degree method, or the like can be used. Further, the CPU 301 stores the average value μ, the standard deviation σ, and the position of the center of gravity of each cluster obtained above in the operation condition DB 370 (step S714). The reason why the average value μ and the standard deviation σ are stored is that it is necessary to restore the standardized target value vector to the target value vector. After that, the CPU 301 ends the target value vector creation processing.

  FIG. 4 is referred to again. The CPU 301 stores the first prediction rule selected in the prediction rule selection process and the standardized target value vector created in the target value vector creation process in the prediction rule DB 350 (step S209), and ends the prediction rule creation process. Note that the second prediction rule is discarded at this point. FIG. 12 is a conceptual diagram showing the configuration of the first prediction rule in the prediction rule DB 350. The first prediction rule is defined by a threshold (upper limit or lower limit) for each input variable in the driving data. As shown in FIG. 12, the prediction rule DB 350 stores, for each record (rule), a rule ID for identifying a rule, upper and lower limit identification information, and a threshold value of each variable. The upper and lower limit identification information is information for identifying whether the threshold included in the record is the upper limit or the lower limit. When the upper and lower limit identification information is “0”, the threshold included in the record is the lower limit, and when the upper and lower limit identification information is “1”, the threshold included in the record is the upper limit. For example, in a record in which the rule ID is “1” and the upper and lower limit identification information is “0”, the lower limit of variable 1 is “−1000”, the lower limit of variable 2 is “1.5”, and the lower limit of variable 3 is “300” and the lower limit of the variable M are “−1000”. “−1000” is the initial value of the lower limit, which is a sufficiently small value for the variable. On the other hand, in the record in which the rule ID is “1” and the upper and lower limit identification information is “1”, the upper limit of variable 1 is “3.2”, the upper limit of variable 2 is “1000”, and the upper limit of variable 3 is “1000”. 411 ", and the lower limit value of the variable M is" 1000 ". “1000” is the initial value of the upper limit, which is a sufficiently large value for the variable.

  FIG. 3 is referred to again. After ending the prediction rule generation process, the CPU 301 returns the process to step S101. When the prediction rule is stored in the prediction rule DB 350 in step S104 (YES in step S104), the CPU 301 determines whether a predetermined control cycle has elapsed after executing the previous control process (that is, transmitting the control signal). It is determined whether or not it is (step S106). If the control cycle has not elapsed (NO in step S106), CPU 301 returns the process to step S101.

  On the other hand, if the control cycle has elapsed (YES in step S106), CPU 301 executes high-concentration NOx emission prediction processing (step S107). FIG. 13 is a flowchart illustrating the procedure of the high-concentration NOx emission prediction process. First, the CPU 301 creates input data from the operation data at the current time t '(step S801). Next, the CPU 301 evaluates a first prediction rule for the created input data (step S802). In this process, it is determined whether or not the input data matches the condition of the first prediction rule. After that, the CPU 301 ends the high concentration NOx emission prediction processing.

  FIG. 3 is referred to again. The CPU 301 determines whether or not the input data has been evaluated as meeting the conditions of the first prediction rule in the high-concentration NOx emission prediction process (step S108). If the input data is evaluated as meeting the conditions of the first prediction rule (YES in step S108), emission of high concentration NOx is predicted. Therefore, the CPU 301 executes a control operation determination process to determine an operation amount for suppressing high-concentration NOx emission (step S109).

  14A and 14B are flowcharts illustrating the procedure of the control operation determination process. First, the CPU 301 reads the average value μ and the standard deviation σ from the operation condition DB 370, and normalizes the input data (step S901). This is because the scales of the standardized target value vectors and clusters and the input data are matched, and the distance between them can be evaluated.

  Next, the CPU 301 initializes the index k of the cluster (step S902). Further, the CPU 301 calculates a distance d1 (k) between the position of the center of gravity of the cluster k (the coordinates of the center of gravity) and the standardized input data (the coordinates of the current value) (step S903).

  Here, the calculation of the distance d1 (k) will be described. Various distances such as a Euclidean distance, a Manhattan distance, and a Mahalanobis distance can be used for the distance calculation. Here, the distance calculation based on the Euclidean distance will be described.

The input variables, the melting furnace air ratio, and directly operable variable as the primary O ₂ flow, windbox temperature, sand temperature gasification furnace outlet temperature, melting furnace furnace top temperature, diaphragm part temperature, two There are variables that cannot be directly manipulated, such as secondary combustion chamber exhaust gas temperature, main steam flow, and vertical flue gas temperature. Regarding input variables that can be directly operated, even if the current value deviates to some extent from the value of the target value vector, there is no problem because the operation amount can be set to the same value as the target value vector. However, for an input variable that cannot be directly operated, if the current value is too far from the value of the target value vector, it takes time to converge on the value of the target value vector. Therefore, for input variables that cannot be directly manipulated, it is desirable that the current value and the value of the target value vector be as close as possible. Therefore, in the present embodiment, a weighted distance is calculated for each input variable.

但し、ｎは変数のインデックスを、Ｎは変数の数を、ｗ_ｎは変数ｎの重み係数を、ｘ_ｎは入力データにおける変数ｎの値を、ｚ_ｎ（ｋ）はクラスタｋの重心における変数ｎの値をそれぞれ示している。 The distance d1 (k) between the coordinates of the center of gravity of the cluster and the coordinates of the current value is calculated according to the following equation.

Where n is the index of the variable, N is the number of variables, w _n is the weighting factor of the variable n, x _n is the value of the variable n in the input data, and z _n (k) is the variable at the centroid of the cluster k. The values of n are shown.

  After calculating the distance d1 (k), the CPU 301 temporarily stores the calculated distance d1 (k) in the RAM 303 or the hard disk 305 (step S904), and determines whether or not the index k has reached a predetermined maximum value K. Is determined (step S905), and if k is smaller than the maximum value K (NO in step S905), k is incremented (step S906), and the process returns to step S903.

On the other hand, if k has reached the maximum value K (YES in step S905), the CPU 301 specifies an index k ′ that minimizes the distance d1 (k ′) (step S907). Since the larger the weight w _n , the greater the specific gravity in the distance calculation, if a cluster k ′ with the smallest distance d 1 (k ′) is selected, a target value vector that is closer to the variable n is selected. become.

但し、ｙ_ｎ（ｓ）は標準目標値ベクトルｓにおける変数ｎの値を示している。 Next, the CPU 301 initializes the index s of the target value vector (step S908). Further, the CPU 301 calculates a distance d2 (s) between the coordinates of the standardized target value vector s belonging to the cluster k ′ and the coordinates of the standardized input data (step S909). Here, the distance d2 (s) is calculated according to the following equation.

Here, y _n (s) indicates the value of the variable n in the standard target value vector s.

  After calculating the distance d2 (s), the CPU 301 temporarily stores the calculated distance d2 (s) in the RAM 303 or the hard disk 305 (step S910), and determines whether the index s has reached the predetermined maximum value S. Is determined (step S911), and if s is less than the maximum value S (NO in step S911), s is incremented (step S912), and the process returns to step S909.

  On the other hand, if s has reached the maximum value S (YES in step S911), the CPU 301 specifies the index s 'at which the distance d2 (s') becomes the minimum (step S913). As a result, the nearest target value vector s' is specified. Further, the CPU 301 performs inverse standardization processing on the standardized target value vector s 'using the average value μ and the standard deviation σ stored in the operating condition DB 370 to restore the target value vector s' (step S914).

但し、Ｇ_ｐＯ２（ｔ’）は目標値ベクトルｓ’に含まれる一次側Ｏ_２流量を、ｆ_Ｏ２（ｔ’）は現在時刻ｔ’における入力データに含まれる供給Ｏ_２流量を、ｆ_ｐｓｕｐ（ｔ’）は同入力データに含まれる補助バーナ空気流量をそれぞれ示している。 Next, the CPU 301 determines the set value of the supply amount of the primary air from the “primary O ₂ flow rate” included in the target value vector s ′ (step S915). The supply amount set value F ₁ (t ′) of the primary air is calculated according to the following equation.

Here, G _pO2 (t ′) is the primary O ₂ flow rate included in the target value vector s ′, f _O2 (t ′) is the supply O ₂ flow rate included in the input data at the current time t ′, and f _psup ( t ') indicates the auxiliary burner air flow rate included in the input data.

但し、ｃｏｎｓｔ_１（ｔ’）〜ｃｏｎｓｔ_９（ｔ’）のそれぞれは中間変数であり、ａ_１〜ａ_１２のそれぞれはモデルパラメータである。なお、モデルパラメータａ_１〜ａ_１２は、運転データから最小二乗法等で導出される。また、Ｇ_ａｒ（ｔ’）は目標値ベクトルｓ’に含まれる溶融炉空気比を、ｄ_Ｏ２（ｔ’）は現在時刻ｔ’の入力データに含まれる二次燃焼室出口Ｏ_２濃度を、ｆ_ｏｓｈ（ｔ’）は同入力データに含まれる押込空気量をそれぞれ示している。 Further, the CPU 301 determines the supply amount setting value of the secondary air from the supply amount setting value F ₁ (t ′) of the primary air obtained as described above and the “melting furnace air ratio” included in the target value vector s ′. (Step S916). The supply amount set value F ₂ (t ′) of the secondary air is calculated according to the following linear prediction formula using each input variable.

However, each of const ₁ (t ′) to const ₉ (t ′) is an intermediate variable, and each of a _{1 to} a ₁₂ is a model parameter. Incidentally, the model parameters _a 1 _{~a 12} is derived by the least squares method or the like from the operating data. G _ar (t ′) is the melting furnace air ratio included in the target value vector s ′, d _O2 (t ′) is the secondary combustion chamber outlet O ₂ concentration included in the input data at the current time t ′, f _osh (t ′) indicates the amount of forced air included in the input data.

  When the supply amounts of the primary and secondary air are determined as described above, the CPU 301 ends the control operation determination process. FIG. 3 is referred to again. Next, the CPU 301 transmits a control signal to operate the primary air supply device 26 and the secondary air supply device 34 according to the operation amount determined in the control operation determination process (step S110), and stores the processing result in the hard disk 305. (Step S111).

  If the processing result is saved, or if the input data is evaluated as not meeting the conditions of the first prediction rule (that is, it is determined that emission of high-concentration NOx is not predicted; NO in step S108), CPU 301 Determines whether to end the exhaust gas control (step S112). If the exhaust gas control is not to be ended (NO in step S112), CPU 301 returns the process to step S101. For example, when an end instruction is given from the operator and the exhaust gas control is to be ended (YES in step S112), the CPU 301 ends the operation of the exhaust gas control.

  By the control operation as described above, emission of high concentration NOx is predicted in advance, and primary and secondary air are supplied to the melting furnace 30 so as to suppress emission of high concentration NOx. Therefore, it is possible to automatically suppress the emission of high-concentration NOx without depending on the skill of the operator.

(Other embodiments)
In the embodiment described above, the melting furnace air ratio at the current time, the primary O ₂ flow, windbox temperature, sand temperature gasification furnace outlet temperature, melting furnace furnace top temperature, diaphragm unit temperature, secondary combustion chamber exhaust gas temperature The configuration for predicting high-concentration NOx gas emissions using input data including the main steam flow rate, exhaust gas flow rate, vertical flue exhaust gas temperature, and control target value of NOx concentration in exhaust gas was described. However, the present invention is not limited to this. For example, at least one of the melting furnace air ratio and the primary-side O ₂ flow rate at the current time, the gasification furnace outlet temperature, the melting furnace top temperature, and the constriction section temperature may be used. In addition, the control target value of the NOx concentration in the exhaust gas and the main steam flow rate may be used. Further, in addition to these, at least one of a wind box temperature, a sand layer temperature, a secondary combustion chamber exhaust gas temperature, an exhaust gas flow rate, and a vertical flue exhaust gas temperature may be used.

  In the above-described embodiment, the configuration in which the prediction rule is generated by machine learning has been described, but the present invention is not limited to this. An operator or the like may create a prediction rule based on experience. Further, in the above-described embodiment, the prediction rule is generated by the decision tree learning. However, the prediction rule may be generated by machine learning other than the decision tree, for example, genetic programming or the like.

  In the above-described embodiment, the configuration in which the nearest cluster of the current value is specified and the nearest target value vector is specified from the target value vectors belonging to the nearest cluster has been described. However, the present invention is not limited to this. . It is also possible to directly specify the nearest target value vector of the current value.

  Further, in the above-described embodiment, the configuration in which all the processes of the exhaust gas control program 310 are executed by the single computer 200 has been described. However, the present invention is not limited to this. It is also possible to provide a distributed system in which the same processing is distributed and executed by a plurality of devices (computers).

  INDUSTRIAL APPLICABILITY The exhaust gas control device and the exhaust gas control method for a gasification and melting furnace plant of the present invention are useful as an exhaust gas control device and an exhaust gas control method for suppressing the generation of NOx gas in a gasification and melting furnace plant.

Reference Signs List 10 gasification and melting furnace plant 15 gasification and melting furnace 20 gasification and melting furnace 26 primary air supply device 30 melting furnace 31 primary combustion chamber 32 secondary combustion chamber 34 secondary air supply device 71 wind box thermometer 72 forced air flow meter 73 sand layer thermometer 74 gasifier outlet temperature gauge 75 the primary air flow meter 76 O ₂ flow meter 77 melting furnace furnace top temperature gauge 79 down portion thermometer 80 secondary air flow meter 81 the secondary combustion chamber exhaust gas temperature gauge 82 main steam flow meter 83 vertical stack gas temperature gauge 84 exhaust gas flowmeter 85 NOx concentration meter 86 O ₂ concentration meter 100 emission control device 200 computer 301 CPU
305 Hard disk 310 Emission control program 320 Result database 330 Learning database 350 Prediction rule database

Claims (13)

Exhaust gas of a gasification and melting furnace plant having a gasification and melting furnace including a gasification furnace for incineration of waste and a melting furnace connected to the gasification furnace and melting coal produced by the gasification furnace. A control device,
An air ratio in the melting furnace, a flow rate of O ₂ gas on the inlet side of the melting furnace, and a data acquisition unit for acquiring a temperature in the gasification melting furnace;
Prediction means for predicting the emission of high-concentration NOx gas from the gasification and melting furnace plant based on the air ratio, the flow rate of the O ₂ gas, and the temperature acquired by the data acquisition means,
Setting means for setting the amount of air flowing into the melting furnace so as to suppress the concentration of the NOx gas when the emission of the high-concentration NOx gas is predicted by the prediction means;
Equipped with a,
The predicting unit calculates a prediction rule having a condition including the air ratio, the flow rate of the O ₂ gas, and the temperature, and a result indicating whether or not the high-concentration NOx gas is discharged. _{(2) The} emission of the high-concentration NOx gas is predicted using the prediction rule generated by the generation unit that generates the flow rate of the gas, the temperature, and the actual value of the concentration of the NOx gas in the exhaust gas. Composed,
An identification unit for identifying a reaction time TR of NOx in the gasification and melting furnace plant based on the actual value of the NOx gas concentration in the exhaust gas and the air ratio,
The generation means includes: a prediction rule having the condition including the air ratio, the flow rate of the O ₂ gas, and the temperature at time t, and the result indicating whether or not the high-concentration NOx gas is discharged at time t + TR. Is configured to generate
Exhaust gas control equipment for gasification and melting furnace plants. Exhaust gas of a gasification and melting furnace plant having a gasification and melting furnace including a gasification furnace for incineration of waste and a melting furnace connected to the gasification furnace and melting coal produced by the gasification furnace. A control device,
An air ratio in the melting furnace, a flow rate of O ₂ gas on the inlet side of the melting furnace, and a data acquisition unit for acquiring a temperature in the gasification melting furnace;
Prediction means for predicting the emission of high-concentration NOx gas from the gasification and melting furnace plant based on the air ratio, the flow rate of the O ₂ gas, and the temperature acquired by the data acquisition means,
Setting means for setting the amount of air flowing into the melting furnace so as to suppress the concentration of the NOx gas when the emission of the high-concentration NOx gas is predicted by the prediction means;
Equipped with a,
The predicting unit calculates a prediction rule having a condition including the air ratio, the flow rate of the O ₂ gas, and the temperature, and a result indicating whether or not the high-concentration NOx gas is discharged. _{(2) The} emission of the high-concentration NOx gas is predicted using the prediction rule generated by the generation unit that generates the flow rate of the gas, the temperature, and the actual value of the concentration of the NOx gas in the exhaust gas. Composed,
The prediction means is configured to predict the emission of the high-concentration NOx gas using a first prediction rule that is the prediction rule whose result indicates that the emission of the high-concentration NOx gas is present. Yes,
The setting means is configured to set the amount of air to be flown into the melting furnace, using a second prediction rule that is the prediction rule indicating that there is no emission of the high-concentration NOx gas. Yes,
Exhaust gas control equipment for gasification and melting furnace plants. The melting furnace has a narrowed portion having a cross-sectional area smaller than other portions,
The temperature includes at least one of the temperature of the gasifier outlet, the temperature of the melting furnace top, and the temperature of the constriction,
An exhaust gas control device for a gasification and melting furnace plant according to claim 1 or 2 . The prediction unit predicts the emission of the high-concentration NOx gas based on at least one of a control target value of a NOx concentration contained in exhaust gas and a main steam flow rate of a boiler communicating with the melting furnace. Is configured as
An exhaust gas control device for a gasification and melting furnace plant according to claim 3 . The melting furnace is configured to burn a part of the pyrolysis gas generated in the gasification furnace and flowing from the gasification furnace, and to burn a pyrolysis gas not burned in the primary combustion chamber. Having a next combustion chamber,
The predicting means includes an exhaust gas flow rate of the gasification / melting furnace plant, an exhaust gas temperature in the secondary combustion chamber, a temperature in a wind box connected to the gasification furnace, and a vertical pipe provided downstream of the secondary combustion chamber. Configured to predict the emission of the high-concentration NOx gas further based on at least one of an exhaust gas temperature in a stack and a temperature of a sand layer provided in the gasifier.
An exhaust gas control device for a gasification and melting furnace plant according to claim 3 or 4 . Further Ru comprising said generating means,
An exhaust gas control device for a gasification and melting furnace plant according to any one of claims 1 to 5 . The generating means is configured to generate the prediction rule by decision tree learning,
An exhaust gas control device for a gasification and melting furnace plant according to claim 6 . The air ratio acquired by the data acquisition unit, among the representative values of the air ratio, the flow rate of the O ₂ gas, and the actual value of the temperature, which match the condition of the second prediction rule, The O ₂ gas flow rate, and a representative value closest to the current value including the temperature is specified, and based on the specified representative value, the amount of air to be flown into the melting furnace is set.
An exhaust gas control device for a gasification and melting furnace plant according to claim 2 . The setting means sets a distance between the coordinates of the plurality of representative values and the coordinates of the current value when each item of the condition including the air ratio, the flow rate of the O ₂ gas, and the temperature is used as a coordinate axis. Is configured to identify a representative value closest to the current value,
An exhaust gas control device for a gasification and melting furnace plant according to claim 8 . The setting means clusters a plurality of the representative values in a coordinate space defined by the coordinate axes, and calculates the current value based on a distance between the obtained barycentric coordinates of the plurality of clusters and the coordinates of the current value. It is configured to specify a closest cluster, and to specify the closest representative value to the current value based on a distance between the coordinates of the plurality of representative values included in the specified cluster and the coordinates of the current value. ing,
An exhaust gas control device for a gasification and melting furnace plant according to claim 9 . The melting furnace is configured to burn a part of the pyrolysis gas generated in the gasification furnace and flowing from the gasification furnace, and to burn a pyrolysis gas not burned in the primary combustion chamber. Having a next combustion chamber,
The setting means sets a primary air amount to be supplied to the primary combustion chamber based on the flow rate of the O ₂ gas included in the specified closest representative value, and sets the primary air amount and the closest representative value. It is configured to set a secondary air amount to be supplied to the secondary combustion chamber based on the air ratio included in,
An exhaust gas control device for a melting furnace plant according to any one of claims 8 to 10 . Exhaust gas of a gasification and melting furnace plant having a gasification and melting furnace including a gasification furnace for incineration of waste and a melting furnace connected to the gasification furnace and melting coal produced by the gasification furnace. A control method,
Obtaining the air ratio in the melting furnace, the flow rate of the O ₂ gas at the inlet side of the melting furnace, and the temperature in the gasification melting furnace;
Estimating the emission of high-concentration NOx gas from the gasification and melting furnace plant based on the obtained air ratio, the flow rate of the O ₂ gas, and the temperature;
Setting the amount of air to flow into the melting furnace so as to suppress the concentration of the NOx gas when the emission of the high-concentration NOx gas is predicted;
Having,
The step of predicting the emission of the high-concentration NOx gas from the gasification and melting furnace plant includes the conditions including the air ratio, the flow rate of the O ₂ gas, and the temperature, and whether or not the high-concentration NOx gas is discharged. The prediction rule generated by the generation unit that generates a prediction rule based on the air ratio, the flow rate of the O ₂ gas, the temperature, and the actual value of the concentration of the NOx gas in the exhaust gas. Predict the emission of said high concentration NOx gas using
Further comprising a step of identifying a reaction time TR of NOx in the gasification and melting furnace plant based on the actual value of the concentration of NOx gas in the exhaust gas and the air ratio,
The prediction rule includes the condition including the air ratio, the flow rate of the O ₂ gas, and the temperature at time t, and the result indicating whether or not the high-concentration NOx gas is discharged at time t + TR. Has been generated,
An exhaust gas control method for a gasification and melting furnace plant. Exhaust gas of a gasification and melting furnace plant having a gasification and melting furnace including a gasification furnace for incineration of waste and a melting furnace connected to the gasification furnace and melting coal produced by the gasification furnace. A control method,
Obtaining the air ratio in the melting furnace, the flow rate of the O ₂ gas at the inlet side of the melting furnace, and the temperature in the gasification melting furnace;
Estimating the emission of high-concentration NOx gas from the gasification and melting furnace plant based on the obtained air ratio, the flow rate of the O ₂ gas, and the temperature;
Setting the amount of air to flow into the melting furnace so as to suppress the concentration of the NOx gas when the emission of the high-concentration NOx gas is predicted;
Having,
The step of predicting the emission of the high-concentration NOx gas from the gasification and melting furnace plant includes the conditions including the air ratio, the flow rate of the O ₂ gas, and the temperature, and whether or not the high-concentration NOx gas is discharged. The prediction rule generated by the generation unit that generates a prediction rule based on the air ratio, the flow rate of the O ₂ gas, the temperature, and the actual value of the concentration of the NOx gas in the exhaust gas. Predict the emission of said high concentration NOx gas using
The step of predicting the emission of high-concentration NOx gas from the gasification and melting furnace plant is performed by using a first prediction rule that is the prediction rule in which the result indicates that the high-concentration NOx gas is discharged, Configured to predict the emission of the high concentration NOx gas,
The step of setting the amount of air to flow into the melting furnace includes the step of setting the amount of air to flow into the melting furnace by using a second prediction rule, which is the prediction rule in which the result indicates that there is no emission of the high-concentration NOx gas. Configured to set the amount,
An exhaust gas control method for a gasification and melting furnace plant.

Images