JP2023074832A - Concentration estimation device, concentration estimation method and program - Google Patents

Abstract

To estimate an oxygen concentration in a heating furnace.SOLUTION: A concentration estimation device for estimating an oxygen concentration in a heating furnace has: a model creation unit that creates a model for estimating the oxygen concentration in the heating furnace with an oxygen concentration measurement value y(t) in the heating furnace at each time t within a predetermined period in the past and predetermined n (n is a predetermined integer of 1 or more) physical quantity measurement values x1(t), x2(t), ..., xn(t) related to the heating furnace as learning data; and an oxygen concentration estimation unit that calculates an estimation value of the oxygen concentration in the heating furnace with the n physical quantity measurement values x1(t'), x2(t'), ..., Xn(t') at a time t' for estimation of the oxygen concentration.SELECTED DRAWING: Figure 1

Description

The present invention relates to a concentration estimation device, a concentration estimation method, and a program.

In order to achieve both energy saving and pollution prevention of the heating furnace, it is important to control the oxygen (O ₂ ) concentration in the heating furnace, and for this purpose, the oxygen concentration is measured by various methods. . For example, a zirconia oxygen concentration meter (see Non-Patent Document 1) is used to measure the oxygen concentration in a heating furnace.

"Instrumentation Bits of Knowledge｜Story of Zirconia Oxygen Analyzer", Internet <URL: https://www.m-system.co.jp/mstoday/plan/mame/b_sensor/9407/index.html>

In general, it is necessary to operate a heating furnace at a low oxygen concentration in order to achieve both energy saving and pollution prevention. do not get This is because if the oxygen concentration becomes too low, incomplete combustion will occur, and the zirconia element will undergo an oxidation reaction with the combustible gas carbon monoxide and unburned combustible fuel as a catalyst. This is because an erroneous measurement may occur such that the measured value of the concentration is near zero.

One embodiment of the present invention has been made in view of the above points, and an object thereof is to estimate the oxygen concentration in a heating furnace.

To achieve the above object, a concentration estimating device according to one embodiment is an oxygen concentration estimating device that estimates the oxygen concentration in a heating furnace, and comprises: Oxygen concentration measured value y(t) and predetermined n physical quantity measured values x ₁ (t), x ₂ (t), . . . , x _n (t) as learning data, a model creation unit for creating a model for estimating the oxygen concentration in the heating furnace, and the n physical quantities at the time t′ to be the target for estimating the oxygen concentration Oxygen concentration estimation for calculating an estimated oxygen concentration in the furnace using the measured values x ₁ (t′), x ₂ (t′), . . . , x _n (t′) and the model and

Oxygen concentration in the heating furnace can be estimated.

It is a figure showing an example of the whole composition of a heating furnace control system concerning this embodiment. It is a figure which shows typically the relationship between an excess air factor and heat loss, and the relationship between an excess air factor and thermal efficiency. FIG. 4 is a diagram schematically showing an installation example of an oxygen concentration meter and peripheral sensors with respect to a heating furnace; FIG. 4 is a diagram schematically showing the relationship between the air-fuel ratio and the oxygen concentration measurement value; It is a figure which shows an example of the hardware constitutions of the oxygen concentration estimation apparatus which concerns on this embodiment. It is a figure showing an example of functional composition of an oxygen concentration estimating device concerning this embodiment. 5 is a flowchart showing an example of oxygen concentration estimation processing in Example 1. FIG. 10 is a flowchart showing an example of oxygen concentration estimation processing in Example 2. FIG.

An embodiment of the present invention will be described below. A heating furnace control system 1 including an oxygen concentration estimating device 10 for estimating the oxygen concentration in the heating furnace will be described below.

<Overall Configuration of Heating Furnace Control System 1>
FIG. 1 shows an example of the overall configuration of a heating furnace control system 1 according to this embodiment. As shown in FIG. 1, the heating furnace control system 1 according to the present embodiment includes an oxygen concentration estimation device 10, a control device 20, an adjustment device 30, a heating furnace 40, an oxygen concentration meter 50, peripheral sensors 60 are included.

The heating furnace 40 is, for example, a facility or device used in various plants (petrochemical plants, various manufacturing plants, etc.), and consumes fuel and oxygen to heat an object (for example, fluid such as oil) by furnace combustion. to heat. The heating furnace 40 is not limited to these, and may be a boiler, an incinerator, or the like, for example.

The oxygen concentration meter 50 is a device that measures the oxygen concentration inside the heating furnace 40 . In the following, it is assumed that a laser oxygen concentration meter 50 ₁ and a zirconia oxygen concentration meter 50 ₂ are installed in the heating furnace 40 as the oxygen concentration meters 50 . However, the zirconia oxygen concentration meter ₅₀₂ may not be installed. In the following, it is assumed that the oxygen concentration meters 50 (the laser oxygen concentration meters 50 ₁ and the zirconia oxygen concentration meters 50 ₂ ) are removed from the heating furnace 40 after the performance data described later are created and stored. .

In addition, the oxygen concentration meter 50 transmits to the oxygen concentration estimation device 10 a measurement value (hereinafter also referred to as an oxygen concentration measurement value) measured at each time t. Hereinafter, at time t, the oxygen concentration measurement value measured by the laser oxygen concentration meter ₅₀₁ is _y1 (t), and the oxygen concentration measurement value measured by the zirconia oxygen concentration meter ₅₀₂ is _y2 (t). do.

The laser oxygen concentration meter ₅₀₁ is an oxygen concentration meter that utilizes an absorption spectroscopic measurement method using a laser. The laser oxygen concentration meter ₅₀₁ has a light emitting part that emits a laser and a light receiving part that receives the laser, and the oxygen concentration is measured from the amount of light lost from the laser light between the light emitting part and the light receiving part. be done.

The peripheral sensors 60 are various devices that measure various physical quantities around or around the heating furnace 40 and various physical quantities of equipment related to the heating furnace 40 . In addition, the peripheral sensor 60 transmits to the oxygen concentration estimating device 10 a measurement value (hereinafter also referred to as a physical quantity measurement value) measured at each time t. Hereinafter, the total number of peripheral sensors 60 is n, and when each peripheral sensor 60 is not distinguished, it is referred to as "peripheral sensor ₆₀ ". , "peripheral sensor _{60n "} . _Also , for i=1 _, 2, . Here, the physical quantities measured by the peripheral sensor 60 include, for example, the temperature in the heating furnace 40, the temperature of the object to be heated, the pressure in the heating furnace 40, the flow rate of fuel, the flow rate of the object to be heated, the flow rate of exhaust gas, and the like. Such a thing is mentioned. However, these physical quantities are examples, and the physical quantities measured by the peripheral sensor 60 are not limited to these. For example, the outside air temperature, wind speed, etc. may be measured as physical quantities.

The oxygen concentration estimation device 10 receives the oxygen concentration measurement values y ₁ (t) and y ₂ (t) from each oxygen concentration meter 50 at each time t for which performance data is to be created and stored, and each peripheral sensor It receives physical quantity measurement values x ₁ (t) _, x ₂ (t), .

Further, the oxygen concentration estimation device 10 obtains physical quantity measurement values x ₁ (t), x ₂ ( _t ), . , and from these measurements, the estimated oxygen concentration at the time t

を計算して制御装置２０に出力する。なお、以下、明細書のテキスト中では、推定値であることを表す記号ハット「＾」をｙの直後に記載し、時刻ｔにおける酸素濃度推定値を「ｙ＾（ｔ）」と表す。

is calculated and output to the control device 20 . Hereinafter, in the text of the specification, a hat symbol representing an estimated value is described immediately after y, and the oxygen concentration estimated value at time t is represented as "y^(t)".

That is, the oxygen concentration estimation device ₁₀ calculates the oxygen concentration estimated value from the physical quantity measurement values x ₁ (t), x ₂ (t), . It functions as a soft sensor that computes ŷ(t). Hereinafter, the model for estimating the oxygen concentration will be referred to as an oxygen concentration estimation model and denoted by f. Further, hereinafter, the time t at which the oxygen concentration is to be estimated is expressed as "t'" in order to distinguish it from the time t at which the performance data is to be created and stored.

Based on the oxygen concentration estimated value y^(t′) received from the oxygen concentration estimating device 10, the control device 20 calculates the optimum manipulated variable for the adjusting device 30, and sends a control command including the manipulated variable to the adjustment. Output to device 30 . The adjusting device 30 is an air damper (or an air valve) that adjusts the amount of air (oxygen) flowing into the heating furnace 40 and a fuel valve that adjusts the amount of fuel flowing into the heating furnace 40 . The operation amount of the air damper is its opening/closing angle (or opening/closing amount), while the operation amount of the air valve is its opening/closing angle (or opening/closing amount).

Note that the control device 20 may output the control command to both the air damper and the fuel valve, or may output the control command to either one (that is, one of the air damper and the fuel valve). In particular, for example, when the fuel flow rate is constant during operation of the heating furnace 40, the control device 20 may output the control command only to the air damper.

Here, heat loss and thermal efficiency in the heating furnace 40 fluctuate depending on the amount of fuel and air flowing into the heating furnace 40, and as a result, the oxygen concentration in the heating furnace 40 also fluctuates. Therefore, the control device 20 calculates the operation amount for the adjustment device 30 so that the heat loss and thermal efficiency in the heating furnace 40 are optimized by a known control technique, and outputs the operation amount to the adjustment device 30 . As such known control techniques, there are various techniques.

Generally, the relationship between excess air ratio and heat loss and the relationship between excess air ratio and thermal efficiency are shown in FIG. In FIG. 2, the vertical axis represents heat loss or thermal efficiency, and the horizontal axis represents excess air ratio. The excess air ratio is the ratio of the amount of air actually flowing into the heating furnace 40 to the theoretical amount of air, which is the amount of air required for combustion per unit fuel. In FIG. 2, line 1001 represents heat loss due to excess air and curve 1002 represents heat loss due to incomplete combustion. As indicated by the straight line 1001, as the excess air ratio becomes greater than 1, heat escapes to heat excess air, resulting in increased heat loss. On the other hand, as indicated by the curve 1002, when the excess air ratio is small, incomplete combustion occurs and heat loss due to CO generation increases, and when a certain threshold is exceeded, soot is generated. Also, in FIG. 2, a curve 2001 represents the thermal efficiency of the heating furnace 40 . As shown in curve 2001, the thermal efficiency is maximized in region D, which includes the excess air ratio, where the heat loss due to excess air and the heat loss due to incomplete combustion are comparable, and decreases as the excess air ratio moves away from region D. Become. Therefore, the control device 20 may calculate the manipulated variable of the regulating device 30 so that the heat loss and the thermal efficiency are within the region D, and output a control command including the manipulated variable to the regulating device 30 .

Note that the overall configuration of the heating furnace control system 1 shown in FIG. 1 is an example, and is not limited to this.

<Installation Example of Oxygen Analyzer 50 and Peripheral Sensor 60 for Heating Furnace 40>
FIG. 3 shows an installation example of the oxygen concentration meter 50 and the peripheral sensor 60 with respect to the heating furnace 40 . In the example shown in FIG. 3, a laser oxygen concentration meter ₅₀₁ and a zirconia oxygen concentration meter ₅₀₂ are installed. In the example shown in FIG. 3, the peripheral sensors 60 include an exhaust gas flowmeter ₆₀₁ , a heated body flowmeter ₆₀₂ , a fuel supply flowmeter ₆₀₃ , a furnace pressure gauge ₆₀₄ , and a furnace temperature gauge. _60-5 , a furnace thermometer _60-6 , and a heated object thermometer _60-7 are installed.

The installation example of the oxygen concentration meter 50 and the peripheral sensor 60 shown in FIG. 3 is merely an example, and needless to say, the present invention is not limited to this.

<Relationship between air-fuel ratio and measured oxygen concentration>
Air-fuel ratio is the ratio of air to fuel (air/fuel). FIG. 4 shows the relationship between the air-fuel ratio and the measured oxygen concentration. In FIG. 4, the vertical axis represents the air-fuel ratio or oxygen concentration, and the horizontal axis represents time. As shown in FIG. 4, when the air-fuel ratio becomes smaller than a certain value (that is, when the amount of oxygen decreases), the measured value of the zirconia oxygen concentration meter ₅₀₂ becomes close to 0, resulting in erroneous measurement. This is because incomplete combustion occurs when the oxygen concentration becomes too low, and as a result, the zirconia element undergoes an oxidation reaction with carbon monoxide and unburned combustible fuel as a catalyst. On the other hand, the laser oximeter ₅₀₁ does not cause such erroneous measurements.

Therefore, in the present embodiment, when the measured value of the zirconia oxygen concentration meter ₅₀₂ is near 0 (that is, when |y ₂ (t)|<ε for a small value ε>0), creates an oxygen concentration estimation model f using the measured value of the laser oxygen concentration meter ₅₀₁ as teaching data (correct data). If the measured value of the zirconia oxygen concentration meter ₅₀₂ is not near 0, either y ₁ (t) or y ₂ (t) may be used as teacher data, and y ₁ (t) and y ₂ The average value of (t) or the like may be used as teacher data.

<Hardware Configuration of Oxygen Concentration Estimating Device 10>
FIG. 5 shows a hardware configuration example of the oxygen concentration estimation device 10 according to this embodiment. As shown in FIG. 5, the oxygen concentration estimation device 10 according to the present embodiment includes an input device 101, a display device 102, an external I/F 103, a communication I/F 104, a processor 105, and a memory device 106. have. Each of these pieces of hardware is communicably connected via a bus 107 .

The input device 101 is, for example, a keyboard, mouse, touch panel, various physical buttons, and the like. The display device 102 is, for example, a display, a display panel, or the like. Note that the oxygen concentration estimation device 10 may not have at least one of the input device 101 and the display device 102, for example.

The external I/F 103 is an interface with an external device such as the recording medium 103a. Examples of the recording medium 103a include a CD (Compact Disc), a DVD (Digital Versatile Disk), an SD memory card (Secure Digital memory card), a USB (Universal Serial Bus) memory card, and the like.

Communication I/F 104 is an interface for connecting oxygen concentration estimation device 10 to a communication network. The processor 105 is, for example, various arithmetic units such as a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit). The memory device 106 is, for example, various storage devices such as SSD (Solid State Drive), RAM (Random Access Memory), ROM (Read Only Memory), and flash memory.

Note that the hardware configuration shown in FIG. 5 is an example, and the oxygen concentration estimation device 10 may have another hardware configuration. For example, the oxygen concentration estimation device 10 may have multiple processors 105 and multiple memory devices 106, and may have various hardware other than the illustrated hardware.

<Functional Configuration of Oxygen Concentration Estimating Device 10>
FIG. 6 shows an example of the functional configuration of the oxygen concentration estimation device 10 according to this embodiment. As shown in FIG. 6, the oxygen concentration estimating device 10 according to this embodiment has a performance data creation unit 201 , a model creation processing unit 202 , and an oxygen concentration estimation unit 203 . These units are implemented by, for example, one or more programs installed in the oxygen concentration estimation device 10 causing the processor 105 to execute processing. Further, the oxygen concentration estimation device 10 according to this embodiment has a performance data storage unit 204 . The storage unit 204 is realized by, for example, the memory device 106, but may be realized by a database server or the like connected via a communication network.

The performance data creation unit 201 receives the oxygen concentration measurement values y ₁ (t) and y ₂ (t) from each oxygen concentration meter 50 at each time t to create and store performance data, and , _xn (t) are received from 60, and actual data { _y ( _t ), _x1 (t), x _{2 (} t), . Here, let y(t)=y ₁ (t) at time t where |y ₂ (t)|<ε for some small value ε>0. On the other hand, at other times t, either y(t)=y ₁ (t) or y(t)=y ₂ (t), or y(t)=(y ₁ (t)+y ₂ (t))/2, y(t)=min( _y1 (t), _y2 (t)) or y(t)=max( _y1 (t), _y2 (t) ), etc. Note that y(t) is teacher data.

In the following, the actual data is z(t):=(y(t), _x1 (t), _x2 (t), ..., _xn (t)), and the actual data storage unit 204 stores the actual data. Suppose the dataset {z(t)|tεT ₁ } is stored. Here, _T1 is a set of times for which performance data is created and stored. For example _, when actual data is to be created and stored from a certain time _t1 to _t2 , _T1 ={t| _t1≤t≤t2 }.

The model creation processing unit 202 creates an oxygen concentration estimation model f from the actual data set {z(t)|tεT ₁ }. Here, the model generation processing unit 202 includes a data acquisition unit 211 and a model generation unit 212 . The data acquisition unit 211 acquires from the performance data storage unit 204 the performance data set {z(t)|tεT ₂ } used for creating the oxygen concentration estimation model f. Here, _T2 is a set of times of _performance data used to create the oxygen concentration estimation model f, and _T2⊆T1 . The model creation unit 212 creates an oxygen concentration estimation model f using the actual data set {z(t)|tεT ₂ } acquired by the data acquisition unit 211 . Note that the oxygen concentration estimation model f is, for example, a statistical model, a machine learning model, or the like, and has a learning target parameter θ.

The oxygen concentration estimating unit 203 obtains physical quantity measurement values x ₁ (t′), x ₂ (t′), _. ' ₎ , and the _{oxygen concentration} estimated value y^(t '). That is, the oxygen concentration estimation unit 203 uses the physical quantity measurement values x ₁ (t′), _{x 2} (t′), . t') ₌ f(x ₁ (t'), x ₂ (t'), . . Note that the oxygen concentration estimated value ŷ(t′) is output to the control device 20 .

<Oxygen concentration estimation process (Example 1)>
The oxygen concentration estimation process according to the first embodiment will be described below with reference to FIG. In the following, it is assumed that the performance data storage unit 204 stores a performance data set {z(t)|tεT ₁ } for a certain period T ₁ in the past. Note that steps S101 and S102 in FIG. 7 are model creation processing performed in advance. On the other hand, steps S103 and S104 are repeatedly performed every time t' (that is, current time t') at which the oxygen concentration is to be estimated.

The data acquisition unit 211 of the model creation processing unit 202 acquires the actual data set {z(t)|tεT ₂ } used for creating the oxygen concentration estimation model f from the actual data storage unit 204 (step S101). Here, the data acquisition unit 211 uses the performance data set {z(t)|tεT ₁ } itself stored in the performance data storage unit 204 as the performance data set {z(t)|tεT ₂ }. Alternatively, a performance data set composed of part of the performance data may be acquired as a performance data set {z(t)|tεT ₂ }.

The model creation unit 212 of the model creation processing unit 202 creates an oxygen concentration estimation model f using the actual data set {z(t)|tεT ₂ } obtained in step S101 (step S102). . That is, the model creation unit 212 uses the actual data set {z(t)|t∈T ₂ } as a learning data set, and calculates the oxygen concentration estimated value y^(t) at time t=f(x ₁ (t), The parameter θ is learned so as to reduce the error between x ₂ (t), . . . , x _n (t)) and y(t). Here, as the oxygen concentration estimation model f, a linear model such as a multiple regression model or a nonlinear model such as a support vector regression (SVR) or neural network can be employed. In general, the relationship between the oxygen concentration and the temperature inside the heating furnace 40 changes sequentially, and the characteristics of each physical quantity in the heating furnace 40 change depending on the oxygen concentration. Therefore, the linear model often has low estimation accuracy. . Therefore, it is particularly preferable to adopt a nonlinear model as the oxygen concentration estimation model f.

The oxygen concentration _estimation unit 203 receives physical quantity measurement values x ₁ (t′), x ₂ (t′), . step S103).

The oxygen concentration _estimation unit 203 calculates the current time from the physical quantity measurement values x ₁ (t′), x ₂ (t′), . An estimated oxygen concentration value y^(t') of t' is calculated (step S104). That is, _the oxygen concentration _estimating unit 203 _calculates the oxygen Calculate the density estimate y^(t'). Note that this oxygen concentration estimated value ŷ(t′) is output to the control device 20 , and the control device 20 controls the operation amount of the adjustment device 30 . Thereby, the oxygen concentration in the heating furnace 40 is controlled.

<Oxygen Concentration Estimation Processing (Example 2)>
The oxygen concentration estimation process according to the second embodiment will be described below with reference to FIG. In the following, it is assumed that the performance data storage unit 204 stores a performance data set {z(t)|tεT ₁ } for a certain period T ₁ in the past. Note that steps S201 to S204 in FIG. 8 are repeatedly performed at each time t' (that is, the current time t') at which the oxygen concentration is to be estimated.

The oxygen concentration _estimation unit 203 receives physical quantity measurement values x ₁ (t′), x ₂ (t′), . step S201).

The data acquisition unit 211 of the model creation processing unit 202 acquires the actual data set {z(t)|tεT ₂ } used for creating the oxygen concentration estimation model f from the actual data storage unit 204 (step S202). _Here , the data acquisition unit 211 receives the physical quantity measurement values x ₁ (t′), x ₂ (t′), . number of performance data are acquired from the performance data storage unit 204, and a performance data set composed of the acquired performance data is defined as a performance data set {z(t)|tεT ₂ }.

Specifically, physical quantity measurement values x _{1 (} t′) _, x ₂ (t′), . ) ^, _{x 2 (} t) _{, .} (t′)−x ₂ (t)) ² + . . . +(x _n (t′)−x _n (t)) ² ) ^1/2 . Then, N pieces (for example, 100 pieces) of z(t) are acquired from the performance data storage unit 204 in ascending order of the distance, and a performance data set composed of these acquired performance data z(t) is created as performance data. Let the set {z(t)|tεT ₂ }. Although the Euclidean distance is used as the distance d in the above description, a distance other than the Euclidean distance may be used.

The model creation unit 212 of the model creation processing unit 202 creates an oxygen concentration estimation model f using the actual data set {z(t)|tεT ₂ } obtained in step S202 (step S203). . That is, the model creation unit 212 uses the actual data set {z(t)|t∈T ₂ } as a learning data set, and calculates the oxygen concentration estimated value y^(t) at time t=f(x ₁ (t), The parameter θ is learned so as to reduce the error between x ₂ (t), . . . , x _n (t)) and y(t). Here, as the oxygen concentration estimation model f, for example, a local linear model such as JIT-PLS (Just-in-time PLS) or LW-PLS (Locally-Weighted PLS) can be adopted. Generally, in the heating furnace 40, the relationship between the oxygen concentration and the temperature inside the furnace changes sequentially, and the characteristics of each physical quantity in the heating furnace 40 change depending on the oxygen concentration. often lower. Therefore, it is preferable to employ a linear model (local linear model) using local learning data as the oxygen concentration estimation model f.

The oxygen concentration estimation unit 203 calculates the physical quantity measurement values x ₁ (t′), x ₂ (t′), . . . , x _n (t′) received in step S201 and the oxygen An oxygen concentration estimated value y^(t') at the current time t' is calculated from the concentration estimation model f (step S204). That is, _the oxygen concentration _estimating unit 203 _calculates the oxygen Calculate the density estimate y^(t'). Note that this oxygen concentration estimated value ŷ(t′) is output to the control device 20 , and the control device 20 controls the operation amount of the adjustment device 30 . Thereby, the oxygen concentration in the heating furnace 40 is controlled.

<Modification>
In _the above embodiment, the oxygen concentration meter ₅₀ is removed after the performance data is created and saved. It does not have to be removed. In this case, the oxygen concentration measurement value y ₂ (t′) of the zirconia oxygen concentration meter ₅₀₂ may also be used as an explanatory variable.

Specifically, the performance data is z( _t ):=(y(t)= _y1 (t), _y2 (t), x1(t), _x2 (t), . . . , _xn (t)), y (t) is the objective variable, y ₂ (t), x ₁ (t), x ₂ (t), ..., x _n (t) is the explanatory variable oxygen concentration Create an estimation model f. Then, when calculating the estimated oxygen concentration, ŷ(t′)=f(y ₂ (t′), x ₁ (t′), x ₂ (t′), . . . , x _n ( t')) calculates the estimated oxygen concentration y^(t') at the current time t'. At this time, for example, a model g that satisfies y^(t)=g(x ₁ (t), x ₂ (t), . . . , x _n (t)) is created in advance, and If ₂ (t')|<ε then compute y^(t')=g(x ₁ (t'), x ₂ (t'), . . . , x _n (t')) , ŷ(t′)=f( _{y 2 (} t′), x ₁ (t′), x ₂ (t′), . _xn (t')) may be calculated.

<Summary>
As described above _, in the heating furnace control system 1 according to the present embodiment, the oxygen concentration estimation model f is created, the oxygen concentration in the heating furnace 40 is estimated by this oxygen concentration estimation model f. As a result, instead of the zirconia oxygen concentration meter ₅₀₂ , which may cause erroneous measurement under low oxygen concentration, it is possible to estimate the oxygen concentration with high accuracy by the oxygen concentration estimation model f even under low oxygen concentration, saving energy. Optimum control of the heating furnace 40 can be achieved to achieve both reduction and pollution prevention.

Moreover, since the laser oxygen concentration meter ₅₀₁ can be removed from the heating furnace 40 after the oxygen concentration estimation model f is created, the laser oxygen concentration meter ₅₀₁ can be installed in another heating furnace 40, for example. , it is possible to similarly create an oxygen concentration estimation model f. Therefore, it is not necessary to prepare a generally expensive laser oxygen concentration meter ₅₀₁ for each heating furnace 40, and the oxygen concentration estimation model f can be created relatively inexpensively.

The present invention is not limited to the specifically disclosed embodiments described above, and various variations, modifications, combinations with known techniques, etc. are possible without departing from the scope of the claims. be.

1 Heating Furnace Control System 10 Oxygen Concentration Estimating Device 20 Controller 30 Adjusting Device 40 Heating Furnace 50 Oxygen Analyzer 60 Peripheral Sensor 101 Input Device 102 Display Device 103 External I/F
103a recording medium 104 communication I/F
105 processor 106 memory device 107 bus 201 performance data creation unit 202 model creation processing unit 203 oxygen concentration estimation unit 204 performance data storage unit 211 data acquisition unit 212 model creation unit

Claims (7)

An oxygen concentration estimation device for estimating the oxygen concentration in a heating furnace,
Oxygen concentration measurement value y(t) in the heating furnace at each time t within a predetermined period in the past and predetermined n (n is a predetermined integer of 1 or more) physical quantity measurements related to the heating furnace a model creation unit that creates a model for estimating the oxygen concentration in the heating furnace using the values x ₁ (t), x ₂ (t), . . . , x _n (t) as learning data;
Using the n physical quantity measurement values x ₁ (t' ₎ , x ₂ (t'), . an oxygen concentration estimator that calculates an estimated oxygen concentration in the heating furnace;
A concentration estimator having A laser oxygen concentration meter is installed in the heating furnace,
2. The concentration estimating device according to claim 1, wherein said oxygen concentration measurement value y(t) is a measurement value _y1 (t) obtained by measuring the oxygen concentration in said heating furnace with said laser oxygen concentration meter. A laser type oxygen concentration meter and a zirconia type oxygen concentration meter are installed in the heating furnace,
y ₁ (t) is the measured value of the oxygen concentration in the heating furnace measured by the laser oxygen concentration meter, and y ₂ (t) is the measured value of the oxygen concentration in the heating furnace measured by the zirconia oxygen concentration meter. ) as
For a predetermined value ε>0, if |y ₂ (t)|<ε, then y(t)=y ₁ (t), and
If |y ₂ (t)|≧ε then y(t)=y ₁ (t), y(t)=y ₂ (t), y(t)=(y ₁ (t)+y ₂ (t))/2, y(t)=min( _y1 (t), _y2 (t)), or y(t)=max( _y1 (t), _y2 (t)) The concentration estimation device according to claim 1 or 2, wherein 4. The concentration estimation device according to claim 2, wherein said laser oximeter is installed so as to be removable from said heating furnace after said learning data is created. The model creation unit
The n physical quantity measurement values x ₁ (t′), x ₂ (t _′ ), . Calculate the distances d (t', t) from the n physical quantity measurement values x ₁ (t), x ₂ (t), ..., x _n (t) at each time t,
The oxygen concentration measurement value y(t) and the n physical quantity measurement values x ₁ (t), x ₂ (t), respectively corresponding to a predetermined number of t in ascending order of the distance d (t′, t), 4. The concentration estimating apparatus according to claim 1, wherein the model is created using . . . , _xn (t) as learning data. An oxygen concentration estimating device that estimates the oxygen concentration in the heating furnace,
Oxygen concentration measurement value y(t) in the heating furnace at each time t within a predetermined period in the past and predetermined n (n is a predetermined integer of 1 or more) physical quantity measurements related to the heating furnace a model creation procedure for creating a model for estimating the oxygen concentration in the heating furnace using the values x ₁ (t), x ₂ (t), . . . , x _n (t) as learning data;
Using the n physical quantity measurement values x ₁ (t' ₎ , x ₂ (t'), . an oxygen concentration estimation procedure for calculating an estimated oxygen concentration in the furnace;
A concentration estimation method that performs An oxygen concentration estimating device that estimates the oxygen concentration in the heating furnace,
Oxygen concentration measurement value y(t) in the heating furnace at each time t within a predetermined period in the past and predetermined n (n is a predetermined integer of 1 or more) physical quantity measurements related to the heating furnace a model creation procedure for creating a model for estimating the oxygen concentration in the heating furnace using the values x ₁ (t), x ₂ (t), . . . , x _n (t) as learning data;
Using the n physical quantity measurement values x ₁ (t' ₎ , x ₂ (t'), . an oxygen concentration estimation procedure for calculating an estimated oxygen concentration in the furnace;
program to run.

Images