JP2963009B2 - Combustion determination / control method and determination / control device using color image - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a combustion judgment / control method and a judgment / control device. More specifically, the present invention relates to a combustion determination / control method and a determination / control device using a color image.

[0002]

2. Description of the Related Art Conventionally, in a combustion device such as a refuse incinerator or a boiler, a determination of a combustion state and a diagnosis of combustion are performed in order to check whether or not combustion is performed correctly.
This is the case where combustion is not performed correctly, NO _X and CO and soot is generated, because cause air pollution. Also, make this determination result and diagnostic result combustion control using, making it possible to suppress the generation of the NO _X and CO and dust have been made.

Various proposals have heretofore been made for the combustion judging method and the judging device or the combustion diagnosing method and the diagnosing device.

For example, Japanese Patent Application Laid-Open No. 1-263414 discloses a combustion diagnosis method for diagnosing the combustion state of a burner, in which the shape of a flame and the amount of combustion process are measured, and the correlation between the shape of the flame and the amount of combustion process is measured. There has been proposed a combustion diagnosis method based on flame shape measurement, characterized by identifying a model representing the relationship and estimating a combustion process amount from a flame shape using the model.

However, in the combustion diagnosis method according to the proposal of Japanese Patent Application Laid-Open No. 1-263414, NO _X
Since it is necessary to measure the amount of combustion process which takes time to measure CO, O ₂ , unburned components in ash, etc., a considerable time delay is caused in combustion diagnosis. Such a time delay is not so problematic when combustion takes several tens of minutes, for example, as in a combustion system using a stoker furnace, but when combustion takes place in over ten seconds, for example, as in a fluidized bed furnace,
The problem arises that the diagnostic results do not match the actual combustion.

[0006]

SUMMARY OF THE INVENTION The present invention has been made in view of the above-mentioned problems of the prior art, and provides a method and an apparatus for judging combustion in which a time delay is reduced to a level that does not cause a practical problem. It is another object of the present invention to provide a combustion control method and a combustion control device using the results.

[0007]

The present inventors have conducted intensive studies on the problems of the prior art. As a result, not only the brightness but also the color of the flame change according to the combustion state. It has been found that the correlation is dependent on characteristic parameters obtained from chromaticity coordinates of a specific color system, and the present invention has been completed.

That is, according to a first aspect of the present invention, there are provided a procedure for measuring a process state quantity, a procedure for capturing a combustion state as a color image, and an image processing of the obtained color image to obtain a red component, a green component, and a blue component. A procedure for dividing the image into three component images,
The resulting red component, green component and blue 3 component image consisting of components consisting of three component color system, for example, a procedure for conversion to the YIQ color system, the color specification from the image after the color system conversion
A step of calculating an average value for each screen of each component of the system, prior to
Using the average value of each component of the color system and the process state quantity as inputs of a neural network, and obtaining a degree of compatibility with a typical combustion state. Related to the determination method.

Here, the process state quantity is, for example, the combustion chamber outlet O ₂ concentration, the combustion chamber furnace pressure, or the combustion chamber outlet temperature.

In the first aspect of the present invention, it is preferable that a procedure for separating a flame region from a captured color image is added. Further, it is more preferable that a procedure for stochastically integrating the fitness levels to evaluate the combustion state is added.

[0011] The second invention of the present invention relates to a combustion control method using a color image, wherein combustion control is performed using a combustion judgment or an evaluation result by the combustion judgment method.

More specifically, by the combustion control, the air supply amount, the ratio between the primary air amount and the secondary air amount, the water injection amount into the combustion chamber or the fuel supply amount is adjusted.

[0013] A first aspect of the third invention of the present invention is the first aspect of the present invention, wherein a process state quantity input processing means, a color image capturing means, and three
Ranaru color system, for example, a YIQ color system conversion unit and wherein the parameter extracting means and the neural network unit, by the color system conversion unit, converted captured image to the <br/> color system is made, the by the feature parameter extracting means, it converted for each screen of each component of the color system
An average value is calculated , and the neural network means calculates a degree of compatibility with a typical combustion state based on the process state quantity from the process state quantity input means and the average value , and evaluates the combustion state. The present invention relates to a combustion determination device using a color image.

According to a second aspect of the third aspect of the present invention, a process state quantity input processing unit, a color image capturing unit, a three-component
Ranaru color system, for example, a YIQ color system conversion unit and wherein the parameter extracting means and the neural network means and probabilistic integration processing unit, by the color system conversion unit, the captured image is the color system made conversion of, by the characteristic parameter extracting means, the average value for each screen of the transformed respective <br/> component of the color system is calculated by the neural network unit, from the process state quantity input means Based on the process state quantity and the average value , the degree of conformity with a typical combustion state is calculated, and the calculated degree of conformity is stochastically processed by the stochastic integrated processing means to evaluate the combustion state. The present invention relates to a combustion determining apparatus using a color image.

Here, the process state quantity is the concentration of O _{2 at} the combustion chamber outlet, the pressure in the furnace of the combustion chamber, or the temperature of the combustion chamber outlet.

According to a first aspect of the fourth aspect of the present invention, a process state quantity input processing unit, a color image capturing unit, and a three-component
A color system, for example, a YIQ color system conversion unit, a feature parameter extraction unit, a neural network unit, a combustion control processing unit, and a process control amount output processing unit, and an image captured by the color system conversion unit. Is the color system
Conversion to have been made, the by the feature parameter extracting means, the average of each screen for each component of the transformed the color system
A value is calculated , and the neural network means calculates a degree of conformity with a typical combustion state based on the process state quantity and the average value from the process state quantity input means, and evaluates the combustion state. A process control amount is calculated by a combustion control processing unit based on the evaluation of the combustion state, and a predetermined process is performed on the process control amount by the process control amount output processing unit and output. The present invention relates to a combustion control device using a color image.

According to a second aspect of the fourth aspect of the present invention, a process state quantity input processing unit, a color image capturing unit, a three-component
A color system comprising, for example, a YIQ color system conversion means, a feature parameter extraction means, a neural network means, a stochastic integration processing means, a combustion control processing means, and a process control amount output processing means. the converted imaged image to the color system is performed, each component of the by the feature parameter extracting means, converted the color system
The average value of each screen is calculated , and the neural network means calculates a degree of conformity with a typical combustion state based on the process state quantity from the process state quantity input means and the average value , By the stochastic integration processing means, the calculated fitness is processed stochastically to evaluate a combustion state, and the combustion control processing means calculates a process control amount based on the evaluation of the combustion state,
The present invention relates to a combustion control device using a color image, wherein a predetermined process is performed on the process control amount by the process control amount output processing means and output.

Here, the process state quantity is, for example, a combustion chamber outlet O ₂ concentration, a combustion chamber furnace pressure, or a combustion chamber outlet temperature, and the process control quantity is, for example, an air supply amount, a primary air amount, It relates to the ratio of the amount of secondary air, the amount of water injected into the combustion chamber, or the amount of fuel supplied.

[0019]

[Function] The process state quantity such as the combustion chamber outlet O ₂ concentration, the combustion chamber furnace pressure, and the combustion chamber outlet temperature are measured, and a color image of the combustion state is captured. From the obtained color image, red, green, and blue are obtained. A three-component image composed of the respective color components is created, a color system conversion is performed on the three-component image, and feature parameters that are greatly related to the combustion state are extracted from the image after the color system conversion. The process state quantities and feature parameters are input to the neural network. In the neural network, the degree of compatibility with a typical combustion state is determined or evaluated based on the input process state quantity and characteristic parameters. However, since the imaging of the color image of the combustion state is performed without a time delay, the determination or evaluation of the combustion state using the image has no practical time delay.
Further, in a preferred embodiment of the present invention in which the obtained conformity is stochastically integrated and the combustion state is evaluated, the integrated processing is stochastically performed. Even if the image changes irregularly in the meantime, highly reliable judgment or evaluation can be made.

Further, if combustion control, for example, adjustment of the air supply amount, the ratio of the primary air amount and the secondary air amount, the amount of water injected into the combustion chamber or the fuel supply amount, is performed using the results of this determination or evaluation, As described above, since the determination is made without any time delay, the combustion control can be performed in response to the combustion state. That is, optimal combustion control can be achieved.

[0021]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described based on embodiments with reference to the accompanying drawings, but the present invention is not limited to only such embodiments.

FIG. 1 is a functional block diagram of a combustion judgment / control device used in the combustion judgment / control method of the present invention. The judgment / control device A includes a color image pickup means 10, a color system conversion means 22, , Feature parameter extracting means 24, process state quantity input processing means 32, neural network means 42, stochastic integration processing means 44, combustion control processing means 46, and process control quantity output processing means 34 as main components. Become.

The color image capturing means 10 captures an image of combustion, and is, for example, a color television camera. The color image captured by the color image capturing unit 10 is input to the color system conversion unit 22 as a composite color image signal such as NTSC or an RGB three primary color component combination signal (hereinafter simply referred to as an RGB signal) via a signal cable. You.

The color system conversion means 22 converts the color system of the input signal. More specifically, the following processing is performed on the input color image signal. First, the input color image signal is stored in an RGB image memory (first image memory). If the input signal is a composite color image signal, it is converted to an RGB signal and then stored in the RGB image memory. Then, RGB
A color system conversion, for example, a conversion to a YIQ color system is performed from the RGB color system image data stored in the image memory, and each component value, for example, (Y, I, Q) is calculated for each pixel. .

The characteristic parameter extracting means 24 extracts characteristic parameters representing the combustion state of one screen from the obtained component values in the new color system. For example, an average value of I and Q per screen is calculated, and the value is extracted as a feature parameter. The values of these extracted feature parameters are input to the neural network means 42 together with the process state quantities from the process state quantity input processing means 32. When extracting the characteristic parameters, it is preferable to perform preprocessing for separating only the flame region so that the combustion state can be more accurately determined. The separation of the flame region is performed, for example, by performing threshold processing on the Y component value representing the luminance. More specifically, an area where the Y component value is equal to or more than a certain value is set as a flame area, and an area where the Y component value is less than a certain value is set as another background area.

Here, the conversion from the RGB color system to the YIQ color system is performed by the following equation (1).

[0027]

(Equation 1)

The process state quantity input processing means 32 performs processing of a signal form of a process state quantity such as a combustion chamber outlet O ₂ concentration, a combustion chamber furnace pressure, and a combustion chamber outlet temperature which are inputted as a process signal from the combustion control device. Then, the signal is converted into a signal suitable for the processing of the combustion determination / control device A. The process state quantity input processing means 32 is, for example, an input interface.

The neural network means 42 obtains a degree of conformity with a typical combustion state based on the input values of the process state quantity and the values of the characteristic parameters. This is to make an appropriate judgment or evaluation. Then, the determination or evaluation result is input to the stochastic integration processing means 44. In addition,
When the stochastic integration processing means 44 is not provided,
The judgment or evaluation result is output as it is.

Here, the neural network means 42 is composed of an input layer, an intermediate layer and an output layer as shown in FIG. 2, for example, and each layer is composed of a plurality of processing units. Each processing unit is coupled between the next layer and the previous layer with a weight coefficient determined by learning, and each processing unit has an adder for summing inputs from the previous layer and a threshold value determined by learning. It has a threshold function. In learning of this neural network, a pair of an input pattern (teacher input) and a target output pattern (teacher output) is presented. Immediately after this presentation, weight and threshold adjustments are made so that the difference between the output of the network and the target output is reduced. At the time of learning, a learning set which is a set of pairs of an input pattern and a target pattern is used, and this is repeatedly presented to the network. When the learning is completed, a network operation test is performed.

More specifically, in this learning, there are a forward propagation step and a back propagation step executed thereafter. Both the forward propagation step and the back propagation step are executed each time a pattern is presented during learning. The forward propagation step begins with the presentation of the input pattern to the input layer of the network and continues as the activity level calculation propagates forward through the hidden layer.
All the processing units of each layer (indicated by a circle in FIG. 2) calculate the sum of inputs and calculate the output by a threshold function. The output layer of the unit then outputs the network.

Next, the output pattern of the network is compared with the target output pattern, and when there is a difference between them, a back-propagation step is started. In the backpropagation step, the calculation of the threshold value and the weight change of the unit of each layer is performed. The calculation is started from the output layer and sequentially traced in the reverse direction to the intermediate layer. In this backpropagation step, the network adjusts the weights and thresholds so that the observed differences are reduced.

Since such learning is performed, the output pattern from the network basically basically matches the target output pattern.

The stochastic integration processing means 44 cannot take an image of the entire combustion area because the imaging by the color image imaging means 10 is performed through the viewing window. In addition, a process is performed to prevent different judgments and evaluations from being made on images having little time lag. This processing will be described more specifically as follows.

Since the output pattern of the neural network means 42 is output as the degree of conformity with each of the patterns of, for example, combustion deterioration, combustion appropriateness, and active combustion, a certain combustion state has two or more patterns, for example, combustion deterioration, combustion appropriateness. Both patterns may be output at a certain degree of matching or higher. For such a state, the stochastic integration processing means 44 calculates reliability intervals for a plurality of support signals using Dempster &Shafer's probability theory, quantifies the ambiguity between the fitness levels, and An evaluation result determined to be highly reliable is output.

The combustion control processing means 46 calculates a process control amount such as an air supply amount, a fuel supply amount, or a water injection amount into the combustion chamber, according to the result of the evaluation of the combustion state.

The process control amount output processing means 34 outputs an air supply amount output as a process signal to the combustion control device,
The processing of the signal form of the process control amount such as the fuel supply amount and the water injection amount into the combustion chamber is performed, and the signal form is converted into a signal suitable for processing by the combustion control device. The process control amount output processing means 46 is, for example, an output interface.

The color system conversion means 22, feature parameter extraction means 24, neural network means 4
2. Stochastic integrated processing means 44 and combustion control processing means 4
6 is specifically realized by, for example, storing a program corresponding to the function in a board computer.

Hereinafter, the present invention will be described in more detail with reference to more specific examples.

Embodiment FIG. 3 is a schematic diagram of a combustion judgment / control device used in this embodiment. The determination / control device A processes a color image captured by the color television camera 10 connected via a cable to evaluate a combustion state and control combustion.

The configuration of the color television camera 10 is not particularly limited, and various types of color television cameras conventionally used for capturing color images can be used.

The combustion determination / control device A includes a process signal input / output processing unit 30 functioning as a process state quantity input processing means 32 and a process control quantity output processing means 34 connected by a data bus, and a color system conversion. The image processing unit 20 functions as the unit 22 and the feature parameter extracting unit 24, and the artificial intelligence processing unit 40 functions as the neural network unit 42, the stochastic integration processing unit 44, and the combustion control processing unit 46. for that reason,
The image processing unit 20 includes, for example, an image input board, a first image memory board (RGB image memory), a high-speed operation board, a second image memory board, and an image processing CPU board.
The artificial intelligence processing unit 40 has, for example, a neural network, a stochastic integration processing unit, and a combustion control processing unit.
Note that a development support computer 50 is connected to the artificial intelligence processing unit 40 of the combustion state determination and control device A for convenience such as modification of a program in a test stage.

The color image from the color television camera 10 is converted by the image input board into chromaticity values of the RGB color system, stored in the first image memory board, and then converted into the RGB color by the high-speed operation board. The system is converted into the YIQ color system, and the component values are calculated. Next, feature parameters are extracted based on the component values. The extracted feature parameters are stored in the second image memory. Here, the characteristic parameters are the component values of Y, I, and Q, respectively. Further, the value of the extracted feature parameter is input to the neural network of the artificial intelligence processing unit 40 by the image processing CPU board together with the process state quantity, for example, the combustion chamber exit temperature.

The neural network evaluates deterioration of combustion, appropriate combustion, active combustion, and the like based on the input characteristic parameter values and process state quantities (see FIG. 4). FIG. 5 shows an example of the evaluation result. As is apparent from FIG. 5, different evaluation results of combustion deterioration and active combustion are obtained. Therefore, Dempster & Sh
Performs stochastic integration using afer's probability theory. That is, the fitness when the combustion is deteriorated, the fitness when the combustion is appropriate, and the fitness when the combustion is active are represented by f _b , f _s and f, respectively.
_a and the integrated fitness is f _bA , f _Ba … f _bsA
In other _words , the integrated fitness degrees f _xY and f _xyZ are obtained by the following equations. _{f xY = (1-f x} ) · f y / (1-f x · f y) f xyZ = (1-f x) · f yZ / (1-f x · f yZ)

[0045] Here, f _bA: f _b, combustion active goodness-of-fit of from f _a f _Ba: f _b, deterioration of combustion goodness-of-fit · · · f from _{f a bsA: f b, f} s, from f _a Combustion active fitness x, y, z: any of a, b, and c, which are different from each other. X, Y, Z: Any of A, B, and C, which are different from each other.

The combustion state in the case of FIG. 5 is determined based on the equation relating to the integrated fitness. From FIG. 5, f _b is 0.16
And f _a can be read as 0.94. When these values are substituted into the above equation and calculated, the integrated fitness f _bA ,
f _Ba is 0.929 and 0.011, respectively. Therefore, it is evaluated that combustion is active.

Next, the correspondence between the evaluation results of the neural network and changes in the characteristics of the combustion chamber was investigated. FIG. 6 shows the result. From FIG. 6, it is observed that the concentration of O _{2 at the} combustion chamber outlet and the CO concentration increase after the signal of combustion deterioration is output, and the decrease of the O ₂ concentration at the combustion chamber outlet is reduced after the signal of active combustion is output. An increase in CO concentration is observed. Therefore, it can be seen that the evaluation by the neural network matches the actual combustion. Also,
Since the combustion state is determined before the measured value of the characteristic change, it can be said that the combustion state is practically determined without time delay.

The learning of the neural network was performed using the development support computer 50 connected to the artificial intelligence processing unit 40. Hereinafter, the learning contents will be described.

The neural network used here is
It is composed of a hierarchical neural network consisting of an input layer, a hidden layer and an output layer. Each cell of the intermediate layer is connected to all input layers. Each cell of the output layer is also connected to all cells of the intermediate layer. Then, the output value O _i of each cell is represented by a jigmoid function of the following equation. O _i = 1 / (1 + exp (−Σω _ij O _j ))

Here, ω _ij is a coupling coefficient from cell j to cell i, and its value is determined by learning using teaching data.

In the learning, the back propagation method is used, and when the teaching data T _i is given, the correction amount of ω _ij can be obtained by the following equation. Δω _ij (k) = αδ _j O _i + βΔω _ij (k−1) δ _j = (T _i −O _i ) O _i (1−O _i )

Here, k indicates the number of repetitions.

As input to the neural network for determining the combustion state, as described above, the component values (characteristic parameters) of the outputs Y, I, and Q of the image processing unit 20, the combustion chamber outlet gas temperature T, and Was used.

Since the output of the image processing unit 20 and the temporal change in the temperature of the gas at the outlet of the combustion chamber are also important information,
30 values were measured for each second, and these were also input to the neural network.

Time series data having the following configuration as a teaching data group for learning is searched from the CO value and O ₂ value of the trend data after operation (see FIG. 6), and combustion deterioration,
A total of 73 patterns were extracted for the three types of appropriate combustion and active combustion, and the teaching of the neural network was repeated 3000 times. As a result, the error with respect to the teaching pattern of the obtained neural network was 0.59%.

[0056] teaching data Example (1) neural network input data pattern _{NI 1: Y 11, Y 12} ... Y 130, I 11, I 12 ... I 130,
_{Q 11, Q 12 ... Q 130} , T 11, T 12 ... T 130 · · · NI i: Y i1, Y i2 ... Y i30, I i1, I i2 ... I i30,
Q _i1 , Q _i2 ... Q _i30 , T _i1 , T _i2 ... T _i30 ... NI ₇₃ : Y ₇₃₁ , Y ₇₃₂ ... Y ₇₃₃₀ , I ₇₃₁ , I ₇₃₂ ...
I ₇₃₃₀ , Q ₇₃₁ , Q ₇₃₂ ... Q ₇₃₃₀ , T ₇₃₁ , T ₇₃₂ ... T ₇₃₃₀

(2) Neural network output data
Pattern NO ₁ : Combustion deterioration ・ ・ ・ NO _i : Proper combustion ・ ・ ・ NO ₇₃ : Active combustion

In the combustion control processing unit, the amount of supplied air, the amount of fuel supplied, and the amount of water injected into the combustion chamber are controlled in accordance with the evaluation result of the combustion state in order to suppress the generation of CO. The following processing is performed.

(1) When it is determined that the combustion has deteriorated When the combustion has deteriorated, the reaction is frozen by rapid cooling,
In addition, since CO is generated by discharging the equilibrium composition gas at a high temperature, the following processing is performed.

Primary air volume The primary air volume is increased. Thereby, the stratified combustion is temporarily activated, and the stratum temperature and the combustion chamber temperature are increased.

Secondary Air Volume The secondary air volume is reduced. Thereby, the cooling of the combustion chamber is suppressed, and the temperature of the combustion chamber rises.

Fuel supply amount The fuel supply amount is increased. As a result, deterioration of combustion due to a decrease in fuel is avoided.

The amount of water injected into the combustion chamber The amount of water injected into the combustion chamber is increased. Thereby, the water term in the CO oxidation reaction formula of Mizutani shown below increases, and the oxidation of CO is promoted, and the CO concentration decreases. -d [CO] /dt=1.2x10 ¹¹ [CO] [O ₂ ] ^0.3 [H ₂ O] ^0.5 exp (-
8050 / T)

[0064](2) When it is determined that combustion is active  If combustion becomes active, mixing is not uniform and local
CO is generated due to the discharge of fuel-rich gas mass
Therefore, the following processing is performed.

Primary air amount The primary air amount is increased. This promotes gas mixing and eliminates O ₂ deficiency.

Secondary air amount The secondary air amount is increased. This promotes gas mixing in the combustion chamber and eliminates O ₂ deficiency.

Fuel supply amount The fuel supply amount is reduced. Thereby, the fuel amount is shifted to the appropriate amount.

The amount of water injected into the combustion chamber The amount of water injected into the combustion chamber is increased. As a result, the water term in the CO oxidation reaction equation increases, and the oxidation of CO is promoted, and the concentration of CO decreases.

Next, according to the above-mentioned procedure, for example, evaluation of deterioration of combustion or active combustion in the stochastic integrated processing unit
It can be seen that when the secondary air amount is reduced or increased as shown in FIG. 6D, the generation of CO is suppressed as shown in FIG. 6B.

[0070]

As it has been described in the foregoing, in the present invention, the combustion chamber exit temperature and the combustion chamber outlet O ₂ concentration, with the process state quantities such as the combustion chamber furnace pressure, a color image of the combustion state imaging Since the characteristic parameters are extracted and the values are input to the neural network to determine or evaluate the combustion state, it is possible to accurately determine or evaluate the combustion state substantially without a time delay. An excellent effect is obtained.

In a preferred embodiment of the present invention, the judgment or evaluation results are stochastically integrated to judge or evaluate the combustion state. Therefore, irregular images can be generated in a short time due to fluctuations in the flame or uneven combustion. An excellent effect is obtained that the combustion state can be determined or evaluated accurately without being affected by such fluctuations.

Further, in the combustion control according to the present invention, according to the determination or evaluation, the process control amount such as the air supply amount, the ratio of primary air to secondary air, the amount of water injected into the combustion chamber, the fuel supply amount, and the like. Therefore, an excellent effect that low-pollution combustion in which CO and the like are suppressed can be achieved and air pollution is prevented can be obtained.

[Brief description of the drawings]

FIG. 1 is a functional block diagram of a determination / control device used in a combustion state determination / control method of the present invention.

FIG. 2 is an explanatory diagram of a neural network used in the present invention.

FIG. 3 is a block diagram of a combustion state determination and control device according to an embodiment of the present invention.

FIG. 4 is an explanatory diagram of a neural network in the embodiment.

FIG. 5 is a graph showing an example of an evaluation result in the example.

FIG. 6 is a graph showing a relationship between evaluation results and combustion characteristics in the example, in which (a) shows the output of the neural network, (b) shows the CO concentration, (c) shows the O ₂ concentration,
(D) shows the amount of secondary air.

[Explanation of symbols]

DESCRIPTION OF SYMBOLS 10 Color image pick-up means, color television camera 20 Image processing part 22 Colorimetric system conversion means 24 Feature parameter extraction means 30 Process signal input / output processing part 32 Process state quantity input processing means 34 Process control quantity output processing means 40 Artificial intelligence processing part 42 Neural network means 44 Stochastic integrated processing means 46 Combustion control processing unit 50 Development support computer A Combustion determination / control device

──────────────────────────────────────────────────続 き Continuing on the front page (72) Inventor Yuichi Miyamoto 1-1, Kawasaki-cho, Akashi-shi Kawasaki Heavy Industries Co., Ltd. Inside the Akashi Factory (72) Inventor Kazuki Ogura 1-1, Kawasaki-cho, Akashi-shi Kawasaki Heavy Industries, Ltd. Akashi Factory (72) Inventor Isao Tsukimoto 1-1, Kawasaki-cho, Akashi-shi Kawasaki Heavy Industries, Ltd. Inside Akashi Plant (72) Inventor Hiroshi Fujiyama 1-3-1, Higashi-Kawasaki-cho, Chuo-ku, Kobe Kawasaki Heavy Industries, Ltd. (72) Inventor Norio Toyoshima 1-3-1 Higashikawasaki-cho, Chuo-ku, Kobe Kawasaki Heavy Industries, Ltd.Kobe Head Office (72) Inventor Hidetaka Miyazaki 1-1-1, Kawasaki-cho, Akashi-shi Kawasaki Heavy Industries, Ltd. ) Inventor Yoshinobu Mori 1-1-1, Kawasaki-cho, Akashi-shi Inside the Akashi factory of Kawasaki Heavy Industries, Ltd. (72) Inventor Motohiro Inoue 1 Kawasaki-cho, Akashi-shi No. 1 Inside the Akashi factory of Kawasaki Heavy Industries, Ltd. (56) References JP-A-5-149535 (JP, A) JP-A-63-298018 (JP, A) JP-B-6-29665 (JP, B2) (58) Field surveyed (Int.Cl. ⁶ , DB name) F23N 5/08 F23N 5/00

Claims (12)

(57) [Claims] 1. A procedure for measuring a process state quantity, a procedure for capturing a combustion state with a color image, and a procedure for processing an obtained color image into three component images of a red component, a green component, and a blue component. When the obtained red component, green component and converting the procedure for the three component image consisting of blue component to the color system consisting of three components, each component of the color system from the converted image to the color system Each painting
Calculating an average value for each surface; and using the average value of each component of the color system and the process state quantity as inputs to a neural network to determine a degree of conformity with a typical combustion state. A combustion determination method using a color image. Wherein said process state quantity, the combustion chamber outlet O ₂
2. The method for judging combustion using a color image according to claim 1, wherein the temperature is a concentration, a pressure in a combustion chamber furnace, or a temperature in a combustion chamber outlet. 3. The method for judging combustion using a color image according to claim 1, further comprising a step of separating a flame region from a captured color image. 4. The method according to claim 1, further comprising a step of stochastically integrating the fitness values to evaluate a combustion state. 5. A combustion control method using a color image, wherein combustion control is performed using a combustion determination or an evaluation result by the combustion determination method according to claim 1, 2, or 3. 6. The combustion control according to claim 1, wherein the combustion control is performed by adjusting an air supply amount, a ratio between the primary air amount and the secondary air amount, a water injection amount into the combustion chamber, or a fuel supply amount. 5. A combustion control method using the color image according to 5. 7. A process state quantity input processing unit, a color image capturing unit, a color system conversion unit comprising three components , a characteristic parameter extracting unit, and a neural network unit, wherein the image is captured by the color system conversion unit. image is made conversion to the color system, wherein the characteristic parameter extracting means, the average value for each screen of each component of the transformed the color system is calculated by the neural network unit, said process state quantity A combustion determination using a color image, wherein a degree of conformity with a typical combustion state is calculated based on the process state quantity from the input means and the average value , and the combustion state is evaluated. apparatus. 8. A color system conversion method comprising : a process state quantity input processing means; a color image capturing means; a color system conversion means comprising three components ; a feature parameter extraction means; a neural network means; and a stochastic integration processing means. by means converts the captured image to the color system is performed by said feature parameter extracting means, the average value for each screen of each component of the transformed the color system is calculated, the neural network means The degree of conformity with a typical combustion state is calculated based on the process state quantity from the process state quantity input means and the average value , and the fitness calculated by the stochastic integrated processing means A combustion judging device using a color image, wherein a degree is stochastically processed to evaluate a combustion state. 9. The combustion chamber outlet O ₂
9. The combustion judging device using a color image according to claim 7, wherein the temperature is a concentration, a pressure in a combustion chamber furnace, or a temperature in a combustion chamber outlet. 10. A process state input means, a color image capturing means, a color system conversion means comprising three components , a characteristic parameter extracting means, a neural network means, a combustion control processing means, and a process control amount output processing means. , by the color system conversion unit, converted captured image to the color system is performed by said feature parameter extracting means, the average value for each screen of each component of the transformed the color system is calculated The neural network means, based on the process state quantity from the process state quantity input means and the average value , the degree of conformity with a typical combustion state is calculated and the combustion state is evaluated, The process control amount is calculated by the combustion control processing means based on the evaluation of the combustion state, and the process control amount is output by the process control amount output processing means. Combustion control device using a color image, characterized in that the predetermined processing is performed is output to Seth control amount. 11. A process state quantity input processing means, a color image capturing means, a color system conversion means comprising three components , a characteristic parameter extracting means, a neural network means, a stochastic integration processing means, a combustion control processing means, and a process control amount. and an output processing unit, by the color system conversion unit, converted captured image to the color system is performed, the characteristic parameters by the extraction means, the transformed each screen of each component of the color system An average value is calculated for each, and the neural network means calculates a degree of conformity with a typical combustion state based on the process state quantity and the average value from the process state quantity input means, The calculated degree of conformity is stochastically processed by the stochastic integration processing means to evaluate a combustion state, and the combustion state is calculated by the combustion control processing means. Evaluation the calculated process control amount based, the the process control variable output processing means, a combustion control device using a color image, characterized in that the predetermined processing is performed is output to the process control amount. 12. The combustion chamber outlet O
₍₂₎ concentration, combustion chamber furnace pressure, or combustion chamber exit temperature, wherein the process control amount relates to the air supply amount, the ratio of the primary air amount and the secondary air amount, the amount of water injected into the combustion chamber, or the fuel supply amount. The combustion control apparatus using a color image according to claim 10 or 11, wherein the combustion control apparatus uses a color image.