JP6718911B2 - Model creation method, plant operation support method, and model creation device - Google Patents

Description

The present disclosure relates to a model creation method, a plant operation support method, and a model creation device.

Patent Document 1 relates to a statistical model (simulation model) for estimating a value of a measurement signal measured when a control signal is given to a plant, and relates to a statistical model such as an opening of an air damper at an operating end of a boiler and an angle of a burner. A control device that minimizes each of the process values by using the NOx, CO, and H ₂ S concentrations contained in the exhaust gas discharged from the boiler as the process parameters (outputs) of the statistical model. ..

Japanese Patent No. 5378288

By the way, when the specifications of the plant and the properties of the fuel change, it is assumed that the relationship between the input parameter of the plant and the process value changes. However, Patent Document 1 does not disclose any knowledge about how to accurately predict a process value when the specifications of the plant or the properties of the fuel change.

At least one embodiment of the present invention is made in view of the above-mentioned conventional problems, and the purpose thereof is to accurately predict a process value in response to changes in plant specifications and fuel properties. It is to provide a model creating method, a plant operation support method, and a model creating apparatus that can be performed.

(1) The model creating method according to at least one embodiment of the present invention is
A model creating method for creating a model showing a relationship between an input parameter of a fuel burning plant and a process value,
Operation data of the plant including at least one of physical parameters related to specifications of the plant or fuel parameters related to properties of the fuel, and a reading step of reading image data of a combustion region of the plant,
An extraction step of extracting a feature amount of the image data,
A model creating step of creating the model using the at least one of the physical parameter or the fuel parameter and the feature amount of the image data as the input parameter,
Equipped with.

According to the model creating method described in the above (1), the model is created by using at least one of the physical parameter or the fuel parameter and the feature amount of the image data as an input parameter, and thereby the difference between the plant specification and the fuel property is determined. In consideration of this, the process value can be accurately predicted using the image data. Further, since one of the input parameters includes the feature amount of the image data of the combustion region, for example, when adopting the plant ash unburned component as the process value (the input parameter of the plant and the plant ash unburned component When creating a model that shows the relationship), it is possible to constantly and quickly evaluate unburned ash content, which is usually difficult to measure quickly, and reduce fuel cost loss by maintaining an optimal combustion state. can do.

(2) In some embodiments, in the model creating method described in (1) above,
The image data is acquired by capturing an image of the combustion region from above by an imaging device capable of capturing at least one of a moving image and a still image.

According to the model creating method described in (2) above, the process value can be accurately predicted by reading the image data taken from above the combustion region and using it for model creation.

(3) In some embodiments, in the model creating method described in (1) or (2) above,
In the extraction step, as the feature amount of the image data, information relating to any one of shape, size, color, shade, brightness, temperature (temperature distribution), wavelength (wavelength distribution) of the combustion region, or its change amount. Extract.

According to the model creating method described in (3) above, the information regarding the shape, size, color, density, brightness, temperature (temperature distribution), wavelength (wavelength distribution) of the combustion region or its change amount can be obtained. Based on this, the process value can be accurately predicted. In addition, the brightness information of the combustion area is information obtained from the image without detecting the flame itself, and even if the flame is not imaged in the exhaust gas, for example, by installing an imaging device in the upper part of the furnace, the image You can get information. This also makes it possible to facilitate the installation of an imaging device (camera inside the furnace) for imaging the inside of the furnace.

(4) In some embodiments, in the model creating method according to any one of (1) to (3) above,
In the model creating step, the model is created using the index related to the exhaust gas component of the plant or the index related to the emission of the plant as the process value.

Exhaust gas components or emissions are generated in the combustion process in the furnace and largely depend on the combustion state in the combustion region of the plant, so the amount of these generations is highly correlated with the image data of the combustion region. Therefore, as described in (4) above, the process value can be accurately estimated by creating a model using the index related to the exhaust gas component of the plant or the index related to the emission of the plant as the process value.

(5) In some embodiments, in the model creating method according to any one of (1) to (4) above,
In the reading step, a parameter relating to at least one of the structure, performance or design condition of the plant is read as the physical parameter,
In the model creating step, the model is created by using at least one of the structure, performance or design condition of the plant and the feature amount of the image data as the input parameter.

The size of the plant, the installation position of the image pickup device, and the injection position of the fuel are different for each plant, and the value of the feature amount is different for each plant even if the process value is the same. Therefore, as described in (5) above, by creating a model in consideration of appropriate physical parameters relating to at least one of the structure, performance, and design conditions of the plant, the characteristics caused by the difference in plant specifications It is possible to correct the difference in quantity and improve the estimation accuracy of the process value.

(6) In some embodiments, in the model creating method according to any one of (1) to (5) above,
In the reading step, a parameter relating to at least one of fuel adjustment, combustion, environmental load or moisture is read as the fuel parameter,
In the model creating step, the model is created using the parameters relating to at least one of fuel adjustment, combustion, environmental load, and water and the feature amount of the image data as the input parameters.

Since the process value fluctuates even under the same plant operating conditions due to changes in the properties of the injected fuel, at least one of fuel adjustment, combustion, environmental load, and moisture as described in (6) above. By creating a model in consideration of an appropriate fuel parameter related to the above, it is possible to correct the difference in the characteristic amount due to the difference in the fuel property and improve the estimation accuracy of the process value.

(7) A plant operation support method according to at least one embodiment of the present invention comprises:
A method for operating a plant, which uses a model showing a relationship between an input parameter of a plant that burns fuel and a process value,
A data reading step of reading operating data of the plant including at least one of a physical parameter related to the specifications of the plant or a fuel parameter related to the property of the fuel, and image data of a combustion region of the plant,
An extraction step of extracting a feature amount of the image data,
A model reading step of reading the model with the at least one of the physical parameter or the fuel parameter and the feature amount of the image data as the input parameter;
Operation data of the plant, image data of a combustion region of the plant, a simulation step of calculating the process value using the model,
An operation instruction step of calculating an operation instruction value of the plant is further provided so that the process value satisfies a predetermined condition.

According to the plant operation support method described in (7) above, by calculating a process value using a model having at least one of a physical parameter or a fuel parameter and a feature amount of image data as an input parameter, The process value can be accurately predicted by using the image data in consideration of the difference between the plant specification and the fuel property. Further, since one of the input parameters includes the feature amount of the image data of the combustion region, for example, when adopting the plant ash unburned component as the process value (the input parameter of the plant and the plant ash unburned component When creating a model that shows the relationship), it is possible to constantly and quickly evaluate unburned ash content, which is usually difficult to measure quickly, and reduce fuel cost loss by maintaining an optimal combustion state. can do. As a result, it is possible to effectively support the operation of the plant.

(8) The model creating device according to at least one embodiment of the present invention is
A model creating device for creating a model showing a relationship between an input parameter of a fuel burning plant and a process value,
Data acquisition configured to acquire operation data of the plant including at least one of physical parameters related to specifications of the plant or fuel parameters related to properties of the fuel, and image data of a combustion region of the plant. Department,
A data extraction conversion unit configured to extract a feature amount of the image data acquired by the data acquisition unit;
A model creating unit configured to create the model using the at least one of the physical parameter or the fuel parameter and the feature amount of the image data as the input parameter,
Equipped with.

According to the model creating apparatus described in (8) above, at least one of the physical parameter or the fuel parameter and the feature amount of the image data are used as the input parameters to create the model, so that the difference between the plant specification and the fuel property can be obtained. In consideration of this, the process value can be accurately predicted using the image data.

(9) A plant operation support device according to at least one embodiment of the present invention,
A plant operation support device using a model showing a relationship between an input parameter of a plant that burns fuel and a process value,
Data acquisition configured to acquire operation data of the plant including at least one of physical parameters related to specifications of the plant or fuel parameters related to properties of the fuel, and image data of a combustion region of the plant. Department,
A data extraction conversion unit configured to extract a feature amount of the image data acquired by the data acquisition unit;
At least one of the physical parameter or the fuel parameter, and a model database that stores the model having the feature amount of the image data as the input parameter,
Operation data of the plant, image data of a combustion region of the plant, a simulation unit that calculates the process value using the model stored in the model database,
An optimization unit configured to obtain an optimum set of input parameters so that the process value satisfies a predetermined condition,
An operation instruction unit that calculates an operation instruction value of the plant from the set of the optimum input parameters obtained by the optimization unit,
Equipped with.

According to the plant operation support apparatus described in (9) above, the process value is calculated using a model in which at least one of the physical parameter or the fuel parameter and the feature amount of the image data are used as input parameters. The process value can be accurately predicted by using the image data in consideration of the difference between the plant specification and the fuel property. Further, since one of the input parameters includes the feature amount of the image data of the combustion region, for example, when adopting the plant ash unburned component as the process value (the input parameter of the plant and the plant ash unburned component When creating a model that shows the relationship), it is possible to constantly and quickly evaluate unburned ash content, which is usually difficult to measure quickly, and reduce fuel cost loss by maintaining an optimal combustion state. can do. Therefore, it is possible to effectively support the operation of the plant.

(10) A plant operation support system according to at least one embodiment of the present invention,
A plant operation support system comprising a remote support system capable of communicating via the local support system and a network,
The local support system is
The driving data, the image data, and the image data in the other local assistance system, which are configured to send the driving data, the image data, and the update result of the model to the remote assistance system, and which are transmitted from the remote assistance system. A first transceiver configured to receive model update results,
The remote support system is
The operation data, the image data, and the update result of the model transmitted from each of the local assistance systems are received, and the update result is transmitted to all other local assistance systems. It includes a second transceiver configured to transmit the image data and the result of updating the model.

According to the plant operation support system described in (10) above, it is possible to share operation data, image data, and model update results in another local support system (for example, a preceding plant).

According to at least one embodiment of the present invention, there are provided a model creating method, a plant operation support method, and a model creating apparatus capable of accurately predicting a process value in response to changes in plant specifications and fuel properties. It

It is a schematic diagram of the boiler plant 100. It is a model creation flow diagram which shows the model creation method which concerns on one Embodiment. The results of the simulation using the model created in FIG. 2 is a flowchart showing the operation instruction flow to provide a driving instructions against the operation control equipment. 1 is an overall configuration diagram showing a boiler plant 100 and an operation control device 200 that controls the boiler plant 100. FIG. 3 is a diagram showing an example of a hardware configuration of an operation control device 200. FIG. It is a schematic diagram showing the relationship of the input and output of a model. It is an example of a data format in the model database DB5. It is an example of a data format in the plant specification database DB3. It is an example of a data format in the fuel property database DB4. It is an example of a data format in the additional parameter candidate database DB6. It is a figure which shows the whole structural example of the driving assistance system 500 which assists model creation. It is a figure which shows the detailed structural example of the driving assistance system 500, and has shown the structure of 300 A of local assistance systems as a typical structural example.

Hereinafter, some embodiments of the present invention will be described with reference to the accompanying drawings. However, the dimensions, materials, shapes, relative positions, and the like of the components described as the embodiments or shown in the drawings are not intended to limit the scope of the present invention thereto, but are merely illustrative examples. Absent.
For example, the expression "relative or absolute" such as "in a certain direction", "along a certain direction", "parallel", "orthogonal", "center", "concentric", or "coaxial" is strict. In addition to representing such an arrangement, it also represents a state in which the components are relatively displaced by a tolerance or an angle or a distance at which the same function can be obtained.
For example, expressions such as "identical", "equal", and "homogeneous" that indicate that they are in the same state are not limited to a state in which they are exactly equal. It also represents the existing state.
For example, the representation of a shape such as a quadrangle or a cylindrical shape does not only represent a shape such as a quadrangle or a cylindrical shape in a strict geometric sense, but also an uneven portion or a chamfer within a range in which the same effect can be obtained. The shape including parts and the like is also shown.
On the other hand, the expressions “comprising”, “comprising”, “comprising”, “including”, or “having” one element are not exclusive expressions excluding the existence of other elements.

Hereinafter, a model creating method for creating a simulation model (hereinafter simply referred to as “model”) showing a relationship between an input parameter (input) and a process value (output) of a plant that burns fuel will be described.

First, a configuration of a boiler plant 100 is shown as an example of a plant that is a modeling target in the model creating method. FIG. 1 is a schematic diagram of a boiler plant 100.
The boiler 2 included in the boiler plant 100 is configured to burn solid fuel. The boiler 2 uses pulverized coal obtained by pulverizing coal as pulverized fuel (solid fuel), combusts the pulverized coal with the combustion burner of the furnace 11, and exchanges heat generated by this combustion with feed water or steam to generate steam. It is a coal-fired boiler that can be produced. The fuel is not limited to coal and may be other fuel that can be combusted in the boiler, such as biomass. Further, various types of fuels may be mixed and used.

The boiler 2 includes a furnace 11, a combustion device 12, and a flue 13. The furnace 11 has, for example, a hollow rectangular tube shape and extends along the vertical direction. The wall surface of the furnace 11 is composed of an evaporation pipe (heat transfer pipe) and fins that connect the evaporation pipe, and the temperature rise of the furnace wall is suppressed by heat exchange with the feed water and steam. Specifically, for example, on the side wall surface of the furnace 11, a plurality of evaporation pipes are arranged side by side in the horizontal direction, and each evaporation pipe is extended along the vertical direction. The fin closes the space between the evaporation tubes. The furnace bottom of the furnace 11 is provided with an inclined surface 62, and the furnace bottom evaporation pipe 70 is provided on the inclined surface 62 to form the bottom surface of the furnace. An image sensor SR 1 is provided above the furnace 11.

The combustion device 12 is provided on the lower side in the vertical direction of the furnace wall forming the furnace 11. Further, the combustion device 12 has a plurality of combustion burners (for example, combustion burners 21, 22, 23, 24, 25) mounted on the furnace wall. The plurality of combustion burners 21, 22, 23, 24, 25 are arranged at equal intervals along the circumferential direction of the furnace 11, for example. However, the shape of the furnace, the arrangement of the burners, the number of combustion burners in one stage, and the number of stages are not limited to the above-mentioned form.

The combustion burners 21, 22, 23, 24, 25 are connected to pulverizers (pulverized coal machines/mills) 31, 32, 33, 34, 35 via the pulverized coal supply pipes 26, 27, 28, 29, 30 respectively. It is connected. When coal is transported by a transport system (not shown) and charged into the crushers 31, 32, 33, 34, 35, the crushers 31, 32, 33, 34, 35 crush the coal to a predetermined fine powder size. .. The pulverized coal (pulverized coal) is supplied to the combustion burners 21, 22, 23, 24, 25 from the pulverized coal supply pipes 26, 27, 28, 29, 30 together with the carrier air (primary air).

Further, in the furnace 11, a wind box 36 is provided at a mounting position of each combustion burner 21, 22, 23, 24, 25. One end of the air duct 37b is connected to the wind box 36, and the other end of the air duct 37b is connected to an air duct 37a for supplying air at a connection point 37d.

A flue 13 is connected vertically above the furnace 11, and a plurality of heat exchangers 41, 42, 43, 44, 45, 46, 47 for generating steam are arranged in the flue 13. ing. The combustion burners 21, 22, 23, 24, 25 inject a mixture of pulverized coal fuel and combustion air into the furnace 11 to form a flame, and combustion gas is generated and flows into the flue 13. Superheated steam is generated by heating the feed water and steam flowing through the furnace wall and the heat exchangers 41 to 47 by the combustion gas, and the steam turbine (not shown) is rotationally driven by the generated superheated steam and connected to the rotary shaft of the steam turbine. Electric power is generated by rotating the generator (not shown). An exhaust gas passage 48 is connected to the flue 13. In the exhaust gas passage 48, a denitration device 50 for purifying the combustion gas, an air heater 49 for exchanging heat between the air flowing from the forced air blower 38a to the air duct 37a and the exhaust gas flowing in the exhaust gas passage 48, and a dust treatment device 51. , And an induction blower 52 are provided. A chimney 53 is provided at the downstream end of the exhaust gas passage 48. The denitration device 50 may not be provided as long as the exhaust gas standard is satisfied.

Further, the pulverized coal conveying air (primary air) is sent from the primary air blower 38b to the air duct 37e passing through the air heater 49 and the air duct 37f bypassing the air heater 49. The primary air merges after the air flow rates of both ducts have been adjusted so as to reach a predetermined temperature, etc., and the primary air is sent to the crushers (mills) 31, 32, 33, 34, 35 via the air duct 37g. To be

The furnace 11 newly injects combustion air (after-air) to perform lean fuel combustion after the fuel is excessively burned by the combustion air (secondary air) introduced into the furnace 11 from the primary air and the wind box 36. It is a so-called two-stage combustion type furnace. Therefore, the furnace 11 is provided with the after-air port 39. One end of an air duct 37c is connected to the after air port 39, and the other end of the air duct 37c is connected to an air duct 37a for supplying air at a connecting point 37d. If the two-stage combustion method is not adopted, the after air port 39 may not be provided.

The air sent from the blower 38 to the air duct 37a is warmed by heat exchange with the combustion gas by the air heater 49, and is passed through the air duct 37b to the secondary air and the air box 37c. It branches off at the connection point 37d with the after-air guided to the after-air port 39.

The image sensor SR1 is provided above the furnace 11 so as to generate image data of the combustion region in the boiler plant 100. The image sensor SR1 constitutes, for example, an image pickup device capable of picking up at least one of a moving image and a still image, and is provided so that the combustion region can be photographed from above. The imaging device may be, for example, a camera such as a digital camera, a video camera, or an infrared camera capable of detecting a specific wavelength. The image data of the combustion region may be an image itself of the inside of the furnace 11 or may be a feature amount that can be extracted from the image. Further, the image may be a still image or a frame (image) forming a moving image. The image sensor SR1 may be installed at a position other than the upper portion of the furnace 11, such as the sidewall of the furnace 11. For example, an image sensor is installed in a portion forming a secondary combustion region in the side wall portion or a portion further above it (a portion closer to the upper portion), and is directed diagonally downward so as to capture an image of the lower side where the primary combustion region is located. May be installed.

FIG. 2 is a model creation flow chart showing a model creation method according to an embodiment.
In the model creating method shown in FIG. 2, a model showing a relationship between an input parameter (input) and a process value (output) of the boiler plant 100 is utilized by utilizing image data of a combustion region in the boiler plant 100 that burns fuel. create. The model according to this embodiment is used for predicting (simulating) the process value based on the input parameters input to the model. In principle, a model is created for each process value, but the present invention is not limited to this, and a single model may output a plurality of process values. Further, here, a boiler plant as a typical power generation plant will be described as an example, but the model creating method described below is not limited to the boiler plant, and can be widely applied to plants that produce industrial products or materials. .. For example, as a plant that burns fuel, a steam supply plant and a steelmaking plant are exemplified in addition to a power generation plant.

First, in the reading step S1, the operation data of the plant 100 and the image data of the combustion region of the plant 100 are read. Further, the operation data read in the reading step S1 includes at least one of a physical parameter related to the specifications of the plant and a fuel parameter related to the property of the fuel, and a process value of the plant 100. When reading the physical parameter in the reading step S1, a parameter relating to at least one of the structure, performance, and design condition of the plant 100 may be read as the physical parameter. Further, the image data of the combustion region of the plant 100 may be either a still image or a moving image that is a sequence of still images acquired by the image sensor SR1 installed in the plant 100. The image data format may be uncompressed format data represented by TIFF or BMP for still images, AVI for moving images, JPEG or PNG for still images, and MPEG for moving images. It may be data in a compressed format represented by or MP4.

Next, in the extraction step S2, the feature amount of the image data read in the reading step S1 is extracted. The feature amount calculation can be processed in parallel with the image data reading by appropriately selecting the device configuration, and the reading of all image data is completed even if the image data volume becomes enormous. The calculation process of the feature amount can be started from before. The feature amount of the image data relates to, for example, the shape, size, color, shade, brightness, temperature (temperature distribution) or wavelength (wavelength distribution) of the combustion region that appears in the image data or is obtained based on the image data. It may be information, or may be the amount of change of at least one of these information. The amount of change refers to the amount of change in space and/or time. The feature amount is information obtained by digitizing the feature of the image data, which is typically calculated from the brightness information of the image data.

When adopting the above-mentioned amount of change as the feature amount, for example, a feature amount obtained by three-dimensional higher-order local autocorrelation feature amount (CHLAC feature amount), CNN (Convolution Neural Network), or AE (AutoEncoder) is used. Good. The CHLAC feature quantity has an advantage that the spatiotemporal fluctuation appearing in the entire image can be expressed compactly. Further, by extracting a feature amount by convolution processing or pooling processing in CNN and by encoding processing in AE, it is possible to effectively reduce and acquire the entire characteristics of the image.

The feature amount extracted based on the brightness information may be the brightness value (brightness value) itself obtained from the image, or may be a statistical value such as the average or peak of the brightness values. Alternatively, the characteristic amount may be any one of the area, shape, and size of a portion having a luminance equal to or higher than a predetermined value, or the amount of change in luminance value. The brightness information may include information that can be converted from the brightness value, such as temperature and temperature distribution obtained by converting the brightness value.

Since the brightness information of the image data is information obtained by converting the grayscale values of R (red), G (green), and B (blue) in the color image into grayscale values of black and white (grayscale), By calculating the feature amount from the RGB grayscale information before conversion, that is, the color information of the image, it is possible to extract the feature amount of more diverse patterns. The feature amount extracted based on the color information of the image may be the grayscale value itself of each of RGB, or may be a statistical value such as an average grayscale value or a peak. Alternatively, it may be a value indicating a correlation between respective wavelengths, such as a ratio of the R value and the G value.

The brightness information is information that can be obtained from an image without detecting the flame itself, and obtains image data even when the flame is not imaged by the exhaust gas, for example, by installing the image sensor SR1 in the upper part of the furnace. You can This also makes it possible to facilitate the installation of an imaging device (camera inside the furnace) for imaging the inside of the furnace.

Next, in the model creating step S3, each step shown in detail below is sequentially executed. First, in step S31, 1 is added to the number N of model creations (initial value is 0). Then, in step S32, the model creation conditions and the additional parameter candidates are read. When the number of times N is 2 or more, the model creation condition and the additional parameter candidate are changed. Here, the model creation condition is a model creation target (process value), method (functional expression), allowable error, and the like. Further, the additional parameter candidate is an additional candidate of the input parameter described later.

Next, in step S33, it is determined whether the plant specifications (operating conditions) or the fuel properties change during the operation of the plant 100. If the plant specifications change during operation of the plant 100 in step S33, physical parameters related to the plant specifications are added to the input parameters of the model in step S34. Here, the physical parameter is a parameter relating to at least one of the structure, performance, and design condition of the plant 100. If the fuel property changes during the operation of the plant 100 in step S33, the fuel parameter related to the fuel property is added to the input parameter of the model in step S35. Here, the fuel parameter is a parameter relating to at least one of fuel adjustment, combustion, environmental load, and moisture. If neither the plant specifications nor the fuel properties change during the operation of the plant 100 in step S33, the input parameter is not added (step S36).

The size of the plant, the installation position of the image pickup device, and the injection position of the fuel are different for each plant, and the value of the feature amount is different for each plant even if the process value is the same. Therefore, as described above, by creating a model in consideration of appropriate physical parameters relating to at least one of the structure, performance, and design conditions of the plant 100, the difference in the feature amount due to the difference in the plant specifications can be reduced. It is possible to correct and improve the estimation accuracy of the process value. Further, since the process value fluctuates even under the same plant operating conditions due to changes in the properties of the fuel to be input, it is appropriate to adjust at least one of fuel adjustment, combustion, environmental load or moisture as described above. By creating a model in consideration of various fuel parameters, it is possible to correct the difference in the characteristic amount due to the difference in the fuel property and improve the estimation accuracy of the process value.

Next, in step S37, a model indicating the relationship between the input parameter of the plant 100 and the process value is machine-learned by using the operation data and the image data read in the reading step S1 to machine-learn the relationship between the input parameter of the model and the process value. To create. For example, a part of the operation data and a part of the image data read in the reading step S1 is used to machine-learn the relationship between the input parameter (at least one of the physical parameter or the fuel parameter and the image data) and the process value, and the plant A model is created showing the relationship between 100 input parameters and process values.

Next, in the verification step S4, each step detailed below is sequentially executed. First, in step S41, of the operation data and image data read in step S1, the accuracy of the model created in step S37 is verified using the operation data and image data not used for machine learning in step S37. .. For example, of the operation data and the image data read in the reading step S1, the operation data and the image data not used for machine learning in step S37 are input to the model created in step S37. Then, the simulation value (virtual process value) of the process value (output) calculated by the model is compared with the process value (actual process value) as the actual measurement value in the operation data read in the reading step S1 to obtain an error. To confirm.

Next, in step S42, it is determined whether the error confirmed in step S41 is within the allowable error range. If the error confirmed in step S41 is within the allowable error range, it is determined that the model created in step S37 is valid. If the error confirmed in S41 exceeds the allowable error, it is determined in step S42 that the model created in step S37 is not valid, and it is confirmed in step S43 whether the number N is equal to or less than the allowable number Nth. .. If the number of times N is equal to or less than the allowable number of times Nth in step S43, the process returns to the model creating step S3, and the model is modified by changing the model creating conditions and additional parameter candidates.

Next, in the output step S5, each step detailed below is executed. First, when it is determined in step S42 that the model created in step S37 is valid, the model is output to an input/output unit or a model database described later in step S51. If the number N of times exceeds the allowable number Nth in step S43, a model creation error is output in step S52. Either the model or the model creation error is output and the model creation flow ends.

In the output step S5, the operator can confirm the relationship (trend) between the input and the output by outputting the relationship between the input parameter of the model and the process value.

According to the model creating method shown in FIG. 2, the model is created by using the physical parameters related to the specifications of the plant 100, the fuel parameters related to the property of the fuel, and the feature amount of the image data of the combustion region as input parameters. The process value can be accurately predicted by using the image data in consideration of the difference in plant specifications and fuel properties. Further, since one of the input parameters includes the feature amount of the image data of the combustion region, for example, when adopting the plant ash unburned component as the process value (the input parameter of the plant and the plant ash unburned component In the case of creating a model showing the relationship), it becomes possible to constantly and quickly evaluate the unburned content in ash, which is usually difficult to measure quickly, and it is possible to reduce the fuel cost and denitration cost by maintaining the optimum combustion state. Loss can be reduced.

Although the method of creating the model of the plant 100 has been described with reference to FIG. 2, the model created in this manner is used by being incorporated in, for example, the operation control device 200 (see FIGS. 4A and 4B) of the plant 100. 3, will be described operation control device 200 of the plant 100 with reference to FIGS. 4A and 4 B.

First, FIG. 3 is a flowchart showing a driving instruction flow for giving the result of the simulation using the model created in FIG. 2 as a driving instruction to the driving control device 200 .

First, in step S61, the operation data of the plant 100 and the image data of the combustion region are read (data reading step). In step 62, the model created by the method shown in FIG. 2 is read (model reading step). Further, in step S63, the feature amount of the image data read in step S6 is extracted as in step S2 (extraction step).

Next, in the simulation step S7, a simulation is performed. First, in S71, simulation conditions are set. The simulation condition is a set of input parameters, that is, at least one of physical parameters related to the specifications of the plant 100 or fuel parameters related to the property of the fuel, and a set of image data of the combustion region of the plant 100.

In step S72, the simulation is executed by inputting the set of input parameters set in step S71 into the model created by the method shown in FIG. As a result of the simulation, the process value (virtual process value) of the plant 100 is calculated.

In the operation instruction step S8, an operation instruction value for the operation control device 200 is calculated so that the process value satisfies the predetermined condition. First, in step S81, the simulation result is evaluated. In step S82, it is determined whether or not the virtual process value is optimum (whether or not a predetermined condition is satisfied). If it is not optimum, the process returns to step S71 to reset the simulation condition and instruct to calculate a new virtual process value.

The evaluation in step S81 may be performed by converting each virtual process value into a score (dimensionless) with a predetermined conversion coefficient. In step S82, it may be determined that the virtual process value is optimum when the total value of the scores is equal to or larger than a predetermined value. Alternatively, the virtual process value is optimal when the simulation is performed in a plurality of cases (simulation conditions) and the score total value is the highest among those results, or when the operator determines that the highest number of cases is optimal. You may judge that. Furthermore, a case with a higher score may be automatically searched for by using a genetic algorithm or a method of particle swarm optimization, and whether or not it is optimum may be determined from the result.

Next, in step S83, a driving instruction value is calculated based on the simulation conditions and the result determined to be optimal, and the result is output to an output screen or the like described later. After that, the operation instruction flow ends.

According to the above operation instruction flow, since the process value can be accurately estimated by using the general-purpose model, the operation support of the plant 100 can be effectively performed.

FIG. 4A is an overall configuration diagram showing the plant 100 and an operation control device 200 that controls the plant 100. FIG. 4B is a diagram showing a hardware configuration of the operation control device 200. The operation control device 200 includes a CPU (Central Processing Unit) 72, a RAM (Random Access Memory) 74, a ROM (Read Only Memory) 76, an HDD (Hard Disk Drive) 78, an input I/F 80, and an output I/F 82. , These are configured using computers connected to each other via a bus 84. The hardware configuration of the operation control device 200 is not limited to the above, and may be configured by a combination of a control circuit and a storage device. Further, the operation control device 200 is configured by a computer executing a program that realizes each function of the operation control device 200. The function of each unit in the operation control device 200 described below is realized by, for example, loading a program held in the ROM 76 into the RAM 74 and executing the program in the CPU 72, and reading and writing data in the RAM 74 and the ROM 76. Further, by providing an arithmetic unit specialized for image processing such as GPU (Graphics Processing Unit), it is possible to more efficiently execute the processing of image data.

Plant 100, in detail, including the configuration shown in FIG. 1, FIG. 4 A, describes typically image sensors SR1, physical sensors SR2, and the operation ends OP. The operation end OP refers to a valve or a damper.

The configuration of the image sensor SR1 is as described above. The physical sensor SR2 is a sensor for detecting operation data including a process value of the plant 100, in addition to a temperature sensor and the like.

The data acquisition unit 301 includes operation data of the plant 100 (at least one of a physical parameter related to the specifications of the plant 100 or a fuel parameter related to the property of the fuel and a process value of the plant 100) and a combustion region of the plant 100. And image data. The data acquisition unit 301 acquires image data from the image sensor SR1 of the plant 100 and stores it in the image database DB1. Further, the data acquisition unit 301 acquires operation data from the physical sensor SR2 and stores it in the operation database DB2.

The image database DB1 stores the image data of the fuel region in the plant 100 acquired by the data acquisition unit 301. The operation database DB2 stores the operation data of the plant 100 acquired by the data acquisition unit 301.

The data extraction/conversion unit 302 reads (extracts) data required for model creation and operation control from the image database DB1 and the operation database DB2, and performs complement or format conversion as necessary. Further, an example of the conversion here is a process of estimating and identifying operation data that cannot be directly measured by the image sensor SR1 or the physical sensor SR2 from other data and the like. Since the estimation process is executed by software using a computer, a value estimated is called a soft sensor value. Further, the data extraction conversion unit 302 reads the image data stored in the image database DB1 and extracts the feature amount of the image data.

The plant specification database DB3 stores physical parameters related to the specifications of the plant 100. Specific examples of physical parameters in the plant specification database DB3 will be described later with reference to FIG. The fuel property database DB4 stores fuel parameters related to the properties of the fuel used in the boiler plant 100. Specific examples of fuel parameters in the fuel property database DB4 will be described later with reference to FIG.

The model creation unit 303 (model creation device) is configured to create a model using at least one of a physical parameter and a fuel parameter and a feature amount of image data as input parameters. In the illustrated form, the model creating unit 303 uses the operation data and image data from the data extracting and converting unit 302, the plant specification data from the plant specification database DB3, and the fuel property data from the fuel property database DB4, It is configured to create a model showing the relationship between the input parameters of the plant 100 and the process values. The created model is stored and stored in the model database DB5.

The simulation unit 304 calculates the virtual process value using the feature amount of the operation data and the image data output from the data extraction conversion unit 302 and the model output from the model database DB5, and outputs the calculation result to the optimization unit 305. To do.

The optimization unit 305 is configured to calculate an optimum set of input parameters so that the process value satisfies a predetermined condition. The optimization unit 305 determines whether or not the virtual process value is optimum (whether or not the virtual process value satisfies a predetermined condition), and outputs the virtual process value to the operation instructing unit 306 when it is determined to be optimum, If it is determined that it is not, the set of input parameters as the simulation condition is reset and output to the simulation unit 304 to perform the simulation again. The driving instruction unit 306 calculates a driving instruction value based on the set of input parameters determined to be optimum, and outputs the driving instruction value to the driving control unit 201 (details are described in the driving instruction step).

The input/output unit 307 displays a model creation result and a verification result, a simulation evaluation result, and a driving instruction proposal screen, and accepts an operator's instruction for each. If additional information is input to the plant specification database DB3 or the fuel property database DB4, the input result is output to each.

In some embodiments, as shown in FIG. 4 A, it may constitute a driving control device 200 including a driving support device 300 and the operation control unit 201.
In this case, the operation control unit 201 controls the operation (opening degree of the valve, etc.) of each operation end OP of the boiler plant 100 based on the operation instruction value output from the operation instruction unit 306 of the operation support device 300. The operation control may be automatically performed based on the operation instruction value or may be performed after the operator's approval at the input/output unit 307. Further, the operation control unit 201 adds the operation instruction value from the operation support apparatus 300 as a bias value to the operation instruction value from the boiler plant control device (not shown), and gives the final operation instruction value. You may.

FIG. 5 is a schematic diagram showing the relationship between model inputs and outputs. As input parameters of the model, in addition to the parameters for the operating end OP, at least one of physical parameters or fuel parameters (both physical parameters and fuel parameters in the illustrated form), and feature amount parameters related to the feature amount of image data are included. And are included. The parameter for the operating end OP is a parameter indicating an instruction value (a valve opening degree, etc.) to the operating end OP. A model is created for each process value. The process value (virtual process value) as the output calculated by the simulation using the model includes, for example, unburned ash content, NOx value, CO value and the like.

Since the amount of exhaust gas components or exhausts generated in the plant 100 is greatly influenced by the combustion state in the combustion region of the plant, the amount of exhaust gas components or exhausts generated has a high affinity with image data in the combustion region. Therefore, the process value is obtained by creating a model using the feature amount extracted from the image data of the image of the inside of the furnace, using the index related to the exhaust gas component of the plant 100 or the index related to the plant emission as the process value. Can be accurately estimated.

Further, it is desirable that the above model is created in consideration of a time lag until the exhaust gas or emission generated in the combustion state indicated by the past image information reaches the measurement point of the state quantity. Such a time lag may vary depending on the type of furnace and the position of the measurement point, and it is necessary to create an estimation model with high estimation accuracy by creating a model considering the time lag between image data and process values. You can

FIG. 6 is an example of a data format in the model database DB5.
The horizontal axis is divided into functions, input parameters, and model details for each plant. The function describes the method of modeling. Examples of modeling methods include, but are not limited to, stepwise method, random forest, k-nearest neighbor method (KNN), and neural network method. Each item of the model formula shown below is described in the model details. Alternatively, a reference destination of another database in which each item is described may be described.
F=f(x,ω,λ,n) (A)
Here, f is a modeling method (function), x is an input parameter, ω is weighting, λ is an intercept, and n is the number of input parameters.

The vertical axis is divided by the model creation unit. When creating a model for each process value, the process values to be modeled are listed.

FIG. 7 is an example of a data format in the plant specification database DB3. The horizontal axis is divided by plant name.
The vertical axis is divided into items that represent plant specifications. Here, the structural specification and the performance specification are distinguished. Structural specifications are dimensions, and furnace dimensions are exemplified. The performance specification is a value indicating the performance of the plant, and examples thereof include exhaust gas temperature and steam temperature. As the structural specifications and performance indexes, not only the representative value of the measurement result but also the value of the design condition may be described.

FIG. 8 is an example of a data format in the fuel property database DB4. The horizontal axis is divided by fuel. The vertical axis is divided into items that represent fuel properties. The fuel property includes information about the fuel such as the fuel component (carbon or water) and the fineness after pulverization, and is exemplified by industrial analysis (fuel ratio etc.) and elemental analysis (carbon amount etc.). Here, the fuel ratio is the ratio of fixed carbon to volatile matter.

FIG. 9 is an example of a data format in the additional parameter candidate database DB6.
The horizontal axis is classified according to the data acquisition method and applicable conditions. The data acquisition method may be a method of acquiring as a measurement value by measurement with the physical sensor SR2, or a method of acquiring as a calculation value (soft sensor value) calculated by combining a plurality of measurement values. Good. If there is no measured value of an appropriate parameter indicating the plant specification, the calculated value may be substituted.

The vertical axis is divided into physical parameters and fuel parameters. The physical parameters include those obtained from boiler specifications such as structural dimensions, and those obtained from measured or calculated values such as gas temperature and steam temperature. The latter may be set by referring to design values from boiler specifications.

The fuel parameters are the motor current value of the crusher table for coal crushing, the pressure acting on the rollers and the differential pressure of fluid (gas, powder), etc., and the fuel consumption (call flow), heat transfer for coal combustion. The amount of heat absorbed by the surface, the boiler output, and the like, the environmental load such as the SO ₂ value in the exhaust gas, and the moisture such as the inlet air temperature of the crusher.

Regarding the operation data regarding the crusher, it is preferable to create a model by using the operation data of two or more crushers as input parameters. In this case, when the virtual process value is calculated, the operation data of one crusher is used as a representative, and when the crusher stops, the operation data of another crusher is switched to. This is because even if one crusher is stopped due to maintenance or the like, operation support can be continued by using the operation data of another crusher. The crusher may be selected according to the operating rate and the burner position for supplying pulverized coal. In particular, it is preferable to select from a crusher that supplies pulverized coal to the burner in the middle stage as much as possible. This is because the average behavior in the boiler can be reflected.

FIG. 10 is a diagram showing an example of the overall configuration of a driving support system 500 that supports model creation.
The driving support system 500 can communicate with a plurality of local support systems 300A, 300B, 300C provided for each of the plurality of boiler plants 100A, 100B, 100C, and local support systems 300A, 300B, 300C via a network N, for example. It comprises a remote support system 400. The boiler plants 100A, 100B, 100C are connected to local support systems 300A, 300B, 300C, respectively. Each of the local support systems 300A, 300B, and 300C is connected to the remote support system via the network N.

FIG. 11 is a diagram showing a detailed configuration example of the driving support system 500, and shows the configuration of the local support system 300A as a representative configuration example. The local support systems 300B and 300C also have the same configuration as the local support system 300A.

The local support system 300A includes a driving support device 300 and a first transmission/reception unit 308. The driving control device 200 may be adopted instead of the driving support device 300. The remote support system 400 includes a second transmission/reception unit 401 and a common model database DB7.

The first transmission/reception unit 308 is configured to transmit the operation data of the plant 100, the image data, and the update result of the model to the second transmission/reception unit 401 at regular intervals or according to an instruction from the second transmission/reception unit 401. The first transmission/reception unit 308 is also configured to receive the operation data, the image data, and the model update result of the plant 100 in the other local support systems 300B and 300C transmitted from the second transmission/reception unit 401.

The second transmission/reception unit 401 is configured to receive the operation data, the image data, and the model update result transmitted from each of the local support systems 300A, 300B, and 300C. When a new update result is received, the update result of the operation data, the image data, and the model is configured to be transmitted to the first transmitting/receiving unit 308 of all other local support systems 300A, 300B, 300C at any time or at regular intervals. ing.

When the first transmission/reception unit 308 receives new operation data and a model update result, it transmits the operation data update result to the operation database DB2 and the model update result to the model database DB5, respectively.

With this configuration, it is possible to share the operation data, the image data, and the model update results in the other local support systems 300A, 300B, and 300C .

The present invention is not limited to the above-described embodiment, and includes a modified form of the above-described embodiment and a combination of these forms as appropriate.

2 Boiler 11 Furnace 12 Combustor 13 Flue 21,22,23,24,25 Combustion burner 26,27,28,29,30 Pulverized coal supply pipe 31,32,33,34,35 Crusher 36 Wind box 37a, 37b, 37c, 37e, 37f, 37g Air duct 37d Connection point 38 Blower 38a Pushing blower 38b Primary air blower 39 After air ports 41, 42, 43, 44, 45, 46, 47 Heat exchanger 48 Exhaust gas passage 49 Air heater 50 Denitration Device 51 Soot and dust treatment device 52 Induction blower 53 Chimney 62 Inclined surface 70 Furnace bottom evaporation pipe 72 CPU
74 RAM
76 ROM
78 HDD
80 Input I/F
82 Output I/F
84 Bus 100 Boiler plant 200 Operation control device 201 Operation control unit 300 Operation support device 300A, 300B, 300C Local support system 301 Data acquisition unit 302 Data extraction conversion unit 303 Model creation unit 304 Simulation unit 305 Optimization unit 306 Operation instruction unit 307 Input/output unit 308 First transmission/reception unit 400 Remote support system 401 Second transmission/reception unit 500 Operation support system DB1 Image database DB2 Operation database DB3 Plant specification database DB4 Fuel property database DB5 Model database DB6 Additional parameter candidate database DB7 Common model database N network OP Control end SR1 Image sensor SR2 Physical sensor

Claims (10)

A model creating method for creating a model showing a relationship between an input parameter of a boiler burning fuel and a process value including an unburned ash content generated by combustion of the fuel ,
A reading step of reading operation data of the boiler including at least one of physical parameters related to specifications of the boiler or fuel parameters related to properties of the fuel, and image data of a combustion region of the boiler ,
An extraction step of extracting a feature amount of the image data,
A model creating step of creating the model using the at least one of the physical parameter or the fuel parameter and the feature amount of the image data as the input parameter,
A method for creating a model, comprising: The model creating method according to claim 1, wherein the image data is acquired by capturing an image of the combustion region from above by an imaging device capable of capturing at least one of a moving image and a still image. 3. In the extracting step, information relating to any of the shape, size, color, density, brightness, temperature, wavelength of the combustion region or the amount of change thereof is extracted as the characteristic amount of the image data. Model creation method described in. In the model creating step, creating the model metrics relating to emissions of indicator or the boiler according to the exhaust gas components of the boiler as the process value, modeling according to any one of claims 1 to 3 Method. In the reading step, a parameter relating to at least one of the structure, performance or design condition of the boiler is read as the physical parameter,
The model creating step creates the model using the at least one of the structure, performance, or design condition of the boiler and the feature amount of the image data as the input parameter. Described model creation method. In the reading step, a parameter relating to at least one of fuel adjustment, combustion, environmental load or moisture is read as the fuel parameter,
6. The model creating step creates the model using as parameters the parameters relating to at least one of fuel adjustment, combustion, environmental load, and water and the feature amount of the image data as the input parameters. The method of creating a model according to item 1. A boiler operation support method using a model showing a relationship between an input parameter of a boiler burning fuel and a process value including unburned ash in unburned matter generated by combustion of the fuel ,
A data reading step of reading operation data of the boiler including at least one of physical parameters related to specifications of the boiler or fuel parameters related to properties of the fuel, and image data of a combustion region of the boiler ,
An extraction step of extracting a feature amount of the image data,
A model reading step of reading the model with the at least one of the physical parameter or the fuel parameter and the feature amount of the image data as the input parameter;
A simulation step of calculating the operating data of the boiler, and the image data of the combustion zone of the boiler, the process values using said model,
The boiler driving support method further comprising a driving instruction step of calculating a driving instruction value of the boiler so that the process value satisfies a predetermined condition. A model creating apparatus for creating a model showing a relationship between an input parameter of a boiler burning fuel and a process value including unburned ash in unburned matter generated by combustion of the fuel ,
Data acquisition configured to acquire operation data of the boiler including at least one of physical parameters related to specifications of the boiler or fuel parameters related to properties of the fuel, and image data of a combustion region of the boiler. Department,
A data extraction conversion unit configured to extract a feature amount of the image data acquired by the data acquisition unit;
At least one of the physical parameter or the fuel parameter, and the model amount configured to create the model using the feature amount of the image data as the input parameter,
A model creating device including. A boiler operation support device using a model showing a relationship between an input parameter of a boiler that burns fuel and a process value that includes unburned ash in unburned matter generated by burning of the fuel ,
Data acquisition configured to acquire operation data of the boiler including at least one of physical parameters related to specifications of the boiler or fuel parameters related to properties of the fuel, and image data of a combustion region of the boiler. Department,
A data extraction conversion unit configured to extract a feature amount of the image data acquired by the data acquisition unit;
At least one of the physical parameter or the fuel parameter, and a model database that stores the model having the feature amount of the image data as the input parameter,
And operating data of the boiler, and the image data of the combustion zone of the boiler, and a simulation unit for calculating the process values using said model stored in the model database,
An optimization unit configured to obtain an optimum set of input parameters so that the process value satisfies a predetermined condition,
An operation instruction unit that calculates an operation instruction value of the boiler from the set of the optimum input parameters obtained by the optimization unit,
Boiler driving support device. A plurality of local support systems including the boiler driving support device according to claim 9;
A boiler operation support system comprising the local support system and a remote support system capable of communicating via a network,
The local support system is
The driving data, the image data, and the image data in the other local assistance system, which are configured to send the driving data, the image data, and the update result of the model to the remote assistance system, and which are transmitted from the remote assistance system. A first transceiver configured to receive model update results,
The remote support system is
The operation data, the image data, and the update result of the model transmitted from each of the local assistance systems are received, and the update result is transmitted to all other local assistance systems. A boiler driving assistance system including a second transceiver configured to transmit as image data and a result of updating the model.

Images