JP5819251B2 - Operation control system for circulating fluidized bed boiler. - Google Patents

Description

  The present invention relates to an operation control system for a circulating fluidized bed boiler.

  Conventionally, a steam pressure control device for a circulating fluidized bed boiler described in Patent Document 1 below is known. In this control device, the steam pressure of the circulating fluidized bed boiler is detected, and the deviation of the steam pressure from a predetermined target pressure is calculated. Then, the steam pressure is maintained at the target pressure by adjusting the fuel supply amount to the furnace based on the deviation value.

Japanese Patent Laid-Open No. 4-6304

  The circulating fluidized bed boiler has a plurality of index items that are indicators of the operating state. And the input value with respect to the setting item relevant to each index item is adjusted so that these several index items may be maintained at a predetermined target value.

  However, the index item of the circulating fluidized bed boiler and the setting item related to the index item are intricately related to each other. For this reason, for example, when a plurality of control devices that maintain one index item at a predetermined target value are combined, the index item to be controlled can be controlled, but another index item cannot be appropriately controlled. There is a case. In the control of this type of circulating fluidized bed boiler, it is desired to perform control to optimize a plurality of setting items so as to simultaneously achieve target values of a plurality of index items.

  Accordingly, an object of the present invention is to provide an operation control system for a circulating fluidized bed boiler capable of performing control for optimizing a plurality of index items of the circulating fluidized bed boiler by a plurality of setting items.

  The operation control system of the present invention is an operation control system for a circulating fluidized bed boiler, and each of input values of a plurality of setting items related to the operation of the circulating fluidized bed boiler, and a plurality of indicators indicating the operating state of the circulating fluidized bed boiler. A boiler control unit that operates the circulating fluidized bed boiler with an operation amount determined based on a comparison with the actual measurement value of each item, and a part of the plurality of setting items and a selected selection setting item Functions of an adjustment value calculation unit that calculates an adjustment value for adjusting the input value of the input, an external input value that is a value input from the outside of the selection setting item, and an adjustment value obtained by the adjustment value calculation unit An input value adjustment unit that passes the adjustment input value to the boiler adjustment unit as an input value of the selected setting item, and the adjustment value calculation unit sets the measured value of each index item to the parent node. Each of the index items is a child To calculate the estimated setting value of each setting item, and input each target value of the index item to the Bayesian network to achieve the target value of the index item. Each target setting value indicating the setting value is calculated, and the selection setting item is selected based on the magnitude of the difference between the estimated setting value and the target setting value, and the target setting value of the selection setting item is The adjustment value of the selection setting item is used.

  According to this operation control system, basically, on the basis of the external input value of the setting item input from the outside, the boiler adjustment unit performs the actual measurement value and the external input value of the index item indicating the operation state of the circulating fluidized bed boiler. The operation amount is determined based on the comparison with the circulating fluidized bed boiler. Here, as the means for adjusting the external input value, the operation control system includes an adjustment value calculation unit and an input adjustment unit. The adjustment value calculation unit calculates a target setting value for achieving the target value by the Bayesian network from the target value of the index item to be the target. Further, an estimated setting value corresponding to the actual measurement value is calculated from the actual measurement value indicating the reality of the index item by the Bayesian network. Then, some setting items are selected from the setting items based on the magnitude of the difference between the estimated setting value and the target setting value, and the target setting value is selected as the adjustment value for the selected selection setting item. And

  The input value adjustment unit sets an adjustment input value including the influence of the adjustment value to the external input value as an input value to the boiler adjustment unit. Here, according to the calculation using the Bayesian network, it is possible to optimize the set values (target set values) for achieving the target values of the plurality of index items in combination. Since the target set value optimized in this way is used as an adjustment value, and the external input value is adjusted based on the adjustment value, control for optimizing a plurality of index items of the circulating fluidized bed boiler using a plurality of setting items is possible. It becomes possible.

  The operation control system of the present invention is an operation control system for a circulating fluidized bed boiler, and each of input values of a plurality of setting items related to the operation of the circulating fluidized bed boiler, and a plurality of indicators indicating the operating state of the circulating fluidized bed boiler. A boiler control unit that operates the circulating fluidized bed boiler with an operation amount determined based on a comparison with the actual measurement value of each item, and a part of the plurality of setting items and a selected selection setting item An appropriate setting value calculation unit that calculates an appropriate setting value indicating an appropriate setting value, an external input value that is a value input from the outside of the selected setting item, and an appropriate setting value obtained by the appropriate setting value calculation unit When there is a setting item whose difference exceeds a predetermined threshold, a warning processing unit that issues a warning is provided, and the appropriate setting value calculation unit calculates the measured value of each of the index items as the setting item. Each index item is a parent node To enter each Bayesian network with each as a child node, calculate the estimated setting value of each setting item, and input each target value of the index item to the Bayesian network to achieve the target value of the index item Each target setting value indicating the setting value of the setting item is calculated, and the selection setting item is selected based on the magnitude of the difference between the estimated setting value and the target setting value. The setting value is an appropriate setting value for the selected setting item.

  According to this operation control system, basically, on the basis of the external input value of the setting item input from the outside, the boiler adjustment unit performs the actual measurement value and the external input value of the index item indicating the operation state of the circulating fluidized bed boiler. The operation amount is determined based on the comparison with the circulating fluidized bed boiler. Here, as a means for issuing a warning when the external input value is not appropriate, the operation control system includes a proper set value calculation unit and a warning processing unit. The appropriate set value calculation unit calculates a target set value for achieving the target value from the target value of the index item to be set by the Bayesian network. Further, an estimated set value corresponding to the actual measurement value is calculated from the actual actual measurement value of the index item by the Bayesian network. Then, some setting items are selected from the setting items based on the magnitude of the difference between the estimated setting value and the target setting value, and the target setting value is appropriately set for the selected selection setting item. Value.

  The warning processing unit compares the external input value with the appropriate set value, and issues a warning when the difference is large. Here, according to the calculation using the Bayesian network, it is possible to optimize the set values (target set values) for achieving the target values of the plurality of index items in combination. Since the target set value optimized in this way is set as a proper set value, and the proper set value is used as a comparison target, the suitability of the external input value is determined and a warning is issued. It is possible to obtain highly accurate information about suitability. As a result, optimal values can be set for a plurality of setting items, and control for optimizing the plurality of index items of the circulating fluidized bed boiler is possible.

  According to the present invention, it is possible to provide an operation control system for a circulating fluidized bed boiler capable of performing control for optimizing a plurality of index items of the circulating fluidized bed boiler by a plurality of setting items.

It is a figure which shows the structure of the CFB boiler which the operation control system which concerns on embodiment of this invention makes object. 1 is a block diagram illustrating an operation control system according to a first embodiment of the present invention. It is a figure which shows an example of the model of a Bayesian network. FIG. 3 is a block diagram illustrating an example of a hardware configuration of the computer apparatus of FIG. 2. It is a flowchart which shows the process by the operation control system of FIG. It is a block diagram which shows the operation control system which concerns on 2nd Embodiment of this invention. It is a flowchart which shows the process by the operation control system of FIG.

  Hereinafter, embodiments of an operation control system of the present invention will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same elements are denoted by the same reference numerals, and redundant description is omitted.

(First embodiment)
With reference to FIG. 1, the boiler which the operation control system of this embodiment makes object is demonstrated first. The boiler 2 is a circulating fluidized bed boiler of the external circulation type (Circulating Fluidized Bed type). The boiler 2 includes a fluidized bed furnace 3 having a vertically long cylindrical shape. A middle portion of the furnace 3 is provided with a fuel inlet 3a for introducing fuel and a gas outlet 3b for discharging combustion gas at the upper portion. The fuel supplied to the furnace 3 from the fuel input device 5 is input into the furnace 3 through the fuel input port 3a.

  A cyclone 7 that functions as a solid-gas separator is connected to the gas outlet 3 b of the furnace 3. The discharge port 7a of the cyclone 7 is connected to a downstream gas processing system via a gas line. A return line 9 called a downcomer extends downward from the bottom outlet of the cyclone 7, and the lower end of the return line 9 is connected to the intermediate side surface of the furnace 3.

  In the furnace 3, the combustion / flowing air introduced from the lower air supply line 3 c causes the solid matter including the fuel input from the fuel input port 3 a to flow, and the fuel flows to about 800 to 900 ° C. while flowing. Burn with. A combustion gas generated in the furnace 3 is introduced into the cyclone 7 with accompanying solid particles. The cyclone 7 separates solid particles and gas by a centrifugal separation action, returns the solid particles separated via the return line 9 to the furnace 3, and removes the combustion gas from which the solid particles have been removed from the discharge port 7 a to the gas line. To the subsequent gas processing system.

  In this furnace 3, a solid material called “in-furnace bed material” is generated and collected at the bottom, and the bed material is sintered and melted and solidified by the concentration of impurities (low melting point materials, etc.) in the in-furnace bed material, or It is necessary to suppress malfunctions caused by incombustible impurities. For this reason, in the furnace 3, the in-furnace bed material is discharged | emitted regularly outside from the discharge port 3d of the bottom part. The discharged bed material is put into the furnace 3 again after removing unsuitable materials such as metal on a circulation line (not shown).

  The gas treatment system includes a gas heat exchange device 13 connected to the discharge port 7a of the cyclone 7 via a gas line, and a bag filter connected to the discharge port 13a of the gas heat exchange device 13 via a gas line. (Dust collector) 15. The gas heat exchanger 13 is provided with a boiler tube 13b that allows water to flow across the exhaust gas flow path. When the high-temperature exhaust gas sent from the cyclone 7 comes into contact with the boiler tube 13b, the heat of the exhaust gas is recovered in the water in the tube, and the generated high-temperature steam is sent to the turbine for power generation through the boiler tube 13b. The bag filter 15 removes fine particles such as fly ash that are still accompanying the combustible gas. The clean gas discharged from the discharge port 15a of the bag filter 15 is discharged from the chimney 19 via the gas line and the pump 17 to the outside.

  Next, an operation control system 21 that performs operation control of the circulating fluidized bed boiler 2 will be described with reference to FIG.

  The operation control system 21 illustrated in FIG. 2 includes a controller 23 and a computer device 25. The controller 23 includes a boiler controller (boiler control unit) 27 and the like that operate the boiler 2 and is a part that performs actual operation of the boiler.

  The controller 23 includes a plurality of sensors 29 a installed in each part of the boiler 2, a setting item input unit 31, an adjustment input value calculation unit 33, and a boiler controller 27. The sensor 29a includes, for example, a temperature sensor that measures the temperature of a predetermined part of the boiler 2, a flow sensor that measures the flow rate of exhaust gas or water, a concentration sensor that measures the concentration of a predetermined substance in the exhaust gas, and the like. Hereinafter, these many sensors 29a are collectively referred to as a sensor group 29. The measured value PV obtained by the sensor group 29 is sent to the boiler controller 27 and the computer device 25.

  The setting item input unit 31 is a part that receives input of each setting item for boiler operation. The boiler operation worker inputs a desired input value for each setting item through the setting item input unit 31. The setting items include, for example, the number of times the blower is operated, the air flow rate, the number of times the air release valve is released, the water injection amount, the valve opening, the coal supply amount (the supply amount of coal supplied to the furnace 3), the sand supply amount, Blow flow rate etc. are included. Hereinafter, the input value of the setting item input by the operator using the setting item input unit 31 is referred to as “worker input value SV1”.

  The adjustment input value calculation unit 33 calculates the adjustment input value SV3 by adding the worker input value (external input value) SV1 and a value passed from the difference calculation unit 47 described later. The calculated adjustment input value SV3 is sent to the boiler controller 27. The boiler controller 27 determines the operation amount MV based on the difference between the adjustment input value SV3 and the measurement value PV from the sensor group 29, and operates the boiler 2. That is, for example, the boiler controller 27 reduces the difference between the operating state (measured value of the sensor group 29) to be obtained from the adjusted input value SV3 and the measured value PV actually obtained from the sensor group 29. The operation amount MV of the operation applied to the boiler 2 is calculated and the operation is executed. Thereby, feedback control of the boiler 2 is performed.

  The computer device 25 includes a target value input unit 37, a Bayesian network inference unit (adjustment value calculation unit) 39, and a difference calculation unit 47.

  The target value input unit 37 is a part that receives input of target values from an operator for a plurality of index items that are indicators of the operating state of the boiler 2. The index items include, for example, pressure deviation, calorie, boiler efficiency, or environmentally hazardous substance discharge concentrations such as CO and NOX. The values of these index items can be derived from the measured values PV obtained by the sensor group 29. In the target value input unit 37, for example, a target value A1 of each index item indicating an ideal driving state to be set as a target is input by an operator.

  The Bayesian network inference unit 39 includes a target setting value calculation unit 41, an estimated setting value calculation unit 43, and an adjustment value derivation unit 45. The Bayesian network inference unit 39 holds a Bayesian network model in which each of the setting items is a parent node and each of the index items is a child node, and performs various operations using the Bayesian network. . Such a Bayesian network model is created in advance based on past operation data of the boiler 2 and stored in advance in the Bayesian network inference unit 39. An example of such a Bayesian network BN is shown in FIG. The Bayesian network BN of FIG. 3 sets the setting items of the boiler 2 such as the number of blower operations, the air flow rate, the air release valve, the water injection amount, the valve opening, the coal supply amount, the sand supply amount, and the blow flow rate. The pressure deviation, the amount of heat, the exhaust gas CO concentration, and the boiler efficiency, which are index items of the boiler 2, are defined as the child node N2.

  The target set value calculation unit 41 inputs each target value A1 of the index item input by the target value input unit 37 as a result variable of the Bayesian network BN (see FIG. 3). Then, each set target value A2 indicating the value of the setting item for achieving the target value A1 is output as a cause variable of the Bayesian network BN. This target set value A2 means, for example, a value of a setting item necessary to achieve an ideal operation state of the target boiler 2. For example, when the Bayesian network BN illustrated in FIG. 3 is used, an ideal pressure deviation, heat quantity, exhaust gas CO concentration, and boiler efficiency to be targeted are input as target values A1 to achieve these target values A1. The blower operation frequency, air flow rate, air release valve, water injection amount, valve opening, coal supply amount, sand supply amount, and blow flow rate are output as the target set value A2. However, these input / output values are assumed to be discrete values due to restrictions on the processing capability of the computer.

  The estimated set value calculation unit 43 calculates an actual measurement value of an index item indicating the current operation state of the boiler 2 from the measurement value PV obtained from the sensor group 29, and uses the actual measurement value as a Bayesian network BN (see FIG. 3). ) As a result variable. Then, the estimated set value A3 is output as a cause variable of the Bayesian network BN. This estimated set value A3 means the value of the set item estimated from the current operation state of the boiler 2. The calculation method of inputting the result variable to the child node of the Bayesian network and outputting the cause variable of the parent node is well known, and thus detailed description thereof is omitted.

  The adjustment value deriving unit 45 selects a setting item having a large difference between the estimated setting value A3 and the target setting value A2. The setting item selected here is referred to as “selected setting item”. For example, an item having a difference between the estimated setting value A3 and the target setting value A2 that is greater than a predetermined threshold may be selected as a selection setting item. Further, when the estimated setting value A3 and the target setting value A2 are arranged in the descending order, a predetermined number of setting items may be selected from the ones with higher ranks as selection setting items. Then, the adjustment value deriving unit 45 employs the target setting value A2 of the selection setting item as the adjustment value SV2 of the selection setting item.

The difference calculation unit 47 calculates a difference between the adjustment value SV2 input from the adjustment value deriving unit 45 and the worker input value SV1 input from the setting item input unit 31, and further calculates a weight α (for example, α is 0). (Value of ≦ α ≦ 1) and the result is sent to the adjustment input value calculation unit 33. As described above, the adjustment input value calculation unit 33 calculates the adjustment input value SV3 by adding the worker input value SV1 and the value of α (SV2−SV1) passed from the difference calculation unit 47. That is, the adjustment input value SV3 is
SV3 = SV1 + α (SV2-SV1)
It is represented by Thus, the input value adjustment unit 51 is configured by combining the difference calculation unit 47 and the adjustment input value calculation unit 33. That is, the input value adjustment unit 51 has a function of passing the adjustment input value SV3, which is a function of the worker input value SV1 and the adjustment value SV2, to the boiler controller 27. The value of the weight α is set in advance and stored in a storage area of the computer device 25, for example.

  Note that the adjustment by the input value adjustment unit 51 is not executed for setting items (non-selection setting items) that are not selected as selection setting items by the adjustment value deriving unit 45. Therefore, for the non-selection setting item, the operator input value SV1 is input to the boiler controller 27 as it is.

  A computer 100 shown in FIG. 4 is an example of hardware constituting the computer device 25 of the present embodiment. The computer 100 includes a CPU and various data processing devices such as a server device that performs processing and control by software and a personal computer. The computer 100 includes a CPU 101, a RAM 102 and a ROM 103 which are main storage devices, an input device 104 such as a keyboard and a mouse which are input devices, an output device 106 such as a display, a communication module 107 which is a data transmission / reception device such as a network card, a hard disk, etc. The auxiliary storage device 108 is configured as a computer system.

  Each functional component of the computer device 25 as shown in FIG. 2 is an input device under the control of the CPU 101 by loading predetermined computer software on the hardware such as the CPU 101 and the RAM 102 shown in FIG. 104, the output device 106, and the communication module 107 are operated, and data is read and written in the RAM 102 and the auxiliary storage device 108. Note that the boiler controller 27, the adjustment input value calculation unit 33, and the setting item input unit 31 included in the controller 23 (FIG. 2) are also realized by software by operating hardware such as the computer 100 according to a program. Also good.

  Next, processing performed by the operation control system 21 will be described with reference to FIG. First, the target value A1 by the operator is input from the target value input unit 37, and the weighting coefficient α used by the difference calculation unit 47 is input and set in advance (S101). Next, the Bayesian network inference unit 39 acquires the measurement value PV from the sensor group 29, and the difference calculation unit 47 acquires the operator input value SV1 from the setting item input unit 31 (S103). Next, the Bayesian network inference unit 39 calculates the adjustment value SV2 based on the target value A1 and the measured value PV (S105). Then, the difference calculation unit 47 and the adjustment input value calculation unit 33 calculate the adjustment input value SV3 and send it to the boiler controller 27 (S107). In the boiler controller 27, the adjustment input value SV3 is set as a new set value, and feedback control based on the measured value PV from the sensor group 29 is performed (S109). Thereafter, the processes of S103 to S109 are repeated until a predetermined end condition is satisfied (S111).

  The effect by the operation control system 21 demonstrated above is demonstrated.

  According to this operation control system 1, basically, the boiler controller 27 is an index item indicating the operation state of the boiler 2 based on the worker input value SV <b> 1 of the setting item input from the outside (worker). The operation amount MV is determined based on the comparison between the actually measured value and the external input value SV, and the boiler 2 is operated. Here, the operation control system 1 includes a Bayesian network reasoning unit (adjustment value calculation unit) 39 and an input value adjustment unit 51 as means for adjusting the worker input value SV1. The Bayesian network inference unit 39 calculates a target set value A2 for achieving the target value A1 by Bayesian network calculation from the target value A1 of the index item to be targeted. Further, an estimated set value A3 corresponding to the actual measurement value is calculated from the actual actual measurement value (derived from the measurement value PV) of the index item by Bayesian network calculation. Then, some setting items are selected from the setting items based on the magnitude of the difference between the estimated setting value A3 and the target setting value A2, and the target setting value A2 is selected for the selected selection setting item. The adjustment value is SV2.

  The input value adjustment unit 51 sets an adjustment input value SV3 including the influence of the adjustment value SV2 to the worker input value SV1 as an input value to the boiler controller 27. Here, according to the calculation using the Bayesian network, it is possible to optimize the set value (versus target set value A2) for achieving the target value A1 of the plurality of index items in combination. Since the target set value A2 optimized in this way is set as the adjustment value SV2, and the operator input value SV1 is adjusted by the adjustment value SV2, as a result, according to the operation control system 21, a plurality of setting items are set. Thus, it is possible to perform control for optimizing a plurality of index items of the boiler 2.

(Second Embodiment)
An operation control system 221 according to the second embodiment of the present invention will be described with reference to FIG. In addition, in the said operation control system 221, about the component same or equivalent to the operation control system 21 of 1st Embodiment, the same code | symbol is attached | subjected and the overlapping description is abbreviate | omitted.

  The controller 223 of the operation control system 221 does not include the adjustment input value calculation unit 33 (see FIG. 2), and the operator input value SV1 input from the operator by the setting item input unit 31 is directly input to the boiler controller 27. Entered.

  The computer device 225 of the operation control system 221 includes a difference determination unit (warning processing unit) 226 and a warning output unit (warning processing unit) 228 instead of the difference calculation unit 47 (see FIG. 2). The difference determination unit 226 receives the adjustment value SV2 of the selection setting item from the Bayesian network inference unit 39 and the operator input value SV1 of each setting item from the setting item input unit 31. Here, considering the meaning of the adjustment value SV2, it can be said that the adjustment value SV2 is a setting value of an appropriate selection setting item for achieving the target value A1. Therefore, hereinafter, the adjustment value SV2 output from the Bayesian network inference unit 39 is referred to as “appropriate setting value SV2”. In other words, the Bayesian network inference unit 39 has a function as an appropriate setting value calculation unit that calculates the appropriate setting value SV2 of the selection setting item for achieving the target value A1 of the index item.

  The difference determination unit 226 determines whether the difference between the appropriate setting value SV2 and the worker input value SV1 exceeds a predetermined threshold among the selection setting items, with respect to the warning output unit 228. Send an alert signal. The warning output unit 228 issues a warning to the worker according to the notification signal. Examples of the warning technique issued here include display of a warning screen on a display monitor included in the computer device 225, pronunciation of warning sound from a speaker, and the like.

  Next, processing performed by the operation control system 21 will be described with reference to FIG. First, the target value A1 by the operator is input and set from the target value input unit 37 (S201). Next, the Bayesian network inference unit 39 acquires the measurement value PV from the sensor group 29, and the difference determination unit 226 acquires the operator input value SV1 from the setting item input unit 31 (S103). Next, the Bayesian network inference unit 39 calculates an appropriate setting value SV2 based on the target value A1 and the measured value PV (S205).

  The difference determination unit 226 calculates a difference between the appropriate setting value SV2 and the worker input value SV1 (S207), and determines whether or not the difference value exceeds a predetermined threshold value (S209). If the determination of Yes is made in S209, the difference determination unit 226 sends an alarm signal, and the warning output unit 228 issues a warning to the worker (S211). When No is determined in S209, the alarm signal processing is not performed. Thereafter, the processes of S203 to S211 are repeated until a predetermined end condition is satisfied (S213).

  The effect by the operation control system 221 demonstrated above is demonstrated.

  According to this operation control system 21, basically, the boiler controller 27 is an index item indicating the operation state of the boiler 2 based on the worker input value SV <b> 1 of the setting item input from the outside (worker). The operation amount MV is determined based on the comparison between the actually measured value and the worker input value SV1, and the boiler 2 is operated. Here, as a means for issuing a warning when the worker input value SV1 is not appropriate, the operation control system 221 includes a Bayesian network inference unit (appropriate set value calculation unit) 39 and a warning processing unit. Yes. The Bayesian network inference unit 39 calculates a target setting value A2 for achieving the target value A1 by the Bayesian network from the target value A1 of the index item to be targeted. Further, an estimated set value A3 corresponding to the actual measurement value is calculated from the actual actual measurement value (derived from the measurement value PV) of the index item by the Bayesian network. Then, some setting items are selected from the setting items based on the difference between the estimated setting value A3 and the target setting value A2, and the target setting value is selected for the selected selection setting item. The appropriate setting value SV2.

  The warning processing unit compares the worker input value SV1 with the appropriate set value SV2, and issues a warning when the difference is large. Here, according to the calculation using the Bayesian network, it is possible to optimize the set value (versus target set value A2) for achieving the target value A1 of the plurality of index items in combination. Since the target set value A2 optimized in this way is set as the appropriate set value SV2, and the appropriate set value SV2 is used as a comparison target, whether the worker input value SV1 is appropriate is determined and a warning is issued. It is possible to obtain highly accurate information regarding the suitability of a plurality of setting items. As a result, optimal values can be set for a plurality of setting items, and control for optimizing the plurality of index items of the boiler 2 becomes possible.

  Although one embodiment of the present invention has been described above, the present invention is not limited to the above-described embodiment, and may be modified without changing the gist described in each claim.

DESCRIPTION OF SYMBOLS 2 ... Circulating fluidized bed boiler, 21,221 ... Operation control system, 27 ... Boiler controller (boiler control part), 39 ... Bayesian network reasoning part (setting value calculating part, appropriate setting value calculating part), 51 ... Input value adjustment 226 ... difference determination unit (warning processing unit), 228 ... warning output unit (warning processing unit), A1 ... target value, A2 ... target setting value, A3 ... estimated setting value, BN ... bayesian network, PV ... measurement Value, MV ... manipulated variable, SV1 ... worker input value (external input value), SV2 ... adjustment value, SV3 ... adjustment input value.

Claims (2)

An operation control system for a circulating fluidized bed boiler,
A manipulated variable determined based on a comparison between input values of a plurality of setting items related to the operation of the circulating fluidized bed boiler and measured values of a plurality of index items indicating the operating state of the circulating fluidized bed boiler. A boiler adjusting unit for operating the circulating fluidized bed boiler,
An adjustment value calculation unit that selects a part from the plurality of setting items and calculates an adjustment value for adjusting the input value of the selected selection setting item;
An adjustment input value that is a function of an external input value that is a value input from the outside of the selection setting item and the adjustment value obtained by the adjustment value calculation unit is used as the input value of the selection setting item. An input value adjusting unit to be passed to the boiler adjusting unit;
With
The adjustment value calculator is
The measured value of each of the index items is input to a Bayesian network in which each of the setting items is a parent node and each of the index items is a child node, and an estimated setting value of each of the setting items is calculated.
Each target value of the index item is input to the Bayesian network, and each target setting value indicating a setting value of the setting item for achieving the target value of the index item is calculated.
The selection setting item is selected based on the magnitude of the difference between the estimated setting value and the target setting value, and the target setting value of the selection setting item is used as the adjustment value of the selection setting item. An operation control system for a circulating fluidized bed boiler. An operation control system for a circulating fluidized bed boiler,
A manipulated variable determined based on a comparison between input values of a plurality of setting items related to the operation of the circulating fluidized bed boiler and measured values of a plurality of index items indicating the operating state of the circulating fluidized bed boiler. A boiler adjusting unit for operating the circulating fluidized bed boiler,
An appropriate setting value calculating unit that selects a part from the plurality of setting items and calculates an appropriate setting value indicating an appropriate setting value of the selected selection setting item;
The setting item exists such that a difference between an external input value that is a value input from the outside of the selection setting item and the appropriate setting value obtained by the appropriate setting value calculation unit exceeds a predetermined threshold. A warning processing unit that issues a warning,
With
The appropriate set value calculator is
The measured value of each of the index items is input to a Bayesian network in which each of the setting items is a parent node and each of the index items is a child node, and an estimated setting value of each of the setting items is calculated.
Each target value of the index item is input to the Bayesian network, and each target setting value indicating a setting value of the setting item for achieving the target value of the index item is calculated.
The selection setting item is selected based on the magnitude of the difference between the estimated setting value and the target setting value, and the target setting value of the selection setting item is selected as the appropriate setting value of the selection setting item. An operation control system for a circulating fluidized bed boiler.

Images