Control device for combustion furnace and control method for combustion furnace

Abstract

To provide a control device for a combustion furnace to properly control the amount of steam discharged from a boiler.SOLUTION: A control device 100 for a combustion furnace comprises: a process data acquisition unit 51 for acquiring process data for the combustion furnace; an operation state information acquisition unit 53 for acquiring operation state data for the combustion furnace; a storage unit 55 for storing the process data and the operation state data; a prediction steam amount calculation unit 57 which calculates a short-period variation predicted steam amount over a prescribed period as a predicted value of the amount of steam that will be discharged from the boiler in one hour on the basis of the process data and the operation state data in the storage unit 55, and calculates a long-period variation predicted steam amount over a long period longer than the prescribed period as a predicted value of the amount of steam that will be discharged from the boiler in two hours on the basis of the process data and the operation state data in the storage unit 55; a short-period control unit 59 which controls a short-period controlled amount on the basis of the short-period variation predicted steam amount; and a long-period control unit 61 which controls a long-period controlled amount on the basis of the long-period variation predicted steam amount.SELECTED DRAWING: Figure 2

Description

[Technical field]

[0001] The present invention relates to an incinerator control device that operates a boiler by utilizing heat from an incinerator that burns materials to be incinerated, and a method for controlling an incinerator. [Background technology]

[0002] Conventionally, power generation systems have been used in which heat generated when materials to be incinerated (e.g., garbage) are burned in an incinerator is used to generate steam in a boiler, and this steam is used to rotate a steam turbine generator to generate power. The amount of steam generated per unit time in the boiler (hereinafter also referred to as "steam flow rate") varies depending on the amount of materials to be incinerated supplied and the quality of the materials to be incinerated. In a power generation system, in order to suppress fluctuations in the amount of power generated, it is necessary to suppress fluctuations in the steam flow rate discharged from the boiler. For example, there is a technology described in Patent Document 1, the source of which is shown below, for suppressing such fluctuations in the steam flow rate discharged from a boiler.

[0003] Patent Document 1 describes a control device that controls the combustion of waste. This control device includes a steam flow rate prediction unit and a control unit. The steam flow rate prediction unit predicts the steam flow rate 60 seconds, 120 seconds, and 180 seconds later using multiple prediction models. The control unit controls combustion to promote combustion when the future predicted value of the steam flow rate falls below a preset lower threshold, and controls combustion to suppress combustion when the predicted value exceeds a preset upper threshold. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2023-59470 A Summary of the Invention [Problem to be solved by the invention]

[0005] In a boiler, the steam flow rate may deviate from the set value due to an excess or shortage of air supply to the combustion space. In addition, an excess or shortage of fuel (refuse in Patent Document 1) may also cause the steam flow rate to deviate from the set value. In a combustion furnace, the combustion state changes from moment to moment, so a control delay occurs and optimal control according to the combustion state cannot be performed, and there is a possibility that the steam flow rate may undershoot below the lower threshold or overshoot above the upper threshold.

[0006] Therefore, there is a demand for technology that can appropriately control the amount of steam discharged from a boiler. [Means for solving the problem]

[0007] The incinerator control device according to the present invention is characterized in that it is an incinerator control device that operates a boiler using heat from an incinerator that burns materials to be incinerated, and is equipped with a process data acquisition unit that acquires process data of the incinerator, an operating state information acquisition unit that acquires operating state data of the incinerator, a storage unit that sequentially stores the process data and the operating state data, a predicted steam amount calculation unit that calculates a short-term fluctuation predicted steam amount over a predetermined period based on the process data and the operating state data stored in the storage unit as a predicted value of the amount of steam discharged from the boiler after a predetermined first hour, and calculates a long-term fluctuation predicted steam amount over a period longer than the predetermined period based on the process data and the operating state data stored in the storage unit as a predicted value of the amount of steam discharged from the boiler after a predetermined second hour, a short-term control unit that controls a short-term control target amount based on the short-term fluctuation predicted steam amount, and a long-term control unit that controls a long-term control target amount based on the long-term fluctuation predicted steam amount.

[0008] With this characteristic configuration, it is possible to reduce fluctuations in the amount of steam by predicting the amount of steam after a predetermined time based on the process data and operation state data stored in the memory unit and performing control based on this prediction result. Furthermore, in this configuration, the short-term fluctuation predicted steam amount and the long-term fluctuation predicted steam amount are calculated separately, so that optimal control can be achieved depending on the cause of the deviation of the steam flow rate from the set value. Therefore, it is possible to appropriately control the steam flow rate discharged from the boiler.

[0009] It is also preferable that the short-term control target amount is the amount of air supplied to the incinerator, and the long-term control target amount is the amount of material to be incinerated supplied to the incinerator.

[0010] With this configuration, it is possible to control the amount of air (which can also be called the "air flow rate") supplied to the incinerator per unit time based on the short-term fluctuation predicted steam amount, and to control the amount of incinerated material (which can also be called the "material supply amount") supplied to the incinerator per unit time based on the long-term fluctuation predicted steam amount. As a result, optimal control can be achieved depending on the cause of deviation of the steam flow rate from the set value.

[0011] It is also preferable that the long-term control unit and the short-term control unit control the short-term control object quantity and the long-term control object quantity so that the fluctuation amount of the amount of steam discharged from the boiler is equal to or less than a predetermined fluctuation amount.

[0012] With this configuration, the amount of fluctuation in the amount of steam discharged from the boiler can be kept below a predetermined amount of fluctuation based on the amount of air supplied to the incinerator and the amount of material to be incinerated supplied to the incinerator, making it possible to appropriately control the amount of steam discharged from the boiler.

[0013] It is also preferable that the short-term control unit corrects the amount of air to be supplied to the incinerator, calculated in accordance with the actual measured value of the amount of steam discharged from the boiler and the set value of the amount of steam discharged from the boiler, based on the short-term fluctuation predicted steam amount, and the long-term control unit corrects the amount of material to be supplied to the incinerator, calculated in accordance with the actual measured value of the amount of steam discharged from the boiler and the set value of the amount of steam discharged from the boiler, based on the long-term fluctuation predicted steam amount.

[0014] With this configuration, the amount of fluctuation in the amount of steam discharged from the boiler can be controlled to a predetermined amount or less without control delay by correcting based on the short-term fluctuation predicted steam amount, compared to a case where the amount of air supplied to the incinerator is simply feedback-controlled according to the actual value of the amount of steam discharged from the boiler and the set value of the amount of steam discharged from the boiler. Also, the amount of fluctuation in the amount of steam discharged from the boiler can be controlled to a predetermined amount or less without control delay by correcting based on the long-term fluctuation predicted steam amount, compared to a case where the amount of incinerated material supplied to the incinerator is simply feedback-controlled according to the actual value of the amount of steam discharged from the boiler and the set value of the amount of steam discharged from the boiler.

[0015] In addition, it is preferable that when the short-term fluctuation predicted steam volume falls below a predetermined amount, the short-term control unit forcibly supplies the material to be incinerated to the incinerator regardless of the long-term fluctuation predicted steam volume.

[0016] With this configuration, it is possible to increase the amount of heat generated by the combustion of the materials to be incinerated and to increase the amount of steam discharged from the boiler, thereby avoiding a situation in which the amount of steam discharged from the boiler is insufficient.

[0017] The characteristic configuration of the incinerator control method according to the present invention is a method for controlling an incinerator that operates a boiler using heat from an incinerator that burns materials to be incinerated, and includes a process data acquisition step for acquiring process data of the incinerator, an operating state information acquisition step for acquiring operating state data of the incinerator, a storage step for sequentially storing the process data and the operating state data in a storage unit, a predicted steam amount calculation step for calculating a short-term fluctuation predicted steam amount over a predetermined period based on the process data and the operating state data stored in the storage unit as a predicted value of the amount of steam discharged from the boiler after a predetermined first hour, and a long-term fluctuation predicted steam amount over a period longer than the predetermined period based on the process data and the operating state data stored in the storage unit as a predicted value of the amount of steam discharged from the boiler after a predetermined second hour, a short-term control step for controlling a short-term control target amount based on the short-term fluctuation predicted steam amount, and a long-term control step for controlling a long-term control target amount based on the long-term fluctuation predicted steam amount.

[0018] With this characteristic configuration, it is possible to reduce fluctuations in the amount of steam by predicting the amount of steam after a predetermined time based on the process data and the operating state data and performing control based on this prediction result. Furthermore, in this method, the short-term fluctuation predicted steam amount and the long-term fluctuation predicted steam amount are calculated separately, so that optimal control can be achieved depending on the cause of deviation of the steam flow rate from the set value. Therefore, it is possible to appropriately control the amount of steam discharged from the boiler.

[0019] It is also preferable that the short-term control target amount is the amount of air supplied to the incinerator, and the long-term control target amount is the amount of material to be incinerated supplied to the incinerator.

[0020] With this configuration, it is possible to control the amount of air supplied to the incinerator based on the short-term fluctuation predicted steam amount, and to control the amount of materials to be incinerated supplied to the incinerator based on the long-term fluctuation predicted steam amount. As a result, optimal control can be achieved according to the cause of the deviation of the steam flow rate from the set value. [Brief description of the drawings]

[0021] [Figure 1] FIG. 1 is a diagram showing a configuration of a power generation system. [Diagram 2] FIG. 2 is a block diagram showing a configuration of a control device. [Diagram 3] 4 is an example of process data stored in a storage unit. [Figure 4] FIG. 11 is a diagram showing pre-processing performed before calculation of a short-term fluctuation predicted steam flow. [Diagram 5] FIG. 13 is an explanatory diagram of calculation of short-term fluctuation predicted steam flow. [Figure 6] FIG. 13 is an explanatory diagram of calculation of long-term fluctuation predicted steam flow. [Figure 7] FIG. 4 is an explanatory diagram of calculation of a short-term fluctuation predicted steam flow and a long-term fluctuation predicted steam flow. [Figure 8] FIG. 11 is a diagram showing an example of a comparison result between a steam flow rate discharged from a boiler and a short-term fluctuation predicted steam flow rate. [Figure 9] FIG. 11 is a diagram showing an example of a comparison result between a steam flow rate discharged from a boiler and a long-term fluctuation predicted steam flow rate. [Figure 10] FIG. 13 is a diagram illustrating control by a short-term control unit and a long-term control unit. [Figure 11] FIG. 4 is a diagram showing an example of a steam flow rate from a boiler when control is performed by a control device. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0022] The incinerator control device according to the present invention is configured to be able to control an incinerator that operates a boiler using heat from the incinerator that burns materials to be incinerated. The incinerator control device (hereinafter referred to as the "control device") 100 of this embodiment will be described below. However, the control device 100 is not limited to the following embodiment, and various modifications are possible within the scope of the gist of the invention.

[0023] Fig. 1 shows a power generation system 1 that generates power using steam from a boiler 20 that operates based on heat from an incinerator 10 controlled by a control device 100 shown in Fig. 2. As shown in Fig. 1, the power generation system 1 includes an incinerator 10, a boiler 20, a steam turbine generator 30, and a chimney 40.

[0024] In this embodiment, the incinerator 10 is configured as a rotary stoker type incinerator in which the furnace body 11 is formed in a cylindrical shape and rotates around the axis. The furnace body 11 is provided with an inlet 11a for the material W to be incinerated on the upstream side and an outlet 11b for the material W to be incinerated on the downstream side. The furnace body 11 has an axis inclined relative to the horizontal direction so that the inlet 11a is higher than the outlet 11b. The furnace body 11 is formed using a metal such as carbon steel. The material W to be incinerated corresponds to, for example, sludge, garbage, etc.

[0025] The furnace body 11 is housed in a cover casing 12. In the furnace body 11, a plurality of water tubes 13 extending along the axial direction are provided at a predetermined interval in the circumferential direction. A metal fin 14 extending along the axial direction is provided between two water tubes 13 adjacent to each other along the circumferential direction. Thus, the water tubes 13 and the fins 14 are arranged alternately along the circumferential direction. The fins 14 are provided with a plurality of air holes 15 penetrating in the radial direction. Such water tubes 13 and fins 14 constitute a fire grate.

[0026] The furnace body 11 is provided with rotation transmission members (not shown) on the inlet 11a side and the outlet 11b side of the furnace body 11, and these rotation transmission members are configured to be rotatable about their axis by a driving device (not shown). The furnace body 11 rotates in response to this rotation.

[0027] A hopper 5 is provided on the inlet 11a side of the furnace body 11. The material to be incinerated W fed into the hopper 5 is supplied to the furnace body 11 by a dust feeder 6. In this embodiment, the dust feeder 6 is of a pusher type.

[0028] A plurality of wind boxes 25 are provided below the furnace body 11, which communicate with the lower end of the cover casing 12. The primary gas (e.g., air) supplied to the wind boxes 25 is introduced into the furnace body 11 from the lower part of the furnace body 11 through the air holes 15. The amount of primary gas supplied to the furnace body 11 and the supply ratio of the primary gas to each combustion area in the furnace body 11 can be adjusted using the rotation speed of the forced draft blower or a flow rate adjustment device (not shown) such as a damper. The amount of primary gas supplied and the supply ratio of the primary gas to each combustion area in the furnace body 11 are configured to be changeable depending on, for example, the components, amount, and distribution state of the material to be incinerated W in the furnace body 11.

[0029] The incineration material W is supplied into the furnace body 11 while the incinerator 10 is rotating at a low speed. The incineration material W supplied to the furnace body 11 is gradually moved downstream while being stirred according to the rotation of the furnace body 11. In addition, while the incineration material W is moving inside the furnace body 11, the primary gas is introduced from the wind box 25 into the furnace body 11. It is preferable to set the supply amount of the primary gas to an amount that maintains slow combustion of the incineration material W. During slow combustion, unburned gas is generated, and this unburned gas is introduced into the secondary combustion chamber 27 provided downstream of the furnace body 11. A secondary gas such as air is supplied to the secondary combustion chamber 27 together with the unburned gas. As a result, the unburned gas is burned. In addition, the unburned components contained in the ash of the incineration material W discharged from the furnace body 11 are burned in the post-combustion stoker 28.

[0030] Boiler 20 is provided above secondary combustion chamber 27 and connected to it, and generates steam by utilizing heat from the exhaust gas discharged from the furnace, post-combustion chamber 29, and secondary combustion chamber 27. Water is supplied to boiler 20 from water supply device 8, and steam is generated by heat exchange with the exhaust gas.

[0031] The steam turbine generator 30 is supplied with steam generated by the boiler 20, and generates electricity by rotating a turbine with the steam. The exhaust gas from which heat has been recovered in the boiler 20 is cooled and subjected to dust removal treatment by a dust removal device installed on the exhaust gas route between the boiler 20 and the chimney 40, and then discharged outside the system through the chimney 40.

[0032] The water supply system 8 includes a condenser that cools and condenses the low-pressure wet steam discharged from the turbine outlet of the steam turbine generator 30, thereby returning it to saturated water and storing it, and a deaerator that degasses the saturated water that is returned from the condenser to the boiler 20 by a pump.

[0033] The operation of such an incinerator 10 is controlled by a control device 100. Fig. 2 is a block diagram showing a schematic configuration of the control device 100. As shown in Fig. 2, the control device 100 is configured with a process data acquisition unit 51, an operation state information acquisition unit 53, a memory unit 55, a predicted steam amount calculation unit 57, a short-term control unit 59, and a long-term control unit 61, and each functional unit is constructed with hardware or software or both with a CPU as a core member in order to perform processing related to the control of the incinerator 10.

[0034] The process data acquisition unit 51 acquires process data of the incinerator 10. The process data is data showing the state of the power generation system 1 when the incinerator 10 burns the incinerated material W. Therefore, the process data is not only data of the incinerator 10, but also includes data showing the state of the boiler 20, for example. Such process data corresponds to, for example, the flow rate of the forced air introduced into the furnace body 11, the pressure from the multiple wind boxes 25 provided below the incinerator 10, the flow rate of the secondary air, the amount of gas generated when the incinerated material W is burned, the flow rate of the gas (exhaust gas) discharged from the chimney 40, the oxygen concentration in the secondary combustion chamber 27, the oxygen concentration at the dust collector outlet, the inlet temperature in the furnace body 11, the temperature of the post-combustion stoker 28, the exhaust gas temperature at the dust collector inlet, the temperature of the gas generated when the incinerated material W is burned, the amount of incinerated material W input into the hopper 5, the pressure of the boiler 20, the amount of steam from the boiler 20 (hereinafter also referred to as the "steam flow rate"), and the temperature of the steam. These are just examples, and data other than these can be used as process data.

[0035] The process of acquiring such process data of the incinerator 10 is referred to as a process data acquisition step in the control method for the incinerator 10 that operates the boiler 20 using heat from the incinerator 10 that combusts the materials W to be incinerated.

[0036] The operating state information acquisition unit 53 acquires operating state data of the incinerator 10. The operating state data is data indicating the state of the equipment related to the operation of the incinerator 10 (power generation system 1). Such data corresponds to, for example, equipment setting values ​​that set the operating state of the equipment and measurement values ​​that indicate the operating state of the equipment. These values ​​do not have to be absolute values, and may be, for example, deviations or relative values ​​with respect to a predetermined value. Such operating state data corresponds to, for example, data related to the movement of the incinerated material W in the incinerator 10, such as the pushing amount of the incinerated material W pushed into the furnace body 11, the dust feeding cycle of the dust feeding device 6, the dust feeding stroke length of the dust feeding device 6, the rotation speed (grate speed) of the furnace body 11, and the cycle setting value of the post-combustion stoker 28, the rotation speed of the forced draft blower fan that pushes air from the wind box 25 or the motor driving the fan, and the damper opening. In addition, it may include the setting value of the steam flow rate of the boiler 20 and a soot blower signal indicating that the soot blower is being operated in the boiler 20. These are just examples, and data other than these can be used as the operating condition data.

[0037] Such a process of acquiring operational status data of the incinerator 10 is referred to as an operational status information acquisition step in the incinerator 10 control method.

[0038] The memory unit 55 sequentially stores the process data acquired by the process data acquisition unit 51 and the operating state data acquired by the operating state information acquisition unit 53. Although details will be described later, the control device 100 uses the process data and the operating state data in controlling the incinerator 10. For this reason, the process data and the operating state data stored in the memory unit 55 are associated with a timestamp indicating the time of acquisition and are continuously stored.

[0039] FIG. 3 shows an example of process data stored in the storage unit 55. In FIG. 3, process data of processes A, B, and C are shown. These process data are stored in association with a time stamp indicating the time when the process data was acquired. Of course, it is possible to configure the storage unit 55 to store process data of processes other than processes A, B, and C, and in fact, operation state data is also stored. Such process data and operation state data can be configured to select relevant variable information from domain knowledge, select according to the accuracy of the prediction result, or select information determined to be important by machine learning (multiple regression analysis, feature analysis, etc.) when predicting the steam flow rate generated in the boiler 20 described later. In this way, the process data and operation state data are accumulated in the storage unit 55.

[0040] The process of sequentially storing such process data and operating state data in the memory unit 55 is referred to as a storage step in the control method for the incinerator 10.

[0041] The predicted steam amount calculation unit 57 calculates a short-term fluctuation predicted steam amount. The short-term fluctuation predicted steam amount is a predicted value of the steam flow rate discharged from the boiler 20 in a predetermined first hour. The first hour may be one hour from the present time, or one hour from a predetermined time point. The predicted steam amount calculation unit 57 calculates a short-term fluctuation predicted steam amount over a predetermined period as such a predicted value. The short-term fluctuation predicted steam amount over a predetermined period is a prediction of the fluctuation of the steam flow rate in a period from a certain time point to a prediction time point, and corresponds to a moving average value from a certain time point to a prediction time point in this embodiment. Therefore, the short-term fluctuation predicted steam amount over a predetermined period corresponds to a short-term moving average value of the steam flow rate. The predicted steam amount calculation unit 57 continuously calculates the short-term fluctuation predicted steam amount consisting of such a moving average value. Therefore, the predicted steam amount calculation unit 57 continuously calculates the short-term fluctuation predicted steam amount consisting of the moving average value from a certain time point to a prediction time point as a predicted value of the steam flow rate discharged from the boiler 20 in a predetermined first hour.

[0042] The short-term fluctuation predicted steam flow rate consisting of such a moving average value is calculated based on the process data and the operating state data stored in the storage unit 55. When calculating the short-term fluctuation predicted steam flow rate, the predicted steam flow rate calculation unit 57 performs preprocessing using the process data and the operating state data stored in the storage unit 55. In this embodiment, as the preprocessing using the process data, calculation of a lag feature amount of the process data, calculation of a moving average value of the process data, and calculation of a lag feature amount for the moving average value of the process data are performed. The number of lags in the calculation of the lag feature amount of the process data, the number of process data used in the calculation of the moving average value of the process data (the time when the process data was acquired), and the number of lags in the calculation of the lag feature amount for the moving average value of the process data differ depending on the scale and configuration of the power generation system 1, and can be changed as appropriate.

[0043] The predicted steam flow calculation unit 57 obtains a lag feature of the process data, a moving average value of the process data, and a lag feature for the moving average value of the process data as preprocessing for calculating the short-term fluctuation predicted steam flow.

[0044] FIG. 4 is a diagram showing pre-processing performed before the calculation of the short-term fluctuation predicted steam volume. As shown in FIG. 4, the process data of the process A from "0:00:00" to "0:00:10" is assumed to be "A1" to "A11". In the example of FIG. 4, s seconds and 2s seconds before are obtained as the lag feature of the process data of the process A. Specifically, "A1_Lags" is obtained as the lag feature s seconds before the time point of "0:00:00", and "A1_Lag2s" is obtained as the lag feature 2s seconds before the time point of "0:00:00". Similarly, "A2_Lags" is obtained as the lag feature s seconds before the time point of "0:00:01", and "A2_Lag2s" is obtained as the lag feature 2s seconds before the time point of "0:00:01".

[0045] Furthermore, the moving average value is calculated for the process data of process A. Specifically, "A1_ma" is calculated as the moving average value at the time point "0:00:00", and "A2_ma" is calculated as the moving average value at the time point "0:00:01".

[0046] Next, a lag feature for the moving average value of the process data of this process A is obtained. Specifically, "A1_ma_Lags" is obtained as a lag feature for the moving average value of the process data of process A s seconds before the time point of "0:00:00", and "A1_ma_Lag2s" is obtained as a lag feature for the moving average value of the process data of process A 2s seconds before the time point of "0:00:00". Similarly, "A2_ma_Lags" is obtained as a lag feature for the moving average value of the process data of process A s seconds before the time point of "0:00:01", and "A2_ma_Lag2s" is obtained as a lag feature for the moving average value of the process data of process A 2s seconds before the time point of "0:00:01".

[0047] Similarly, the process data of process B from "0:00:00" to "0:00:10" are "B1" to "B11", and s seconds and 2s seconds before are obtained as lag features of the process data of process B. Specifically, "B1_Lags" is obtained as the lag feature s seconds before the time point of "0:00:00", and "B1_Lag2s" is obtained as the lag feature 2s seconds before the time point of "0:00:00". Similarly, "B2_Lags" is obtained as the lag feature s seconds before the time point of "0:00:01", and "B2_Lag2s" is obtained as the lag feature 2s seconds before the time point of "0:00:01". Although not shown in the figure, the moving average value of the process data of process B and the lag feature for the moving average value of the process data of process B are also obtained.

[0048] In addition, as pre-processing using the operating state data, calculation of a lag feature amount of the operating state data, calculation of a moving average value of the operating state data, and calculation of a lag feature amount for the moving average value of the operating state data are performed. The number of lags in the calculation of the lag feature amount of the operating state data, the number of operating state data used in the calculation of the moving average value of the operating state data (the time when the operating state data was acquired), and the number of lags in the calculation of the lag feature amount for the moving average value of the operating state data differ depending on the scale and configuration of the power generation system 1, and can be changed as appropriate.

[0049] Although not shown in the figure, the predicted steam amount calculation unit 57 calculates a lag feature amount of such operating state data, a moving average value of the operating state data, and a lag feature amount for the moving average value of the operating state data as preprocessing for calculating the short-term fluctuation predicted steam amount.

[0050] As shown in Fig. 5, the predicted steam amount calculation unit 57 continuously calculates a short-term fluctuation predicted steam amount (see Fig. 7) consisting of a moving average value from a certain time point to a prediction time point as a predicted value (objective variable) of a steam flow rate discharged from the boiler 20 after a predetermined first hour by machine learning (regression model) using the lag feature amount of the process data obtained by preprocessing, the moving average value of the process data, and the lag feature amount for the moving average value of the process data, the process data, the lag feature amount of the operation state data, the moving average value of the operation state data, and the lag feature amount for the moving average value of the operation state data, and the operation state data as explanatory variables. Specifically, a prediction model of the steam flow rate is generated by machine learning based on a combination of a preprocessed data set and correct answer data of the steam flow rate (in this embodiment, the correct answer data is a moving average value from a certain time point discharged after one hour from the time of the preprocessed data set to the prediction time point). There are various prediction models, and it is possible to perform the prediction using various known machine learning algorithms. Thereafter, the steam flow rate is predicted using the preprocessed data set at the present time or at a certain time point and the machine learning model. As input for machine learning, multiple moving average patterns may be used for one piece of data, or a weighted average value may be used instead of a moving average.

[0051] The window width and the number of steps for obtaining the moving average value, and the number of lags and the number of steps for obtaining the lag feature value may be determined so as to obtain the best accuracy while comparing with the prediction accuracy of the steam flow rate from the boiler 20. For evaluation of the prediction accuracy, known prediction evaluation indices such as RMSE, MSE, MAE, coefficient of determination R2, and AIC may be used.

[0052] For example, the predicted steam flow rate calculation unit 57 can predict a 60-second moving average value of the steam flow rate as a short-term fluctuation prediction 300 seconds later. Of course, such 60 seconds and 300 seconds are merely examples and can be changed as appropriate.

[0053] The objective variable may be the difference between the steam flow rate after the first hour and the current steam flow rate, the deviation of the steam flow rate after the first hour, or the class (classification model) of the steam flow rate after the first hour. The deviation of the steam flow rate can be calculated by (actual value-set value) / set value. The optimal value of the first hour varies depending on the scale of the power generation system 1. Therefore, it is advisable to use the maximum time for which prediction accuracy is guaranteed.

[0054] Here, for example, if the amount of combustion air is not appropriate for the amount of materials W to be incinerated in the incinerator 10, or if the amount of materials W to be incinerated in the incinerator 10 is insufficient or excessive, the steam flow rate deviates from the set value. In this case, if dust supply control is performed based on the short-term fluctuation predicted steam amount, the steam flow rate may overshoot the set value, particularly if the amount of combustion air is not appropriate for the amount of materials W to be incinerated in the incinerator 10. Therefore, in this control device 100, a long-term fluctuation predicted steam amount, which will be described later, is used.

[0055] The predicted steam amount calculation unit 57 calculates a long-term fluctuation predicted steam amount. The long-term fluctuation predicted steam amount is a predicted value of the steam flow rate discharged from the boiler 20 after a predetermined second hour. The second hour may be two hours from the present time, or may be two hours from a predetermined time point. The second hour may be the same length as the first hour described above, or may be a different length. The "predetermined time point" may be the same as the "predetermined time" that starts from the first hour described above, or may be different. The predicted steam amount calculation unit 57 calculates a long-term fluctuation predicted steam amount for a period longer than a predetermined period as such a predicted value. The long-term fluctuation predicted steam amount for a period longer than a predetermined period is a prediction of fluctuations in the steam flow rate from a certain time point to a prediction time point, which is longer than the period used to calculate the short-term fluctuation predicted steam amount described above, and corresponds to a moving average value from a certain time point to a prediction time point in this embodiment. For this reason, the long-term fluctuation predicted steam amount for a predetermined period corresponds to a long-term moving average value of the steam flow rate. Therefore, the long-term fluctuation predicted steam volume is a moving average value over a longer period than the short-term fluctuation predicted steam volume. The predicted steam volume calculation unit 57 continuously calculates the long-term fluctuation predicted steam volume consisting of such a moving average value. Therefore, the predicted steam volume calculation unit 57 continuously calculates the long-term fluctuation predicted steam volume consisting of a moving average value from a certain point in time to a prediction point in time, which is a longer period than the short-term fluctuation predicted steam volume, as a predicted value of the steam flow rate discharged from the boiler 20 in the predetermined second hour.

[0056] The long-term fluctuation predicted steam flow composed of such a moving average value is calculated based on the process data and the operating state data stored in the memory unit 55. When calculating the long-term fluctuation predicted steam flow, the predicted steam flow calculation unit 57 performs pre-processing using the process data and the operating state data stored in the memory unit 55. The pre-processing using the process data and the operating state data has been explained in the calculation of the short-term fluctuation predicted steam flow described above, and therefore will not be explained here.

[0057] As shown in FIG. 6, the predicted steam amount calculation unit 57 continuously calculates a long-term fluctuation predicted steam amount (see FIG. 7) consisting of a moving average value from a certain time point to a prediction time point as a predicted value (objective variable) of a steam flow rate discharged from the boiler 20 after a predetermined second hour by machine learning (regression model) using the lag feature amount of the process data obtained by preprocessing, the moving average value of the process data, and the lag feature amount for the moving average value of the process data, the process data, the lag feature amount of the operation state data, the moving average value of the operation state data, and the lag feature amount for the moving average value of the operation state data, and the operation state data as explanatory variables. Specifically, as in the case of the short-term fluctuation predicted steam amount described above, a prediction model of the steam flow rate is generated by first performing machine learning based on a combination of a preprocessed data set and correct answer data of the steam flow rate. There are various prediction models, and it is possible to perform the prediction using various known machine learning algorithms. After that, the steam flow rate is predicted using the preprocessed data set and the machine learning model. Note that, as an input for machine learning, multiple moving average patterns may be used for one data, and a weighted average value may be used instead of a moving average.

[0058] Also in this case, the window width and the number of steps for obtaining the moving average value, and the number of lags and the number of steps for obtaining the lag feature value may be determined so as to obtain the best accuracy while comparing with the prediction accuracy of the steam flow rate from the boiler 20. For evaluation of the prediction accuracy, known prediction evaluation indices such as RMSE, MSE, MAE, coefficient of determination R2, AIC, etc. may be used.

[0059] For example, the predicted steam flow rate calculation unit 57 can predict a moving average value of the steam flow rate for 1800 seconds as a long-term fluctuation prediction for 900 seconds later. Of course, such 1800 seconds and 900 seconds are only examples and can be changed as appropriate.

[0060] The objective variable may be the difference between the steam flow rate after the second hour and the current steam flow rate, the deviation of the steam flow rate after the second hour, or the class (classification model) of the steam flow rate after the second hour. The deviation of the steam flow rate can be calculated by (actual value-set value) / set value. The optimal value of the second hour varies depending on the scale of the power generation system 1. Therefore, it is advisable to use the maximum time for which prediction accuracy is guaranteed.

[0061] Fig. 8 shows the calculation result of the short-term fluctuation predicted steam flow rate, which predicts the steam flow rate 300 seconds from now, using a 60-second moving average value of the steam flow rate. Fig. 9 shows the calculation result of the long-term fluctuation predicted steam flow rate, which predicts the steam flow rate 900 seconds from now, using a 1800-second moving average value of the steam flow rate. As shown in Fig. 8, when the predicted value is slid by 300 seconds, the value becomes closer to the actual measured value. As shown in Fig. 9, when the predicted value is slid by 900 seconds, the value becomes closer to the actual measured value. In this way, the predicted steam flow rate calculation unit 57 can appropriately predict the future steam flow rate.

[0062] The process of calculating a short-term fluctuation predicted steam volume over a specified period based on the process data and operating state data stored in memory unit 55 as a predicted value of the steam flow rate discharged from boiler 20 after a specified first hour, and calculating a long-term fluctuation predicted steam volume over a period longer than the specified period based on the process data and operating state data stored in memory unit 55 as a predicted value of the steam flow rate discharged from boiler 20 after a specified second hour, is referred to as a predicted steam volume calculation step in the control method for incinerator 10.

[0063] The process data and operating state data used by the predicted steam amount calculation unit 57 to calculate the short-term fluctuation predicted steam amount may be the same as the process data and operating state data used to calculate the long-term fluctuation predicted steam amount. Alternatively, the predicted steam amount calculation unit 57 may appropriately select and use optimal parameters when creating a machine learning model used to calculate the short-term fluctuation predicted steam amount and the long-term fluctuation predicted steam amount. In the case of selective use, the process data and operating state data used to calculate the short-term fluctuation predicted steam amount and the process data and operating state data used to calculate the long-term fluctuation predicted steam amount may all be different from each other, or may be partially different from each other. Furthermore, even in the case of selective use, the process data and operating state data used to calculate the short-term fluctuation predicted steam amount and the process data and operating state data used to calculate the long-term fluctuation predicted steam amount may be the same as each other.

[0064] Returning to FIG. 2, the short-term control unit 59 controls the short-term control target amount based on the short-term fluctuation predicted steam amount. The short-term fluctuation predicted steam amount is calculated and transmitted by the predicted steam amount calculation unit 57 as described above. The short-term control target amount is a control amount performed to burn the incineration target W in the incinerator 10 using the short-term fluctuation predicted steam amount, and corresponds to the amount of air supplied to the incinerator 10 in this embodiment. The air supplied to the incinerator 10 means combustion air. Therefore, the short-term control unit 59 controls the amount of combustion air according to the short-term fluctuation predicted steam amount calculated by the predicted steam amount calculation unit 57. Such an amount of combustion air can be controlled by the fan of the forced draft blower that pushes in air from the wind box 25 or the rotation speed of the motor that drives the fan, or the damper opening.

[0065] In this embodiment, the short-term control unit 59 corrects the amount of air to be supplied to the incinerator 10, which is calculated based on the actual value of the steam flow rate discharged from the boiler 20 and the set value of the steam flow rate discharged from the boiler 20, based on the short-term fluctuation predicted steam amount. That is, as shown in Fig. 10, the short-term control unit 59 calculates the control amount of the forced air amount by PID control based on the actual value and the set value of the steam flow rate, and corrects this control amount by PID control with the short-term fluctuation predicted steam amount to control the amount of forced air. Note that in practice, the PID control is not performed only on the steam flow rate, but the control amount of the PID control is calculated including, for example, the temperature of the furnace body 11 and the amount of the incinerated material W.

[0066] The short-term control unit 59 may set a correction amount in response to deviation of the short-term control target amount from a predetermined range set based on a preset threshold value, and may perform correction based on this correction amount. The threshold value and the correction amount may be set according to the scale and configuration of the power generation system 1.

[0067] In addition, the short-term control unit 59 can also be configured to calculate the deviation between the steam flow rate from the boiler 20 and the short-term control target amount, set a correction amount according to this deviation, and perform correction based on this correction amount.

[0068] The process of controlling the short-term control target amount based on such a short-term fluctuation predicted steam amount is referred to as a short-term control step in the control method for the incinerator 10.

[0069] The long-term control unit 61 controls the long-term control target amount based on the long-term fluctuation predicted steam amount. The long-term fluctuation predicted steam amount is calculated and transmitted by the predicted steam amount calculation unit 57 as described above. The long-term control target amount is a control amount performed to burn the incineration target W in the incinerator 10 using the long-term fluctuation predicted steam amount, and corresponds to the amount of the incineration target W supplied to the incinerator 10 in this embodiment. The incineration target W supplied to the incinerator 10 is pushed into the furnace body 11 by the dust supply device 6. Therefore, the long-term control unit 61 controls the amount of the incineration target W pushed into the furnace body 11 by the dust supply device 6 according to the long-term fluctuation predicted steam amount calculated by the predicted steam amount calculation unit 57. Such an amount of the incineration target W can be controlled by controlling the dust supply cycle of the dust supply device 6 and the dust supply stroke length of the dust supply device 6.

[0070] In this embodiment, the long-term control unit 61 corrects the amount of materials W to be supplied to the incinerator 10, which is calculated based on the actual measurement value of the steam flow rate discharged from the boiler 20 and the set value of the steam flow rate discharged from the boiler 20, based on the long-term fluctuation predicted steam amount. That is, as shown in Fig. 10, the long-term control unit 61 calculates the control amount (operation period) of the dust feeder 6 by PID control based on the actual measurement value and the set value of the steam flow rate, and controls the dust feeder 6 by correcting this control amount by PID control with the long-term fluctuation predicted steam amount. Note that in practice, the PID control is not performed based on only the steam flow rate, but the control amount of the PID control is calculated including, for example, the temperature of the furnace body 11 and the amount of materials W to be incinerated.

[0071] The long-term control unit 61 may set a correction amount in response to deviation of the long-term controlled variable from a predetermined range set based on a preset threshold value, and may perform correction based on this correction amount. The threshold value and the correction amount may be set according to the scale and configuration of the power generation system 1.

[0072] In addition, the long-term control unit 61 can also be configured to calculate the deviation between the steam flow rate from the boiler 20 and the short-term control target amount, set a correction amount according to this deviation, and perform correction based on this correction amount.

[0073] The process of controlling the long-term control target amount based on such a long-term fluctuation predicted steam amount is called a long-term control step in the control method for the incinerator 10.

[0074] Here, factors that cause the steam flow rate to deviate from the set value include an inappropriate amount of combustion air relative to the amount of incinerated materials W in the furnace body 11, and an insufficient or excessive amount of incinerated materials W in the furnace body 11. For example, if the amount of incinerated materials W pushed into the furnace body 11 by the dust feeder 6 is controlled based on the short-term fluctuation predicted steam amount, and the cause of the steam flow rate deviating from the set value is that the amount of combustion air is not appropriate relative to the amount of incinerated materials W in the furnace body 11, the steam flow rate generated by the boiler 20 may overshoot the set value. Therefore, as in this embodiment, by controlling the amount of incinerated materials W pushed into the furnace body 11 by the dust feeder 6 based on the long-term fluctuation predicted steam amount, it is possible to prevent overshooting.

[0075] FIG. 11 shows the change in the steam flow rate from the boiler 20 (a 30-minute moving average value of the steam flow rate) when the control device 100 controls the incinerator 10 by controlling the amount of air supplied to the incinerator 10 based on the short-term fluctuation predicted steam amount and controlling the amount of material W to be incinerated supplied to the incinerator 10 based on the long-term fluctuation predicted steam amount. As shown in FIG. 11, the 30-minute moving average value of the steam flow rate is within 3% of the threshold value. In this way, the control device 100 can suppress the fluctuation in the steam flow rate.

[0076] Other embodiments In the above embodiment, the incinerator 10 has been described as a rotary stoker type incinerator, but the incinerator 10 is not limited to a rotary stoker type incinerator and may be an incinerator other than a rotary stoker type incinerator.

[0077] In the above embodiment, the short-term control unit 59 has been described as controlling the amount of air supplied to the incinerator 10 based on the short-term fluctuation predicted steam volume, but the short-term control unit 59 may also control the amount of air supplied to the incinerator 10 based on the short-term fluctuation predicted steam volume and the long-term fluctuation predicted steam volume.

[0078] In the above embodiment, the short-term control unit 59 and the long-term control unit 61 are described as being configured as separate entities, but it is also possible to configure, for example, a single control unit having the short-term control unit 59 and the long-term control unit 61.

[0079] In the above embodiment, the short-term control unit 59 has been described as controlling the amount of forced air by correcting the control amount by PID control based on the actual value and set value of the steam flow rate with the short-term fluctuation predicted steam volume. However, it is also possible to configure the short-term control unit 59 to calculate a correction amount by PID control based on the set value of the steam flow rate and the short-term fluctuation predicted steam volume, and to control the forced air by correcting the control amount by PID control based on the actual value and set value of the steam flow rate with this correction amount.

[0080] In the above embodiment, the long-term control unit 61 has been described as controlling the dust supply device 6 by correcting the control amount by PID control based on the actual measured value and set value of the steam flow rate with the long-term fluctuation predicted steam amount. However, it is also possible to configure the device to calculate a correction amount by PID control based on the set value of the steam flow rate and the long-term fluctuation predicted steam amount, and to correct the control amount by PID control based on the actual measured value and set value of the steam flow rate with this correction amount to control the dust supply device 6.

[0081] In the above embodiment, the short-term control amount is the amount of air supplied to the incinerator 10, and the long-term control amount is the amount of material W to be incinerated supplied to the incinerator 10. However, at least one of the short-term control amount and the long-term control amount may be configured to include the rotation speed of the incinerator 10 or the speed of the grate in the secondary combustion chamber 27. In this case, too, it is preferable to determine and control the correction amount from the predicted value of the steam flow rate.

[0082] In the above embodiment, the long-term control unit 61 and the short-term control unit 59 have been described as controlling the short-term control object quantity and the long-term control object quantity so that the fluctuation amount of the steam flow rate discharged from the boiler 20 is equal to or less than a preset fluctuation amount. In this case, however, the "preset fluctuation amount" used in the short-term control object quantity and the "preset fluctuation amount" used in the long-term control object quantity may be the same value or different values.

[0083] In the above embodiment, it has been described that the short-term control unit 59 controls the amount of air supplied to the incinerator 10 based on the short-term fluctuation predicted steam amount. However, if the short-term fluctuation predicted steam amount drops significantly, the supply of the materials to be incinerated W may be controlled. Alternatively, the short-term control unit 59 may be configured to forcibly supply materials to be incinerated W to the incinerator 10 regardless of the long-term fluctuation predicted steam amount if a predetermined time has passed since the last supply of materials to be incinerated W and the short-term fluctuation predicted steam amount falls below a preset amount. [Industrial Applicability]

[0084] INDUSTRIAL APPLICABILITY The present invention can be used in an incinerator control device and an incinerator control method that operate a boiler by utilizing heat from an incinerator that burns materials to be incinerated. [Explanation of symbols]

[0085] 10: Incinerator 20: Boiler 51: Process data acquisition unit 53: Operation status information acquisition unit 55: Storage section 57: Predicted steam volume calculation section 59: Short-term control section 61: Long-term control section 100: Control device (incinerator control device) W: Incinerated material

Claims

1. A control device for an incinerator that operates a boiler using heat from an incinerator that burns materials to be incinerated, A process data acquisition unit that acquires process data of the incinerator; An operating state information acquisition unit that acquires operating state data of the incinerator; a storage unit that sequentially stores the process data and the operating state data; a predicted steam amount calculation unit that calculates a short-term fluctuation predicted steam amount over a predetermined period based on the process data and the operational state data stored in the storage unit as a predicted value of the amount of steam discharged from the boiler in a predetermined first hour, and calculates a long-term fluctuation predicted steam amount over a period longer than the predetermined period based on the process data and the operational state data stored in the storage unit as a predicted value of the amount of steam discharged from the boiler in a predetermined second hour; a short-term control unit that controls a short-term control target quantity based on the short-term fluctuation predicted steam flow; a long-term control unit that controls a long-term controlled quantity based on the long-term fluctuation predicted steam quantity; A control device for an incinerator comprising:

2. The short-term control target amount is the amount of air supplied to the incinerator, The incinerator control device according to claim 1 , wherein the long-term control target amount is the amount of the material to be incinerated supplied to the incinerator.

3. The incinerator control device according to claim 2, wherein the long-term control unit and the short-term control unit control the short-term control target quantity and the long-term control target quantity so that the fluctuation amount of the amount of steam discharged from the boiler is equal to or less than a preset fluctuation amount.

4. The short-term control unit corrects the amount of air to be supplied to the incinerator, which is calculated based on the actual measured value of the amount of steam discharged from the boiler and the set value of the amount of steam discharged from the boiler, based on the short-term fluctuation predicted steam amount; The incinerator control device according to claim 3, wherein the long-term control unit corrects the amount of material to be supplied to the incinerator, calculated based on the actual measured amount of steam discharged from the boiler and the set value of the amount of steam discharged from the boiler, based on the long-term fluctuation predicted steam amount.

5. The incinerator control device according to any one of claims 2 to 4, wherein the short-term control unit forcibly supplies the incinerator with the material to be incinerated regardless of the long-term fluctuation predicted steam volume when the short-term fluctuation predicted steam volume falls below a preset volume.

6. A method for controlling an incinerator that uses heat from an incinerator that burns materials to be incinerated to operate a boiler, comprising the steps of: A process data acquisition step of acquiring process data of the incinerator; An operating state information acquisition step of acquiring operating state data of the incinerator; a storage step of sequentially storing the process data and the operating state data in a storage unit; a predicted steam amount calculation step of calculating a short-term fluctuation predicted steam amount over a predetermined period based on the process data and the operational state data stored in the storage unit as a predicted value of the amount of steam discharged from the boiler after a predetermined first hour, and calculating a long-term fluctuation predicted steam amount over a period longer than the predetermined period based on the process data and the operational state data stored in the storage unit as a predicted value of the amount of steam discharged from the boiler after a predetermined second hour; a short-term control step of controlling a short-term control target quantity based on the short-term fluctuation predicted steam flow; a long-term control step of controlling a long-term controlled quantity based on the long-term fluctuation predicted steam quantity; A method for controlling an incinerator comprising:

7. The short-term control target amount is the amount of air supplied to the incinerator, 7. The incinerator control method according to claim 6, wherein the long-term control target amount is the amount of the material to be incinerated supplied to the incinerator.

Images