JP2009228995A - Coal type discriminating device and coal type discriminating method for coal burning boiler - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a coal type discriminating device for a coal burning boiler can accurately and quickly discriminate a coal type by taking into consideration the fluctuation typical to plants and perform operation of the coal burning boiler corresponding to the coal type. <P>SOLUTION: The coal type discriminating device of the coal burning boiler for discriminating the coal type based on a measurement signal of the coal burning boiler to be controlled includes: an exterior input interface for taking in a measurement signal from a controlling object, a measurement signal database for retaining the measurement signal taken in from the controlling object, a model for estimating a measurement signal value obtained when an operating signal is provided to the coal burning boiler to be controlled for each coal type, a learning part for learning a generation method of a model input so that a model output estimated by the model achieves a model output target value, an estimating part for calculating a difference between the measurement signal retained in the measurement signal database with the measurement signal estimated by the model as an estimation signal, and a determination part for determining a coal type or a mixed coal rate based on the estimation signal calculated by the estimating part. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to a coal-fired boiler type identification apparatus and a coal-fired boiler type identification method.

  Coal-fired boilers used in thermal power plants generally use coal imported from all over the world as fuel from the viewpoint of stable fuel supply. The climate and soil quality vary depending on the origin of the coal import, so there are differences in the coalification process, resulting in a wide range of coal properties.

  Different coal properties change the combustion characteristics of coal, which greatly affects the boiler efficiency of coal-fired boilers. Therefore, it is necessary to grasp the type of coal type of coal and operate the coal-fired boiler corresponding to the type of coal.

  Conventionally, the type of coal type is determined according to the empirical knowledge of the operator, the corresponding coal type is set in the operation control parameter calculation program installed in the operation control device of the coal fired boiler, and the operation of the coal fired boiler is performed. The operator manually adjusted the operation control parameters as necessary, but there was a problem that the type of coal could not be accurately determined.

  Therefore, the type of coal is determined by analyzing the coal ash from the various state quantities of the plant including the coal-fired boiler and by analyzing the coal ash after coal combustion and measuring the unburned content in the coal ash. Technology is provided.

  As the former, for example, in Japanese Patent No. 3746528, the amount of heat absorbed by the furnace and the reheater is estimated from the flow measurement data such as the temperature, pressure, and flow rate of the furnace and reheater of the coal fired boiler, and calculated in advance. There is disclosed a technique for identifying a coal type by calculating a signal corresponding to a fuel ratio on the basis of a relative difference from the absorbed heat amount of a reference coal base.

  Further, in Japanese Patent Laid-Open No. 3-191205, based on the detection values of various state quantities of a coal-fired boiler, the correlation between the state quantities is determined using the concept of the probabilistic distance in the multivariate analysis method and the coal type. A technique for discriminating the blend ratio is disclosed.

  As the latter, for example, in Japanese Patent Application Laid-Open No. 2003-74833, coal ash generated by coal combustion discharged from a coal-fired boiler is obtained by using a laser-induced breakdown method, and its constituent components are Si, Al, Fe, and Ca. By detecting the signal intensity of C and calculating the unburned content in the coal ash, the unburned content in the coal ash is reduced by controlling the operation of the mill that refines the coal based on the unburned content. Technology for improving the combustion efficiency of coal-fired boilers is disclosed.

Japanese Patent No. 3746528 Japanese Patent Laid-Open No. 3-191205 JP 2003-74833 A

  By the way, when controlling the operation of a coal-fired boiler according to the type of coal, it is necessary to process the state quantity of the coal-fired boiler, taking into account fluctuations peculiar to the plant of the coal-fired boiler when determining the coal type, etc. There is.

  In the technology described in Japanese Patent No. 3746528, the relative difference between the amount of heat absorbed based on the measurement signal of the state quantity of the coal-fired boiler and the amount of heat absorbed based on the reference coal is calculated. Plant-specific fluctuations such as noise components added to this measurement signal for some reason when transmitting a measurement signal that detects the state value of a fired boiler, and sudden fluctuations in the measurement signal such as pressure, flow rate, etc. When fluctuations occur, these calculated values also fluctuate, making it difficult to accurately determine the coal type.

  Moreover, in the technique described in Unexamined-Japanese-Patent No. 2003-74833, since the coal ash after combustion is analyzed with a coal fired boiler and the unburned part is computed from the component, this analysis result is used for boiler operation control. It takes time to reflect on. Until this analysis result is obtained, the influence of the coal type is not reflected in the operation of the coal-fired boiler, so the coal type cannot be determined quickly.

  In the technique described in Japanese Patent Laid-Open No. 3-191205, the correlation is expressed as a stochastic distance for each coal type based on the average of the state quantity of the coal-fired boiler plant and the variance / covariance matrix. However, there is a problem in that it takes time to calculate the mean and variance / covariance matrix, and the type of coal cannot be quickly determined.

  Further, since the above technology does not take into account when each state quantity is subject to fluctuations peculiar to the plant of the coal-fired boiler, if the fluctuation fluctuation peculiar to the plant occurs, the calculated value fluctuates, and the exact type of coal is changed. Discrimination becomes difficult.

  The purpose of the present invention is to accurately and quickly determine the type of coal in consideration of fluctuations peculiar to the plant of the coal-fired boiler generated in the state quantity of the measured coal-fired boiler, and to operate the coal-fired boiler corresponding to the type of coal. It is to provide a coal type identification device for a coal-fired boiler and a coal type identification method for a coal-fired boiler.

  The coal-fired boiler coal type discriminating apparatus according to the present invention is a coal-fired boiler that calculates a coal type or coal mixture ratio to be used in a coal-fired boiler based on the value of a state quantity measurement signal obtained from the controlled coal-fired boiler. In the coal type discriminating apparatus, the coal type discriminating apparatus includes an external input interface that captures the measurement signal from the control target, a measurement signal database that stores the measurement signal captured from the control target, and a coal burning target to be controlled. A model for estimating the value of the measurement signal of the coal type obtained when an operation signal is given to the boiler for each coal type, and a model for giving the model output estimated by the model close to the measurement signal from which noise has been removed A learning unit for learning an input generation method, the measurement signal stored in the measurement signal database, and the model reflecting the learning result Thus an estimation unit for calculating a difference between the estimated measurement signal as the estimated signal, characterized in that it comprises a determination unit which determines the coal type or CCS, the imported coal is blended rate based on the estimated signal calculated by the estimation unit.

  The coal-fired boiler type identification apparatus according to the present invention is a coal-fired boiler that calculates a coal type or a coal mixture rate to be used in a coal-fired boiler based on the value of a state quantity measurement signal obtained from the controlled coal-fired boiler. In the coal type discriminating device of the boiler, the coal type discriminating device includes an external input interface that captures the measurement signal from the control target, a measurement signal database that stores the measurement signal captured from the control target, and coal to be controlled A model that estimates the value of the measurement signal of the coal type obtained when the operation signal is given to the fired boiler for each coal type, and the model output estimated by the model approaches the measurement signal from which noise has been removed. A learning unit for learning how to generate a model input to be given, a measurement signal stored in the measurement signal database, and a model estimated by the model An estimation unit that calculates a difference from a signal as an estimation signal; and a determination unit that determines a coal type or a coal mixture ratio based on the estimation signal calculated by the estimation unit and its log likelihood ratio. To do.

  The method for determining the coal type of a coal-fired boiler according to the present invention is a coal-fired boiler that calculates a coal type or coal mixture ratio to be used in a coal-fired boiler based on the value of a state quantity measurement signal obtained from a controlled coal-fired boiler. In the coal type discrimination method, the measurement signal taken from the control target is stored in a measurement signal database, and the value of the measurement signal of the coal type obtained when the operation signal is given to the control target is used to determine the coal type. The model output estimated by the model is trained to generate a model input to be given to the model so that the model output estimated by the model approaches the measurement signal from which noise is removed, and the measurement signal stored in the measurement signal database and the learning Reflecting the result, the difference from the measurement signal estimated by the model is calculated and estimated as an estimated signal, and based on the estimated signal, the coal type or And judging charcoal rate.

  In addition, the method for determining the coal type of a coal-fired boiler according to the present invention is a method for determining the type of coal used in a coal-fired boiler based on the value of a measurement signal obtained from a controlled object, or a coal type determination method for a coal-fired boiler. The measurement signal taken from the control object is stored in a measurement signal database, the value of the measurement signal of the coal type obtained when the operation signal is given to the control object is estimated for each coal type using a model, A model input generation method given to the model is learned so that the model output estimated by the model approaches the measurement signal from which noise is removed, and the measurement signal stored in the measurement signal database and the learning result are reflected to reflect the learning result. A difference with the measurement signal estimated by the model is calculated and estimated as an estimation signal, and based on the estimated signal and its log likelihood ratio, And judging charcoal rate.

  According to the present invention, it is possible to accurately and quickly determine the coal type in consideration of fluctuations peculiar to the plant of the coal-fired boiler generated in the measured state quantity of the coal-fired boiler, and to operate the coal-fired boiler corresponding to the coal type. This makes it possible to implement a coal-fired boiler coal type discriminating apparatus and a coal-fired boiler coal type discriminating method.

  Hereinafter, a coal-fired boiler coal type discriminating apparatus and a coal-fired boiler coal type discriminating method according to embodiments of the present invention will be described with reference to the drawings.

  FIG. 1 shows a coal-fired boiler coal type discriminating apparatus and a coal-fired boiler coal type discriminating method according to an embodiment of the present invention.

  In FIG. 1, a coal-fired boiler according to the present embodiment has a coal-fired boiler described later as a control target 100, and a boiler control device 1000 that controls the control target 100 is a coal-fired boiler. A coal type discriminating device 200 for discriminating the coal type of coal supplied as a maintenance tool, a maintenance tool 910 for maintaining the coal type discriminating device 200, and an input device for an operator of the controlled object 100 to input to the maintenance tool 910 900 and an image display device 950 for displaying various data.

  Information on various state quantities of the controlled object 100 that is a coal-fired boiler measured by various measuring instruments described below is transmitted to the coal type discriminating apparatus 200 as measurement information 1.

  Then, as shown in FIG. 2, a coal type, which will be described later, or a coal mixture rate determined by the calculation of the coal type determination device 200 is input to the boiler control device 1000, and the boiler control device 1000 performs an arithmetic process to perform a coal burning boiler. Are output to air dampers 160, 161, 162, and 163, which will be the operation ends of the coal-fired boiler, as command signals for the control object 100, and are operated respectively, and the coal-fired boiler is made efficient according to the type of coal or the coal mixture ratio. Drive well.

  As shown in FIG. 1, the coal type discriminating apparatus 200 is provided with an external input interface 210 that takes the measurement signal 1 obtained by measuring the state quantity of the plant from the controlled object 100 into the coal type discriminating apparatus 200. The measurement signal 1 from the controlled object 100 is taken in via the external input interface 210.

  Further, the coal type discriminating apparatus 200 is provided with an external output interface 270, and the coal type data determined by the determination unit 700 of the coal type discriminating apparatus 200 is installed in the maintenance tool 910 via the external output interface 270. To the data transmission / reception processing unit 930 as an output signal 51.

  The measurement signal 2 captured from the controlled object 100 via the external input interface 210 is transmitted to and stored in the measurement signal database 220 installed in the coal type discriminating apparatus 200, and installed in the coal type discriminating apparatus 200. To the switching unit 230.

  In accordance with the switching signal 20 output from the switching unit 230, the switching unit 230 transmits the measurement signal 2 to the model creation unit 300 or the estimation unit 600 installed in the coal type discrimination device 200, respectively.

  If the switching signal 20 output from the switching unit 230 is “model creation”, the measurement signal 4 is transmitted from the switching unit 230 to the model creation unit 300.

  If the switching signal 20 output from the switching unit 230 is “estimated”, the measurement signal 8 is transmitted from the switching unit 230 to the estimation unit 600.

  The learning unit 500 installed in the coal type discriminating apparatus 200 is connected to the model 400 installed in the charcoal type discriminating apparatus 200.

  The model 400 has a function of simulating the coal-fired boiler 100 to be controlled for each characteristic coal type. That is, as a result of giving the output signal 51 from the coal type discriminating apparatus 200 to the coal-fired boiler 100 to be controlled, model input is performed in the same manner as obtaining the state quantity measurement signal 1 from the coal-fired boiler 100 to be controlled. 12 is input to the model 400, the operation of the coal fired boiler 100 is simulated with the model 400, and the model output 13 is output as a simulation result.

  The model output 13 output from the model 400 is a predicted value of the measurement signal 1.

  The model 400 simulates the characteristics of the coal-fired boiler 100 to be controlled, and has a function of simulating and calculating the model output 13 with respect to the model input 12 using a model formula based on a physical law or a statistical method. Have.

  The model parameter 7 necessary for the model 400 is input to the model 400 from the model creation unit 300 installed in the coal type discrimination device 200.

  The model creation unit 300 uses the previous model parameter 5 stored in the model parameter database 240 installed in the coal type discrimination device 200 and the model 400 using the measurement signal 4 transmitted from the switching unit 230. With the ability to generate

  In addition, when the model parameter database 240 does not have the previous model parameter 5, the model creation unit 300 uses the model parameter newly generated by a random number or the like and the measurement signal 4 transmitted from the switching unit 230 and uses the model 400. Have the ability to generate

  The model creation unit 300 stores the newly created model parameter as the current model parameter 6 in the model parameter database 240.

  The model creation unit 300 is connected to the learning unit 500, extracts model parameters 7 necessary for learning from the model parameter database 240, and transmits them to the learning unit 500.

  The learning unit 500 obtains the model parameters 7 stored in the model parameter database 240 via the model creation unit 300.

  The learning unit 500 learns and generates a model input 12 to be input to the model 400 using the model parameter 7 and the model output 13.

  In the learning unit 500, the model parameter 7 in the model 400 is updated via the model input 12 and the model output 13, and the updated learning information is transmitted to the model parameter database 240 as the updated model parameter 10.

  The estimation unit 600 installed in the coal type discrimination device 200 receives the measurement signal 8 and the switching signal 20 transmitted from the switching unit 230 when “estimation” is input to the switching unit 230 by the switching signal 20. Similarly, a model output 14 obtained by being simulated by the model 400 to which the model parameter 7 for estimation is transmitted from the model creation unit 300 received is obtained, and the estimation signal 9 is generated.

  The estimation signal 9 generated by the estimation unit 600 is transmitted to the determination unit 700 and the external output interface 270 installed in the coal type determination device 200.

  The discriminating unit 700 calculates the coal type discrimination and the coal mixing rate based on the estimation signal 9 obtained from the estimation unit 600, and transmits the discrimination signal 15 of the coal type and the coal mixing rate obtained as a result of the calculation to the external output interface 270. To do.

  An operator of the control target 100 that is a coal-fired boiler uses an input device 900 including a keyboard 901 and a mouse 902, and a maintenance tool 910 connected to the image display device 950, so that the coal type discrimination device 200 can be used. Information stored in various databases provided can be accessed.

  The maintenance tool 910 includes an external input interface 920, a data transmission / reception processing unit 930, and an external output interface 940.

  The input signal 31 generated by the input device 900 is taken into the maintenance tool 910 via the external input interface 920. The data transmission / reception processing unit 930 acquires the database information 30 provided in the coal type discrimination device 200 according to the information of the input signal 32 input via the external input interface 920.

  The data transmission / reception processing unit 930 transmits an output signal 33 obtained as a result of processing the database information 30 of the coal type discrimination device 200 to the external output interface 940 and outputs the output signal 34 from the external output interface 940 to the image display device 950. And display.

  In the coal-fired boiler coal type discriminating apparatus of this embodiment, all the databases are arranged inside the coal type discriminating apparatus 200, but these can be arranged outside the coal type discriminating apparatus 200. In this embodiment, all the signal processing functions for generating the output signal 51 are arranged inside the coal type discriminating apparatus 200, but these may be arranged outside the coal type discriminating apparatus 200.

  Next, for the coal-fired boiler coal type discriminating apparatus that is an embodiment in which the present invention is applied to a thermal power plant equipped with a coal-fired boiler, information stored in a database installed in the coal type discriminating apparatus of the present embodiment, The signal processing function will be described.

  First, the mechanism of the thermal power plant power generation provided with the coal-fired boiler of the controlled object 100 will be described with reference to FIG.

  In FIG. 2, fuel coal is supplied to a mill 110 via a coal feeder 112 from a coal bunker 111 storing coal. In the mill 110, the coal is finely pulverized by an internal roller into pulverized coal, and the furnace 101 is passed through a burner 102 installed in the furnace 101 constituting the coal-fired boiler together with primary air for transporting coal and secondary air for combustion adjustment. The pulverized coal as fuel is burned in the furnace 101.

  The fuel pulverized coal and the primary air are led from the pipe 134 and the secondary air is led from the pipe 141 to the burner 102, and after-air for two-stage combustion is introduced into the furnace 101 through the after-air port 103 installed in the furnace 101.

  This after air is guided from the pipe 142 to the after air port 103.

  High-temperature combustion gas generated by burning fuel coal in the furnace 101 flows downstream along the path indicated by the arrow in the furnace 101 and passes through a heat exchanger 106 disposed in the furnace 101. After heat exchange, it becomes combustion exhaust gas, is discharged from the furnace 101, and flows down to the air heater 104 installed outside the furnace 101.

  The combustion exhaust gas that has passed through the air heater 104 is then released from the chimney to the atmosphere after removing harmful substances contained in the combustion exhaust gas with an exhaust gas treatment device (not shown).

  The feed water circulating in the furnace 101 is led to the furnace 101 through the feed water pump 105 from the condenser 113 that condenses the steam that has passed through the turbine 108 into the condensate, and the heat exchanger 106 installed in the furnace 101 contains the inside of the furnace 101. It is heated by the combustion gas flowing down and becomes high-temperature and high-pressure steam. In this embodiment, the number of heat exchangers 106 is shown as one, but a plurality of heat exchangers may be arranged.

  The high-temperature and high-pressure steam generated in the heat exchanger 106 is guided to the steam turbine 108 via the turbine governor valve 107, and the steam turbine 108 is driven by the energy of the steam, and the generator 109 connected to the steam turbine 108 is connected to the generator 109. Rotate to generate electricity.

  For example, FIG. 2 shows various measuring instruments for detecting the state quantity, which is the operating state of the thermal power plant. FIG. 2 shows a temperature path for supplying steam generated by the heat exchanger 106 disposed in the furnace 101 to the steam turbine 108. A measuring instrument 151 and a pressure measuring instrument 152 are installed to measure the temperature T and pressure P of the steam.

  In addition, a flow rate measuring device 150 is installed in a path for supplying this condensate to the heat exchanger 106 from a condenser 113 that cools the steam flowing down the steam turbine 108 and condenses it into condensate. The flow rate of water is measured, and the generator 109 is provided with a generation output measuring instrument 153 to measure the amount of power generated by the generator 109.

  Further, the furnace 101 is provided with a concentration measuring device 154 for measuring NOx concentration and / or CO concentration in combustion gas generated by burning pulverized coal of fuel inside the furnace 101.

  In general, many measuring instruments other than those shown in FIG. 2 are arranged in the thermal power plant, but the illustration is omitted here.

  Information on various state quantities of the controlled object 100 that is a coal-fired boiler measured by these various measuring instruments described above is transmitted to the coal type discriminating apparatus 200 as measurement information 1.

  The coal type determined by the calculation of the coal type discriminating apparatus 200 or the coal mixture rate is input to the boiler control apparatus 1000, and is processed by the boiler control apparatus 1000 to generate a command signal for the controlled object 100 that is a coal-fired boiler. Based on this, the air dampers 160, 161, 162, and 163 described below, which are the operation ends of the coal-fired boiler, are respectively operated, and the coal-fired boiler can be efficiently operated according to the type of coal or the coal mixture ratio.

  Next, primary air and secondary air introduced into the furnace 101 from the burner 102 installed in the furnace 101 of the coal-fired boiler that is the control target 100, and into the furnace 101 from the after air port 103 installed in the furnace 101. The route of the after-air to be input will be described.

  The primary air is guided from the fan 120 to the pipe 130, and is branched into a pipe 132 that passes through the inside of the air heater 104 and a pipe 131 that bypasses the air heater 104, and flows down the pipe 132 and the pipe 131. The primary air joins again through the pipe 133 and is guided to the mill 110.

  The air passing through the air heater 104 is heated by the combustion exhaust gas discharged from the furnace 101, and pulverized coal generated by the mill 110 is conveyed to the burner 102 through the pipe 133 using this primary air.

  The secondary air and the after air are led from the fan 121 to the pipe 140 and flow down the pipe 140 passing through the inside of the air heater 104 and heated, and then the secondary air pipe 141 on the downstream side of the pipe 140, The pipe is branched to an after-air pipe 142 and led to a burner 102 and an after-air port 103 installed in the furnace 101, respectively.

  In the thermal power plant including the coal-fired boiler that is the control target 100 shown in FIG. 2, the above-described various measuring devices that detect the operating state of the thermal power plant are arranged and acquired from these measuring devices. The measurement signal 1 indicating the state quantity of the thermal power plant of the controlled object 100 is configured to be input to the external input interface 210 installed in the coal type discrimination device 200.

  Further, as shown in FIG. 3, an air damper 162 and an air damper 163 are provided in the secondary air pipe 141 and the after-air pipe 142 branched on the downstream side of the pipe 140 disposed in the air heater 104. Similarly, an air damper 161 and an air damper 160 are respectively disposed on the pipe 132 disposed inside the air heater 104 and the pipe 131 bypassing the air heater 104.

  By operating these air dampers 160, 161, 162, and 163, the areas through which air passes in the pipes 131, 132, 141, and 142 are changed, and the air dampers 160, 161, 162, and 163 pass through these pipes 131, 132, 141, and 142. The air flow rate supplied to the furnace 101 is individually adjusted.

  And the output signal 51 of the coal type judged in the coal type discrimination | determination apparatus 200 based on the measurement signal 1 which shows the state quantity of the thermal power plant provided with the coal burning boiler input from the control object 100 is output, and this output signal 51 The operation of the coal fired boiler 100 is controlled by operating operating devices such as the water supply pump 105, the mill 110, and the air dampers 160, 161, 162, and 163 based on the above.

  Next, information stored in the measurement signal database 220 and the estimation signal database 230 installed in the coal type discrimination device 200 constituting the coal type discrimination device of the coal burning boiler of the present embodiment will be described.

  FIG. 4 is a diagram for explaining a mode of information stored in the measurement signal database 220 installed in the coal type discrimination apparatus 200 of the coal burning boiler according to the present embodiment, and FIG. 5 is a coal burning boiler according to the present embodiment. It is a figure explaining the outline of the model structure of the model 400 installed in the charcoal type discrimination device 200.

  As shown in FIG. 4, in the measurement signal database 220 of the coal type discrimination device 200, information of measurement signal data that is the measurement signal 1 indicating the state quantity measured by the coal-fired boiler 100 to be controlled is installed. Each measured instrument is input via the external input interface 210 and stored together with each measurement time.

  For example, the flow rate value F and the temperature value T measured by the flow rate measuring device 150, the temperature measuring device 151, the pressure measuring device 152, the power generation output measuring device 153, and the concentration measuring device 154 installed in the thermal power plant shown in FIG. The pressure value P, the power generation output value E, and the NOx concentration D contained in the combustion gas are stored in the measurement signal database 220 of the coal type discrimination device 200 together with time information.

  In the measurement signal data shown in FIG. 4, data is stored at a cycle of 1 second, but the sampling cycle of data collection can be arbitrarily set.

  In order to make it easy to use the measurement signal data stored in the measurement signal database 220, each measurement signal data is assigned a unique number called a PID number.

  Similarly, the information stored in the estimated signal database 250 is also calculated when the signal estimated to remove the noise component or processed by the estimation unit 600, as shown in the model structure of the model 400 in FIG. Various signals are stored in the estimated signal database 250 together with time information.

  The model creation unit 300 installed in the coal type discrimination device 200 sets model parameters in the model 400 according to the switching signal 20. If the switching signal 20 is “model creation”, the model parameter 7 necessary for newly constructing a model is output from the model creation unit 300 to the model 400 to set a new model.

  When utilizing the past model parameters, the past model parameters stored in the model parameter database 240 are loaded. If the switching signal 20 is “estimation”, the model parameter 7 of the model 400 used for estimation is loaded from the model parameter database 240 into the model 400 via the model creation unit 300.

  Next, the operation of the model 400 and the learning unit 500 installed in the coal type discriminating apparatus 200 constituting the coal type discriminating apparatus of the coal burning boiler according to the present embodiment will be described.

  FIG. 5 is a diagram for explaining the model structure of the model 400. This model structure is composed of an input layer, a mapping layer, a bottleneck layer, a demapping layer, and an output layer, and has a structure in which nodes of each layer are mutually coupled.

  The node portion uses a linear or nonlinear function, but generally uses a sigmoid function. Each node connection has a weighting coefficient, and represents the strength of the mutual relationship between the nodes. Normally, the model parameter refers to this weighting factor.

  As an input signal for the model 400, a related measurement signal taken from the controlled object 100, which is a coal-fired boiler, is input. In the case of coal type, a measurement signal related to the heat absorption amount may be selected. For example, the temperature and pressure near the heat exchanger 106 in the furnace 101.

  Also, the amount of water contained in the coal storage area varies depending on the weather. If the moisture content is different, the combustion method is different even for the same coal type, so that it becomes an important input signal candidate for the model 400. However, it is not limited to this.

  The learning unit 500 determines model parameters for the model 400. As a technique, a teacher signal is given to the output signal of the model, and the parameter is corrected so that the absolute value or the square error of the difference becomes small. In general, such a parameter correction method is called learning.

  The model 400 uses a self-associative neural network having five layers and a symmetrical number of nodes around the bottleneck layer as shown in FIG. Since the structure of the self-associative neural network and the learning method thereof are well-known techniques, the following “MA Kramer: Nonlinear Principal Component Analyzing Neural Networks, AlChE J. Vol. 2, 1991 "is shown as a reference.

  The feature of the self-associative neural network is that the same signal as the input signal is given as a teacher signal. When an input signal is given to the model 400, the same signal as the input signal is obtained as an output signal by learning.

  Thereby, a non-linear relationship between input signals can be established in the model 400. In general, the number of bottleneck layers is generally smaller than the number of input signals, and this also has the function of extracting only the main components of the input signals. Therefore, if this model 400 is prepared for each coal type, an estimation model for each coal type can be constructed.

  A sigmoid function, which is a general function, may be used for the nodes of the model 400, but the measurement signal of the plant has many fluctuation elements, and the number of data is also scattered. Is often appropriate. Therefore, a model 400 using a Gaussian function is applied to each node. In this case, the average and variance of each node are added as parameters. The learning method is also described in the above-mentioned reference as a Radial Basis Function network.

  FIG. 6 is a plot of the relationship between the coal type and the measurement signal A, which is the output value of the node. The number of points that can be plotted on the graph varies depending on the plant conditions. For example, in a new plant, it is obtained from design value information, but the number of data is small. On the other hand, the number of data increases in a plant with many years of operation.

  Thus, since the difference in the number of data occurs depending on the plant situation, a distribution is assumed for each data, and the difference in the number of data is expressed by the shape of the distribution. When the number of data is small, since the variance is large, the distribution becomes wide. When the number of data is large, the distribution is small and the distribution is sharp.

  If there is prior information on the data, the distribution shape can be assumed. However, in the case of new data or the like, it is necessary to estimate the distribution based on the data obtained without the prior information. There are many known methods for estimating a distribution only from data, but a normal distribution may be assumed from a central limit theorem that the distribution approaches a normal distribution as the number of data increases regardless of the population distribution.

  If the distribution can be assumed, the shape can be determined from the mean and the variance. The assumption of the normal distribution based on the central limit theorem is described in detail, for example, in “Introduction to Statistics, Department of Statistics, Faculty of Liberal Arts, The University of Tokyo, Tokyo University Press, Published July 10, 1991”.

  From the above viewpoint, it is more appropriate to use a Gaussian function for each node function. In addition, there is no case where a Gaussian function is applied to the basis function of the self-associative neural network, and this combination makes it possible to construct an estimation model that reflects the number of data and is robust to plant fluctuations.

  FIG. 7 is a diagram illustrating a flowchart of arithmetic processing in the learning unit 500 for creating the model 400 installed in the coal type discriminating apparatus 200 constituting the coal type discriminating apparatus of the coal burning boiler of the present embodiment. It should be noted that parameters necessary for executing this flowchart are stored in the model parameter database 240. The form of information stored in the model parameter database 240 will be described later.

  As shown in FIG. 7, in step 401, it is selected whether to use a model parameter set in the past or to create a new model parameter.

  When a new model parameter is created, the initial value of the model parameter is set using a random number in step 402.

  Next, in step 403, the measurement signal 4 that is the input signal of the model 400 and the teacher signal is extracted from the measurement signal database 220.

  In step 404, the learning unit 500 sets parameters necessary for learning such as the number of learning, the learning coefficient, and the number of nodes. When a new model parameter is created, a default value stored in the model parameter database 240 is used.

  In step 405, the learning unit 500 sequentially updates the model parameters from the initial values by learning. As a method for updating the model parameters by learning, the Back Propagation method or the like is used. This learning method is described in detail in “Neural network and measurement control, edited by Nishikawa and Kitamura, Asakura Shoten, published January 25, 1995”.

  Basically, the model parameter is updated in the learning unit 500 so that the difference between the output signal when the input signal is given to the model 400 and the teacher signal is eliminated. The difference between the output signal from the model 400 and the teacher signal is generally expressed by a square error and is called an evaluation function. A variation of the evaluation function when each model parameter is varied is subjected to partial differential calculation, and a value obtained by multiplying the obtained value by the learning coefficient is used as an update of the model parameter.

  When this is repeated in the learning unit 500, the difference between the output signal of the model 400 and the teacher signal disappears, and the evaluation function approaches zero. When the evaluation function approaches zero, the partial differential value also approaches zero, and the update amount of the model parameter approaches zero.

  In the numerical calculation, since it is never completely zero, in step 406, when the evaluation function is equal to or less than the set value, it is considered that learning in the learning unit 500 is completed, and the model creation is ended. If the learning end condition is not satisfied, the iterative calculation is stopped when the number of learning repetitions reaches the set number of times, and the process returns to step 404 to set the learning parameters again.

  If the use of the past model parameter is selected in step 401, it is selected in step 407 whether or not the past model parameter is set as an initial value and corrected by learning. In the case of correction, the process proceeds to step 403. If not corrected, since the past model parameters are used as they are, it is not necessary to reconstruct the model 400, and the model creation ends.

  In this embodiment, a radial basis function network using a Gaussian function for a node is used, but a network model using another basis function is used from the situation of the plant to be controlled and the characteristics of the measurement signal. Also good.

  FIG. 8 is a diagram for explaining the form of information stored in the model parameter database 240 installed in the coal type discriminating apparatus 200 constituting the coal type discriminating apparatus of the coal burning boiler of the present embodiment.

  In FIG. 8, the model parameter database 240 includes a plurality of coal types, IDs corresponding to these coal types, creation date / time, learning coefficient, learning frequency, end condition, number of nodes (input / output layer, mapping / decoding). Specific examples of mapping layer, bottleneck layer) and parameter values are shown.

Here, the parameter value is a parameter for determining a weighting coefficient and a basis function. The weighting factors are the mutual couplings of the nodes and are stored as W ₁₁ , W ₁₂ ,. The parameters that determine the basis function are, for example, a slope and an input side translation amount in the case of a sigmoid function, and a center value, a variance value, and an input signal translation amount in the case of a Gaussian function. The ID value of 000 indicates the default value of the learning parameter when a new model parameter of the corresponding coal type is created. The number of nodes and parameter values are usually blank for new creation.

  Next, the operation of the model 400 and the estimation unit 600 installed in the coal type discriminating apparatus 200 constituting the coal type discriminating apparatus of the coal burning boiler according to the present embodiment will be described with reference to FIG. The estimation unit 600 calculates the estimated degree of each coal type based on the measurement signal 2 obtained from the control object 100.

  In FIG. 1, first, when the switching signal 20 becomes “estimation”, the model parameter 7 used for estimation of each coal type is set in the model 400 from the model creation unit 300.

  In addition, the measurement signal 8 stored in the measurement signal database 220 is input to the model 400 and the estimation unit 600 from the switching unit 230.

  In the model 400, the measurement signal 8 is input as an input signal to the model of each coal type constructed by the model parameter 7 set by the model creation unit 300. As a result, the output signal obtained by the calculation of the model 400 is transmitted to the estimation unit 600 as the model output 14.

  The estimation unit 600 calculates the difference between the model output 14 and the measurement signal 8 for each time, and outputs the difference together with the model output 14 to the determination unit 700 as the estimation signal 9. The determination unit 700 determines the coal type determined by the following calculation and outputs the determined coal type to the external output interface 270 and the estimated signal database 250.

  Next, the operation of the determination unit 700 will be described in detail. The determination unit 700 determines the coal type and the coal mixture rate based on the estimation signal 9 input from the estimation unit 600. The estimation signal 9 includes a difference between the model output 14 and the measurement signal 8 when the measurement signal 8 is input to the model 400 for each coal type.

  Since the model 400 is prepared for each coal type and the relationship at that time is modeled, there is almost no difference between the output signal of the model 400 that is the same as the coal type of the measurement signal 8 and the measurement signal 8. That is, the determination unit 700 may determine which coal type is based on the magnitude of the estimation signal 9. However, if this type of judgment is simply determined by setting a threshold, the noise component added to the measurement signal for some reason when transmitting the measurement signal that detects the state value of the coal-fired boiler, In other words, it is affected by fluctuations and fluctuations peculiar to the plant such as sudden fluctuations in measurement signals that occur in measurement objects such as pressure and flow rate. Therefore, the determination unit 700 uses the log likelihood ratio shown in Equation (1) for the determination of the coal type and the coal mixture ratio.

In the equation (1), Xn is the value of the estimated signal 9 at time n. For example, H0 represents a hypothesis that is established for coal type A, and H1 represents a hypothesis that is not coal type A. That is, P (Xn | H ₀ ) represents the probability that Xn is coal type A, and P (Xn | H ₁ ) represents the probability that coal type A is not. The probability distribution of H ₀ and H ₁ is generally expressed by a normal distribution, for example, and the center value and variance are set based on the characteristics of the coal type.

  For example, it is appropriate to set based on the distribution chart showing the relationship between each coal type and the node output value shown in FIG. In the equation (1), the estimated signal 9 becomes large, that is, the value of the equation becomes positive when approaching a distribution that is not coal type A. Conversely, when the estimated signal 9 becomes small, the value of the expression (1) becomes negative. Therefore, if the state other than the coal type A continues, the value of the expression (1) increases. When this value increases, it is determined that it is not coal type A when it becomes larger than the value determined by the following equation (2).

  In equation (2), α is the probability of false detection, and β is the probability of detection failure. In general, both are set to 0.001. Moreover, if it becomes smaller than the value determined by the following formula (3), it is determined as coal type A.

  In this method, when the same state is continued, the value of the equation (1) changes, and therefore, a noise component added to the measurement signal for some reason when transmitting the measurement signal detecting the state value of the coal fired boiler In addition, fluctuations and fluctuations peculiar to a coal-fired boiler plant such as sudden fluctuations in measurement signals such as pressure and flow rate are small and hardly affected by the change in the value of equation (1).

  In the determination of the coal type in the determination unit 700, calculation is performed for each input signal. Therefore, for the model 400 for each coal type, the model 400 having the largest number of corresponding input signals in the above determination for each input signal is selected. Then, the coal type simulated by the model 400 is determined as the current coal type.

  It is also possible to determine the type of coal by the above-described method using the sum of the estimated signals 9 or the average value as Xn.

  Next, when the fuel coal is a mixture of two or more types of coal, the determination of the type of coal in the determination unit 700 and the method for determining the coal mixture rate will be described.

  When two or more coal types are mixed as coal, it is determined by the above-described method that two or more coal types correspond.

  For example, assuming that coal type A and coal type B correspond to the mixed coal types, the judgment unit 700 sums up the difference of the estimated signals 9 for each input signal of coal type A, and the input signal of coal type B The difference of the estimated signal 9 for each is summed. The sum of these two values is used as the denominator, and each value is used as the numerator, so the relative ratio can be obtained.

  It is also possible to calculate using an average value or a median value instead of the total value. If the median value is used, even if sudden fluctuation peculiar to the plant occurs, the influence is small. Therefore, a method using the total value, the average value, and the median value is applied according to the characteristics of the target plant.

  Next, as shown in FIG. 9, the estimated signal database 250 installed in the coal type discriminating apparatus 200 constituting the coal type discriminating apparatus of the coal-fired boiler of this embodiment includes, for example, a plurality of coal types, The PID for each species, the input signal, the model output 14, and the estimated signal 9 are stored for each time.

  The external output interface 270 transmits the coal type determined by the determination unit 700 and the calculated coal mixture rate as an output signal 51 to the maintenance tool 910.

  Next, in the coal type determination apparatus for the coal-fired boiler according to the present embodiment, the operator of the thermal power plant including the coal-fired boiler that is the control target 100 uses the maintenance tool 910 to determine the charcoal that the image display device 950 has determined. The method of displaying the seed, the coal mixture rate, and the information of each database will be described.

  FIGS. 10-14 is an Example of the screen displayed on the image display apparatus 950 installed in the coal type discrimination | determination apparatus of the coal burning boiler of a present Example. The operator uses the keyboard 901 of the input device 900 or the mouse 902 to perform an operation such as inputting a parameter value in a blank area on these screens.

  FIG. 10 is an initial screen displayed on the image display device 950. The operator selects a necessary button from the learning condition setting button 951, the estimation condition setting button 952, and the information display button 953 shown in FIG. 10, moves the cursor 954 using the mouse 902, and clicks the mouse 902. To select and press the required button.

  FIG. 11 is a diagram illustrating a learning condition setting screen in the coal type discriminating apparatus 200 constituting the coal type discriminating apparatus of the coal burning boiler according to the present embodiment. When the operator clicks the learning condition setting button 951 with the mouse in FIG. 10, the screen in FIG. 11 is displayed.

  The operator inputs settings necessary for the model 400 for each coal type. The coal type is selected in the coal type switching menu 963 displayed on the upper right of the screen of FIG. In the model generation field 961 of the screen of FIG. 11, the learning coefficient, the number of learnings, and the end condition necessary for executing the learning process flowchart in the learning unit 500 shown in FIG. It is possible to modify the values entered in or already entered.

  Also, using this function, the operator can change the default value whose ID is 000. In the model structure field 962 of the screen in FIG. 11, the structure of the model 400, the types of basis functions to be set for the nodes, and values necessary for setting the parameters are input.

  When the save button 964 displayed at the bottom of FIG. 11 is clicked, the information input in the model generation field 961 and the model structure field 962 is stored in the model parameter database 240 in the coal type discriminating apparatus 200 in FIG. It is stored for each coal type entered in the switching menu 963.

  Further, the information input to the model generation field 961 and the model structure field 962 is set to “model learning” in the switching signal 20 and transferred to the model creation unit 300 in the coal type discrimination device 200 of FIG. The

  When a cancel button 965 displayed at the bottom of FIG. 11 is clicked, information input in the model creation field 961, the model structure field 962, and the coal type switching menu 963 is cancelled. Further, when the return button 966 is clicked, the screen returns to the screen of FIG.

  FIG. 12 is a diagram illustrating an estimation condition setting screen in the coal type discriminating apparatus 200 constituting the coal type discriminating apparatus of the coal burning boiler according to the present embodiment. In FIG. 10, when the operator clicks the estimation condition setting button 952 with the mouse, the screen of FIG. 12 is displayed.

  The operator selects a coal type in the estimation coal type switching menu 973 displayed on the upper right of the screen of FIG. 12 for the model 400 used for estimation for each coal type. The model generation information column 971 on the screen of FIG. 12 displays the model-specific ID of the selected coal type, the learning coefficient used for learning, the number of learnings when learning is completed, and the learning error. The model 400 whose ID is 000 is not displayed.

  In the model structure information column 972 of the screen of FIG. 11, the structure of the selected model 400, basis functions, and information on parameters set to the basis functions are displayed. In the discrimination setting value column 977, the probability of erroneous detection and the probability of detection failure are input.

  When the transfer button 974 displayed at the bottom of FIG. 12 is clicked, information input to the model generation information column 971, the model structure information column 972, and the discrimination setting column 977 is stored in the coal type discrimination device 200 of FIG. “Estimation” is set in the switching signal 20 and is transferred to the model creation unit 300. The model creation unit 300 sets the model parameter 7 in the estimation unit 600 based on the transferred information.

  When a cancel button 975 displayed at the bottom of FIG. 12 is clicked, information input to the model creation information column 971, the model structure information column 972, and the estimated coal type switching menu 973 is cancelled. In addition, when the return button 976 is clicked, the screen of FIG. 10 is restored.

  FIG. 13 shows an image display device 950 displaying information stored in the measurement signal database 220 and the estimation signal database 250 in the coal type discrimination device 200 constituting the coal type discrimination device of the coal burning boiler of this embodiment. Therefore, this is a screen for setting the conditions.

  When the operator clicks the information display button 953 with the mouse in FIG. 10, FIG. 13 is displayed.

  The operator inputs a measurement signal or an operation signal to be displayed on the image display device 950 together with its range (upper limit / lower limit) in the input field 981 of FIG. In addition, the time to be displayed is input in the time input field 982.

  By clicking a display button 983 displayed at the bottom of FIG. 13, a trend graph as shown in FIG. 14 is displayed on the image display device 950. Further, when the return button 991 displayed at the bottom of FIG. 14 is clicked, the screen of FIG. 13 is restored.

  Further, the user can return to the screen of FIG. 10 by clicking a return button 984 displayed at the bottom of FIG.

  In addition to the images described above, any information stored in the database in the coal type discrimination device 200 can be displayed on the image display device 950 in any manner.

  According to the above-described embodiment, the type of coal is discriminated accurately and quickly in consideration of fluctuations peculiar to the plant of the coal-fired boiler generated in the measured state quantity of the coal-fired boiler. It is possible to realize a coal type identification device for a coal-fired boiler and a coal type identification method for a coal-fired boiler that enable operation of the boiler.

  The present invention is applicable to a coal-fired boiler type identification apparatus and a coal-fired boiler type identification method.

The control block diagram which shows schematic structure of the coal type discrimination | determination apparatus of the coal burning boiler which is one Example of this invention. The schematic block diagram of the thermal power plant provided with the coal burning boiler to which the coal type discrimination | determination apparatus of the Example of this invention shown in FIG. 1 is applied. The fragmentary figure which shows the air heater of the thermal power plant provided with the coal burning boiler shown in FIG. Explanatory drawing which shows the aspect of the data memorize | stored in the measurement signal database installed in the coal kind discrimination | determination apparatus of the coal burning boiler which is an Example of this invention shown in FIG. Explanatory drawing which shows the structure of the model installed in the coal type discrimination | determination apparatus of the coal burning boiler which is the Example of this invention shown in FIG. Explanatory drawing which shows the relationship between the coal type used as the modeling object installed in the coal type discrimination | determination apparatus of the coal burning boiler which is the Example of this invention shown in FIG. 1, and a node output. The flowchart which shows the operation | movement in the model preparation part installed in the coal kind discrimination | determination apparatus of the coal burning boiler which is an Example of this invention shown in FIG. Explanatory drawing which shows the aspect of the data memorize | stored in the model parameter database installed in the coal type discrimination | determination apparatus of the coal burning boiler which is an Example of this invention shown in FIG. Explanatory drawing which shows the aspect of the data memorize | stored in the estimation signal database installed in the coal kind discrimination | determination apparatus of the coal burning boiler which is the Example of this invention shown in FIG. The initial screen displayed on the image display apparatus installed in the coal kind discrimination | determination apparatus of the coal burning boiler which is the Example of this invention shown in FIG. The first half screen of the learning condition setting screen displayed on the image display apparatus installed in the coal type discrimination | determination apparatus of the coal burning boiler which is an Example of this invention shown in FIG. The first half screen of the estimation condition setting screen displayed on the image display apparatus installed in the coal type discrimination device of the coal burning boiler which is the embodiment of the present invention shown in FIG. The display information setting screen displayed on the image display apparatus installed in the coal kind discrimination | determination apparatus of the coal burning boiler which is an Example of this invention shown in FIG. The trend graph of the measured value displayed on the image display apparatus installed in the coal kind discrimination | determination apparatus of the coal burning boiler which is the Example of this invention shown in FIG.

Explanation of symbols

  100: control target, 200: coal type discriminating device, 210: external input interface, 220: measurement signal database, 230: switching unit, 240: model parameter database, 250: estimation signal database, 260: learning parameter database, 300: model Creation unit, 400: model, 500: learning unit, 600: estimation unit, 700: determination unit, 900: input device, 901: keyboard, 902: mouse, 910: maintenance tool, 920: external input interface, 930: data transmission / reception Processing unit, 940: external output interface, 950: image display device.

Claims (14)

In the coal fired boiler coal type discriminating device that calculates the coal type or coal mixture ratio used in the coal fired boiler based on the value of the state quantity measurement signal obtained from the controlled coal fired boiler,
The coal type discrimination device provided an operation signal to an external input interface for capturing the measurement signal from the control target, a measurement signal database for storing the measurement signal captured from the control target, and a coal-fired boiler to be controlled. A model that estimates the value of the measurement signal of the coal type that is sometimes obtained for each coal type, and a method of generating a model input that is given to the model so that the model output estimated by the model approaches the measurement signal from which noise has been removed A learning unit; an estimation unit that calculates a difference between the measurement signal stored in the measurement signal database and the measurement signal estimated by the model reflecting the learning result; and the calculation unit that calculates the estimation unit. A coal type discriminating device for a coal-fired boiler, comprising a judgment unit that determines a coal type or a coal mixture ratio based on an estimated signal . In the coal fired boiler coal type discriminating device that calculates the coal type or coal mixture ratio used in the coal fired boiler based on the value of the state quantity measurement signal obtained from the controlled coal fired boiler,
The coal type discrimination device provided an operation signal to an external input interface for capturing the measurement signal from the control target, a measurement signal database for storing the measurement signal captured from the control target, and a coal-fired boiler to be controlled. Learn the model that estimates the value of the measurement signal of the coal type that is sometimes obtained for each coal type, and how to generate the model input that is given to the model so that the output of the model estimated by the model approaches the measurement signal from which noise has been removed A learning unit that calculates a difference between a measurement signal stored in the measurement signal database and a measurement signal estimated by the model as an estimation signal, the estimation signal calculated by the estimation unit, and its log likelihood A coal type discrimination device for a coal-fired boiler, comprising a judgment unit that determines a coal type or a coal mixture ratio based on a ratio. In the coal type discrimination device for a coal-fired boiler according to claim 1 or claim 2,
The determination unit installed in the coal type discrimination device is configured to determine a coal type or a coal mixture rate based on the estimation signal calculated by the estimation unit and its log likelihood ratio. Coal-fired boiler type identification device. In the coal type discrimination device of the coal fired boiler according to claim 1,
The determination unit installed in the coal type discriminating apparatus calculates the absolute value of the difference between the measurement signal stored in the measurement signal database and the measurement signal estimated by the model for each coal type, and the sum of the absolute values A coal type determination apparatus for a coal-fired boiler, wherein the coal type or coal mixture ratio is determined based on a relative ratio using at least one of a value, an average value, and a median value. In the coal classification apparatus of the coal fired boiler described in any one of Claims 1 thru | or 4,
The coal type discriminating apparatus includes a user interface for inputting at least one of parameters for determining a model structure, a basis function type, and a basis function shape to the coal type discriminating apparatus as an external input function. A coal type discrimination device for coal-fired boilers. In the coal type discrimination device for a coal fired boiler according to any one of claims 1 to 5,
The coal type discriminating device includes a measurement signal related to a heat absorption amount of a furnace, which is a measurement signal of a state quantity obtained from a coal-fired boiler to be controlled, taken from an external input interface, and a measurement signal related to moisture of coal. A coal type discrimination device for a coal-fired boiler, comprising a model creation unit that creates the model using at least one. In the coal type discrimination device for a coal-fired boiler according to claim 1 or claim 2,
The model provided in the coal type discriminating device is a self-associative neural network as a model for estimating the value of the measurement signal of the coal type for each coal type based on the measurement signal stored in the measurement signal database. And is configured to calculate an estimated value of the measurement signal for each coal type, and the estimation unit is configured to calculate a difference between the measurement signal and an estimated value of the measurement signal obtained from the model. An apparatus for discriminating the type of coal in a coal-fired boiler. In the coal type discrimination device for a coal-fired boiler according to claim 6 or claim 7,
The coal type discriminating apparatus includes a display device that displays at least one of a measurement signal, an estimated value for each coal type, a difference between the measurement signal and the estimated value, a coal type, and a coal mixture rate as time passes. An apparatus for discriminating coal types of a coal-fired boiler. In the method of determining the coal type of the coal-fired boiler that calculates the coal type or coal mixture ratio used in the coal-fired boiler based on the value of the measurement signal of the state quantity obtained from the coal-fired boiler to be controlled,
The measurement signal captured from the control object is stored in a measurement signal database, and the value of the measurement signal of the coal type obtained when an operation signal is given to the control object is estimated for each coal type using a model, and the model The model output estimated by the method is trained to generate a model input to be given to the model so as to approach the measurement signal from which noise is removed, and the measurement signal stored in the measurement signal database and the learning result are reflected to reflect the model. A method for determining a coal type of a coal-fired boiler, comprising: calculating a difference from the measurement signal estimated by the step S1 to estimate the difference as a presumed signal; and determining a coal type or a coal mixture rate based on the estimated signal. In the method of determining the coal type of the coal-fired boiler that calculates the coal type or coal mixture used in the coal-fired boiler based on the value of the measurement signal obtained from the controlled object,
The measurement signal captured from the control object is stored in a measurement signal database, and the value of the measurement signal of the coal type obtained when an operation signal is given to the control object is estimated for each coal type using a model, and the model The model output estimated by the method is trained to generate a model input to be given to the model so as to approach the measurement signal from which noise is removed, and the measurement signal stored in the measurement signal database and the learning result are reflected to reflect the model. Of a coal-fired boiler characterized by calculating a difference from a measurement signal estimated by the above and estimating it as an estimated signal, and determining a coal type or a coal mixture ratio based on the estimated signal and its log likelihood ratio Charcoal type identification method. In the method for determining the coal type of the coal-fired boiler according to claim 9 or claim 10,
The difference between the measurement signal stored in the measurement signal database and the estimated value of the estimated measurement signal is calculated as an absolute value of both of the total value, average value, and median value of the absolute values. A method for determining a coal type of a coal-fired boiler, wherein a coal type and a coal mixture ratio are determined based on a relative ratio using at least one. In the coal fired boiler type identification method according to any one of claims 9 to 11,
At least one of the measurement signal related to the heat absorption amount of the furnace and the measurement signal related to the moisture content of the coal among the measurement signals obtained from the coal fired boiler, and the measurement signal related to the heat absorption amount of the furnace, and A method for discriminating a coal type of a coal-fired boiler, wherein the model is created using at least one of measurement signals related to moisture of coal. In the method for determining the coal type of the coal-fired boiler according to claim 9 or claim 10,
In the model, based on the measurement signal stored in the measurement signal database, the measurement signal for each coal type using a self-associative neural network as a model for estimating the value of the measurement signal of the coal type for each coal type. A method for discriminating the type of coal in a coal-fired boiler, characterized in that an estimated value is calculated. In the method for determining the coal type of the coal-fired boiler according to claim 9 or claim 10,
Coal type identification of a coal-fired boiler, characterized in that at least one of a measurement signal, an estimated value for each coal type, a difference between the measurement signal and the estimated value, a coal type, and a coal mixture rate is displayed on a display device over time Method.

Images