Index value calculation device, index value calculation method, and index value calculation program

Abstract

To calculate an index value related to corrosion of a heat transfer pipe from easily obtainable data.SOLUTION: An index value calculation device (1) comprises a content determination unit (101) for determining the sulfur content and chlorine content of fuel for a boiler, and an index value calculation unit (103) for calculating an index value related to corrosion of a heat transfer pipe from the sulfur content and the chlorine content determined by the content determination unit (101), by using a learned model (113).SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an index value calculation device and the like that calculates an index value related to corrosion of a heat transfer tube that recovers exhaust heat in a boiler. [Background technology]

[0002] In boilers installed in power plants that generate electricity using the waste heat from burning fuel, the waste heat is recovered using heat transfer tubes such as water tubes and superheater tubes. These heat transfer tubes are exposed to high temperatures for long periods of time and are also affected by corrosive components contained in the fuel, making them susceptible to corrosion. For this reason, continuous management of the heat transfer tubes and frequent repair and replacement are required to prevent corrosion from progressing to a point where the tubes are no longer suitable for practical use.

[0003] Prior art related to heat transfer tube management is, for example, Patent Document 1, which discloses a technique for predicting the lifespan of boiler heat transfer tubes based on measured values ​​of hydrogen chloride concentration in boiler combustion gas. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6871662 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the above-described conventional techniques have a problem in that the data used for prediction is not easily available. Specifically, the technique of Patent Document 1 continuously measures the hydrogen chloride concentration in the combustion gas of the boiler and calculates an integrated value, and estimates the boiler heat transfer tube thickness based on a predetermined correlation coefficient and the calculated integrated value. Therefore, it is necessary to continuously measure the hydrogen chloride concentration in the combustion gas of the boiler for a certain period of time. As such, the technique of Patent Document 1 does not make it easy to obtain the data used for prediction.

[0006] An object of one aspect of the present invention is to provide an index value calculation device or the like that is capable of calculating an index value related to corrosion of a heat transfer tube from readily available data. [Means for solving the problem]

[0007] In order to solve the above problem, an index value calculation device according to one embodiment of the present invention includes a content identification unit that identifies the sulfur content and chlorine content of a fuel, and an index value calculation unit that calculates the index value from the sulfur content and chlorine content identified by the content identification unit using a trained model constructed by machine learning using the sulfur content and chlorine content of the fuel as explanatory variables and an index value related to corrosion of a heat transfer tube that recovers exhaust heat generated when the fuel is combusted as a target variable.

[0008] In addition, in order to solve the above-mentioned problems, an index value calculation device according to another aspect of the present invention includes a composition identification unit that identifies the composition of ash adhering to heat transfer tubes that recover exhaust heat in a boiler provided in a target facility, and an index value calculation unit that calculates the index value for the target facility from the composition identified by the composition identification unit using a trained model constructed by machine learning using the composition of ash adhering to heat transfer tubes of boilers in the target facility or other facilities as an explanatory variable and an index value related to corrosion of the heat transfer tube as a target variable.

[0009] In order to solve the above-mentioned problems, an index value calculation method according to one embodiment of the present invention is an index value calculation method executed by one or more information processing devices, and includes: a content identification step of identifying the sulfur content and chlorine content of fuel for a boiler; and an index value calculation step of calculating the index value from the sulfur content and chlorine content identified in the content identification step using a trained model constructed by machine learning using the sulfur content and chlorine content of the fuel as explanatory variables and an index value related to corrosion of heat transfer tubes that recover exhaust heat generated when the fuel is combusted as a target variable.

[0010] In addition, in order to solve the above-mentioned problems, an index value calculation method according to another aspect of the present invention is an index value calculation method executed by one or more information processing devices, and includes a composition identification step of identifying the composition of ash adhering to heat transfer tubes that recover exhaust heat in a boiler provided in a target facility, and an index value calculation step of calculating the index value in the target facility from the composition identified in the composition identification step using a trained model constructed by machine learning using the composition of ash adhering to heat transfer tubes of boilers in the target facility or other facilities as an explanatory variable and an index value related to corrosion of the heat transfer tube as a target variable. [Effects of the Invention]

[0011] According to one aspect of the present invention, it is possible to calculate an index value related to corrosion of a heat transfer tube from readily available data. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a block diagram showing an example of the configuration of an index value calculation device according to a first embodiment of the present invention. [Figure 2] FIG. 1 is a diagram showing the arrangement and configuration of heat transfer tubes in a waste incineration facility. [Figure 3] FIG. 2 is a diagram showing the flow of steam passing through the interior of a secondary superheater and a tertiary superheater, and the flow of exhaust gas passing around the secondary superheater and the tertiary superheater. [Figure 4] 4 is a flowchart illustrating an example of a process executed by the index value calculation device. [Figure 5] FIG. 10 is a block diagram showing an example of the configuration of an index value calculation device according to a second embodiment of the present invention. [Figure 6] 4 is a flowchart illustrating an example of a process executed by the index value calculation device. DETAILED DESCRIPTION OF THE INVENTION

[0013] [Embodiment 1] (Device configuration) 1 is a block diagram showing an example of the configuration of an index value calculation device 1 according to this embodiment. The index value calculation device 1 is a device that calculates an index value related to corrosion of a heat transfer tube that recovers exhaust heat generated when fuel is combusted and transfers it to a boiler.

[0014] The index value calculation device 1 can also calculate an index value related to corrosion of heat transfer tubes in, for example, a waste incineration facility equipped with a boiler for power generation. In this case, the fuel is garbage (waste). The index value calculation device 1 can also calculate an index value related to corrosion of heat transfer tubes in, for example, a power generation facility that generates power by burning biomass fuel. In this case, the fuel is biomass fuel.

[0015] As shown in the figure, the index value calculation device 1 includes a control unit 10 that controls all the units of the index value calculation device 1, and a storage unit 11 that stores various data used by the index value calculation device 1. The index value calculation device 1 also includes a communication unit 12 that enables the index value calculation device 1 to communicate with other devices, an input unit 13 that accepts input of various data to the index value calculation device 1, and an output unit 14 that enables the index value calculation device 1 to output various data.

[0016] The control unit 10 also includes a content identification unit 101, a temperature calculation unit 102, and an index value calculation unit 103. The memory unit 11 stores operating data 111, a temperature calculation formula 112, and a trained model 113.

[0017] The content identifying unit 101 identifies the sulfur content and chlorine content of the boiler fuel in the target facility for which the index value for heat transfer tube corrosion is to be calculated. When the boiler fuel is garbage, i.e., waste, the content identifying unit 101 identifies the sulfur content and chlorine content of the garbage to be incinerated. For example, the sulfur content may be the weight percent concentration of sulfur contained in the garbage to be incinerated (a value obtained by dividing the weight of the sulfur components contained in the garbage by the dry weight obtained by subtracting the weight of water from the weight of the garbage, and converting the result to a percentage). Note that any index value may be used to indicate the content. For example, a ratio to a predetermined reference value may be used as the index value indicating the content. The same applies to the chlorine content. The sulfur content and chlorine content may be input via the input unit 13 or may be obtained from another device via communication via the communication unit 12.

[0018] The temperature calculation unit 102 calculates the exhaust gas temperature, which is the temperature of the exhaust gas emitted when fuel is burned, and the tube wall temperature of the heat transfer tube through thermal calculations related to the heat transfer tube. Methods for calculating the exhaust gas temperature and the tube wall temperature will be explained later in the sections "Method for calculating exhaust gas temperature" and "Method for calculating tube wall temperature."

[0019] The index value calculation unit 103 calculates an index value related to corrosion of the heat transfer tube. More specifically, the index value calculation unit 103 uses the trained model 113 to calculate the index value from the sulfur content and chlorine content identified by the content identification unit 101 and the exhaust gas temperature and tube wall temperature calculated by the temperature calculation unit 102. Note that it is not essential to use the exhaust gas temperature and tube wall temperature.

[0020] The index value calculated by the index value calculation unit 103 may be related to the corrosion of the heat transfer tube. For example, the index value calculation unit 103 may calculate an index value indicating the rate of thinning of the heat transfer tube, i.e., the degree to which the thickness of the heat transfer tube will become thinner over a predetermined period, as an index value for predicting the degree of corrosion of the heat transfer tube. Furthermore, for example, the index value calculation unit 103 may calculate an index value indicating the remaining life of the heat transfer tube based on the calculated rate of thinning, the current wall thickness of the heat transfer tube, and the minimum wall thickness of the heat transfer tube. Similarly, the index value calculation unit 103 may calculate, as an index value, the amount of thinning over a predetermined period, a predicted value of the wall thickness of the heat transfer tube after a predetermined period, or the like. Note that a trained model 113 using the remaining life of the heat transfer tube as the objective variable may be constructed. In this case, the index value calculation unit 103 can calculate the remaining life of the heat transfer tube without performing the above-described calculation.

[0021] The operating data 111 is the operating data of the target facility for which the index value is to be calculated, and is used to calculate the exhaust gas temperature and the pipe wall temperature. The temperature calculation formula 112 is a mathematical formula for calculating the exhaust gas temperature and the pipe wall temperature. Details of the temperature calculation formula 112 and the operating data 111 will be explained later in the sections "Method for calculating exhaust gas temperature" and "Method for calculating pipe wall temperature."

[0022] The trained model 113 is a model for calculating an index value related to corrosion of heat transfer tubes. More specifically, the trained model 113 is a trained model constructed by machine learning using the sulfur content and chlorine content of fuel as explanatory variables and an index value related to corrosion of heat transfer tubes that recover exhaust heat generated when the fuel is combusted as a target variable. The trained model may be machine-learned using data acquired at the target facility for which the index value is to be calculated, or may be machine-learned using data acquired at another facility. Details of the trained model will be explained later in the section "About the trained model."

[0023] As described above, the index value calculation device 1 includes a content identification unit 101 that identifies the sulfur content and chlorine content of the boiler fuel, and an index value calculation unit 103 that calculates an index value from the sulfur content and chlorine content identified by the content identification unit 101 using a trained model 113 constructed by machine learning using the sulfur content and chlorine content of the fuel as explanatory variables and an index value related to corrosion of heat transfer tubes that recover exhaust heat generated when the fuel is burned as a target variable.

[0024] Because it is known that the sulfur content and chlorine content of fuel have a significant impact on heat transfer tube corrosion, the above configuration makes it possible to calculate an index value related to heat transfer tube corrosion. Furthermore, the sulfur content and chlorine content of fuel can be identified without operating the target facility for which the index value is to be calculated, and these data are relatively easy to obtain. Therefore, the above configuration has the effect of enabling the index value related to heat transfer tube corrosion to be calculated from relatively easy-to-obtain data. For example, the above configuration makes it possible to calculate an index value related to heat transfer tube corrosion during the design stage of the facility for which the index value is to be calculated, and to reflect the index value in the design.

[0025] (About the trained model) As described above, the trained model 113 is a trained model constructed by machine learning using the sulfur content and chlorine content of the fuel as explanatory variables and an index value related to corrosion of the heat transfer tubes that recover the exhaust heat generated when the fuel is burned as the objective variable.

[0026] The explanatory variables of the trained model 113 need only include at least the sulfur content and chlorine content of the fuel, and various other information related to corrosion of the heat transfer tubes can also be included in the explanatory variables. In this embodiment, in addition to the sulfur content and chlorine content of the fuel, an example is described in which the exhaust gas temperature (more precisely, the exhaust gas temperature around the heat transfer tube), which is the temperature of the exhaust gas emitted during fuel combustion, and the tube wall temperature of the heat transfer tube are also used as explanatory variables. Since it is known that the exhaust gas temperature and tube wall temperature also have a significant impact on the corrosion of the heat transfer tube, the above configuration makes it possible to calculate a highly accurate index value related to the corrosion of the heat transfer tube.

[0027] As described above, the index value calculation device 1 may also include a temperature calculation unit 102 that calculates the exhaust gas temperature and the tube wall temperature by thermal calculation related to the heat transfer tube. In this case, the index value calculation unit 103 calculates an index value from the exhaust gas temperature and the tube wall temperature calculated by the temperature calculation unit 102 and the sulfur content and chlorine content identified by the content identification unit 101, using a trained model 113 whose explanatory variables include the exhaust gas temperature and the tube wall temperature.

[0028] Although the exhaust gas temperature and the tube wall temperature usually need to be measured while the facility for which the index value is to be calculated is operating, the above-described configuration calculates the exhaust gas temperature and the tube wall temperature of the heat transfer tube through thermal calculations related to the heat transfer tube. Therefore, with the above-described configuration, the index value for the corrosion of the heat transfer tube can be calculated without operating the facility for which the index value is to be calculated.

[0029] Of course, the exhaust gas temperature and the pipe wall temperature do not necessarily have to be calculated by the index value calculation device 1, and the index value may be calculated using the exhaust gas temperature and the pipe wall temperature input by the user of the index value calculation device 1 via the input unit 13 or obtained from another device by communication via the communication unit 12. In this case, the temperature calculation unit 102 may be omitted.

[0030] The trained model 113 may be constructed by machine learning using training data that indicates the relationship between explanatory variables and target variables. The training data may be data that associates the sulfur content and chlorine content of fuel used in the target facility for which the index value is to be calculated, or the exhaust gas temperature and pipe wall temperature calculated from operating data collected at the facility (or collected at the facility), with the index value (e.g., wall thinning rate) at the facility. In this way, by using data collected at the facility for which the index value is to be calculated as training data, the accuracy of calculating the index value at the facility can be improved.

[0031] Note that values ​​of the sulfur content, etc., which are explanatory variables of the trained model 113, and values ​​of the index value, which is the objective variable, generally show common trends for general power generation facilities. Therefore, even if the trained model 113 is machine-learned using data collected at a specific facility as training data, it is not limited to use at that facility, but is a general-purpose model that can also be used to calculate index values ​​at other facilities.

[0032] In other words, the training data for the trained model 113 may be data acquired at the target facility for which the index value is to be calculated, or may be data acquired at another facility. However, in either case, if the operating conditions of the facility affect corrosion of the heat transfer tubes, it is preferable to use data acquired under at least such operating conditions as those of the target facility as training data. For example, if it is decided that the target facility will be operated at a steam temperature of 400 degrees, it is preferable to use a trained model 113 constructed using data acquired under conditions of a steam temperature of 400 degrees or close to that as training data.

[0033] The learning algorithm of the trained model 113 is not particularly limited as long as it can derive a target variable from the explanatory variables described above. For example, a learning algorithm such as a neural network or a support vector machine may be applied. Also, for example, a forward propagation neural network such as an extreme learning machine (ELM) may be applied. Experiments conducted by the present inventors have confirmed that by applying an ELM as the trained model 113, index values ​​with sufficient accuracy for practical use can be calculated using a relatively small amount of training data.

[0034] The index value calculation device 1 may generate the trained model 113 and the above-described teacher data used in the machine learning of the trained model 113. In this case, a teacher data generation unit that generates the teacher data and a learning unit that generates the trained model 113 may be added to the control unit 10 in FIG.

[0035] (About the arrangement and configuration of heat transfer tubes) The index value calculation device 1 can also calculate an index value related to corrosion of heat transfer tubes in a waste incineration facility equipped with a boiler for power generation. The following describes the arrangement and configuration of heat transfer tubes in a waste incineration facility 5 with reference to Fig. 2. Fig. 2 is a diagram showing the arrangement and configuration of heat transfer tubes in a waste incineration facility 5.

[0036] In the waste incineration facility 5 shown in Figure 2, waste is burned in a combustion chamber 51. High-temperature exhaust gas generated by the combustion of the waste flows into a flow path 52 provided above the combustion chamber 51. The walls of the combustion chamber 51 and the flow path 52 form water pipe walls 53. As shown in a partially enlarged view in Figure 2, the water pipe wall 53 is configured such that a water pipe 531 is arranged inside a heat-insulating wall 532. Water circulates inside the water pipe 531.

[0037] Also provided in flow path 52 are an exhaust gas economizer 54 that preheats boiler feedwater, a steam drum 55 that evaporates circulating water inside water pipes 531 to generate steam, a primary superheater 56, a secondary superheater 57, and a tertiary superheater 58. As shown enlarged in Fig. 2, primary superheater 56 is composed of a continuous superheater tube 562 extending from an inlet 561 to an outlet 563. Although not shown in the figure, secondary superheater 57 and tertiary superheater 58 are also composed of a continuous serpentine superheater tube similar to primary superheater 56.

[0038] The water pipe 531 is connected to an exhaust gas economizer 54, and the circulating water in the water pipe 531 that has been heated by the exhaust gas is supplied to the exhaust gas economizer 54. This circulating water is further heated in the exhaust gas economizer 54 and supplied to a steam drum 55, which evaporates the circulating water and converts it into steam.

[0039] The steam generated by the steam drum 55 is supplied to the primary superheater 56 and superheated. More specifically, the steam generated by the steam drum 55 enters the superheater tube 562 from the inlet 561 of the primary superheater 56, is superheated in the superheater tube 562, and is discharged from the outlet 563. The superheated steam is then superheated again in the secondary superheater 57, and then further superheated in the tertiary superheater 58 before being supplied to a steam turbine (not shown). The steam turbine is rotated by this superheated steam, and this rotational power is used to generate electricity.

[0040] In this way, in the waste incineration facility 5, the exhaust heat generated by burning waste in the combustion chamber 51 is recovered by the water pipe 531 and the superheater tubes in the primary superheater 56 to the tertiary superheater 58. In other words, the water pipe 531 and the superheater tubes in the primary superheater 56 to the tertiary superheater 58 are heat transfer tubes that recover exhaust heat. The index value calculation device 1 can calculate index values ​​related to corrosion of such water pipes 531 and superheater tubes.

[0041] (Calculation method for exhaust gas temperature) A method for calculating the exhaust gas temperature by the temperature calculation unit 102 will be described with reference to Fig. 3. Fig. 3 is a diagram showing the flow of steam passing through the interior of secondary superheater 57A and tertiary superheater 58A, and the flow of exhaust gas passing around secondary superheater 57A and tertiary superheater 58A. Although not shown, a primary superheater is disposed downstream of secondary superheater 57A in the direction of exhaust gas flow.

[0042] The tertiary superheater 58A shown in the figure is provided adjacent to the secondary superheater 57A. As indicated by the dashed-dotted arrow in Figure 3, steam that has entered the secondary superheater 57A passes through the interior of the secondary superheater 57A, then enters the tertiary superheater 58A, passes through the interior of the tertiary superheater 58A, and is released from the tertiary superheater 58A. On the other hand, the exhaust gas flows from the tertiary superheater 58A toward the secondary superheater 57A.

[0043] In FIG. 3, the exhaust gas temperature at the inlet of the secondary superheater 57A is T g,2,in (℃), the exhaust gas temperature at the outlet of the secondary superheater 57A is T g,2,out Similarly, the exhaust gas temperature at the inlet of the tertiary superheater 58A is expressed as T g,3,in (℃), the exhaust gas temperature at the outlet of the tertiary superheater 58A is T g,3,out (℃).

[0044] Among the above temperatures, the exhaust gas temperature T at the inlet of the tertiary superheater 58A g,3,in can be measured by providing a thermometer near the inlet of the tertiary superheater 58A. g,3,out is the specific heat of the exhaust gas c (kJ / m 3 N ° C) and the enthalpy h of the exhaust gas at the outlet of the tertiary superheater 58A g,3,out (kJ / m 3 N), it can be expressed as the following equation (1), where the specific heat c is a constant.

[0045]

number

[0046] In addition, the exhaust gas temperature T g,2,in is T g,3,out That is, T g,2,in =T g,3,out The following relationship holds: The exhaust gas temperature T g,2,out is the specific heat of the exhaust gas c (kJ / m 3 N℃) and the enthalpy h of the exhaust gas at the outlet of the secondary superheater 57A g,2,out (kJ / m 3 N), it can be expressed as the following formula (2).

[0047]

number

[0048] Also, h in formula (1) g,3,out is the exhaust gas flow rate F (m 3 N / h), the enthalpy of the exhaust gas at the inlet of the tertiary superheater 58A h g,3,in (kJ / m 3 N), steam flow rate V (m 3 N / h), steam enthalpy at the inlet of the tertiary superheater 58A h v,3,in (kJ / m 3 N), and steam enthalpy h at the outlet of the tertiary superheater 58A v,3,out (kJ / m 3 N), it can be expressed as the following formula (3). Note that the exhaust gas flow rate F and steam flow rate V can be measured.

[0049]

number

[0050] Also, h in the above formula (3) g,3,in is the specific heat of the exhaust gas c (kJ / m 3 N°C) and T g,3,in It can be calculated from the following formula (4). g,3,in is the measured T g,3,inIt can be calculated by multiplying by the constant specific heat c.

[0051]

number

[0052] Also, h in formula (2) g,2,out is expressed by the following formula (5). v,2,in (kJ / m 3 N) is the steam enthalpy at the inlet of the secondary superheater 57A, and h v,2,out (kJ / m 3 N) is the steam enthalpy at the outlet of the secondary superheater 57A.

[0053]

number

[0054] In addition, the steam enthalpy can be calculated from the steam pressure and steam temperature, which can be measured. Therefore, the temperature calculation unit 102 calculates the steam enthalpy h using the measured values ​​of the steam pressure and steam temperature in the tertiary superheater 58A. v,3,out , h v,3,in These calculated values, the measured values ​​of the exhaust gas flow rate F and the steam flow rate V, and T g,3,in The product of the measured value of and the specific heat of the exhaust gas, h g,3,in (Equation (4) above) is substituted into equation (3) above, and h g,3,out Then, the temperature calculation unit 102 calculates the calculated h g,3,out By substituting into the above formula (1), the exhaust gas temperature T g,3,out can be calculated.

[0055] Further, the temperature calculation unit 102 calculates the steam enthalpy h using the measured values ​​of the steam pressure and steam temperature in the secondary superheater 57A. v,2,out , h v,2,in Calculate these values ​​and the h calculated as above. g,3,outBy substituting the measured values ​​of the exhaust gas flow rate F and the steam flow rate V into the above formula (5), h g,2,out Then, the temperature calculation unit 102 calculates the calculated h g,2,out By substituting into the above formula (2), the exhaust gas temperature T g,2,out can be calculated.

[0056] The formula used in the above calculation may be stored in the storage unit 11 as the temperature calculation formula 112. The measured values ​​used in the above calculation may be input as the operating data 111.

[0057] (Calculation method for tube wall temperature) Next, we will explain how to calculate the tube wall temperature. m (℃), and the exhaust gas temperature around the superheater tube is T g (℃), the tube wall temperature T m is the exhaust gas temperature T g , the heat transfer rate Q (kcal / h), the outer diameter r2 of the superheater tube, and the gas heat transfer coefficient α g (kcal / m 2 h °C) and the length L (m) of the superheater tube, is expressed as the following formula (6).

[0058]

number

[0059] The heat transfer amount Q is calculated by multiplying the heat transfer coefficient K (kcal / mh℃) and the exhaust gas temperature T g and the fluid temperature in the superheater tube T f (°C) and the length L of the superheater tube, it is expressed as the following formula (7).

[0060]

number

[0061] Then, by substituting the right side of the formula (7) for the heat transfer amount Q in the formula (6), the following formula (8) is derived.

[0062]

number

[0063] In addition, the heat transfer coefficient K is the gas heat transfer coefficient α g , the outer diameter of the superheater tube r2 (m), the inner diameter of the superheater tube r1 (m), the thermal conductivity λ (kcal / mh℃), and the heat transfer coefficient α of the fluid in the superheater tube f (kcal / m 2 h °C), it is expressed as the following formula (9).

[0064]

number

[0065] In the above formulas (8) and (9), the thermal conductivity λ and the gas heat transfer coefficient α g , the heat transfer coefficient of the fluid α f , inner radius r1, and outer radius r2 are all constants. Therefore, from equation (9), the overall heat transfer coefficient K is also a constant. Therefore, the temperature calculation unit 102 converts the exhaust gas temperature calculated as described above into T g and fluid temperature T f By substituting into the above formula (8), the tube wall temperature T m can be calculated.

[0066] For example, the tube wall temperature T near the outlet of the tertiary superheater 58A m,3,out When calculating the temperature T g,3,out , the heat transfer coefficient K, and the fluid (i.e., steam) temperature T near the outlet of the tertiary superheater 58A. f,3,out is substituted into the above formula (8). Formula (8) may be stored in the storage unit 11 as the temperature calculation formula 112. f,3,out can be input as the operation data 111.

[0067] (Processing flow) The flow of processing (index value calculation method) executed by the index value calculation device 1 will be described with reference to Fig. 4. Fig. 4 is a flowchart showing an example of processing executed by the index value calculation device 1. Note that, below, an example of calculating an index value related to corrosion of the superheater tubes included in the tertiary superheater 58A shown in Fig. 3 will be described.

[0068] In S11, the temperature calculation unit 102 accepts input of operating data 111. The operating data 111 may be input via the input unit 13, or may be input from another device by communication via the communication unit 12. Specifically, the operating data 111 includes various measurement values ​​used to calculate the exhaust gas temperature and the pipe wall temperature, as described above in "Method for calculating exhaust gas temperature."

[0069] In S12, the temperature calculation unit 102 calculates the exhaust gas temperature near the tertiary superheater 58A and the tube wall temperature of the superheater tube of the tertiary superheater 58A using the operating data 111 input in S11 and a temperature calculation formula 112. For example, as explained above in the "Calculation method of exhaust gas temperature," the temperature calculation unit 102 calculates the exhaust gas temperature T g,3,out Then, the temperature calculation unit 102 may calculate the calculated exhaust gas temperature T g,3,out Using the operating data 111 and the formula (8), the tube wall temperature T of the superheater tube of the tertiary superheater 58A is calculated. m may be calculated.

[0070] In S13, the content identification unit 101 identifies the sulfur content and chlorine content of the boiler fuel in the target facility. For example, if the boiler fuel is waste to be incinerated, the sulfur content and chlorine content of the waste are identified in S13. The sulfur content and chlorine content may be input via the input unit 13, or may be obtained from another device by communication via the communication unit 12. Furthermore, the sulfur content and chlorine content identified in S13 may be determined by actually analyzing the fuel (e.g., waste), or may be estimated values ​​calculated based on the composition of general fuels, etc.

[0071] In S14, the index value calculation unit 103 uses the trained model 113 to calculate an index value for corrosion of the superheater tube of the tertiary superheater 58A from the exhaust gas temperature and tube wall temperature calculated in S12 and the sulfur content and chlorine content identified in S13. Specifically, the index value calculation unit 103 inputs the exhaust gas temperature, tube wall temperature, sulfur content, and chlorine content into the trained model 113, and an index value is output from the trained model 113. This completes the processing of FIG. 4. The index value calculation unit 103 may store the calculated index value in the memory unit 11, output it to the output unit 14, or transmit it to another device via the communication unit 12.

[0072] As described above, the index value calculation method according to this embodiment includes a content identification step (S13) of identifying the sulfur content and chlorine content of the boiler fuel, and an index value calculation step (S14) of calculating an index value from the sulfur content and chlorine content identified in S13 using a trained model 113 constructed by machine learning using the sulfur content and chlorine content of the fuel as explanatory variables and an index value related to corrosion of heat transfer tubes that recover exhaust heat generated when the fuel is combusted as a response variable. Thus, according to the index value calculation method according to this embodiment, an index value related to corrosion of heat transfer tubes can be calculated from easily available data, namely the sulfur content and chlorine content of the fuel.

[0073] [Embodiment 2] Other embodiments of the present invention will be described below. For ease of explanation, the same reference numerals will be used to designate components having the same functions as those described in the above embodiment, and the description thereof will not be repeated.

[0074] (Device configuration) The configuration of the index value calculation device 2 according to this embodiment will be described with reference to Fig. 5. Fig. 5 is a block diagram showing an example of the configuration of the index value calculation device 2. Like the index value calculation device 1 of the first embodiment, the index value calculation device 2 is a device that calculates an index value related to corrosion of a heat transfer tube that recovers exhaust heat generated when fuel is combusted and transfers it to a boiler.

[0075] The index value calculation device 2 differs from the index value calculation device 1 of the first embodiment in that the control unit 10 and the storage unit 11 are replaced by a control unit 20 and a storage unit 21, respectively. The control unit 20 includes a composition identification unit 201 and an index value calculation unit 202. In addition, the storage unit 21 stores a trained model 211.

[0076] The composition identification unit 201 identifies the composition of ash attached to a heat transfer tube that recovers exhaust heat in a boiler. For example, the composition identification unit 201 may identify the weight percent concentration of each component contained in the ash, which is identified by performing a component analysis on the ash attached to the heat transfer tube, as the ash composition. Details of the composition identified by the composition identification unit 201 will be described later in the section "Regarding the trained model."

[0077] The ash composition may be input via the input unit 13, or may be acquired from another device by communication via the communication unit 12. The ash composition may be determined by analyzing ash that has actually adhered to the heat transfer tubes as described above, or may be an assumed design value (a value that is assumed to be the composition based on the design of the facility).

[0078] The index value calculation unit 202 calculates an index value related to the corrosion of the heat transfer tube. More specifically, the index value calculation unit 202 calculates an index value from the composition of the ash identified by the composition identification unit 201 using the trained model 211. The calculated index value may be related to the corrosion of the heat transfer tube, as in the first embodiment. For example, the index value calculation unit 202 may calculate an index value indicating the rate of wall thinning, the remaining life of the heat transfer tube, or the like.

[0079] The trained model 211 is a model for calculating index values ​​related to corrosion of heat transfer tubes, similar to the trained model 113 of embodiment 1. The explanatory variable of the trained model 211 is the composition of ash adhering to the heat transfer tubes of the boiler, and in this respect it differs from the trained model 113. The trained model 211 may be machine-trained using data acquired at the target facility for which the index values ​​are to be calculated, or may be machine-trained using data acquired at another facility, and in this respect it is similar to the trained model 113.

[0080] As described above, the index value calculation device 2 includes a composition identification unit 201 that identifies the composition of ash adhering to heat transfer tubes that recover exhaust heat in a boiler provided in the target facility, and an index value calculation unit 202 that calculates an index value for the target facility from the composition identified by the composition identification unit 201 using a trained model 211 constructed by machine learning using the composition of ash adhering to heat transfer tubes of boilers in the target facility or other facilities as an explanatory variable and an index value related to corrosion of the heat transfer tube as a target variable.

[0081] Since it is known that the composition of ash adhering to heat transfer tubes is correlated with the corrosion of the heat transfer tubes, the above configuration makes it possible to calculate an index value related to the corrosion of the heat transfer tubes. Furthermore, the above configuration has the effect of enabling the index value related to the corrosion of the heat transfer tubes to be calculated from the ash composition, which is data that is relatively easy to obtain.

[0082] (About the trained model) The trained model 211 is a trained model constructed by machine learning using the composition of ash adhering to a heat transfer tube as an explanatory variable and an index value related to corrosion of the heat transfer tube as a target variable. The explanatory variables of the trained model 211 may indicate the composition of all components that make up the ash, or may indicate the composition of some of the components. The composition identification unit 201 identifies the content of the components that are explanatory variables of the trained model 211.

[0083] For example, the composition identifying unit 201 may identify at least the sulfur content and chlorine content of the ash adhering to the heat transfer tube as the composition of the ash. Since the sulfur content and chlorine content of the ash adhering to the heat transfer tube are known to have a strong correlation with the corrosion of the heat transfer tube, the above configuration makes it possible to calculate a highly accurate index value related to the corrosion of the heat transfer tube.

[0084] Furthermore, for example, the composition identifying unit 201 may identify at least the content of alkali metals in the ash adhering to the heat transfer tube as the composition of the ash. Since it is known that the content of alkali metals in the ash adhering to the heat transfer tube correlates with the corrosion of the heat transfer tube, the above configuration makes it possible to calculate a highly accurate index value related to the corrosion of the heat transfer tube. Note that examples of alkali metals contained in the ash adhering to the heat transfer tube include sodium and potassium.

[0085] Furthermore, for example, the composition identifying unit 201 may identify at least the heavy metal content in the ash adhering to the heat transfer tube as the composition of the ash. Since it is known that the heavy metal content in the ash adhering to the heat transfer tube correlates with the corrosion of the heat transfer tube, the above configuration makes it possible to calculate a highly accurate index value related to the corrosion of the heat transfer tube. Note that examples of heavy metals contained in the ash adhering to the heat transfer tube include copper, zinc, and lead.

[0086] Alternatively, a trained model 211 may be used that uses the compositions of all the major components contained in the ash adhering to the heat transfer tube as explanatory variables. In this case, the composition identification unit 201 may identify the contents of oxygen, magnesium, aluminum, silicon, phosphorus, calcium, and the like in addition to the above-mentioned sulfur, chlorine, sodium, potassium, copper, zinc, and lead.

[0087] Similar to the trained model 113 of the first embodiment, the trained model 211 may be constructed by machine learning using training data that indicates the relationship between explanatory variables and target variables. The training data may correspond to the composition of ash collected at the facility for which the index value is to be calculated or at another facility, and the value of the index value (e.g., the rate of wall thinning) at the facility. Also, similar to the trained model 113, the algorithm of the trained model 211 is not particularly limited as long as it can derive the target variable from the explanatory variables as described above.

[0088] The index value calculation device 2 may also generate the trained model 211 and the above-described training data used in the machine learning of the trained model 211. In this case, a training data generation unit that generates training data and a learning unit that generates the trained model 211 may be added to the control unit 20 in FIG.

[0089] (Processing flow) The flow of processing (index value calculation method) executed by the index value calculation device 2 will be described with reference to Fig. 6. Fig. 6 is a flowchart showing an example of processing executed by the index value calculation device 2. Note that the following describes an example of calculating an index value related to corrosion of the superheater tube 562 in the waste incineration facility 5 shown in Fig. 2.

[0090] In S21, the composition identification unit 201 identifies the composition of the ash attached to the superheater tube 562. The ash composition may be input via the input unit 13, or may be input from another device by communication via the communication unit 12. As described above, the ash composition identified in S21 may be identified by analyzing the ash actually attached to the superheater tube 562, or may be an assumed design value.

[0091] In S22, the index value calculation unit 202 calculates an index value related to the corrosion of the superheater tube 562 from the composition of the ash identified in S21, using the trained model 211. Specifically, the index value calculation unit 202 inputs the composition of the ash, i.e., the amount of each component contained in the ash, into the trained model 211, and an index value is output from the trained model 211. This completes the processing in FIG. 6. The index value calculation unit 202 may store the calculated index value in the memory unit 21, output it to the output unit 14, or transmit it to another device via the communication unit 12.

[0092] As described above, the index value calculation method according to this embodiment includes a composition identification step (S21) of identifying the composition of ash adhering to heat transfer tubes that recover exhaust heat in a boiler provided in the target facility, and an index value calculation step (S22) of calculating an index value for the target facility from the composition identified in S21 using a trained model 211 constructed by machine learning using the composition of ash adhering to heat transfer tubes of boilers in the target facility or another facility as an explanatory variable and an index value related to corrosion of the heat transfer tube as a response variable. This makes it possible to calculate an index value related to corrosion of heat transfer tubes from easily available data, namely the ash composition.

[0093] [Modification] The execution entity of each process described in the above-mentioned embodiment may be any entity and is not limited to the above-mentioned examples. For example, the index value calculation method shown in FIG. 4 may be configured to be executed by multiple information processing devices instead of the index value calculation device 1. For example, the processes of S11 and S12 in FIG. 4 may be executed by one information processing device, and the exhaust gas temperature and pipe wall temperature calculated by that information processing device may be output to another information processing device. In this case, the other information processing device may perform the processes of S13 and S14. The same applies to the index value calculation method shown in FIG. 6, and may be configured to be executed by multiple information processing devices instead of the index value calculation device 2.

[0094] [Software implementation example] The functions of the index value calculation devices 1 and 2 (hereinafter referred to as "devices") can be realized by a program (index value calculation program) that causes a computer to function as the devices, and that causes a computer to function as each control block of the devices (particularly each part included in the control units 10 and 20).

[0095] In this case, the device includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., a memory) as hardware for executing the program. The control device and storage device execute the program, thereby realizing the functions described in each of the above embodiments.

[0096] The program may be non-transitory and may be recorded on one or more computer-readable recording media. The recording media may or may not be included in the device. In the latter case, the program may be supplied to the device via any wired or wireless transmission medium.

[0097] Furthermore, some or all of the functions of the control blocks can be realized by logic circuits. For example, an integrated circuit in which a logic circuit that functions as each of the control blocks is formed is also included in the scope of the present invention. In addition, the functions of the control blocks can also be realized by, for example, a quantum computer.

[0098] The present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention. [Explanation of symbols]

[0099] 1. Index value calculation device 101 Content Specification Department 102 Temperature calculation section 103 Index value calculation unit 113 trained models 2. Index value calculation device 201 Composition Identification Department 202 Index value calculation unit 211 trained models

Claims

1. a content specifying unit for specifying the sulfur content and the chlorine content of the boiler fuel; an index value calculation unit that calculates the index value from the sulfur content and chlorine content specified by the content specification unit using a trained model constructed by machine learning using the sulfur content and chlorine content of the fuel as explanatory variables and an index value related to corrosion of a heat transfer tube that recovers exhaust heat generated when the fuel is combusted as a target variable, explanatory variables of the trained model include an exhaust gas temperature, which is a temperature of exhaust gas emitted when the fuel is combusted, and a tube wall temperature of the heat transfer tube; a temperature calculation unit that calculates the exhaust gas temperature and the tube wall temperature by thermal calculation regarding the heat transfer tube, the index value calculation unit calculates the index value from the exhaust gas temperature and the pipe wall temperature calculated by the temperature calculation unit and the sulfur content and the chlorine content specified by the content specification unit, using the trained model; The temperature calculation unit calculates the exhaust gas temperature at the exhaust gas outlet of the heat transfer tube, which is used as an explanatory variable of the trained model, from the actual measured value of the exhaust gas temperature at the exhaust gas inlet of the heat transfer tube using a mathematical formula that models the heat balance in the heat transfer tube.

2. An index value calculation method executed by one or more information processing devices, a content determination step of determining the sulfur content and chlorine content of the boiler fuel; an index value calculation step of calculating the index value from the sulfur content and chlorine content identified in the content identification step using a trained model constructed by machine learning using the sulfur content and chlorine content of the fuel as explanatory variables and an index value related to corrosion of a heat transfer tube that recovers exhaust heat generated when the fuel is combusted as a target variable, explanatory variables of the trained model include an exhaust gas temperature, which is a temperature of exhaust gas emitted when the fuel is combusted, and a tube wall temperature of the heat transfer tube; a temperature calculation step of calculating the exhaust gas temperature and the tube wall temperature by thermal calculation regarding the heat transfer tube, In the index value calculation step, the index value is calculated using the trained model from the exhaust gas temperature and the pipe wall temperature calculated in the temperature calculation step, and the sulfur content and the chlorine content identified in the content identification step; In the temperature calculation step, an index value calculation method is used to calculate the exhaust gas temperature at the exhaust gas outlet of the heat transfer tube, which is used as an explanatory variable of the trained model, from the actual measured value of the exhaust gas temperature at the exhaust gas inlet of the heat transfer tube using a mathematical formula that models the heat balance in the heat transfer tube.

3. An index value calculation program for causing a computer to function as the index value calculation device of claim 1, the index value calculation program causing a computer to function as the content determination unit, the index value calculation unit, and the temperature calculation unit.

Images