Operation assistance device, operation assistance method, operation assistance program, and plant management system

Abstract

An operation assistance device 4 according to one aspect of the present disclosure assists the operation of a plant 2, the operation assistance device 4 comprising: an acquisition unit (target data acquisition unit 100b) that acquires target data on the basis of a measurement value pertaining to at least one of temperature, pressure, and flow rate pertaining to one or more sites on which a heat transfer medium flows in the plant 2; and an output unit 108 that, on the basis of the target data and one or more pieces of reference data when the plant 2 is operating in a normal state, outputs assistance information relating to a flow failure of the heat transfer medium or a portent thereof at one or more sites, wherein the one or more reference data is based on a measurement value corresponding to the target data.

Description

Operation support device, operation support method, operation support program, and plant management system

[0001] The present disclosure relates to an operation assistance device, an operation assistance method, an operation assistance program, and a plant management system.

[0002] Conventionally, technologies for detecting abnormalities in plants have been known. For example, Patent Document 1 describes a technology in which, upon receiving an alarm and abnormality information from a failure sign monitoring system, an artificial intelligence platform searches an event database for past events that are highly relevant to the event that caused the abnormality, and outputs the search results. However, the technology described in Patent Document 1 does not provide sufficient support for plant operation.

[0003] Japanese Patent Application Laid-Open No. 2020-201764

[0004] The present disclosure aims to support plant operations.

[0005] An operation assistance device according to one aspect of the present disclosure is an operation assistance device that assists in the operation of a plant, and includes: an acquisition unit that acquires target data based on measured values ​​related to at least one of temperature, pressure, and flow rate for one or more parts of the plant through which a heat transfer medium flows; and an output unit that outputs assistance information related to a flow disorder or a sign thereof of the heat transfer medium in one or more parts, based on the target data and one or more reference data for when the plant is operating under normal conditions, wherein the one or more reference data are based on measured values ​​corresponding to the target data.

[0006] An operation assistance method according to another aspect of the present disclosure is an operation assistance method for assisting the operation of a plant, which causes a computer to execute the following steps: acquiring target data based on measured values ​​of at least one of temperature, pressure, and flow rate for one or more locations in the plant through which a heat transfer medium flows; and outputting support information regarding flow disorders or signs of such disorders in the heat transfer medium at one or more locations based on the target data and one or more reference data for when the plant is operating normally, wherein the one or more reference data are based on measured values ​​corresponding to the target data.

[0007] An operation assistance program according to another aspect of the present disclosure is an operation assistance program that assists in the operation of a plant, and causes a computer to function as: an acquisition means that acquires target data based on measured values ​​related to at least one of temperature, pressure, and flow rate for one or more parts of the plant through which a heat transfer medium flows; and an output means that outputs assistance information related to flow disorders or signs of flow disorders of the heat transfer medium at one or more parts based on the target data and one or more reference data for when the plant is operating under normal conditions, wherein the one or more reference data are based on measured values ​​corresponding to the target data.

[0008] A plant management system according to another aspect of the present disclosure is a plant management system including a plant and an operation assistance device that assists in the operation of the plant, wherein the operation assistance device includes: an acquisition unit that acquires target data based on measured values ​​related to at least one of temperature, pressure, and flow rate for one or more locations in the plant through which a heat transfer medium flows; and an output unit that outputs assistance information related to a flow disorder or a sign thereof of the heat transfer medium in the one or more locations based on the target data and one or more reference data for when the plant is operating under normal conditions, wherein the one or more reference data are based on measured values ​​corresponding to the target data.

[0009] According to the present disclosure, plant operation can be supported.

[0010] FIG. 1 is a diagram showing an overview of a plant management system 1. FIG. 2 is a diagram showing an example of the overall configuration of the plant management system 1. FIG. 3 is a diagram showing an example of the functional configuration of a driving assistance device 4. FIG. 4 is a diagram for explaining an example of the operation of the driving assistance device 4. FIG. 5 is a diagram for explaining an example of the operation of the driving assistance device 4. FIG. 6 is a diagram for explaining an example of the display screen of the driving assistance device 4. FIG. 7 is a diagram showing an example of hardware of the driving assistance device 4. FIG. 8 is a diagram for explaining another example of the operation of the driving assistance device 4.

[0011] <1. Overview> In recent years, under the Feed-in Triff (FIT) system, the number of biomass-based steam power plants has rapidly increased. Materials used as biomass include construction waste, wood chips, wood pellets, and palm kernel shells (PKS). However, biomass fuels contain large amounts of alkaline substances, such as sodium and potassium, which can cause agglomeration of the circulating material, which is the heat transfer medium in CFB (Circulating Fluidized Bed) boilers and other boilers. Agglomeration of the heat transfer medium in a furnace can cause flow problems and lead to plant shutdowns. Furthermore, biomass fuels vary in shape and composition, and when supplied to a furnace, they can temporarily increase the alkali concentration in the heat transfer medium, increasing the risk of plant shutdowns.

[0012] One possible method for detecting the occurrence or signs of flow disturbance is to analyze the alkali concentration in the circulating material obtained by alkali purging. However, this method requires time to evaluate the operating status of the plant. Furthermore, plant operators need considerable skill to detect the occurrence of flow disturbance based on time-series data or scatter diagrams of operating data.

[0013] A plant management system 1 according to the present disclosure can efficiently support plant operation. FIG. 1 is a diagram illustrating an overview of the plant management system 1. The plant management system 1 includes a plant 2 and an operation support device 4. A heat transfer medium flows in a boiler of the plant 2. The operation support device 4 acquires, from a sensor installed in the plant 2, measurement values ​​related to the boiler, such as temperature, pressure, and flow rate, as operation data to be determined (S1). Next, the operation support device 4 compares the operation data acquired during normal operation of the plant 2 (e.g., when the plant 2 is operating normally without any faults) with the operation data to be determined (S2). If the operation support device 4 detects a flow disturbance or a sign of a flow disturbance in the boiler by comparing the operation data during normal operation with the operation data to be determined, it outputs a message to that effect to an operator of the plant 2 (S3).

[0014] The plant management system 1 enables even unskilled operators to easily detect flow disturbances or their precursors. Furthermore, since the plant management system 1 can detect flow disturbances and their precursors based on operational data obtained from sensors already installed in the plant 2, there is no need to increase the number of instruments, making it easy to implement. Furthermore, the plant management system 1 can detect flow disturbances and their precursors regardless of the type of fuel.

[0015] In the present disclosure, a "part of plant 2" may be any of devices, equipment, and parts thereof that constitute plant 2. Examples of parts of plant 2 include a boiler, a furnace, a separator, a material supply device, a material storage device, an exhaust facility, and a drainage facility. Other examples of parts include an upper wall surface of a furnace, a middle wall surface of a furnace, a lower wall surface of a furnace, an exhaust port of a furnace, and an intake port of a furnace.

[0016] In this disclosure, the term "heat transfer medium" includes a material that flows together with the fuel in the boiler. The heat transfer medium may also be referred to as a flowing medium or a circulating material. An example of the heat transfer medium is silica sand.

[0017] In the present disclosure, "the heat transfer medium flows through one or more parts of the plant 2" includes the heat transfer medium circulating or passing through the one or more parts.

[0018] In the present disclosure, a state in which "the plant 2 is operating in a normal state" includes a state in which there is no flow disturbance or a sign of such a disturbance in the plant 2. The "normal state" can also be said to be a state in which no alert has been issued regarding a flow disturbance in the plant 2. The "normal state" can also be said to be a state in which no abnormality has occurred in the plant 2. Note that in the present disclosure, "abnormality" is not limited to an abnormality that can stop the operation of the plant 2, but also includes a state in which the operation of the plant 2 can continue but is deviated from an ideal operating state.

[0019] In the present disclosure, the "state in which a flow disturbance has occurred" includes a state in which the operating efficiency of the plant 2 (including the efficiency of the combustion process, the boiler efficiency, and the safety of the plant 2) has decreased due to the flow disturbance. Also, in the present disclosure, the "state in which a sign of a flow disturbance has occurred" includes a state in which there is a high probability that the operating efficiency of the plant 2 will decrease in the future due to the flow disturbance.

[0020] 2. Configuration An example of the configuration of the plant management system 1 will be described with reference to FIG.

[0021] 2 is a diagram showing the overall configuration of the plant management system 1. The plant management system 1 includes a plant 2, a DCS (discrete control system) 2, an operation support device 4, and a communication network 5.

[0022] Plant 2 includes a CFB boiler. As shown in Fig. 2, the CFB boiler is equipped with a fuel bunker, drum, furnace, separator, wall seal, air heater, superheater, main steam outlet, water inlet, dust collector, chimney, induced draft fan, forced draft fan, bottom ash cooler, bottom ash discharge channel, fly ash discharge channel, and ash tank connection channel. These devices and facilities are provided with sensors for measuring temperature, pressure, flow rate, etc.

[0023] The operation support device 4 acquires operation data of the plant 2 from various sensors installed in the plant 2 via the DCS 2 and the communication network 5. The operation support device 4 detects flow disturbances or signs of such disturbances in the heat transfer medium of the plant 2 based on the acquired operation data, and outputs support information to assist the operators of the plant 2 in operating the plant 2. The operation support device 4 may include output devices such as a display and a speaker, and input devices such as a keyboard, a touch panel, and a mouse.

[0024] 3 is a diagram showing an example of the configuration of the driving assistance device 4. The driving assistance device 4 includes a control unit 10, a storage unit 12, a network interface unit 14, and a bus 16. The control unit 10, the storage unit 12, and the network interface unit 14 are electrically connected via the bus 16.

[0025] (Controller 10) The controller 10 functions as an acquirer 100, a generator 102, a determiner 104, an estimator 106, and an outputter 108 by executing various programs stored in the memory 12, which will be described later.

[0026] —Acquisition Unit 100— The acquisition unit 100 acquires operational data based on measured values ​​of at least one of temperature, pressure, and flow rate for one or more portions in the plant 2 through which the heat transfer medium flows.

[0027] - Definition of Measurement Value Related to Part - The measurement value related to the temperature of a specific part of the plant 2 may be any of the temperature of the wall surface of the specific part, the temperature of the gas inside the specific part, and the temperature of the material (i.e., heat transfer medium or fuel) flowing in the specific part.

[0028] The measured value of the pressure at a specified location of plant 2 may be either the pressure of the gas inside the specified location, or the force acting on the wall surface of the specified location by a material (i.e., a heat transfer medium or fuel) flowing in the specified location.

[0029] The measured value of the flow rate at a predetermined location in the plant 2 may be any of the flow rate of gas inside the predetermined location, the flow rate of a substance (i.e., a heat transfer medium or a fuel) flowing at the predetermined location, and the aperture of a flow control valve connected to the location (e.g., the inlet valve aperture, the outlet valve aperture, the damper aperture, etc.). Typically, the aperture of a flow control valve is automatically controlled according to the measured value of the flow rate at the predetermined location, and therefore may be information indirectly indicating the measured value of the flow rate at the predetermined location. Furthermore, the measured value of the flow rate at the predetermined location may include a measured value of the flow velocity at the predetermined location.

[0030] Reference Data and Target Data In one embodiment, the acquisition unit 100 includes a reference data acquisition unit 100a, a target data acquisition unit 100b, and a driving load information acquisition unit 100c.

[0031] The reference data acquiring unit 100a acquires reference data, which is operating data related to a predetermined part when the plant 2 is operating in a normal state. The reference data is data that serves as a reference when determining whether a flow rate disturbance or a sign thereof has occurred in the plant 2.

[0032] The target data acquisition unit 100b acquires target data, which is driving data related to a predetermined part during a target determination period. In one embodiment, the target determination period is a period after the reference data acquisition unit 100a acquires the reference data. In one embodiment, the target determination period is a period after the generation unit 102, which will be described later, generates a learning model. In another embodiment, the target data acquisition unit 100b continuously acquires the target data at predetermined time intervals (e.g., one-minute intervals or ten-second intervals).

[0033] The reference data is based on measurements corresponding to the target data. That is, the reference data includes measurements that can be compared with the target data. It can also be said that the reference data and the target data include measurements of common parts and common physical quantities.

[0034] Measurement Value of Predetermined Location In one embodiment, the target data is a measurement value of at least one of the temperature, pressure, and flow rate at a predetermined location of the plant 2. The target data is, for example, "the temperature of the wall surface at the top of the furnace."

[0035] In one embodiment, the reference data is a measurement value corresponding to the target data at a predetermined location when the plant 2 is operating under normal conditions. For example, if the target data is the "temperature of the wall surface of the upper part of the furnace," an example of the reference data is the "temperature of the wall surface of the upper part of the furnace when the plant 2 is operating under normal conditions."

[0036] Measurement Values ​​at Two Locations In one embodiment, the target data is generated by comparing measurement values ​​of at least one of the temperature, pressure, and flow rate at the first location and the second location of the plant 2. The target data is, for example, "the temperature difference between the temperature of the upper wall surface of the furnace (corresponding to the temperature of the first location) and the temperature of the lower wall surface of the furnace (corresponding to the temperature of the second location)."

[0037] In one embodiment, the reference data is a measurement value for each of the first and second portions when the plant 2 is operating under normal conditions, and is generated by comparing the measurement value corresponding to the target data. For example, if the target data is "the temperature difference between the temperature of the upper wall surface of the furnace and the temperature of the lower wall surface of the furnace," an example of the reference data is "the temperature difference between the temperature of the upper wall surface of the furnace and the temperature of the lower wall surface of the furnace when the plant 2 is operating under normal conditions."

[0038] Measurement Values ​​of Multiple Combinations In one embodiment, when there are multiple combinations including at least two parts in one or more parts of the plant 2, the target data may include (1) first target data generated by comparing measurement values ​​of at least one of temperature, pressure, and flow rate for each part included in the first combination, and (2) second target data generated by comparing measurement values ​​of at least one of temperature, pressure, and flow rate for each part included in the second combination.

[0039] For example, if plant 2 has three parts, part A, part B, and part C, the target data may include (1) the temperature difference between part A and part B (corresponding to the first combination) (corresponding to the first target data), and (2) the pressure difference between part B and part C (corresponding to the second combination) (corresponding to the second target data).

[0040] In one embodiment, when there are multiple combinations of at least two parts in one or more parts of the plant 2, the reference data may include (1) first reference data which is measurement values ​​for each part included in the first combination when the plant 2 is operating under normal conditions, and which is generated by comparing measurement values ​​corresponding to the first target data, and (2) second reference data which is measurement values ​​for each part included in the second combination when the plant 2 is operating under normal conditions, and which is generated by comparing measurement values ​​corresponding to the second target data.

[0041] For example, if the target data includes the temperature difference between parts A and B and the pressure difference between parts B and C, the reference data may include (1) the temperature difference between parts A and B (corresponding to the first combination) when plant 2 is operating under normal conditions (corresponding to the first reference data), and (2) the pressure difference between parts B and C (corresponding to the second combination) when plant 2 is operating under normal conditions (corresponding to the second reference data).

[0042] The operating load information acquisition unit 100c acquires information related to the operating load of the plant 2 when the operating data was acquired. Specifically, when the reference data acquisition unit 100a acquires reference data, the operating load information acquisition unit 100c acquires information related to the operating load of the plant 2 when the reference data was acquired. Furthermore, when the target data acquisition unit 100b acquires target data, the operating load information acquisition unit 100c acquires information related to the operating load of the plant 2 when the target data was acquired. Note that an example of the operating load of the plant 2 is the ratio of the actual evaporation rate to the rated evaporation rate in a boiler of the plant 2, etc.

[0043] In the present disclosure, "obtaining information" includes making the information processable by the control unit 10. Obtaining information may mean any of receiving the information by another device, reading the information from the storage unit 12, and obtaining the information as a result of some kind of calculation by the control unit 10.

[0044] The generation unit 102 generates a learning model by learning the reference data acquired by the reference data acquisition unit 100 a as learning data. The generation unit 102 may generate the learning model by supervised learning or unsupervised learning.

[0045] The learning model generated by the generation unit 102 through supervised learning may be either a regression model or a classification model. Regression models include learning models based on simple regression analysis, multiple regression analysis, etc. Classification models include learning models based on SVM (Support Vector Machine), decision tree, k-nearest neighbor method, logistic regression, etc.

[0046] The learning model generated by the generation unit 102 through unsupervised learning may be any of a learning model based on probability distribution, a learning model based on clustering, a learning model based on association analysis, etc. The learning model based on probability distribution may be intended for either outlier detection or change point detection.

[0047] The learning model generated by the generation unit 102 may be a learning model including a neural network. The learning model including a neural network may include a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), etc.

[0048] In one embodiment, the generation unit 102 generates a learning model that is trained by associating one or more reference data with each of a plurality of operating loads related to the plant 2. That is, the generation unit 102 may generate a learning model that is trained by learning values ​​or ranges of operating data that are considered appropriate for each operating load of the plant 2.

[0049] The determination unit 104 determines whether or not there is a flow disorder or a sign of a flow disorder in the heat transfer medium based on the target data acquired by the target data acquisition unit 100 b and the reference data acquired by the reference data acquisition unit 100 a. In one embodiment, the determination unit 104 determines whether or not there is a flow disorder or a sign of a flow disorder in the heat transfer medium by comparing the target data with the reference data.

[0050] The determination by the determination unit 104 of whether or not there is a flow disorder or a sign of such a disorder in the heat transfer medium includes outputting the possibility that there is a flow disorder or a sign of such a disorder in the heat transfer medium. That is, the output by the determination unit 104 is not limited to a true / false value, but may be a continuous value based on stages, scores, etc.

[0051] In one embodiment, the determination unit 104 determines whether or not there is a flow disorder or a sign of a flow disorder in the heat transfer medium by inputting the target data as determination data into the learning model generated by the generation unit 102. Note that inputting the target data into the learning model that has learned the reference data is one form of comparing the target data with the reference data.

[0052] In one embodiment, when the generation unit 102 generates a learning model in which one or more reference data are associated with each of a plurality of operating loads related to the plant 2 and the model is trained, the judgment unit 104 judges whether there is a flow disorder or a sign of a flow disorder in the heat transfer medium by inputting, into the learning model, information related to the operating load of the plant 2 at the time the target data was acquired, along with the target data.

[0053] —Estimation Unit 106— Based on the relationship between the target data and the reference data, the estimation unit 106 estimates the cause of the flow disturbance or a sign thereof of the heat transfer medium in a predetermined portion of the plant 2. The following exemplary patterns are possible for the relationship between the cause of the flow disturbance or a sign thereof and the target data and the reference data.

[0054] (1) If a flow obstruction occurs in a boiler due to agglomeration of the heat transfer medium, the temperature inside the boiler may rise compared to normal. This is because, when the heat transfer medium agglomerates, the thermal energy that would have been stored in the heat transfer medium is instead stored in other substances (e.g., gas and fuel) inside the boiler. Furthermore, if agglomerates of the heat transfer medium accumulate near a temperature sensor, the agglomerates may interfere with accurate measurement by the temperature sensor, causing the measured temperature inside the boiler to drop compared to normal.

[0055] (2) When flow obstruction occurs due to the accumulation of combustion ash inside the boiler, the measured temperature inside the boiler tends to be lower than usual. This is because the combustion ash covers the temperature sensor, preventing it from measuring the temperature inside the boiler correctly.

[0056] (3) When flow obstruction occurs due to the intrusion of foreign matter into the boiler through fuel, etc., the temperature and pressure inside the boiler tend to become uneven because the intrusion of foreign matter into the boiler inhibits the flow of the heat transfer medium and fuel.

[0057] As exemplified in (1) to (3) above, there is a close correlation between the relationship between the target data and the reference data and the cause of the flow disturbance or its precursor, and therefore, based on the relationship between the target data and the reference data, it is possible to estimate the cause of the flow disturbance or its precursor in the heat transfer medium at a predetermined location in the plant 2. Note that the relationship between the cause of the flow disturbance or its precursor and the target data and the reference data is not limited to the examples in (1) to (3) above.

[0058] In one embodiment, the estimation unit 106 refers to information in which causes are associated with each of one or more conditions, and estimates the cause of the flow disturbance or its precursor in the heat transfer medium at a specified location in the plant 2 based on whether the relationship between the target data and the reference data satisfies any of the one or more conditions.

[0059] - Output Unit 108 - The output unit 108 outputs support information regarding flow problems or signs of flow problems in the heat transfer medium based on the target data and the reference data. The support information may include graphics, characters, numbers, colors, graphs (e.g., scatter plots, time-series data), etc. The support information may also be audio.

[0060] In one embodiment, the support information includes a determination result by the determination unit 104. For example, when the determination unit 104 determines that a flow disorder of the heat transfer medium has occurred, the output unit 108 may display a warning mark and text stating "A flow disorder has occurred" on the display screen as support information. In addition, in one embodiment, the determination result by the determination unit 104 includes an output obtained when target data is input to the learning model generated by the generation unit 102.

[0061] In one embodiment, the support information includes information comparing the target data with the reference data. The output unit 108 may output, as the support information, a graph in which the reference data and the target data are plotted superimposed on a common scatter plot, for example.

[0062] In one embodiment, the support information includes information obtained by comparing the first target data with the first reference data and information obtained by comparing the second target data with the second reference data. The output unit 108 may output, as the support information, a first graph in which the temperature difference between the site A and the site B when the plant 2 is operating in a normal state (corresponding to the first reference data) and the temperature difference between the site A and the site B during the target determination period (corresponding to the first target data) are plotted superimposed on a common scatter plot, and a second graph in which the pressure difference between the site B and the site C when the plant 2 is operating in a normal state (corresponding to the second reference data) and the pressure difference between the site B and the site C during the target determination period (corresponding to the second target data) are plotted superimposed on a common scatter plot, for example.

[0063] In one embodiment, the support information includes information on the cause estimated by the estimation unit 106. For example, if the estimation unit 106 estimates that a flow disorder caused by aggregation of the heat transfer medium has occurred in region A, the output unit 108 may display text such as "Aggregation of the heat transfer medium may have occurred in region A" on the display screen as support information.

[0064] In the present disclosure, "support information includes specified information" may mean either that the support information includes the specified information as is, or that the support information includes information obtained by appropriately processing the specified information.

[0065] (Storage unit 12) The storage unit 12 stores various programs executed by the control unit 10. The storage unit 12 also stores various information necessary for the operation of the driving assistance device 4, such as the target data and reference data acquired by the acquisition unit 100, and the learning model generated by the generation unit 102.

[0066] (Network Interface Unit 14 ) The network interface unit 14 realizes communication with other devices via the communication network 5 .

[0067] 3. Operation> The operation of the plant management system 1 and examples of display screens will be described with reference to FIGS.

[0068] 4 is a conceptual diagram of a boiler in a plant 2 in the example described below. A heat transfer medium flows inside the boiler. The boiler has a section A, a section B, and a section C, and a temperature sensor and a pressure sensor are provided in each section.

[0069] [Acquisition of Reference Data to Generation of Learning Model] FIG. 5 is a flowchart showing the operations performed by the driving assistance device 4 from acquisition of reference data to generation of a learning model.

[0070] The operation support device 4 first acquires reference data (S100). In this example, the reference data acquired by the operation support device 4 is the temperature difference between the portion A and the portion B when the plant 2 is operating under normal conditions. Next, the operation support device 4 acquires information related to the operating load of the boiler when the reference data is acquired (S102).

[0071] Next, the operation support device 4 determines whether a sufficient number of reference data have been acquired to generate a learning model (S104). If a sufficient number of reference data have not been acquired to generate a learning model (NO in S104), the operation support device 4 again acquires the reference data and information about the boiler operating load when the reference data were acquired (S102-S104).

[0072] On the other hand, if a sufficient number of reference data have been acquired to generate a learning model (YES in S104), the operation support device 4 associates the reference data with the operating load of the boiler and trains the learning model (S106). Specifically, the operation support device 4 determines a mathematical formula showing the relationship between the operating load of the boiler and the reference data by simple regression analysis (S106a). That is, the operation support device 4 determines a mathematical formula showing the relationship between the operating load of the boiler and the temperature difference between part A and part B when the plant 2 is operating under normal conditions.

[0073] The operation support device 4 further determines, based on the formula determined in S106a, a formula indicating the relationship between the boiler operating load and the upper limit of the operating data for which it can be determined that no flow disturbance or its precursor has occurred in the plant 2 (S106b). Similarly, based on the formula determined in S106a, the operation support device 4 determines, based on the formula determined in S106a, a formula indicating the relationship between the boiler operating load and the lower limit of the operating data for which it can be determined that no flow disturbance or its precursor has occurred in the plant 2 (S106c). That is, the operation support device 4 determines a formula indicating the relationship between the boiler operating load and the upper and lower limits of the temperature difference between portion A and portion B for which it can be determined that no flow disturbance or its precursor has occurred in the plant 2.

[0074] In this example, the formula determined by the simple regression analysis in S106a is expressed as "y = f(x)" using the function f. Note that "x" is the operating load of the boiler, and "y" is the temperature difference between the parts A and B when the plant 2 is operating under normal conditions. In this case, the formula determined in S106b and the formula determined in S106c may be expressed as "y = f(x) + α / 2" and "y = f(x) - α / 2," respectively. Here, "α" is a constant corresponding to the allowable range of the temperature difference between the parts A and B.

[0075] Hereinafter, the lines drawn on the graph using the formulas determined in S106a-S106c will be referred to as the "reference line," the "upper threshold line," and the "lower threshold line," respectively. Furthermore, below, when the upper threshold line and the lower threshold line are not particularly distinguished from each other, they will be collectively referred to as the "threshold line." Specific examples of the reference line and the threshold line will be described with reference to the example display screen of FIG. 7, which will be described later.

[0076] [Acquisition of Target Data to Output of Assistance Information] FIG. 6 is a flowchart showing the operations performed by the driving assistance device 4 from acquisition of target data to output of assistance information.

[0077] The driving support device 4 first acquires target data (S200). In this example, the target data acquired by the driving support device 4 is the temperature difference between part A and part B. Next, the driving support device 4 acquires information related to the operating load of the boiler at the time the target data was acquired (S202).

[0078] Next, the driving assistance device 4 inputs the target data and information about the operating load at the time the target data was acquired into the learning model generated in S106. As a result, the driving assistance device 4 determines whether the target data is within the upper and lower limits of the operating data that can determine that no flow disturbance or its precursor has occurred in the plant 2 (S206). If the target data is within the upper and lower limits (YES in S206), the processing ends. On the other hand, if the target data is outside the range (NO in S206), the driving assistance device 4 estimates the cause of the flow disturbance or its precursor based on the relationship between the reference data learned in S106 and the target data acquired in S200 (S208), and outputs an alert and the cause estimated in S208 as assistance information (S210).

[0079] In addition, the driving assistance device 4 generates a learning model that learns reference data for the pressure difference between parts A and C using a method similar to that described in S100-S106 and S200-S210, and inputs the target data into the learning model.

[0080] Fig. 7 is a diagram showing an example of a display screen in the operation support device 4. An operator of the plant 2 can visually check this example of a display screen. The example of the display screen in Fig. 7 displays a plot legend d100, a line legend d102, a graph display area d104, a graph display area d106, an alert d108, text d110, and a switching button d112.

[0081] The plot legend d100 and the line legend d102 display the legends of the graphs displayed in the graph display area d104 and the graph display area d106. Specifically, the plot legend d100 indicates that circular plots on the graph correspond to reference data, and square plots correspond to target data. Furthermore, the line legend d102 indicates that solid lines on the graph correspond to reference lines, and dotted lines correspond to threshold lines. That is, the presence of all square plots between the two dotted lines corresponds to the target data being within the upper and lower limits of the operating data within which it can be determined that no flow disturbance or its precursor has occurred in the plant 2. On the other hand, the presence of at least a portion of the square plots outside the two dotted lines corresponds to the target data being outside the upper and lower limits of the operating data within which it can be determined that no flow disturbance or its precursor has occurred in the plant 2 (i.e., within the range within which it is determined that a flow disturbance or its precursor has occurred).

[0082] The graph display area d104 displays a scatter diagram showing the relationship between the boiler's operating load and the reference data and target data for the temperature difference between parts A and B. The graph display area d104 also displays the reference line and threshold line determined in S106a-S106c. In this example, all target data is included between the upper threshold line and the lower threshold line. Therefore, no alert is displayed for the temperature difference between parts A and B (see YES in S206).

[0083] The graph display area d106 displays a scatter plot showing the relationship between the boiler's operating load and the reference data and target data for the pressure difference between parts A and C. The graph display area d106 also displays a reference line and a threshold line determined in a manner similar to S106a-S106c. In this example, target data exists that exceeds the upper threshold line. Therefore, an alert d108 is displayed for the pressure difference between parts A and C, along with text d110 indicating a flow disorder or a probable cause of the same. The text d110 reads, "There may be a foreign object between parts A and C." Each of the graph display area d104, the graph display area d106, the alert d108, and the text d110 is a form of support information.

[0084] The switching button d112 is a button that can be selected or pressed by an operator of the plant 2 to switch the data displayed in the graph display area d104 and the graph display area d106. By pressing the switching button d112, the operator of the plant 2 can display data related to, for example, the temperature difference between the site A and the site C, the pressure difference between the site B and the site C, and the pressure difference between the site A and the site C in the graph display area d104 and the graph display area d106.

[0085] 4. Effects An operation assistance device 4 according to one aspect of the present disclosure is an operation assistance device 4 that assists in the operation of a plant 2, and includes: an acquisition unit (target data acquisition unit 100b) that acquires target data based on measured values ​​related to at least one of temperature, pressure, and flow rate, for one or more parts in the plant 2 through which a heat transfer medium flows; and an output unit 108 that outputs assistance information related to a flow failure or a sign thereof of the heat transfer medium in the one or more parts, based on the target data and one or more reference data for when the plant 2 is operating in a normal state, wherein the one or more reference data are based on measured values ​​corresponding to the target data.

[0086] As described above, the plant management system 1 equipped with the operation support device 4 allows even non-expert operators to easily detect flow disturbances or their precursors. Furthermore, since the plant management system 1 can detect flow disturbances or their precursors based on operational data obtained from sensors already installed in the plant 2, there is no need to increase the number of instruments, making it easy to implement. Furthermore, the plant management system 1 can detect flow disturbances or their precursors regardless of the type of fuel.

[0087] The driving assistance device 4 according to one embodiment further includes a determination unit 104 that determines whether or not there is a flow disorder or a sign of such a disorder in the heat transfer medium in one or more locations based on the target data and one or more reference data, and the assistance information includes the determination result by the determination unit 104.

[0088] According to this configuration, the operators of the plant 2 can understand the judgment results made by the operation support device 4, and can therefore more easily recognize flow disturbances or signs thereof in the plant 2.

[0089] In one embodiment, the judgment unit 104 judges whether there is a flow disorder or a sign of a flow disorder in the heat transfer medium in one or more locations by inputting target data as judgment data into a learning model that has been trained with one or more reference data as learning data.

[0090] According to this configuration, it becomes possible to more easily compare the reference data with the target data, and the accuracy of the determination result is improved.

[0091] In one embodiment, the learning model learns by associating one or more reference data with each of a plurality of operating loads related to the plant 2, the target data acquisition unit 100b further acquires information regarding the operating load at the time the target data was acquired, and the determination unit 104 inputs the target data and information regarding the operating load at the time the target data was acquired into the learning model, thereby determining whether there is a flow disorder or a sign of such a disorder in the heat transfer medium in one or more locations.

[0092] Generally, the range of operational data for which it is determined that no flow disturbance or its precursor has occurred varies depending on the operational load. With this configuration, the determination is made taking such trends into consideration, thereby improving the accuracy of the determination result.

[0093] In one embodiment, the one or more parts include a first part and a second part different from the first part, the target data is generated by comparing measured values ​​of at least one of temperature, pressure, and flow rate for each of the first part and the second part, the one or more reference data are measured values ​​for each of the first part and the second part when the plant 2 is operating under normal conditions, and are generated by comparing the measured values ​​corresponding to the target data, and the support information includes information obtained by comparing the target data with the one or more reference data.

[0094] To detect flow disturbances or their precursors, it is effective to use operational data obtained by comparing measurements from multiple locations as reference data and target data. This is because abnormalities in the flow of heat transfer media tend to appear as unevenness in temperature, pressure, etc. This configuration makes it possible to detect such unevenness, improving the accuracy of the judgment results.

[0095] The driving assistance device 4 according to one embodiment further includes a memory unit 12 that stores a plurality of combinations of at least two parts in one or more parts, and the plurality of combinations stored in the memory unit 12 include a first combination and a second combination. The target data includes first target data generated by comparing measurement values ​​for at least one of temperature, pressure, and flow rate for each part included in the first combination, and second target data generated by comparing measurement values ​​for at least one of temperature, pressure, and flow rate for each part included in the second combination. The one or more reference data include one or more first reference data that are measurement values ​​for each part included in the first combination when the plant 2 is operating in a normal state and are generated by comparing measurement values ​​corresponding to the first target data, and one or more second reference data that are measurement values ​​for each part included in the second combination when the plant 2 is operating in a normal state and are generated by comparing measurement values ​​corresponding to the second target data. The assistance information includes information obtained by comparing the first target data with the one or more first reference data, and information obtained by comparing the second target data with the one or more second reference data.

[0096] For example, even if a flow disorder or its precursor cannot be detected from the difference in the measurement values ​​of the parts included in the first combination, a flow disorder or its precursor may be detectable from the difference in the measurement values ​​of the parts included in the second combination. This configuration makes it possible to comprehensively detect a flow disorder or its precursor based on the combination of multiple parts.

[0097] In one embodiment, the target data acquiring unit 100b may continuously acquire the target data at predetermined time intervals.

[0098] This configuration makes it possible to continuously monitor for the occurrence of flow disturbance or its precursors, thereby enabling the operators of the plant 2 to take measures at an early stage.

[0099] The driving assistance device 4 according to one embodiment may further include an estimation unit 106 that estimates the cause of a flow disorder or a precursor to such a disorder in the heat transfer medium in one or more locations based on the relationship between the target data and one or more reference data, and the assistance information may include information regarding the cause estimated by the estimation unit 106.

[0100] This configuration allows the operators of the plant 2 to easily grasp the cause of the flow disturbance or its precursor.

[0101] The above-described effects are merely examples and do not limit the scope of application of the present disclosure.

[0102] 8, an example of a hardware configuration in which the driving assistance device 4 is realized by a computer 70 will be described. Note that the functions of each device may be realized by dividing them into multiple devices.

[0103] As shown in FIG. 8, the computer 70 includes a processor 700 , a storage device 702 , an input I / F 704 , a data I / F 706 , a communication I / F 708 , and a display device 710 .

[0104] The processor 700 controls various processes in the computer 70 by executing programs stored in the storage device 702. For example, each functional unit included in the control unit 10 of the driving assistance device 4 can be realized by the processor 700 executing the programs stored in the storage device 702.

[0105] The storage device 702 is a storage medium such as a RAM (Random Access Memory), etc. The RAM temporarily stores the program code of the program executed by the processor 700 and data required when the program is executed.

[0106] The storage device 702 may also be a non-volatile storage medium such as a hard disk drive (HDD) or flash memory. The storage device 702 stores an operating system and various programs for implementing the above-described configurations. The storage medium storing the various programs may be a non-transitory computer-readable medium. In addition, the storage device 702 may also store tables that register various information and a database that manages the tables. Such programs and data are loaded into the storage device 702 as needed and referenced by the processor 700.

[0107] The input I / F 704 is a device for receiving input from a user. Specific examples of the input I / F 704 include a camera, a button, a microphone, a keyboard, a mouse, a touch panel, various sensors, a wearable device, etc. The input I / F 704 may be connected to the computer 70 via an interface such as a USB (Universal Serial Bus).

[0108] The data I / F 706 is a device for inputting data from outside the computer 70. A specific example of the data I / F 706 is a drive device for reading data stored in various storage media. The data I / F 706 may be provided outside the computer 70. In this case, the data I / F 706 is connected to the computer 70 via an interface such as a USB.

[0109] The communication I / F 708 is a device for performing data communication with devices external to the computer 70 via the communication network 5, either wired or wirelessly. The communication I / F 708 may be provided external to the computer 70. In this case, the communication I / F 708 is connected to the computer 70 via an interface such as a USB.

[0110] The display device 710 is a device for displaying various types of information. Specific examples of the display device 710 include a liquid crystal display, an organic EL (Electro-Luminescence) display, and a display of a wearable device. The display device 710 may be provided outside the computer 70. In this case, the display device 710 is connected to the computer 70 via, for example, a display cable. Furthermore, when a touch panel is used as the input I / F 704, the display device 710 can be configured as an integral part of the input I / F 704.

[0111] Furthermore, the components included in the various devices of the driving assistance device 4 described in the above embodiment are assumed to realize predetermined processing in cooperation with other hardware by the processor 700 executing a program stored in the storage device 702. In other words, these components are assumed to be software or firmware, as well as corresponding hardware, and in both of these concepts, they are also referred to as "functions," "means," "parts," "processing circuits," "units," or "modules," and can be interpreted as such.

[0112] 6. Modifications In the above embodiment, examples have been described in which a learning model based on simple regression analysis is primarily used, but this is not limiting. The learning model may include a neural network such as that shown in FIG. 9 . Specifically, the learning model may include a neural network including: (1) input layer nodes (where N is a natural number) that accept inputs of the operating load, temperature of a first portion, pressure of the first portion, flow rate of the first portion, ..., temperature of an Nth portion, pressure of the Nth portion, and flow rate of the Nth portion for the plant 2; (2) multiple intermediate layer nodes; and (3) output layer nodes that output values ​​corresponding to normality, aggregation occurrence, and foreign matter contamination, respectively. A learning model including such a neural network enables detection of a flow disturbance or its precursor by comprehensively taking into account measurements at multiple portions. The output value obtained from the "normal" node may correspond to the likelihood that a flow disorder or its precursor has occurred, the output value obtained from the "aggregation occurrence" node may correspond to the likelihood that a flow disorder or its precursor has occurred due to aggregation of the heat transfer medium, and the output value obtained from the "foreign matter contamination" node may correspond to the likelihood that a flow disorder or its precursor has occurred due to the contamination of foreign matter.

[0113] Although the above embodiment has been described mainly assuming a CFB boiler, the application of the present disclosure is not limited to this, and the present disclosure can be applied to any device that uses a heat transfer medium that may cause flow disturbance.

[0114] In the above embodiment, the plant 2 mainly uses biomass fuel as fuel, but the application of the present disclosure is not limited to this. For example, the present disclosure can also be applied to a plant 2 that uses waste wood fuel.

[0115] In the above embodiment, an example has been described in which the operation support device 4 outputs the support information to a display screen of the operation support device 4 itself, but this is not limiting. The operation support device 4 may also transmit the support information to a terminal device held by an operator of the plant 2.

[0116] 7. Embodiments of the Present Disclosure The present disclosure includes, for example, the following embodiments, in which the correspondence with the above-described embodiments is indicated in parentheses.

[0117] [Supplementary Note 1] An operation assistance device 4 according to one aspect of the present disclosure is an operation assistance device 4 that assists in the operation of a plant 2, and includes: an acquisition unit (target data acquisition unit 100b) that acquires target data based on measured values ​​related to at least one of temperature, pressure, and flow rate, for one or more parts in the plant 2 through which a heat transfer medium flows; and an output unit 108 that outputs assistance information related to a flow failure or a sign thereof of the heat transfer medium in the one or more parts, based on the target data and one or more reference data for when the plant 2 is operating in a normal state, wherein the one or more reference data are based on measured values ​​corresponding to the target data.

[0118] [Supplementary Note 2] The driving assistance device 4 described in Supplementary Note 1 may further include a determination unit 104 that determines whether or not there is a flow disorder or a sign of a flow disorder of the heat transfer medium in one or more parts based on the target data and one or more reference data, and the assistance information may include a determination result by the determination unit 104.

[0119] [Supplementary Note 3] In the driving assistance device 4 described in Supplementary Note 2, the determination unit 104 may determine whether or not there is a flow disorder or a sign of a flow disorder of the heat transfer medium in one or more parts by inputting target data as determination data into a learning model that has learned one or more reference data as learning data.

[0120] [Supplementary Note 4] In the operation assistance device 4 described in Supplementary Note 3, the learning model may learn by associating one or more reference data with each of a plurality of operating loads related to the plant 2, the acquisition unit (target data acquisition unit 100b) may further acquire information related to the operating load at the time the target data was acquired, and the determination unit 104 may input the target data together with information related to the operating load at the time the target data was acquired into the learning model, thereby determining whether or not there is a flow disorder or a sign of such a disorder in the heat transfer medium in one or more locations.

[0121] [Supplementary Note 5] In the driving assistance device 4 described in any one of Supplementary Notes 1 to 4, the one or more parts may include a first part and a second part different from the first part, the target data may be generated by comparing measured values ​​of at least one of temperature, pressure, and flow rate for the first part and the second part, respectively, the one or more reference data may be measured values ​​for the first part and the second part when the plant 2 is operating in a normal state, and may be generated by comparing the measured values ​​corresponding to the target data, and the assistance information may include information obtained by comparing the target data with the one or more reference data.

[0122] [Appendix 6] The driving assistance device 4 described in any one of Supplementary Notes 1 to 5 may further include a memory unit 12 that stores a plurality of combinations of at least two parts in one or more parts, and the plurality of combinations stored in the memory unit 12 may include a first combination and a second combination, the target data may include first target data generated by comparing measurement values ​​of at least one of temperature, pressure, and flow rate for each of the parts included in the first combination, and second target data generated by comparing measurement values ​​of at least one of temperature, pressure, and flow rate for each of the parts included in the second combination, the one or more reference data may include one or more first reference data that are measurement values ​​for each of the parts included in the first combination when the plant 2 is operating in a normal state and are generated by comparing measurement values ​​corresponding to the first target data, and one or more second reference data that are measurement values ​​for each of the parts included in the second combination when the plant 2 is operating in a normal state and are generated by comparing measurement values ​​corresponding to the second target data, and the assistance information may include information obtained by comparing the first target data with the one or more first reference data, and information obtained by comparing the second target data with the one or more second reference data.

[0123] [Supplementary Note 7] In the driving assistance device 4 according to any one of Supplementary Notes 1 to 6, the acquisition unit (target data acquisition unit 100b) may continuously acquire the target data at predetermined time intervals.

[0124] [Appendix 8] The driving assistance device 4 described in any one of Appendices 1 to 7 may further include an estimation unit 106 that estimates a cause of a flow disorder or a precursor thereof of the heat transfer medium in one or more locations based on a relationship between the target data and one or more reference data, and the assistance information may include information related to the cause estimated by the estimation unit 106.

[0125] [Supplementary Note 9] An operation assistance method according to another aspect of the present disclosure is an operation assistance method for assisting the operation of a plant 2, which causes a computer to execute the following steps: acquiring target data based on measured values ​​of at least one of temperature, pressure, and flow rate for one or more parts of the plant 2 through which a heat transfer medium flows; and outputting assistance information related to a flow disorder or a sign thereof of the heat transfer medium in the one or more parts based on the target data and one or more reference data for when the plant 2 is operating in a normal state, wherein the one or more reference data are based on measured values ​​corresponding to the target data.

[0126] [Supplementary Note 10] An operation assistance program according to another aspect of the present disclosure is an operation assistance program that assists in the operation of a plant 2, and causes a computer to function as: an acquisition means that acquires target data based on measured values ​​related to at least one of temperature, pressure, and flow rate for one or more parts in the plant 2 through which a heat transfer medium flows; and an output means that outputs assistance information related to a flow disorder or a sign thereof of the heat transfer medium in the one or more parts based on the target data and one or more reference data for when the plant 2 is operating in a normal state, wherein the one or more reference data are based on measured values ​​corresponding to the target data.

[0127] [Supplementary Note 11] A plant management system 1 according to another aspect of the present disclosure is a plant 2 management system including a plant 2 and an operation support device 4 that supports operation of the plant 2. The operation support device 4 includes: an acquisition unit (target data acquisition unit 100b) that acquires target data based on measured values ​​related to at least one of temperature, pressure, and flow rate, related to one or more parts in the plant 2 through which a heat transfer medium flows; and an output unit 108 that outputs support information related to a flow failure or a sign thereof of the heat transfer medium in the one or more parts, based on the target data and one or more reference data when the plant 2 is operating in a normal state, wherein the one or more reference data are based on measured values ​​corresponding to the target data.

[0128] 1... Plant management system, 2... Plant, 3... DCS, 4... Operation support device, 5... Communication network, 10... Control unit, 12... Memory unit, 14... Network interface unit, 70... Computer, 100... Acquisition unit, 100a... Reference data acquisition unit, 100b... Target data acquisition unit, 100c... Operation load information acquisition unit, 102... Generation unit, 104... Determination unit, 106... Estimation unit, 108... Output unit

Claims

1. An operation support device for supporting the operation of a plant, comprising: an acquisition unit that acquires target data based on a measurement value related to at least one of temperature, pressure, and flow rate regarding one or more parts in the plant where a heat transfer medium flows; and an output unit that outputs support information regarding a flow obstruction or its sign of the heat transfer medium in the one or more parts based on the target data and one or more reference data when the plant is operating in a normal state, wherein the one or more reference data are based on the measurement value corresponding to the target data.

2. The operation support device according to claim 1, further comprising a determination unit that determines whether or not there is a flow obstruction or its sign of the heat transfer medium in the one or more parts based on the target data and the one or more reference data, and wherein the support information includes the determination result by the determination unit.

3. The operation support device according to claim 2, wherein the determination unit determines whether or not there is a flow obstruction or its sign of the heat transfer medium in the one or more parts by inputting the target data as determination data to a learning model that has learned the one or more reference data as learning data.

4. The learning model learns by associating the one or more reference data with each of a plurality of operation loads regarding the plant. The acquisition unit further acquires information regarding the operation load when the target data is acquired. The determination unit determines whether or not there is a flow obstruction or its sign of the heat transfer medium in the one or more parts by inputting, to the learning model, the information regarding the operation load when the target data is acquired together with the target data.

5. The above one or more parts include a first part and a second part different from the first part, the target data is generated by comparing measurement values related to at least one of temperature, pressure, and flow rate for each of the first part and the second part, the above one or more reference data are measurement values related to each of the first part and the second part when the plant is operating in a normal state, and are generated by comparing measurement values corresponding to the target data, and the support information includes information obtained by comparing the target data with the above one or more reference data. The operation support device according to claim 1.

6. The operation support device according to claim 1, further comprising a storage unit that stores a plurality of combinations of at least two parts among the above one or more parts. The plurality of combinations stored in the storage unit include a first combination and a second combination. The target data includes first target data generated by comparing measurement values related to at least one of temperature, pressure, and flow rate for each part included in the first combination, and second target data generated by comparing measurement values related to at least one of temperature, pressure, and flow rate for each part included in the second combination. The above one or more reference data include one or more first reference data that are measurement values related to each part included in the first combination when the plant is operating in a normal state and are generated by comparing measurement values corresponding to the first target data, and one or more second reference data that are measurement values related to each part included in the second combination when the plant is operating in a normal state and are generated by comparing measurement values corresponding to the second target data. The support information includes information obtained by comparing the first target data and the above one or more first reference data, and information obtained by comparing the second target data and the above one or more second reference data.

7. The acquisition unit continuously acquires the target data at a predetermined time interval. The operation support device according to claim 1.

8. An estimating unit that estimates a cause of a heat transfer medium flow obstruction or a sign thereof in the one or more parts based on a relationship between the target data and the one or more reference data, is further provided, and the support information includes information regarding the cause estimated by the estimating unit. The operation support device according to claim 1.

9. An operation support method for supporting the operation of a plant, which causes a computer to perform: a step of acquiring target data based on a measurement value related to at least one of temperature, pressure, and flow rate regarding one or more parts in the plant where a heat transfer medium flows; and a step of outputting support information regarding a heat transfer medium flow obstruction or a sign thereof in the one or more parts based on the target data and one or more reference data when the plant is operating in a normal state, wherein the one or more reference data are based on a measurement value corresponding to the target data. The operation support method.

10. An operation support program for supporting the operation of a plant, which causes a computer to function as: an acquisition means for acquiring target data based on a measurement value related to at least one of temperature, pressure, and flow rate regarding one or more parts in the plant where a heat transfer medium flows; and an output means for outputting support information regarding a heat transfer medium flow obstruction or a sign thereof in the one or more parts based on the target data and one or more reference data when the plant is operating in a normal state, wherein the one or more reference data are based on a measurement value corresponding to the target data. The operation support program.

11. A plant management system including a plant and an operation support device for supporting the operation of the plant, wherein the operation support device includes: an acquisition unit that acquires target data based on a measurement value related to at least one of temperature, pressure, and flow rate regarding one or more parts in the plant where a heat transfer medium flows; and an output unit that outputs support information regarding a heat transfer medium flow obstruction or a sign thereof in the one or more parts based on the target data and one or more reference data when the plant is operating in a normal state, wherein the one or more reference data are based on a measurement value corresponding to the target data. The plant management system.

Images