Maintenance management support system of power generation plant and maintenance management support method of power generation plant

Abstract

To enable support of maintenance management of devices contained in a power generation plant system by using quantitative indexes of a required performance of the system (containing performance to be satisfied by the system even when the devices have deteriorated).SOLUTION: A maintenance management support system 100 of a power generation plant includes: a deteriorated device identifying matrix 50 which outputs a deteriorated device and a deterioration cause with input of an evaluation result of increase and decrease of a measurement data group when the device has deteriorated; and an index evaluation matrix 40 which outputs, as a second index, a measurement data estimation value having a strong correlation with a required performance to be satisfied by the system when the device has deteriorated with input of a first index being measurement data or a linear combination value of the measurement data group when the device has deteriorated. A deteriorated device candidate of the system and a cause of deterioration are estimated on the basis of the deteriorated device identifying matrix 50, and a second quantitative index of a required performance (containing performance to be satisfied by the system even when device has deteriorated) is calculated on the basis of the index evaluation matrix 40.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a power plant maintenance support system and a power plant maintenance support method capable of supporting the maintenance management of equipment included in a system of the power plant. [Background technology]

[0002] A power plant is composed of multiple systems with different roles to be played. Each system is designed to meet its own required specifications, but the required specifications of the system are not necessarily set assuming normal operation. For example, the reactor auxiliary cooling seawater system is used to remove heat from regular equipment (power generation equipment) during normal operation, but its required performance is heat removal performance in the event of an accident. Therefore, the required specifications of the equipment included in the reactor auxiliary cooling seawater system are set to satisfy the heat removal performance in the event of an accident.

[0003] Conventionally, it has been difficult to evaluate the required performance (e.g., heat removal performance) under different operating conditions (e.g., during an accident) using measurement data of a system during normal operation. As a conventional technique, a method has been disclosed in which information (data) related to the deterioration rate and failure rate of power plant equipment is collected, and the maintenance frequency evaluation of the power plant equipment is performed based on the collected data (actual situation) (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2019-133360 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, the method described in Patent Document 1 could not quantitatively evaluate the deterioration amount (margin for required performance) of the system performance of the power plant. Therefore, even if there is a margin for deterioration of the required performance of the system, maintenance work has to be performed at the time when the equipment deteriorates, and it is not possible to rationally reduce the frequency of maintenance according to the degree of deterioration of the required performance of the system.

[0006] The present invention has been made in consideration of the above background, and has an objective of providing a power plant maintenance support system and a power plant maintenance support method that are capable of supporting the maintenance management of equipment included in a power plant system by using quantitative indicators of the required performance of the power plant system (including the performance that the system must satisfy even when the equipment is deteriorated). [Means for solving the problem]

[0007] In order to solve the above problems, a power plant maintenance support system according to one aspect of the present invention includes a measurement knowledge database that stores a measurement data group consisting of a plurality of measurement data acquired through a plurality of measuring instruments provided in the power plant, and a maintenance knowledge database that stores maintenance information about equipment provided in a system of the power plant, the maintenance knowledge database storing a deteriorated equipment identification matrix that receives an evaluation result of an increase or decrease in the measurement data group when equipment is deteriorated and outputs deteriorated equipment and a cause of deterioration, and an index evaluation matrix that receives a first index that is a linear combination value of the measurement data or the measurement data group when equipment is deteriorated and outputs a measurement data estimate value that has a strong correlation with the required performance that the system should satisfy when equipment is deteriorated as a second index. The power plant maintenance support system further includes an index evaluation unit that calculates and outputs an index of the system using information on the measurement data group of the actual equipment in the measurement knowledge database and the index evaluation matrix during normal operation of the power plant, a deteriorated equipment identification unit that estimates and outputs deteriorated equipment candidates and causes of deterioration using information on the measurement data group of the actual equipment in the measurement knowledge database and the deteriorated equipment identification matrix, and a display processing unit that displays and processes the output information of the index evaluation unit and the deteriorated equipment identification unit. Effect of the Invention

[0008] According to at least one aspect of the present invention, it is possible to realize a power plant maintenance support system and a power plant maintenance support method that can support the maintenance management of equipment included in a power plant system by using quantitative indicators of the required performance of the power plant system (including the performance that the system must satisfy even when equipment is deteriorated). Problems, configurations and effects other than those described above will become apparent from the following description of the embodiments. [Brief description of the drawings]

[0009] [Figure 1] 1 is a block diagram showing an example of the configuration of a power plant maintenance support system according to a first embodiment of the present invention. [Diagram 2] 3 is a table showing an example of data stored in a maintenance knowledge database of the power plant maintenance support system according to the first embodiment of the present invention. [Diagram 3] 4 is a table showing an example of data stored in a measurement knowledge database of the power plant maintenance support system according to the first embodiment of the present invention. [Figure 4] 2 is a diagram showing details of an index evaluation unit of the power plant maintenance support system according to the first embodiment of the present invention. FIG. [Diagram 5] 2 is a diagram showing details of a deteriorated equipment identification unit of the power plant maintenance support system according to the first embodiment of the present invention. FIG. [Figure 6] FIG. 11 is a block diagram showing an example of the configuration of a power plant maintenance support system according to a second embodiment of the present invention. [Figure 7] FIG. 11 is a diagram showing details of a maintenance proposal determination unit of a power plant maintenance support system according to a second embodiment of the present invention. [Figure 8] FIG. 11 is a diagram showing details of a maintenance work proposal unit of a power plant maintenance support system according to a second embodiment of the present invention. [Figure 9] FIG. 11 is a block diagram showing an example of the configuration of a power plant maintenance support system according to a third embodiment of the present invention. [Figure 10]FIG. 11 is a diagram showing details of a monitoring strengthening determination unit of a power plant maintenance support system according to a third embodiment of the present invention. [Figure 11] FIG. 11 is a diagram showing details of a monitoring strengthening proposal unit of a power plant maintenance support system according to a third embodiment of the present invention. [Figure 12] FIG. 11 is a block diagram showing an example of the configuration of a power plant maintenance support system according to a fourth embodiment of the present invention. [Figure 13] FIG. 13 is a diagram showing details of an analysis model tuning and sensitivity analysis unit of a power plant maintenance support system according to a fourth embodiment of the present invention. [Figure 14] FIG. 13 is a diagram showing details of a deteriorated equipment identification matrix constructing unit of a power plant maintenance support system according to a fourth embodiment of the present invention. [Figure 15] FIG. 13 is a diagram showing details of an index evaluation matrix constructing unit of the power plant maintenance support system according to the fourth embodiment of the present invention. [Figure 16] FIG. 13 is a block diagram showing an example of the configuration of a power plant maintenance support system according to a fifth embodiment of the present invention. [Figure 17] FIG. 13 is a diagram showing details of a risk determination unit of a power plant maintenance support system according to a fifth embodiment of the present invention. [Figure 18] FIG. 13 is a block diagram showing an example of the configuration of a power plant maintenance support system according to a sixth embodiment of the present invention. [Figure 19] FIG. 13 is a diagram showing an example of a proposal format created by a proposal creation unit of the power plant maintenance support system according to the sixth embodiment of the present invention. [Figure 20] 1 is a block diagram showing an example of a hardware configuration of a computer constituting a power plant maintenance support system according to an embodiment of the present invention; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, examples of modes for carrying out the present invention (hereinafter, referred to as "embodiments") will be described with reference to the accompanying drawings. In this specification and the accompanying drawings, identical or similar components are given the same reference numerals, and duplicate explanations may be omitted, or only differences may be explained. In addition, when there are multiple identical or similar components, they may be explained with different subscripts added to the same reference numerals. In addition, when it is not necessary to distinguish between these multiple components, the subscripts may be omitted. The number of each component may be singular or plural, unless otherwise specified.

[0011] In the following embodiments, various information will be described in table format, but the various information may be in a data format other than the table format. Also, for example, various names such as "XX information", "XX table", "XX list", and "XX list" are interchangeable. Also, when describing identification information, expressions such as "identification information", "name", and "ID" are used, but these are interchangeable.

[0012] <First embodiment> [Configuration of power plant maintenance support system] First, a configuration of a power plant maintenance support system according to a first embodiment of the present invention will be described with reference to Fig. 1. The present invention is a system capable of supporting the maintenance management of equipment included in a power plant system by using a quantitative index of required performance of the system (performance that the system should satisfy).

[0013] FIG. 1 is a block diagram showing an example of the configuration of a power plant maintenance support system according to a first embodiment of the present invention. The power plant maintenance support system 100 according to this embodiment is composed of a maintenance knowledge database 1, a measurement knowledge database 2, an index evaluation unit 7, a deteriorated equipment identification unit 8, and a display processing unit 15. An example of data stored in the maintenance knowledge database 1 and the measurement knowledge database 2 will be described below with reference to Figs. 2 and 3.

[0014] [Conservation Knowledge Database] FIG. 2 is a table showing an example of data stored in the maintenance knowledge database 1. As shown in FIG. The maintenance knowledge database 1 stores inspection records and information about malfunctions (deterioration) that have occurred in the past. In this specification, "malfunction" includes not only breakdowns and malfunctions, but also deterioration of performance. Conversely, when expressed as "deterioration," it can refer to malfunctions of equipment (systems) in general.

[0015] The maintenance knowledge database 1 has items such as "date and time," "system name," "fault," "maintenance," and "related documents." "Date and time" stores information indicating the date and time when a malfunction (deterioration) occurred in the past. The "system name" stores information indicating the name of a system that has equipment that has previously experienced a malfunction (deterioration). The information stored in the "system name" may be a character string such as alphanumeric characters. In other words, the information stored in the "system name" may be information that can uniquely identify a system.

[0016] "Malfunction" has two sub-categories: "Equipment" and "Cause." "Equipment" stores information that can identify the equipment in question, such as the name of the equipment where the malfunction occurred. The location of the malfunction is identified from the "system name" and "equipment." Figure 2 shows "Valve C" and "Heat Exchanger D (short for heat exchanger D)" as examples of equipment. "Cause" stores information indicating the cause of the malfunction. In this specification, the cause of the malfunction can also be rephrased as the malfunction phenomenon. In Figure 2, "clogging" and "leak" are shown as examples of causes.

[0017] "Maintenance" stores information indicating the measures taken to address the problem. Figure 2 shows "cleaning" and "replacement" as examples of maintenance. "Related documents" stores information on various related documents issued when dealing with defects. "Related documents" can store information indicating the location of related documents, such as URL (Uniform Resource Locator) information.

[0018] Although not shown in the figure, the maintenance knowledge database 1 also stores maintenance information such as the current monitoring frequency of each device (pumps, valves, piping, heat exchangers, etc.), the maintenance frequency of time-based maintenance of the device, instruction manuals, and two types of matrix information described below, as well as a threshold value for index X described below. The monitoring frequency is the frequency with which measurement data (pressure, temperature, flow rate, etc.) is acquired to check the soundness of the device. Time-based maintenance is maintenance that is performed at a predetermined frequency, such as once a month or once every six months.

[0019] [Measurement knowledge database] FIG. 3 is a table showing an example of data stored in the measurement knowledge database 2. As shown in FIG. The measurement knowledge database 2 stores power plant trial operation data (date and time, system name, measuring instrument ID, measurement data, etc.). Measurement data sets obtained periodically during normal operation (pressure, temperature, flow rate, etc. measured by various measuring instruments in various systems) are also stored in this database. Figure 3 shows an example in which the maintenance knowledge database 1 has items such as "date and time", "system name", "measuring instrument ID", "type", and "measurement value".

[0020] The "date and time" field stores information indicating the date and time when the measurement data was acquired during the test run of the power plant. The "system name" stores information indicating the name of the system in which the measuring instrument that output the measurement data during the test run is located. The information stored in the "system name" is not limited to the name of the system, but may be any information that can uniquely identify the system. "Measurement instrument ID" stores ID (IDentification) information for identifying the measurement instrument that output the measurement data during the test run. The measurement instrument ID is not limited to ID, but may be any information that can identify the measurement instrument.

[0021] "Type" and "Measurement value" are examples of measurement data. "Type" is information that indicates the type of measurement data (physical quantity) measured by the measuring instrument to which the target measuring instrument ID is assigned. In Figure 2, "temperature," "flow rate," and "pressure" are shown as examples of types. A "measurement value" is the value (physical quantity) of data measured by a measuring instrument.

[0022] During normal operation, measurement data is collected periodically. Old data is deleted and replaced with new data as appropriate according to the capacity limits of the storage device that stores the data, but important data such as test run data is kept in the storage device permanently.

[0023] Next, the operation of the power plant maintenance support system 100 according to this embodiment will be described with reference to FIGS.

[0024] [Index Evaluation Department] FIG. 4 is a diagram showing the index evaluation unit 7 in detail. The index evaluation unit 7 receives a group of measurement data relating to a specific system of an online actual machine during normal operation from the measurement knowledge database 2, and receives information on the index evaluation matrix 40 relating to the specific system from the maintenance knowledge database 1. The index evaluation matrix 40 inputs an index X (first index) which is a linear combination value of measurement data or a group of measurement data during normal operation of the actual equipment, and outputs an estimated measurement data value having a strong correlation with the required performance (system health) that the system should satisfy when equipment deteriorates as an index Y (second index). The index evaluation matrix 40 is information that connects normal operation (measurement data of the actual equipment) and accidents (indexes that satisfy the required performance of the system).

[0025] The index evaluation unit 7 calculates an index Y from the index X using the received index evaluation matrix 40. Here, if a threshold value, which will be described later, is set in advance for the index X, it is possible to check the state of performance deterioration of the system by comparing the threshold value with the index X. The index Y is an index that quantitatively represents the deterioration of the system performance.

[0026] Specific examples of the index X include, for example, the measurement data values ​​of the water temperature at the inlet and outlet of the heat exchanger on the heat dissipation side and the water temperature at the inlet of the heat exchanger on the heat receiving side during normal operation, and a linear combination value of these measurement data values. Also, a specific example of the index Y is, for example, the water temperature at the outlet of the heat exchanger during an accident (an index of the heat removal performance of the heat exchanger during an accident). The required performance can also be rephrased as the performance that should be met in a specific situation (for example, during an accident).

[0027] [Deteriorated Equipment Identification Department] FIG. 5 is a diagram showing details of the deteriorated device identification unit 8. As shown in FIG. The deteriorated equipment identification unit 8 receives a group of measurement data relating to a specific system of an online actual machine during normal operation from the measurement knowledge database 2, and receives information on the deteriorated equipment identification matrix 50 relating to the specific system from the maintenance knowledge database 1. The deteriorated equipment identification matrix 50 receives as input the evaluation results of the increase or decrease in the measurement data group (high or low measured values) when equipment deteriorates, and outputs the deteriorated equipment and the cause of the deterioration.

[0028] The deteriorated equipment identification unit 8 first compares a group of measurement data of the online actual equipment during normal operation with a group of measurement data of the actual equipment in a state without equipment deterioration, and evaluates the deviation (high / low) of the group of measurement data of the online actual equipment during normal operation from the "normal state". Note that the group of measurement data of the actual equipment at the start of normal operation when no equipment malfunction (deterioration) occurs is stored in advance in the measurement knowledge database 2 as data of the "normal state".

[0029] Next, after evaluating the deviation (high / low) from the normal state of the measurement data group of the actual equipment, the deteriorated equipment identification matrix 50 is used to extract equipment that may be malfunctioning (candidate deteriorated equipment), the cause of the malfunction, and candidate maintenance methods for the malfunction from the combination of high and low values ​​of the measurement data group of the actual equipment (e.g., P1, P2, ΔP3, T1, etc.). The high and low values ​​of the measurement data group of the actual equipment correspond to changes in the measurement data. Note that the maintenance candidates refer to candidate maintenance methods, and may hereinafter be referred to simply as "maintenance methods".

[0030] In the example shown in Figure 5, when the combination of high and low levels of the measurement data group of the actual equipment is "P1: low, ΔP3: low," "Valve A, Valve B" are extracted as equipment that may be malfunctioning (candidate deteriorated equipment #1, #2), the cause of the malfunction is "clogging," and a candidate maintenance measure for the malfunction is "cleaning."

[0031] It should be noted that even if different equipment has different malfunctions, the combination of high and low measurement data groups may be the same. Therefore, in general, it is not possible to narrow down the degraded equipment candidates, malfunction causes, and malfunction maintenance candidates to one, and the evaluation results are output in the form of a list including multiple candidates. For example, in Figure 5, when "P1: low, ΔP3: low" is observed, valve A (clogging) and valve B (clogging) are extracted as degraded equipment candidates #1 and #2 and their cause candidates.

[0032] [Display processing section] The display processing unit 15 (FIG. 1) receives the outputs of the index evaluation unit 7 and the deteriorated equipment identification unit 8, i.e., the current values ​​of the indexes (index X and index Y) and the threshold value of index X, a list of equipment that may be deteriorated, information on measuring instruments (measuring instrument IDs, etc.) whose measured values ​​deviate (high / low) from the normal state, etc. Then, the display processing unit 15 performs processing to display this information online on a display device 16 (operator monitoring screen) such as a central control panel in the central control room.

[0033] This allows operators and other relevant personnel to detect system malfunctions (possibility of the system being unable to meet required performance) online. Furthermore, when a malfunction is likely to occur in the system, operators and other relevant personnel can check candidate degraded equipment for which maintenance work should be performed to resolve the malfunction. Moreover, operators can determine the necessity of maintenance work for candidate degraded equipment by comparing the displayed index X with a threshold value.

[0034] As described above, the power plant maintenance support system 100 (FIG. 1) of this embodiment can support the maintenance management of equipment included in a power plant system by using an index of the quantitative deterioration amount of the required performance of the system (including the performance that the system must satisfy even when equipment is deteriorated). Operators and other managers, who previously performed equipment maintenance work by inspecting equipment more frequently regardless of the degree of deterioration of the system's performance requirements, can now perform maintenance work at appropriate times based on quantitative indicators, thereby streamlining the maintenance management work of equipment in the power plant's system.

[0035] <Second embodiment> FIG. 6 is a block diagram showing an example of the configuration of a power plant maintenance support system according to the second embodiment of the present invention. A power plant maintenance support system 100A according to the second embodiment differs from the power plant maintenance support system 100 (FIG. 1) according to the first embodiment in that a maintenance proposal determination unit 9 and a maintenance work proposal unit 10 are provided subsequent to the index evaluation unit 7. Note that FIG. 6 omits the display device 16 shown in FIG. 1. With this configuration, the following points are improved in this embodiment compared to the first embodiment.

[0036] In the first embodiment described above, the index X had to be compared with the threshold value by an operator, but in this embodiment, the comparison work can be automated by adding the maintenance proposal determination unit 9. Also, by adding the maintenance work proposal unit 10, it becomes possible to automatically extract information related to maintenance stored in the maintenance knowledge database 1 (knowledge related to the maintenance of candidate deteriorated devices) and display the extracted information as proposal information by the display processing unit 15. In addition, by storing the proposal information output by the maintenance work proposal unit 10 as new data (additional items) in the maintenance knowledge database 1, it is possible to automatically and continuously expand knowledge related to maintenance.

[0037] [Maintenance proposal judgment department] FIG. 7 is a diagram showing the maintenance proposal determination unit 9 in detail. The maintenance suggestion determination unit 9 receives the index X calculated by the index evaluation unit 7 as an input and determines whether the index X is equal to or greater than a threshold value V1. The threshold value V1 is a threshold value for determining the necessity of maintenance work aimed at restoring the functionality of a candidate deteriorated device. Functional restoration includes repair, cleaning, adjustment, and even replacement of the device. The index X can also be said to be an index for determining whether or not to perform maintenance (this embodiment) or to strengthen monitoring (third embodiment) by applying a threshold value.

[0038] An example of threshold value V1 is shown in the lower part of Fig. 7. In the graph shown in the lower part of Fig. 7, the horizontal axis indicates the measurement data or its linear combination value (index X), and the vertical axis indicates the measurement data estimated value (index Y) that has a strong correlation with the required performance. The graph in the lower part of Fig. 7 corresponds to the index evaluation matrix 40 shown in Fig. 4.

[0039] If the index X≧V1 (YES judgment), the maintenance proposal determination unit 9 judges that maintenance work is required for any of the deteriorated device candidates, and generates a maintenance work proposal trigger signal for executing the maintenance work proposal unit 10.

[0040] A typical system is designed to be robust so that minor malfunctions in the equipment do not impair the required performance. Therefore, when the measurement data or the linear combination value of the measurement data group during normal operation of the actual equipment (index X) is lower than the threshold V1 (NO judgment), the measurement data estimate value (index Y), which has a strong correlation with the required performance that the system must satisfy, hardly changes (required performance is not impaired). However, when the measurement data or the linear combination value of the measurement data group during normal operation of the actual equipment (index X) exceeds the threshold V1, a deterioration in the required performance of the system (increase in index Y in the figure) can be seen. In the graph at the bottom of Figure 7, an increase in index Y can be seen when index X exceeds the threshold V1.

[0041] By setting the threshold value V1 in this way, it becomes possible to identify the timing when the deterioration of the required performance of the system (heat removal performance during an accident, etc.) starts, using the index X. Note that, although Fig. 7 shows an example in which the deterioration of the required performance of the system starts when the index X becomes equal to or greater than the threshold value V1, there may also be cases in which the deterioration of the required performance of the system starts when the index X falls below the threshold value V1 (the index Y declines to the right).

[0042] [Maintenance work proposal department] FIG. 8 is a diagram showing the maintenance work proposal unit 10 in detail. The maintenance work proposal unit 10 is started upon receiving a maintenance work proposal trigger signal issued by the maintenance proposal determination unit 9. The maintenance work proposal unit 10 receives an index X and an index Y from the maintenance proposal determination unit 9. The maintenance work proposal unit 10 also receives knowledge related to equipment maintenance of deteriorated equipment candidates (such as the manufacturer name, instruction manual, parts ordering history, and deteriorated equipment identification matrix of the equipment) from the maintenance knowledge database 1. Furthermore, the maintenance work proposal unit 10 also receives a list of deteriorated equipment candidates, causes of malfunctions, and maintenance candidates for the malfunctions (deteriorated equipment candidate list 80) from the deteriorated equipment identification unit 8.

[0043] Then, when there is a possibility that the required performance cannot be maintained due to the performance deterioration of the system (when a maintenance work proposal trigger signal is generated), the maintenance work proposal unit 10 outputs, in a table format, the index, the cause of the malfunction, the maintenance candidate (maintenance method), and various knowledge (examples of proposed information) for each device (deteriorated device candidate) registered in the deteriorated device candidate list 80. The output information is displayed on the display device 16 by the display processing unit 15. The various knowledge is information such as the manufacturer name, instruction manual, and parts order history of the device. This makes it possible to realize the efficiency of the maintenance work of the devices included in the system. The maintenance work proposal unit 10 stores the output information (proposal information) as new data in the maintenance knowledge database 1, thereby automatically and continuously expanding the knowledge related to maintenance.

[0044] As described above, by using the power plant maintenance support system 100A (FIG. 6) according to this embodiment, the following effects can be obtained in addition to the effects obtained in the first embodiment. The power plant maintenance support system 100A is provided with an automatic determination function for when an index X, which is a linear combination value of measurement data or a group of measurement data during normal operation of an actual plant, exceeds a threshold value V1, and is also capable of displaying appropriate maintenance information on the display device 16. This reduces the burden on operators involved in the maintenance management of the power plant.

[0045] <Third embodiment> FIG. 9 is a block diagram showing an example of the configuration of a power plant maintenance support system according to the third embodiment of the present invention. The power plant maintenance support system 100B according to the second embodiment differs from the power plant maintenance support system 100A according to the second embodiment (see FIG. 6) in that a monitoring strengthening determination unit 11 and a monitoring strengthening proposal unit 12 are provided subsequent to the maintenance proposal determination unit 9. With this configuration, the following points are improved in this embodiment compared to the second embodiment.

[0046] In the second embodiment described above, when the index X reaches the threshold value V1 (timing when the required performance of the system starts to deteriorate), various maintenance-related information of the device (the index, cause of the malfunction, maintenance method, manufacturer name of the device, instruction manual, parts order history, etc.) is output to the display device 16. However, in consideration of the time required for securing maintenance workers and preparing replacement parts for the device, it is preferable to recognize the signs of malfunction before the required performance of the system starts to deteriorate.

[0047] In this embodiment, by adding the monitoring strengthening determination unit 11, it is possible to suggest to the operator that the monitoring of equipment that may cause the start of deterioration of the required performance of the system in the future be strengthened. Also, similar to the maintenance work suggestion unit 10, by adding the monitoring strengthening suggestion unit 12, it is possible to automatically extract information related to maintenance stored in the maintenance knowledge database 1 (information for strengthening the monitoring of potential deteriorated equipment), and display the extracted information as suggested information by the display processing unit 15.

[0048] [Supervision Enhancement Judgment Department] FIG. 10 is a diagram showing the monitoring strengthening determination unit 11 in detail. When the preservation proposal determination unit 9 makes a NO determination, the monitoring enhancement determination unit 11 determines whether or not the index X calculated by the index evaluation unit 7 is greater than or equal to the threshold value V2, with the index X as the input. The threshold value V2 is a threshold value for determining the necessity of monitoring enhancement, which is for the purpose of monitoring the deterioration progress of the deterioration equipment candidates.

[0049] An example of the threshold value V2 is described in the lower part of FIG. 10. In the graph shown in the lower part of FIG. 10, the horizontal axis represents the measurement data or its linearly combined value (index X), and the vertical axis represents the measurement data estimated value (index Y) that is strongly correlated with the required performance. The graph in the lower part of FIG. 10 corresponds to the index evaluation matrix 40 shown in FIG. 4.

[0050] The threshold value V2 is set to a value smaller than the threshold value V1 at which deterioration of the required performance (increase in index Y in FIG. 7) occurs, and that value needs to be appropriately changed according to the accumulation of operation experience. That is, the value of the threshold value V2 needs to be set to a value with an appropriate time margin so that there is no risk that the index X will quickly shift from "V2" to "V1". Therefore, it is necessary to determine the deterioration progress speed of the horizontal axis (index X) in the lower part of FIG. 10 based on the operation experience and set it appropriately.

[0051] When the index X ≥ V2 (YES determination), the monitoring enhancement determination unit 11 determines that monitoring enhancement of the deterioration equipment candidates is necessary and generates a monitoring enhancement proposal trigger signal for executing the monitoring enhancement proposal unit 12. On the other hand, when the index X < V2 (NO determination), the monitoring enhancement determination unit 11 does nothing and ends the process.

[0052] By setting the threshold value V2 in this way, it becomes possible to smoothly perform the prior preparation of the preservation work (securing appropriate resources such as preparing replacement parts) when the index X exceeds the threshold value V1. Thereby, the occurrence time of an unplanned stop of the power generation plant or the like can be minimized. Note that in FIG. 10, an example is shown in which when the index X becomes greater than or equal to the threshold value V2, enhancement of the equipment performance monitoring is proposed. However, a case where enhancement of the equipment performance monitoring is proposed when the index X is below the threshold value V2 is also conceivable, and in that case, V1 < V2.

[0053] [Monitoring Enhancement Proposal Unit] FIG. 11 is a diagram showing the details of the monitoring strengthening suggestion unit 12. As shown in FIG. The monitoring strengthening proposal unit 12 is started upon receiving a monitoring strengthening proposal trigger signal issued by the monitoring strengthening determination unit 11. The monitoring strengthening proposal unit 12 receives an index X and an index Y from the monitoring strengthening determination unit 11. The monitoring strengthening proposal unit 12 also receives knowledge related to equipment maintenance (measuring instrument ID, measurement frequency, deteriorated equipment identification matrix, etc.) from the maintenance knowledge database 1. The monitoring strengthening proposal unit 12 also receives deteriorated equipment candidates, combination information of increases and decreases (high / low) in the measurement data group for each deteriorated equipment candidate, the cause of the malfunction, and a list of malfunctioning maintenance candidates (deteriorated equipment candidate list 80) from the deteriorated equipment identification unit 8. The monitoring strengthening proposal unit 12 acquires information (measuring instrument ID, measurement frequency, etc.) of the measuring instruments in which changes were observed in the measurement data (P1, P2, ΔP3, . . . ) for each deteriorated equipment candidate. The combination information of increases and decreases (high / low) in the measurement data group for each deteriorated equipment candidate becomes information that leads to identification of the malfunctioning equipment (deteriorated equipment candidate) and the cause of the malfunction (utilizing the deteriorated equipment identification matrix).

[0054] Then, the monitoring strengthening proposal unit 12 uses the received information to organize in a table format the indicators, measuring device IDs for monitoring the deterioration, and the current measuring frequencies of the measuring device IDs (examples of proposal information) for each deteriorated device candidate and deterioration cause, and outputs the organized information. The output information is displayed on the display device 16 by the display processing unit 15.

[0055] When there is a possibility that index X will exceed threshold value V1 in the near future, monitoring strengthening proposal unit 12 uses a deteriorated equipment identification matrix 50 to identify measuring instrument IDs whose measurement data values ​​increase or decrease as deterioration of deteriorated equipment candidates progresses, targeting deteriorated equipment candidates at the time index X exceeds threshold value V2. After the power plant maintenance team considers increasing the measurement frequency of measuring instruments with the identified measuring instrument IDs, operators or the like manually increase the measurement frequency using the operating means on the central control panel. By increasing the measurement frequency, it is possible to improve the estimation accuracy of the timing when index X will exceed threshold value V1. It is desirable to appropriately optimize the new measurement frequency set to strengthen monitoring according to the accumulation of operating results.

[0056] As a measure to strengthen monitoring, not only increasing the measurement frequency but also manually adding new measurement items (monitoring items) is possible. Also, for equipment important to the safety or operation of the power plant, it is possible to carry out preventive maintenance work (preventive maintenance) instead of increasing the monitoring frequency based on the monitoring strengthening proposal trigger of this embodiment. By carrying out preventive maintenance using threshold value V2 as a trigger, index X can be maintained below threshold value V1, and the occurrence of maintenance work can be prevented in advance.

[0057] As described above, by using the power plant maintenance support system 100B (FIG. 9) according to this embodiment, the following effects can be obtained in addition to the effects obtained in the second embodiment. By using the threshold value V2, the power plant maintenance support system 100B can know the signs of equipment malfunction before the index X exceeds the threshold value V1, and can display information on the ID of a measuring instrument that should be monitored more intensively and the measurement frequency on the display device 16. This reduces the burden required for identifying a measuring instrument whose measurement frequency should be changed and for collecting information such as the current measurement frequency of the measuring instrument, and can notify the operator of the possibility of a malfunction occurring in the future with the required performance of the system.

[0058] <Fourth embodiment> FIG. 12 is a block diagram showing an example of the configuration of a power plant maintenance support system according to a fourth embodiment of the present invention. A power plant maintenance support system 100C according to the fourth embodiment differs from the power plant maintenance support system according to the third embodiment (see FIG. 9) in that the power plant maintenance support system 100C has a configuration for constructing two types of matrices (deteriorated equipment identification matrix, index evaluation matrix) offline. That is, the power plant maintenance support system 100C has a design / site knowledge database 3, an analytical model tuning and sensitivity analysis unit 4, a deteriorated equipment identification matrix construction unit 5, and an index evaluation matrix construction unit 6. With such a configuration, the following points are improved in this embodiment compared to the third embodiment.

[0059] In this embodiment, first, two types of matrices are constructed by performing multiple analyses offline using test operation data acquired before the start of normal operation. Generally, system analysis requires a certain amount of computer resources, so it is difficult to evaluate the required performance of a system online based on measurement data during normal operation.

[0060] In contrast, in the method according to the present embodiment, all the work related to the matrix creation is performed offline, so that numerous sensitivity analyses and two types of matrix construction can be performed without depending on computer resources or calculation speed. Sensitivity analysis quantitatively shows how each input parameter affects the output of the system. Sensitivity analysis can also analyze the interactions between input parameters that may have a significant effect on the output.

[0061] [Design / Site Knowledge Database] The design / site knowledge database 3 (not shown) stores design information and site information of various systems and equipment. The design information includes, for example, system configuration diagrams such as piping and instrumentation diagrams (P&IDs), single-line diagrams, and equipment layout diagrams, control system information such as interlock block diagrams (IBDs), and design specifications for systems and equipment. The site information includes information such as the actual installation status of equipment at the power plant site.

[0062] Below, we will explain in detail the process of constructing two types of matrices offline. As a first step in constructing the matrix, an analysis model construction unit (not shown) acquires information required for constructing the analysis model (system configuration, equipment specifications, equipment installation positions, control information, etc.) from the design / site knowledge database 3, and constructs an analysis model. The analysis model construction unit may be provided in the power plant maintenance support system, or may be installed outside the power plant maintenance support system.

[0063] Next, in the analytical model tuning and sensitivity analysis unit 4, a plurality of analyses (sensitivity analyses) are performed using the constructed analytical model and information in the measurement knowledge database 2. Then, the analysis results are transferred from the analytical model tuning and sensitivity analysis unit 4 to the degraded equipment identification matrix construction unit 5 and the index evaluation matrix construction unit 6. Next, the degraded equipment identification matrix construction unit 5 and the index evaluation matrix construction unit 6 construct a degraded equipment identification matrix and an index evaluation matrix.

[0064] [Analysis model tuning and sensitivity analysis part] FIG. 13 is a diagram showing details of the analytical model tuning and sensitivity analysis unit 4. As shown in FIG. The analytical model tuning and sensitivity analysis unit 4 constructs an analytical model of the system based on information such as the system configuration diagram, control system information, and design specifications of the system and equipment read from the design / site knowledge database 3 (S1301).

[0065] The analytical model of the system is constructed based on design information (e.g., pump performance, pressure loss characteristics of valves / pipes / heat exchangers, heat exchange performance of heat exchangers, pipe length and installation height, control method, etc.). However, the system performance assumed at the time of design is generally different from the system performance of the actual equipment. Therefore, the analytical model tuning and sensitivity analysis unit 4 adjusts the parameters of the analytical model (pump performance, pressure loss coefficient of valves / pipes / heat exchangers, heat exchange performance of heat exchangers, etc.) using the boundary conditions of the system during trial operation (environmental pressure, temperature, flow rate, etc.) and the trial operation data of the actual equipment in the measurement knowledge database 2 (e.g., pressure distribution, temperature distribution, flow rate distribution, etc. in the system), and constructs a parameter-adjusted analytical model (S1302).

[0066] For example, the analytical model tuning and sensitivity analysis unit 4 adjusts the parameters of the analytical model (pressure loss coefficient, pump performance, etc.) so as to minimize the differences between the actual equipment and the analytical model with respect to the boundary conditions of the system during trial operation (environmental pressure, temperature, flow rate, etc.), as well as the pressure distribution, temperature distribution, and flow rate distribution in the system during trial operation.

[0067] The parameter-adjusted analysis model is premised on the trial operation conditions, but the analysis required for constructing the matrix is ​​two types of operation conditions: normal operation and operation conditions for the required performance evaluation of the system (for example, accident conditions for a safety system). Therefore, two types of analysis models are constructed in which the analysis conditions are changed from the trial operation conditions to the operation conditions for normal operation and required performance evaluation (S1303, S1305), and various malfunctions of the equipment (pumps, piping, heat exchangers, etc.) included in the system and various changes in the external boundary conditions are comprehensively extracted. Examples of various malfunctions include leakage from the system, clogging of the system, pump head deterioration, and deterioration of heat transfer performance of the heat exchanger. In addition, examples of various changes in the external boundary conditions include changes in seawater temperature, air temperature, and pressure / temperature changes of various external systems that affect the system.

[0068] Next, the analytical model tuning and sensitivity analysis unit 4 performs sensitivity analysis for various malfunctions of the equipment included in the system and various changes in the external boundary conditions (S1304, S1306). 13 to 15 described later, the result of the sensitivity analysis during normal operation (S1304) is denoted as "analysis A," and the result of the sensitivity analysis under operating conditions for evaluating the required performance of the system (S1306) is denoted as "analysis B."

[0069] In this embodiment, the analytical model is tuned using the test run data, but the tuning data is not limited to this. For example, the analytical model can be tuned using a group of initial measurement data after the start of normal operation or a group of initial measurement data after restarting after the end of a regular inspection.

[0070] As a second stage of the matrix construction, the sensitivity analysis results of the analytical model tuning and sensitivity analysis unit 4 are passed to the degraded equipment identification matrix construction unit 5 and the index evaluation matrix construction unit 6. Then, the degraded equipment identification matrix and the index evaluation matrix construction unit 6 construct a degraded equipment identification matrix and an index evaluation matrix.

[0071] [Deterioration Equipment Identification Matrix Construction Department] FIG. 14 is a diagram showing details of the deteriorated device identification matrix constructing unit 5. As shown in FIG. In the following description, "measurement data" refers to pressure, temperature, flow rate, etc. at locations where measuring instruments such as pressure gauges, thermometers, and flow meters are installed on an actual device. "Measurement data analysis values" refer to analysis values ​​obtained by a parameter-adjusted analysis model of pressure, temperature, flow rate, etc. at locations where measuring instruments are installed.

[0072] The deteriorated equipment identification matrix construction unit 5 receives analysis A (sensitivity analysis result during normal operation) from the analysis model tuning and sensitivity analysis unit 4 (S1401). Next, the deteriorated equipment identification matrix construction unit 5 calculates the difference between the measurement data analysis value during normal operation (analysis A) assuming degradation of a specific equipment and the measurement data analysis value of the base case of the sensitivity analysis (analysis result during normal operation with no equipment degradation) (S1402).

[0073] Next, the deteriorated device identification matrix construction unit 5 judges whether the calculated difference is greater than the measurement accuracy of the actual device (S1403). If the calculated difference is greater than the measurement accuracy of the actual device (YES judgment in S1403), the deteriorated device identification matrix construction unit 5 classifies each difference in the group of measurement data analysis values ​​as "high" or "low" (S1404). Here, if each difference in the group of measurement data analysis values ​​is positive, it is judged as "high", and if it is negative, it is judged as "low".

[0074] On the other hand, if the calculated difference is equal to or less than the measurement accuracy of the actual device (NO in S1403), deteriorated device identification matrix constructing section 5 determines that there is no significant difference (S1405).

[0075] By performing such a judgment individually for various defects and various measurement data analysis values, a "high" or "low" table of measurement data analysis values ​​can be created for each degraded device and the cause of that degradation (S1406) (see Figure 5).

[0076] Furthermore, since measures can be devised if the degraded equipment and the cause of the degradation are clear, this table also lists potential maintenance work (repair, cleaning, adjustment, replacement, etc.). In this invention, this table is called the "degraded equipment identification matrix." The constructed degraded equipment identification matrix 1400 is stored in the maintenance knowledge database 1. The blank areas in the degraded equipment identification matrix 1400 correspond to the measurement data with "no significant difference" described above.

[0077] [Index Evaluation Matrix Construction Department] FIG. 15 is a diagram showing the index evaluation matrix constructing unit 6 in detail. The index evaluation matrix constructing unit 6 receives as input the analysis results of both analysis A and analysis B. First, the index evaluation matrix constructing unit 6 identifies the analysis value (index Y) of analysis B that has a strong correlation with the required performance of the system (S1501). In this step S1501, the index evaluation matrix construction unit 6 extracts, from analysis B (the sensitivity analysis results of the operating conditions for evaluating the required performance of the system), the measurement data analysis values ​​(heat exchanger flow rate, etc.) that are highly correlated with the analysis results of the required performance of the system (heat removal amount in the event of an accident, etc.) as "index Y".

[0078] Next, the index evaluation matrix constructing unit 6 analyzes and identifies the analytical value of analysis A that has a strong correlation with the analytical value of analysis B (index Y) or a linear combination value (index X) of the analytical values ​​(S1502). In this step S1502, the index evaluation matrix construction unit 6 extracts a measurement data analysis value or a linear combination value (index X) of a group of measurement data analysis values ​​that is highly correlated with index Y from the measurement data analysis value of analysis A (sensitivity analysis result during normal operation) or a linear combination value (z=A·x+B·y+··, A and B are constants) of various measurement data analysis values ​​(x, y,...).

[0079] Then, the index evaluation matrix construction unit 6 constructs a relational equation (shown as a graph in FIG. 15) with index X as the horizontal axis (input) and index Y as the vertical axis (output) (S1503). This input / output relational equation is called an "index evaluation matrix" in this invention. The constructed index evaluation matrix 1500 is stored in the maintenance knowledge database 1.

[0080] In this embodiment, the relational expression that inputs the measurement data analysis value or the linear combination value (index X) of the measurement data analysis value group that has a strong correlation with the index Y and outputs the index Y is called a matrix, but the matrix is ​​not limited to this. For example, a table showing the relationship between the index X and the index Y may be created and called an index evaluation matrix.

[0081] As described above, by using the power plant maintenance support system 100C (FIG. 12) according to this embodiment, the following effects can be obtained in addition to the effects obtained in the third embodiment. The power plant maintenance support system 100C can process online maintenance support algorithms at high speed during normal operation by constructing two types of matrices offline in advance, which allows maintenance support to be performed without relying on computer resources.

[0082] The block configuration for constructing the two types of matrices offline shown on the left side of Fig. 12 is the same as that of the power plant maintenance support system 100B according to the third embodiment, but is not limited to this example. The configuration for constructing the two types of matrices offline in this embodiment can also be applied to the first and second embodiments described above, or the fifth and sixth embodiments described below.

[0083] <Fifth embodiment> FIG. 16 is a block diagram showing an example of the configuration of a power plant maintenance support system according to a fifth embodiment of the present invention. A power plant maintenance support system 100D according to the fifth embodiment differs from a power plant maintenance support system 100C (see FIG. 12) according to the fourth embodiment in that a risk determination unit 13 is provided subsequent to the monitoring strengthening determination unit 11. With this configuration, the following points are improved in this embodiment compared to the fourth embodiment.

[0084] In the fourth embodiment, the maintenance proposal determination unit 9 determines whether to perform maintenance work on the deteriorated equipment candidate based on the index X, and the monitoring strengthening determination unit 11 determines whether to strengthen monitoring of the deteriorated equipment candidate. However, the degree of influence (risk importance) on the safety of the entire power plant when the deteriorated equipment candidate breaks down cannot always be expressed by the index of the system. Therefore, in this embodiment, a risk determination unit 13 is provided that determines the risk importance of the equipment.

[0085] FIG. 17 is a diagram showing the risk determination unit 13 in detail. When the monitoring intensification determination unit 11 makes a NO determination, the risk determination unit 13 receives an index of the system from the monitoring intensification determination unit 11 and receives a candidate deteriorated equipment list from the deteriorated equipment identification unit 8. The risk determination unit 13 also receives risk importance information of the equipment constituting the power plant from the design / site knowledge database 3. For example, the risk importance information is a value of risk importance. The risk importance information of the equipment may be in a list format in which the risk importance information of the equipment constituting the power plant is described.

[0086] The risk determination unit 13 determines whether or not the value of the risk importance of the deteriorated device candidate is higher than a predetermined value (S1701). If the value of the risk importance of the deteriorated device candidate is higher than the predetermined value (YES determination in S1701), the risk determination unit 13 determines whether or not the index X received from the monitoring strengthening determination unit 11 is equal to or higher than a threshold value V3 (V2>V3) (S1702).

[0087] An example of threshold value V3 is shown in the lower part of Fig. 17. In the graph shown in the lower part of Fig. 17, the horizontal axis indicates the measurement data or its linear combination value (index X), and the vertical axis indicates the measurement data estimated value (index Y) that has a strong correlation with the required performance. The graph in the lower part of Fig. 17 corresponds to the index evaluation matrix 40 shown in Fig. 4.

[0088] When the risk importance of the candidate for deteriorated equipment is high (YES determination in S1701) and the index X ≥ V3 (YES determination in S1702), the risk determination unit 13 issues a monitoring enhancement proposal trigger signal and delivers the values of the index X and the index Y to the monitoring enhancement proposal unit 12. That is, in the present embodiment, by adding the risk determination unit 13, based on the risk importance information, when the index X is equal to or greater than the threshold value V3 smaller than the threshold value V2, a monitoring enhancement proposal can be made.

[0089] As described above, by using the power plant maintenance support system 100D (FIG. 16) according to the present embodiment, in addition to the effects obtained in the fourth embodiment, the following effects can be obtained. The power plant maintenance support system 100D can enhance the monitoring of deteriorated equipment that has a great impact on the safety of the power plant (high risk importance) by adopting a threshold value V3 smaller than the threshold value V2. Therefore, in addition to the deterioration of the system function of the power plant, it is possible to rationalize the maintenance management of the power plant based on the risk to the safety of the entire power plant.

[0090] In FIG. 17, an example is shown in which a monitoring enhancement is proposed when the index X becomes equal to or greater than the threshold value V3. Conversely, a case where a monitoring enhancement is proposed when the index X falls below the threshold value V3 is also conceivable, and in that case, V2 < V3. Further, in the present embodiment, a configuration is shown in which the risk determination unit 13 acquires equipment risk importance information from the design / field knowledge database 3 (FIG. 18) provided in the power plant maintenance support system 100D, but the present invention is not limited to this example. For example, the risk determination unit 13 may acquire equipment risk importance information by any method such as acquiring equipment risk importance information from a server on a communication network (not shown).

[0091] <Sixth Embodiment> FIG. 18 is a block diagram showing a configuration example of a power plant maintenance support system according to the sixth embodiment of the present invention. A power plant maintenance support system 100E according to the sixth embodiment differs from a power plant maintenance support system 100D (see FIG. 16) according to the fifth embodiment in that a proposal creation unit 14 is provided after the maintenance work proposing unit 10 and the monitoring strengthening proposing unit 12. With this configuration, the following points are improved in this embodiment compared to the fifth embodiment.

[0092] In the above-mentioned fifth embodiment, the display processing unit 15 enables the operator to detect a system malfunction (the possibility that the system may not satisfy the required performance) online. Moreover, in the fifth embodiment, it is possible to extract (a list) of equipment candidates that should be strengthened in monitoring or maintained in order to eliminate the system malfunction.

[0093] However, in general, to actually carry out maintenance work or strengthened monitoring of equipment, it is necessary to prepare various documents related to the implementation of the maintenance work and obtain the consent of the relevant parties and the manager who decides whether or not to carry out the repairs. The relevant parties are, for example, the operators and employees of the repair department who carry out the maintenance. The manager is, for example, the director of the power plant. By using the proposal preparation unit 14 of this embodiment, it is possible to automate the preparation of proposals to a certain extent, reduce the burden of document preparation, and minimize the time delay until the strengthened monitoring or maintenance work is actually carried out.

[0094] The proposal creation unit 14 automatically creates a proposal regarding the maintenance of the candidate deteriorated device, using the maintenance work proposal information from the maintenance work proposal unit 10 and the monitoring strengthening proposal information from the monitoring strengthening proposal unit 12. The proposal creation unit 14 stores the contents of the created proposal (proposal information) in the maintenance knowledge database 1.

[0095] FIG. 19 is a diagram showing an example of a proposal format created by the proposal creation unit 14. As shown in FIG. The proposal format shown in Fig. 19 includes, for example, the following items: "Diagnosis date" when a deterioration diagnosis was performed by a power plant maintenance support system, "Equipment name" indicating a candidate for deteriorated equipment, "Proposal" indicating proposal information (e.g., strengthened monitoring), "Malfunction type" corresponding to the cause of the malfunction (e.g., clogging), and "Index" indicating the magnitude relationship between the index X and the thresholds V1 to V3. Fig. 19 shows an example in which the diagnosis date is "XXXX / YY / ZZ", the equipment name is "Valve A", the proposal is "strengthened monitoring", and the malfunction type is "clogging". Fig. 19 also shows an example in which the index X is located between the thresholds V2 and V1 by an arrow.

[0096] Furthermore, as shown in FIG. 19, the proposal format includes the items "Monitoring items and monitoring frequency" and "Time trend graph of monitoring items and indicators." "Monitoring items and monitoring frequency" has the items "Measuring instrument ID," "Type of measurement data," and "Measurement frequency." For example, the first row of the "Monitoring items and monitoring frequency" table shows an example where the measuring instrument ID is "YYY1," the "Type" is "Temperature," and the measurement frequency is "X times / day." In addition, the "Time trend graph of monitoring items and indicators" displays the change in indicators over time for each monitoring item (e.g., equipment) in a graph. When there are multiple observation items, it is possible to display time trend graphs of indicators for multiple monitoring items side by side.

[0097] Note that this proposal format is merely an example. The procedure for creating a proposal may differ for each company organization and facility. Therefore, it is desirable for the proposal creation unit 14 to provide only a framework that is highly customizable so that the maintenance personnel who implement and / or manage the maintenance work can freely edit the proposal format.

[0098] As described above, by using the power plant maintenance support system 100E (FIG. 18) according to this embodiment, the following effects can be obtained in addition to the effects obtained in the fifth embodiment. In the power plant maintenance support system 100E, by having a proposal creation unit 14, it is possible to automate proposal creation, reduce the burden of document creation, and minimize the time lag until strengthened monitoring or maintenance work is performed.

[0099] The proposal creation unit 14 in this embodiment is not limited to the fifth embodiment, but can also be applied to the second or third embodiment described above. do.

[0100] [Hardware configuration of the control system for the power plant maintenance support system] Next, the hardware configuration of the control system of the power plant maintenance support system 100, 100A to 100E according to each embodiment of the present invention will be described with reference to FIG.

[0101] Fig. 20 is a block diagram showing an example of the hardware configuration of a control system of a maintenance support system for a power plant. A calculator 200 shown in Fig. 20 is an example of hardware used as a computer. The computer 200 includes a central processing unit (CPU) 201, a read only memory (ROM) 202, and a random access memory (RAM) 203, which are all connected to a bus. The computer 200 further includes a non-volatile storage 206 and a communication interface 207.

[0102] The CPU 201 reads out program code of software for realizing each function according to each embodiment from the ROM 202, loads it into the RAM 203, and executes it. Variables, parameters, etc. generated during the arithmetic processing of the CPU 201 are temporarily written into the RAM 203, and these variables, parameters, etc. are read out by the CPU 201 as appropriate. The CPU 201 executes the program code read out from the ROM 202, thereby realizing the function of each processing block of the power plant maintenance support systems 100, 100A to 100E. The CPU 201 may be replaced with another processor such as an MPU (Micro Processing Unit).

[0103] As the non-volatile storage 206, for example, a hard disk drive (HDD), a solid state drive (SSD), an optical disk, a magneto-optical disk, or a non-volatile memory is used. In addition to an operating system (OS) and various parameters, a program for making the computer 200 function may be recorded in the non-volatile storage 206. The ROM 202 and the non-volatile storage 206 record programs and data necessary for the CPU 201 to operate, and are used as an example of a computer-readable non-transient storage medium storing a program executed by the computer 200. The maintenance knowledge database 1 (FIG. 1), the measurement knowledge database 2 (FIG. 2), and the design / site knowledge database 3 are stored in the non-volatile storage 206 (FIG. 12). Note that a cloud environment can also be utilized to store this information.

[0104] For example, a communication device such as a network interface card (NIC) is used as the communication interface 207. The communication interface 207 is configured to be capable of transmitting and receiving various data to and from an external device via a communication network such as a local area network (LAN) or the Internet, or a dedicated line.

[0105] As described above, the present invention is not limited to the above-described embodiments, and various other modifications and applications are possible without departing from the gist of the invention described in the claims. For example, the above-described embodiments are described in detail and specifically to explain the present invention in an easy-to-understand manner, and are not necessarily limited to those including all of the components described. In addition, it is also possible to add, replace, or delete other components to a part of the configuration of each embodiment.

[0106] In addition, the above-mentioned configurations, functions, processing units, etc. may be realized in part or in whole by hardware, for example, by designing them as integrated circuits. As the hardware, a broad processor device such as an FPGA (Field Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit) may be used.

[0107] Furthermore, each component of the power plant maintenance support system according to the above-described embodiment may be implemented in any hardware as long as the respective hardware can transmit and receive information to each other via a network. Furthermore, the processing performed by a certain processing unit may be realized by a single piece of hardware, or may be realized by distributed processing using multiple pieces of hardware.

[0108] In the above-described embodiment, the control lines and information lines are those that are considered necessary for the explanation, and not all control lines and information lines in the product are necessarily shown. In reality, it may be considered that almost all components are connected to each other. [Explanation of symbols]

[0109] 1...maintenance knowledge database, 2...measurement knowledge database, 3...design and site knowledge database, 4...analysis model tuning and sensitivity analysis section, 5...deteriorated equipment identification matrix construction section, 6...index evaluation matrix construction section, 7...index evaluation section, 8...deteriorated equipment identification section, 9...maintenance proposal judgment section, 10...maintenance work proposal section, 11...monitoring strengthening judgment section, 12...monitoring strengthening proposal section, 13...risk judgment section, 14...proposal creation section, 15...display processing section, 16...display device, 40,1500...index evaluation matrix, 50,1400...deteriorated equipment identification matrix, 100,100A-100E...power plant maintenance support system

Claims

1. a measurement knowledge database that stores a group of measurement data consisting of a plurality of measurement data acquired through a plurality of measuring instruments installed in the power plant; a maintenance knowledge database storing maintenance information about equipment installed in a system of the power plant, the maintenance knowledge database storing a deteriorated equipment identification matrix which receives an evaluation result of an increase or decrease in the group of measurement data when equipment is deteriorated, and outputs deteriorated equipment and the cause of the deterioration, and an index evaluation matrix which receives an input of a first index which is a linear combination value of the measurement data or the group of measurement data when equipment is deteriorated, and outputs a measurement data estimated value having a strong correlation with the required performance that the system should satisfy when equipment is deteriorated as a second index; an index evaluation unit that calculates and outputs an index of a system by using information of the measurement data group of the actual machine in the measurement knowledge database and the index evaluation matrix during normal operation of the power plant; a degraded equipment identification unit that estimates and outputs degraded equipment candidates and causes of degradation using information of the measurement data group of the actual equipment in the measurement knowledge database and the degraded equipment identification matrix; a display processing unit that displays output information of the index evaluation unit and the deteriorated device identification unit. Maintenance support system for power plants.

2. a maintenance proposal determination unit that issues a maintenance proposal trigger when the first index input from the index evaluation unit is equal to or greater than a first threshold for determining the necessity of maintenance work on the deteriorated device candidate; a maintenance work proposal unit that proposes maintenance work for the deteriorated equipment candidate by using information from the maintenance knowledge database and the deteriorated equipment identification unit when the maintenance proposal trigger is issued, The display processing unit processes and displays output information of the maintenance work suggestion unit and the deteriorated equipment identification unit. The power plant maintenance support system according to claim 1 .

3. a monitoring strengthening determination unit that issues a monitoring strengthening proposal trigger when the first indicator input from the indicator evaluation unit is determined to be less than the first threshold value in the maintenance proposal determination unit and the first indicator is equal to or greater than a second threshold value for determining the necessity of strengthening monitoring of the deteriorated device candidate; a monitoring strengthening suggestion unit that, when the monitoring strengthening suggestion trigger is issued, proposes strengthening of monitoring of the deteriorated equipment candidate by using information of the maintenance knowledge database and the deteriorated equipment identification unit, The display processing unit displays and processes output information of the monitoring strengthening suggestion unit, the maintenance work suggestion unit, and the deteriorated equipment identification unit. The power plant maintenance support system according to claim 2 .

4. a risk determination unit that issues the monitoring strengthening suggestion trigger when the monitoring strengthening determination unit determines that the first index input from the index evaluation unit is less than the second threshold, and when the degree of influence of the deteriorated equipment candidate on the safety of the entire power plant is higher than a predetermined value and the first index is equal to or greater than a third threshold that is smaller than the second threshold. The power plant maintenance support system according to claim 3 .

5. a proposal creation unit that automatically creates a proposal regarding the maintenance of the deteriorated device candidate by using the maintenance work proposal information from the maintenance work proposal unit and the monitoring strengthening proposal information from the monitoring strengthening proposal unit. The power plant maintenance support system according to claim 4.

6. A design / site knowledge database for storing design information and site information of the power plant's system and equipment; an analytical model tuning and sensitivity analysis unit that performs a sensitivity analysis to evaluate in advance, before starting operation of the power plant, an increase or decrease in a group of measurement data due to equipment deterioration, using a parameter-adjusted analytical model in which parameters of the analytical model constructed based on each piece of information stored in the design / site knowledge database are tuned using test operation information from the measurement knowledge database; and a degraded equipment identification matrix construction unit that constructs the degraded equipment identification matrix by using an analysis result of the analysis model tuning and sensitivity analysis unit; an index evaluation matrix constructing unit that constructs the index evaluation matrix using an analysis result of the analysis model tuning and sensitivity analysis unit; The power plant maintenance support system according to any one of claims 1 to 5.

7. The analytical model tuning and sensitivity analysis unit constructs the parameter-adjusted analytical model by tuning parameters of the analytical model so that differences between an actual system and the analytical model regarding boundary conditions of the system during a test run, and pressure distribution, temperature distribution, and flow rate distribution in the system during a test run are minimized. The power plant maintenance support system according to claim 6.

8. A power plant maintenance support method using a power plant maintenance support system including a measurement knowledge database storing a measurement data group consisting of a plurality of measurement data acquired through a plurality of measuring instruments provided in the power plant, and a maintenance knowledge database storing maintenance information on equipment provided in a system of the power plant, the method comprising: The maintenance knowledge database stores a deteriorated equipment identification matrix which receives an evaluation result of an increase or decrease in the group of measurement data during equipment deterioration and outputs deteriorated equipment and a cause of deterioration, and an index evaluation matrix which receives an input of a first index which is a linear combination value of the measurement data or the group of measurement data during equipment deterioration and outputs a measurement data estimated value having a strong correlation with a required performance that a system should satisfy during equipment deterioration as a second index, A process in which an index evaluation unit calculates and outputs an index of a system by using information of the measurement data group of the actual machine in the measurement knowledge database and the index evaluation matrix during normal operation of the power plant; a process of estimating and outputting deteriorated equipment candidates and deterioration causes by using information of the measurement data group of the actual equipment in the measurement knowledge database and the deteriorated equipment identification matrix by a deteriorated equipment identification unit; and executing a display process for displaying output information of the index evaluation unit and the deteriorated device identification unit. A method for supporting maintenance of a power plant.

Images