JP2017021702A - Failure foretaste monitoring method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To ensure constant detection accuracy for a failure foretaste of device provided in a plant and promptly detecting the failure foretaste of the device without variation in the detection accuracy depending on a person in charge.SOLUTION: With respect to a plurality of devices disposed in a plant 10, sensors Se1 to Sen for measuring a behavior of each device, and an analysis server 53 for monitoring a failure foretaste of each device on the basis of measurement data measured by each sensor are provided. A failure foretaste monitoring method is implemented by the analysis server 53 in such a manner that the analysis server 53 executes: a problematic portion display processing step of dividing an activation process for the plant 10 into a plurality of periods t0 to t1 on the basis of an operation content in the activation process, and confirming validity of a behavioral state whenever each period ends on the basis of the measurement data, thereby displaying a failure foretaste portion of each device; and a process management step (S235) of transitioning to the next period when confirming that the behavioral state in each period is appropriate.SELECTED DRAWING: Figure 4

Description

  The present invention relates to a failure sign monitoring method suitable for monitoring a failure sign of equipment arranged in a plant.

Conventionally, plants such as nuclear power plants, thermal power plants, and hydroelectric power plants have been equipped with multiple devices, and these devices are inspected and repaired if they have failed. Is going to do.
Further, at a stage earlier than such maintenance inspection, the person in charge discovered a sign of equipment failure while confirming changes in measurement data for monitoring the state of the equipment during operation of the plant.
In addition, for failure signs of equipment, compare with the threshold value set in advance for each equipment, and when the measured value acquired from the equipment becomes larger than the threshold value, an alarm is generated, The equipment was being repaired.
The person in charge has been performing visual monitoring at a monitoring frequency of, for example, once / h in the central operation room and once / day at the site, targeting instruments provided in the control panel or equipment.
In the central operation room of the plant, plant abnormalities and system operation status are classified and systematized and displayed in the ANN window provided on the alarm display panel. It was supposed to respond according to the determined procedure.

  Patent Document 1 discloses an abnormality detection method for detecting an abnormality of a plant or equipment at an early stage, obtaining observation data from a plurality of sensors, modeling learning data composed of normal data, and modeling the observation data. A technology is disclosed that detects the presence or absence of abnormalities in observation data based on the similarity to the learning data, evaluates the influence of each sensor signal, constructs the judgment condition rule, and selects and displays the sensor signal according to the abnormality Yes.

JP 2011-059790 A

Conventionally, for example, regarding a failure sign of equipment, a monitoring system that relies on visual confirmation by a person in charge has been adopted. For this reason, there are monitoring items that depend on the skill level of the person in charge, and the evaluation result is not constant for such monitoring items depending on the skill level of the person in charge.
In the central control room, it was difficult to detect a sign of abnormality before the occurrence of ANN.
Furthermore, as described above, the monitoring frequency such as once / 1h, once / day, etc. is adopted, and it is difficult to monitor in real time.
In addition, when monitoring observation data and detecting anomalies by comparing with a set threshold value, the threshold value is set by paying attention to the physical quantity to be measured. May occur.
The present invention has been made in view of the above, and the object thereof is to provide a certain detection accuracy without a variation depending on a person in charge of a failure sign of a device provided in a plant, and to promptly detect a failure sign of a device. It is that it can be detected.

  In order to solve the above problem, the invention according to claim 1 is based on a plurality of devices arranged in a plant, a sensor for measuring the behavior of each device, and measurement data measured by each sensor. A failure sign monitoring device for monitoring a failure sign of each device, the failure sign monitoring method by the failure sign monitoring device, wherein the failure sign monitoring device is based on the operation contents in the start-up process of the plant The startup process is divided into a plurality of periods, and the sign of failure of each device is displayed by checking the validity of the behavior state at the end of each period based on the measurement data. A problem location display processing step, and a process management step that shifts to the next period when the behavior state in each period is confirmed to be valid, and That.

  ADVANTAGE OF THE INVENTION According to this invention, there is no variation depending on the person in charge of the failure sign of the equipment provided in the plant, there is a certain detection accuracy, and the failure sign of the equipment can be detected promptly.

It is a mimetic diagram for explaining the composition of the plant concerning the embodiment of the present invention. It is a block diagram which shows the system for monitoring the failure sign of the apparatus provided in the plant which concerns on embodiment of this invention. It is a graph which shows the relationship between each operation process and output of the plant which concerns on embodiment of this invention. It is a main flowchart which shows the problem location display process by the analysis server which concerns on embodiment of this invention. It is a flowchart which shows the subroutine of the two-dimensional matrix display process (the said preparation process) by the analysis server which concerns on embodiment of this invention. It is a flowchart which shows the subroutine of the core invariant comparison process (comparison start) by the analysis server which concerns on embodiment of this invention. It is a flowchart which shows the subroutine of the monitoring process by the analysis server which concerns on embodiment of this invention. It is a flowchart which shows the subroutine of the automatic extraction process about the influence range of the abnormality sign by the analysis server which concerns on embodiment of this invention. It is a flowchart which shows the subroutine of the failure sign detection process by the analysis server which concerns on embodiment of this invention. It is a flowchart which shows the subroutine of the real-time monitoring process by the invariant monitoring by the analysis server which concerns on embodiment of this invention. It is a flowchart which shows the subroutine of the equipment inspection process by the analysis server which concerns on embodiment of this invention. It is a flowchart which shows the subroutine of the real-time monitoring process by the invariant monitoring by the analysis server which concerns on embodiment of this invention. It is a flowchart which shows the subroutine of the problem location identification process by the analysis server which concerns on embodiment of this invention. (A)-(e) is a figure which shows the analysis result by the analysis server 53 which concerns on embodiment of this invention.

Hereinafter, the present invention will be described in detail with reference to embodiments shown in the drawings.
The present invention does not vary depending on the person in charge of a failure sign of equipment provided in a plant, has a certain detection accuracy, and has the following configuration in order to quickly detect a failure sign of equipment.
That is, the failure sign monitoring method of the present invention provides a failure sign of each device based on a plurality of devices arranged in the plant, a sensor for measuring the behavior of each device, and measurement data measured by each sensor. A failure sign monitoring method using the failure sign monitoring device, the failure sign monitoring device dividing the start-up process into a plurality of periods based on the operation contents in the plant start-up process. In addition, by confirming the appropriateness of the behavior state at the end of each period based on the measurement data, the problem location display processing step for displaying the failure sign location of each device and the behavior state in each period are valid. When it is confirmed that the process management step is performed, a process management step for transferring to the next period is executed.
With the above configuration, there is no variation depending on the person in charge of the failure sign of the equipment provided in the plant, there is a certain detection accuracy, and the failure sign of the equipment can be detected quickly.
Hereinafter, the features of the present invention will be described in detail with reference to the drawings.

Drawing 1 is a mimetic diagram for explaining the composition of plant 10 concerning the embodiment of the present invention. This embodiment is applied to a nuclear reactor or turbine provided in a nuclear power plant as an example of a plant.
The nuclear reactor building 11 includes a nuclear reactor 13. The reactor 13 includes a reactor containment vessel 15, a nuclear pressure vessel 17 (steam 17a, water 17b), a steam dryer 19, a steam separator 21, a fuel assembly 23, a control rod 25, a recirculation pump 26, And a pressure suppression chamber 27 is provided.
The turbine building 31 includes a turbine 33, a generator 35, a condenser 37 (water 37 a), a water outlet 39, a water intake 41 (condenser cooling water 41 a), a pump 43, and a water supply pump 45.
For example, the recirculation pump 26 includes sensors Se1 to Se3 at three different positions, and outputs measurement data detected by the sensors Se1 to Se3 to the sensor monitoring device 51 # 1.
Although FIG. 1 shows that measurement data detected by the sensors Se1 to Se3 provided in the recirculation pump 26 is transmitted to the sensor monitoring device 51 # 1, in this embodiment, the reactor building 11 In addition, measurement data detected by a plurality of sensors provided in each device arranged in the turbine building 31 or the like is output to the sensor monitoring device 51.

FIG. 2 is a block diagram showing a system 50 for monitoring a failure sign of equipment provided in the plant 10 according to the embodiment of the present invention.
The system 50 of the present embodiment includes sensor monitoring devices 51 # 1 to 55 # n, a network N1, an analysis server 53, a network N2, and a plurality of client terminals 55 # 1 to 55 # n.
The sensor monitoring devices 51 are each connected to the analysis server 53 via the network N1. The measurement data from each sensor collected in the sensor monitoring devices 51 (# 1 to #n) is received by the analysis server 53 via the network N1.
Based on the measurement data acquired from the sensor monitoring device 51, the analysis server 53 monitors failure signs of a plurality of devices arranged in the plant 10.
The analysis server 53 divides the start-up process into a plurality of periods based on the operation contents in the start-up process of the plant 10, and checks the validity of the behavior state every time each period ends based on the measurement data. Thus, when a failure sign portion of each device is displayed and it is confirmed that the behavior state in each period is appropriate, the process proceeds to the next period.

The analysis server 53 detects the failure sign of each device by monitoring the measurement data of each sensor in real time, and displays the problem location.
The analysis server 53 divides the inside of the process into a plurality of periods based on the operation content in the CR pattern changing process or the stopping process of the plant 10, and based on the measurement data, the behavior state is changed every time the period ends. By confirming the validity, the sign of failure of each device is displayed, and when it is confirmed that the behavior state in each period is valid, the process proceeds to the next period.
The analysis server 53 detects the failure sign of each device by monitoring the measurement data of each sensor in real time in the trial operation process of the plant, and when the failure sign of any one of a plurality of devices is detected, the measurement data Based on the above, by confirming the validity of the behavior state, the sign of failure of each device is displayed.
Each of the client terminals 55-1 to 55-n includes a display unit and an operation unit, and is equipped with a GUI (Graphical User Interface) function configured to operate a graph and an icon displayed on the display unit by the operation unit. It is a computer.
The analysis server 53 includes a communication control unit 61, a communication control unit 63, a main control unit 65, an operation unit 67, a data storage unit 69, a display control unit 71, a display unit 73, a disk control unit 75, a database unit 77, and a bus. 79 is provided.

The communication control unit 61 controls data communication between the devices by Ethernet (registered trademark) communication via the network N1. The communication control unit 63 controls data communication between the devices by Ethernet (registered trademark) communication via the network N2.
The main control unit 65 includes a read only memory (ROM), a random access memory (RAM), a central processing unit (CPU), and a hard disk drive (HDD). The main control unit 65 reads the operating system OS from the HDD, expands it on the RAM, starts the OS, reads a program (processing module) from the HDD under the OS management, and executes various processes.
The operation unit 67 supplies an operation signal corresponding to a user's operation on the keyboard, mouse, and the like to the main control unit 65.
The data storage unit 69 has a RAM and stores data.
The display control unit 71 generates a display image such as screen data or a graph based on the display information and outputs it to the display unit 73.
The display unit 73 displays display images such as screen data and graphs output from the display control unit 71.
The disk control unit 75 controls the database unit 77 to read / write input / output data.
The database unit 77 is composed of an HDD and accumulates data.

FIG. 3 is a graph showing the relationship between each operation process and output of the plant 10 according to the embodiment of the present invention.
In the graph shown in FIG. 3, the vertical axis represents the output amount of power, and the horizontal axis represents time. In this graph, as an operation process of the plant, [1] a start process representing the output amount when starting the plant, [2] a steady process representing the output amount when the plant has shifted to the steady state, and operating the plant [3] CR pattern change process, which represents the output amount when the pattern of the control rod 25 is changed, and [4] Stop process, which represents the output amount when the plant is shifted from the steady state to the stopped state [5] An equipment inspection process and the like representing a stop state when equipment inspection is performed on the are shown.

In the [1] start-up process shown in FIG. 3, the time from time t0 to t1 can be divided into a plurality of periods, and in the [4] stop process, the time from time t4 to t5 is similarly expressed. It can be divided into a plurality of periods.
In the present embodiment, the plant 10 will be described, but a system may be used instead of such a plant. Here, the system represents a system (system) in which individual devices are arranged in order and function so as to function as a whole, for example, a series of devices such as pumps, piping, valves, loads, etc. Say. In this embodiment, as a system, a reactor steam generation system, a control system, a radiation monitor system, a core cooling system, a reactor handling device, a reactor auxiliary system, a control panel, fuel, a waste treatment system, a plant system, The plant auxiliary system, on-site electrical system, power transmission / reception system, reactor containment vessel and incidental facilities, various buildings and incidental facilities, water intake facilities and incidental facilities, and on-site facilities will be handled.

・・・式（１）
なお、近似式については、線形回帰法の他にも様々な方法が提案されており、何れの手法を採用してもよい。 <Relationship model>
Here, a method for constructing a relationship model employed in the present embodiment, that is, a method for constructing a relationship model representing a relationship between two sensors based on measurement data acquired from each sensor will be described.
First, from the measurement data acquired from each sensor, it is identified whether there is a correlation between the measurement data measured for the device.
Here, a mathematical expression-based approximate expression such as B = f (A) is generated as the correlation between the two points from the time-series data of the two measurement points (sensors) for a certain period of time. As an approximate expression generation method, a method called linear regression may be used.
For example, the coefficients (a ₁ , a) of the approximate expression (prediction formula) shown in Formula (1) are set so that the difference (absolute value) between the predicted value totaled over a certain period and the measured value y (t) is minimized. ₂ ,..., B ₀ , b ₁ ,.

... Formula (1)
In addition to the linear regression method, various methods have been proposed for the approximate expression, and any method may be employed.

・・・式（２）
を算出する。ここで、左辺はフィット値を表し、右辺は基準値を表す。
定性的には、左辺は時系列データを予測式（式（１））を用いて予測できた割合を表しており、時系列データを８０％予測できる場合を関係性があるとするならば、ｆ_ｔｈ＝０．８とすればよい。
なお、基準値として、正常状態における測定値の平均値、又は標準偏差値を用いてもよい。 Furthermore, a fit value representing an index of how much the approximate expression can approximate the actual data is generated from the generated approximate expression and the time series data used at the time of generation. When approximation is performed using the least square method as the linear regression method, the fit value can be a determination coefficient in the least square method.
Next, the fit value is compared with a predetermined threshold value, and if it is equal to or greater than the threshold value, the relationship between the two points (approximation formula and fit value) may be adopted as the relationship model.
For example, the main control unit 65, based on the measured value, the average value of the measured value, the predicted value, and the setting parameter (reference value), according to the equation (2),

... Formula (2)
Is calculated. Here, the left side represents a fit value, and the right side represents a reference value.
Qualitatively, the left side represents the ratio that the time series data can be predicted using the prediction formula (formula (1)), and if the time series data can be predicted by 80%, f _th = 0.8 may be set.
In addition, you may use the average value of the measured value in a normal state, or a standard deviation value as a reference value.

FIG. 4 is a main flowchart showing a problem location display process by the analysis server 53 according to the embodiment of the present invention.
In the present embodiment, as shown in FIG. 3, the operation process of the plant is divided into five processes, and the problem location is displayed in each process.
First, in the problem location display process, in step S <b> 10, the main control unit 65 acquires the current operation process from the plant control device (not shown) via the communication control unit 61. This plant control apparatus is an apparatus that controls each device arranged in the plant 10, and outputs tag information representing, for example, five processes to the analysis server 53 as an operation process.
In step S15, the main control unit 65 has the following operation steps acquired from the plant control device: [1] start-up step, [2] steady operation step, [3] CR pattern change step, [4] stop step, [5] equipment Determine one of the inspection processes.
[2] If it is determined that the process is a steady operation process, in step S20, the main control unit 65 calls a failure sign detection process (S600) which is a subroutine. On the other hand, when it is determined as [5] facility inspection process, in step S25, the main control unit 65 calls a facility inspection process (S900) which is a subroutine. On the other hand, if [1] [3] [4] is determined, in step S30, the main control unit 65 calls a two-dimensional matrix display process (preparation process) (S100) which is a subroutine.
When returning from the subroutine, the process proceeds to step S32.

  In step S32, the main control unit 65 determines whether [1] the starting process is at timing t1, [3] the CR pattern changing process is at timing t3, and [4] the stopping process is at timing t5. Here, the process is terminated when [1] the start process is at timing t1, [3] the CR pattern changing process is at timing t3, and [4] the stop process is at timing t5 (S32, Yes). On the other hand, if [1] the starting process is not at timing t1, [3] the CR pattern changing process is at timing t3, and [4] the stopping process is not at timing t5 (S32, No), the process proceeds to step S35.

In step S35, the main control unit 65 calls a core invariant comparison process (comparison start) (S200), which is a subroutine. When returning from the subroutine, the process proceeds to step S40.
In step S <b> 40, the main control unit 65 displays the result on the display unit 73.
When returning from the subroutine, the process proceeds to step S45.
In step S45, the main control unit 65 determines whether or not there is a large difference compared to the same time in the past.
If there is a large difference compared to the same previous work (S45, yes), the process proceeds to step S50. On the other hand, if there is no significant difference compared to the same previous work (S45, none), step S35. Return to.

In step S50, based on the comparison result, the main control unit 65 displays a location where a problem is likely to occur on the display unit 73 (selection of related parameters).
In step S55, the main control unit 65 determines whether or not there is an abnormal state.
Here, when it is an abnormal state (S55, Yes), it progresses to step S60, and when it is not an abnormal state (S55, No), it returns to step S35.
In step S60, the main control unit 65 calls an automatic extraction process (S500) for the influence range of the abnormality sign, which is a subroutine.
When returning from the subroutine, the process proceeds to step S35.

Here, the test items in the periodic test process represented by the CR pattern changing process will be described.
As test items, R- [1] reactor protection system includes (1) half scram test. The R- [2] control rod drive system includes (1) insertion, extraction (notch) test, (2) scram discharge water container isolation test, and (3) control rod drive water pump preliminary machine start-up test.
R- [3] Nuclear instrumentation system (1) Neutron source region, Neutron instrumentation (SRM) test, (2) Intermediate region Neutron instrumentation (IRM) test, (3) Output region Neutron instrumentation (APRM) test (4) Activation region There is a neutron instrumentation (SRNM) test. R- [4] Main steam system has (1) 10% main steam isolation valve closing test. The R- [5] low pressure core spray system includes (1) a motor operated valve test, (2) a pump manual start test, and (3) a testable check valve operation test. The R- [6] low-pressure water injection system has (1) motor operated valve test, (2) pump manual start test, and (3) testable check valve operation test. R- [7] High pressure core spray system (1) Motorized valve operation test (including auxiliary seawater system), (2) Pump manual start-up test (including auxiliary machine cooling system, seawater system), (3) Reverse test possible There is a stop valve operation test.

R- [8] The reactor isolation cooling system has (2) manual pump start-up test and (3) testable check valve operation test. R- [9] The boric acid water injection system has (1) motor operated test and (2) pump manual start test. R- [10] Containment vessel cooling systems include (1) motor-operated valve operation test (including reactor auxiliary system cooling system) and (2) pump manual start-up test. R- [11] The reactor auxiliary cooling system has (1) reactor auxiliary machine cooling water pump and reactor auxiliary seawater pump manual startup test.
R- [12] The emergency gas treatment system has (1) manual start-up test. R- [13] The flammable gas concentration control system includes (1) motor-operated valve operation test and (2) blower manual start test normal temperature operation test. R- [14] (1) There is a pump operation test in the fuel pool makeup water system.
R- [15] The suppression pool purification system has (1) pump manual start-up test. T- [1] Turbine main valves include: (1) Main shut-off valve 10% closing test, (2) Turbine bypass valve slight opening test, (3) Extraction check valve and drain valve operation test, (4) Intercept There is a valve micro-closing test. T- [2] Turbine safety device includes (1) emergency governor oil trip test by lockout, (2) thrust protection device operation test, (3) power load unbalance circuit test, (4) backup overspeed circuit Test, (5) Turbine master trip solenoid valve operation test.

T- [3] Turbine hydraulic system includes (1) oil pump automatic start test, (2) jacking oil pump operation test, (3) main oil tank oil level alarm test, (4) turbine oil filtration pump operation test, (5) Turbine oil transfer pump operation test, (6) Control oil pump spare machine automatic start test. T- [4] For the water supply system, (1) RFP / T emergency oil pump automatic start test, (2) RFP / T thrust protection device operation test, (3) RFP / T main oil pump spare machine automatic start test, (4) RFP • T low pressure and high pressure steam stop valve open / close test, (5) RFP • T oil tank oil level alarm test, and (6) emergency governor oil trip test by RFP • T lockout. T- [5] The circulating water system has (1) circulating water piping intake side and discharge side siphon breaker valve operation test. E- [1] The generator has (1) emergency seal oil pump automatic start test, (2) seal oil differential pressure alarm test, (3) seal oil float trap operation test, (4) stator cooling water pump automatic There is a start-up test and (5) shaft seal N2 gas filled valve operation test.
E- [2] Emergency power supply includes (1) diesel generator manual start test, (2) fuel supply system confirmation test, (3) start-up air compressor automatic start test, and (4) fuel transfer pump operation test. is there. E- [3] In-house storage batteries include (1) pilot storage battery confirmation test and (2) charger confirmation test. E- [4] Electricity and others (1) There is an automatic start test for switchgear air compressors. S- [1] Instrumented compressed air systems include (1) an instrumentation air compressor automatic start test and an in-house air / instrument communication valve / in-house air shut-off valve operation test. S- [2] The in-house compressed air system has (1) an in-house air compressor automatic start test. S- [3] The air conditioning ventilation system has (1) central control room air conditioning ventilation system isolation operation and outside air intake operation test. S- [4] Fire extinguishing system has (1) fire pump operation test.

In addition to the test items described above, test items in the nuclear power plant will be described.
The R-301 reactor emergency stop system includes (1) a trip logic circuit test using a scram test switch. The R-302 control rod drive system includes (1) control rod insertion, pull-out test (CR drive test), and (2) control rod drive water pump preliminary machine start-up test.
The R-303 nuclear reactor instrumentation system includes (1) SRNM function test and (2) APRM function test.
The R-304 main steam system has (1) a main steam isolation valve 10% closed test. The R-305 high-pressure core water injection system has (1) high-pressure core water injection pump manual start-up test (high rated capacity operation) and (2) high-pressure core water injection system electric valve operation test (including testable check valve operation test). .
For R-306 residual heat removal system, (1) Low pressure injection pump manual start-up test (including containment vessel spray cooling system), (2) Low pressure injection system motor operated valve operation test (including testable check valve operation test, storage) Container spray cooling system)
The R-307 boric acid water injection system includes (1) a boric acid water injection pump manual activation test (using pure water), and (2) a boric acid water injection system motor operated valve test.
The R-308 isolation system cooling system includes (1) manual isolation test of the isolation system cooling system pump and (2) isolation system cooling valve motor operation test (including testable check valve operation test). is there.
The R-309 emergency gas treatment system includes (1) an emergency gas treatment system manual activation test.

The R-310 combustible gas concentration control system includes (1) a combustible gas concentration control system motor operated valve operation test and (2) a combustible gas concentration control system blower normal temperature operation test.
The R-311 central control room ventilation air conditioning system includes (1) a central control room ventilation air conditioning system isolation operation and an outside air intake operation test.
The R-312 suppression pool purification system includes (1) a suppression pool purification pump manual activation test.
The R-313 reactor auxiliary coolant system and the auxiliary coolant seawater system include (1) a reactor auxiliary coolant pump and a reactor auxiliary coolant seawater pump manual start-up test.
T-301 turbine includes (1) turbine main steam stop valve individual valve 10% closing test, (2) turbine bypass valve individual valve slight open test, (3) extraction check valve and extraction pipe drain valve operation test, ( 4) Turbine intercept valve fine-close test, (5) Oil trip test by lockout, (6) Power load imbalance circuit test, (7) Turbine backup overspeed circuit test, (8) Turbine master trip solenoid valve test , (9) Oil pump automatic start test, (10) Jacking oil pump start test, and (11) Control oil pump automatic start test.
The T-302 circulating water system has (1) circulating water piping intake side and discharge side siphon destruction valve operation test.

The steam turbine for driving the T-303 reactor water pump includes (1) RFP-T main oil pump spare machine automatic start test, (2) RFP-T emergency oil pump automatic start test, and (3) RFP-T low pressure. There are steam stop valve half-closed and high pressure steam stop valve full-closed tests, (4) RFP-T thrust protection device operation test, and (5) emergency governor oil trip test by RFP-T lockout.
The E-301 generator and auxiliary generator have (1) automatic seal oil pump automatic start test, (2) seal oil differential pressure alarm test, and (3) stator cooling water pump spare machine automatic start test. .
E-302 emergency diesel generator, (1) emergency diesel generator manual start-up test, (2) emergency diesel generator, fuel oil system confirmation test, (3) emergency diesel generator, fuel transfer pump operation test, ( 4) Emergency diesel power generation facility There is an air compressor automatic start test.
The E-303 battery has (1) a pilot battery check test.
The S-301 instrumented compressed air system includes (1) an instrumented compressed air system air compressor automatic start test, and (2) an SA → IA communication valve operation test.
The S-302 fire extinguishing system includes (1) a fire pump operation test.

FIG. 5 is a flowchart showing a subroutine (S100) of two-dimensional matrix display processing (preparation processing) by the analysis server 53 according to the embodiment of the present invention.
In step S105, the main control unit 65 acquires measurement data from the database. That is, the main control unit 65 acquires the measurement data from the database stored in the database unit 77 to the data storage unit 69.
Accordingly, the main control unit 65 can acquire the measurement item ID, measurement data, and measurement time data acquired from the database in the data storage unit 69 in association with the measurement item name. Here, the contents of the measurement data are shown in Table 1.

In step S <b> 110, the main control unit 65 extracts a monitoring parameter group based on the system and stores the monitoring parameter group in the data storage unit 69.
As a result, the monitoring parameter group is stored in the data storage unit 69.
In step S115, the main control unit 65 creates a two-dimensional matrix table in which the display positions of the correlated sensors are arranged at the positions in the vertical axis direction and the horizontal axis direction. indicate.
In step S120, the main control unit 65 determines a period for comparison.

In step S125, the main control unit 65 calculates a fit value representing the strength of the relationship between all the monitoring parameters in accordance with the formula (2) in the past normal operation period as a reference.
In step S <b> 130, the main control unit 65 calculates a reference value (average value, standard deviation value) of the fit value and stores it in the data storage unit 69.
As a result, the data storage unit 69 stores the fit value and the reference value of the fit value.
Next, the process in the subroutine is terminated and the process returns.

FIG. 6 is a flowchart showing a subroutine (S200) of the core invariant comparison process (comparison start) by the analysis server 53 according to the embodiment of the present invention.
The core invariant comparison process (comparison start) is applied to the test operation process after [5] facility inspection process.
First, in step S205, the main control unit 65 calls a monitoring process (S300) which is a subroutine. In this subroutine, the main control unit 65 executes an invariant monitoring process based on the relationship model created in the state before the inspection.
When returning from the subroutine, the process proceeds to step S210.
In step S210, the main control unit 65 reads the comparison target period fit value and reference value (average value or standard deviation value) from the data storage unit 69 into the data storage unit 69, and compares the comparison target period fit value and reference value. Compare the value.
In step S215, the main control unit 65 determines whether or not the state is different from normal. For example, it is determined whether or not the fit value is larger than the reference value.
If the fit value is greater than the reference value (S215, Yes), the process proceeds to step S220. If the fit value is not greater than the reference value (S215, No), the process proceeds to step S225.

In step S220, the main control unit 65 displays the intersections indicating the relationship of the two-dimensional matrix table in red.
In step S225, the main control unit 65 displays the intersections indicating the relationship of the two-dimensional matrix table in white.
As a result, as shown in FIGS. 14A to 14D, a two-dimensional matrix table color-coded into red and white is displayed on the display unit 73. In the present embodiment, the two-dimensional matrix table that is color-coded into red and white is configured to be displayed. However, other two colors may be used for display.
In step S230, the main control unit 65 determines whether all the matrices (targets) have been compared.

If all the matrices (targets) are compared (S230, Yes), the process proceeds to step S237. On the other hand, if all the matrices (targets) are not compared yet (S230, No), the process proceeds to step S235.
In step S235, the main control unit 65 designates the next matrix (target) and returns to step S210.
In step S237, the main control unit 65 determines whether it is necessary to create a database. If database creation is necessary (S237, Yes), the process proceeds to step S240. On the other hand, if it is not necessary to create a database (S237, No), the processing in the subroutine is terminated and the process returns.
Note that a message for inquiring whether or not a database is necessary may be displayed on the display unit 73 and the will of the person in charge may be confirmed by the GUI function using the operation unit 67.

In step S240, the main control unit 65 determines whether the comparison result is the same as the past.
If the comparison result is the same as the past (S240, Yes), the process proceeds to step S245. On the other hand, if the comparison result is not the same as the past (S240, No), the process proceeds to step S255.
In step S245, the main control unit 65 calls a relationship model creation process (re-creation) (S400), which is a subroutine.
When returning from the subroutine, the process proceeds to step S250.
In step S250, the main control unit 65 sets the created relationship model in the data storage unit 69 as a monitoring model.
In step S <b> 255, when it is determined that the main control unit 65 is not the same as the past, the main control unit 65 displays a message on the display unit 73 urging the user to identify the cause.
For example, the main control unit 65 displays a message “Please check the display screen to identify the cause” on the display unit 73 via the display control unit 71.
Next, the process in the subroutine is terminated and the process returns.

According to the present embodiment, the analysis server 53 divides the startup process into a plurality of periods t0 to t1 based on the operation content in the startup process of the plant 10, and each period ends based on the measurement data. By confirming the appropriateness of the behavior state every time, the failure sign point of each device is displayed, and when the behavior state in each period is confirmed to be valid, by moving to the next period, Since the failure sign location can be displayed, there is no variation depending on the person in charge of the failure sign of the equipment provided in the plant, there is a certain detection accuracy, and the failure sign of the equipment can be detected quickly.
As a result, when it is necessary to monitor a plurality of events continuously for a long period of time, such as an activation process, a great effect can be obtained in strengthening the monitoring function.

  According to this embodiment, the analysis server 53 divides the inside of the process into a plurality of periods t40 to t5 based on the operation content in the CR pattern changing process or the stopping process of the plant, and based on the measurement data, By confirming the appropriateness of the behavioral state at the end of each period, the failure signs of each device are displayed, and when it is confirmed that the behavioral state in each period is valid, Since the behavioral state in each period can be confirmed to be valid, there is no variation depending on the person in charge of the failure sign of the equipment installed in the plant, there is a certain detection accuracy, and the failure sign of the equipment is detected quickly. can do.

  According to the present embodiment, the measurement data measured by each sensor Se1 to Sen is acquired, the monitoring parameter group is extracted based on the measurement data, and the correlation between the measurement data of each sensor included in the monitoring parameter group Calculate the fit value indicating the strength of the average, calculate the average value and standard deviation of the multiple fit values obtained in the past normal state as a reference, the average value and standard deviation value of the fit value in the normal state, Since the validity of the behavioral state can be confirmed by comparing with the fit value of the period, there is no variation depending on the person in charge of the failure sign of the equipment provided in the plant, there is a certain detection accuracy, It is possible to quickly detect a failure sign of a device.

FIG. 7 is a flowchart showing a monitoring process subroutine (S300) by the analysis server 53 according to the embodiment of the present invention.
In the monitoring process, in step S305, the main control unit 65 determines whether or not the relationship model used for the monitoring process has been set in the data storage unit 69.
Here, if the relationship model has been set in the data storage unit 69 (S305, Yes), the process proceeds to step S310. On the other hand, if the relationship model has not been set in the data storage unit 69 (S305, No), Return from the subroutine.
In step S <b> 310, the main control unit 65 acquires measurement data from the sensor monitoring device 51.
In step S315, the main control unit 65 determines whether a similar tendency appears in the acquired measurement data.
Here, when the same tendency appears in the measurement data (S315, Yes), the processing in the subroutine is terminated and the process returns. On the other hand, when the same tendency does not appear in measurement data (S315, No), it progresses to step S320.
In step S <b> 320, the main control unit 65 extracts abnormal factor candidates from the database unit 77 and stores them in the data storage unit 69.
Next, the process in the subroutine is terminated and the process returns.

FIG. 8 is a flowchart showing a subroutine (S500) of automatic extraction processing for the influence range of the abnormality sign by the analysis server 53 according to the embodiment of the present invention.
In the automatic extraction process for the influence range of the abnormality sign, in step S505, the main control unit 65 generates an alarm to notify the person in charge when the abnormality sign exceeds the threshold value.
In step S510, the main control unit 65 searches the database unit 77 for information on sensor and system failure cases related to abnormality signs.

In step S515, the main control unit 65 extracts similar events from the database unit 77.
In step S520, the main control unit 65 displays the abnormal part on the display unit 73.
In step S522, the main control unit 65 determines whether it is necessary to create a database. If database creation is necessary (S522, Yes), the process proceeds to step S525. On the other hand, if the database is not required (S522, No), the processing in the subroutine is finished and the process returns.
Note that a message for inquiring whether or not a database is necessary may be displayed on the display unit 73 and the will of the person in charge may be confirmed by the GUI function using the operation unit 67.
In step S525, the main control unit 65 obtains the acquired data acquired in the process of executing the processing steps so far, failure location specifying information for specifying the failure location, and abnormality detection information (know-how) when an abnormality is detected. A database to be stored together with a process tag representing each process and a time stamp is generated, and a record number is added and stored in the database unit 77.

  Next, the process in the subroutine is terminated and the process returns.

  According to the present embodiment, data that can be acquired in the process of executing each step, failure point display information for displaying a failure sign point, abnormality detection information when an abnormality is detected, display information of a failure sign point, By generating a database that stores each tag along with a tag representing each process and a time stamp, it is possible to improve the accuracy of identifying future failure sign points.

FIG. 9 is a flowchart showing a subroutine (S600) of failure sign detection processing by the analysis server 53 according to the embodiment of the present invention.
In the failure sign detection process, in step S605, the main control unit 65 determines whether or not the monitoring period ends. When the monitoring period ends (S605, Yes), the processing in the subroutine ends and returns. On the other hand, if the monitoring period has not expired (S605, No), the process proceeds to step S615.
Note that a message for inquiring whether the monitoring period is over may be displayed on the display unit 73 and the will of the person in charge may be confirmed by the GUI function using the operation unit 67.
In step S615, the main control unit 65 calls a real-time monitoring process (S700) based on invariant monitoring, which is a subroutine.
When the process returns from the subroutine, the process proceeds to step S620.
In step S620, the main control unit 65 determines whether there is a sign or a sign. That is, the main control unit 65 determines whether or not the total value (anomaly score) of the collapsed invariant exceeds the allowable range.
Here, when the total value of the collapsed invariant exceeds the allowable range (S620, Yes), the process proceeds to step S625. On the other hand, when the total value of the collapsed invariant exceeds the allowable range (S620, No), the process returns to step S605.
In step S625, the main control unit 65 calls an automatic extraction process (S500) for the influence range of the abnormality sign, which is a subroutine.
When the process returns from the subroutine, the process proceeds to step S630.

In step S <b> 630, the main control unit 65 displays a message urging the specific work of the problem location on the display unit 73. For example, the main control unit 65 issues an alarm notification by displaying a message “please specify the problem location” on the display unit 73 via the display control unit 71.
In step S <b> 635, the main control unit 65 displays on the display unit 73 a temporal change in parameters related to the influence range of the abnormality sign.
In step S640, the main control unit 65 uses the relationship model for strengthening monitoring in parallel. (Supervision)

In step S645, the main control unit 65 determines whether or not there is an abnormal state.
Here, when it is in an abnormal state (S645, Yes), it progresses to step S650, and when it is not in an abnormal state (S645, No), it progresses to step S655.
In step S650, the main control unit 65 displays a message for prompting treatment on the target location on the display unit 73. For example, the main control unit 65 displays a message “Please apply to the target location” on the display unit 73 via the display control unit 71.
In step S655, the main control unit 65 calls a relationship model creation process (S400) which is a subroutine.
When the process returns from the subroutine, the process proceeds to step S615.

  According to the present embodiment, the analysis server 53 is provided in the plant because it can detect a failure sign of each device by displaying measurement data of each sensor in real time and display a problem location. There is no variation depending on the person in charge of the failure sign of the device, there is a certain detection accuracy, and the failure sign of the device can be detected promptly.

FIG. 10 is a flowchart showing a subroutine (S700) of real-time monitoring processing by invariant monitoring by the analysis server 53 according to the embodiment of the present invention.
In the real-time monitoring process using invariant monitoring, in step S705, the main control unit 65 acquires the relationship model corresponding to the steady operation process from the database stored in the database unit 77 in the data storage unit 69.
In step S <b> 710, the main control unit 65 acquires measurement data from the sensor monitoring device 51.
In step S715, the main control unit 65 calculates a predicted value of each sensor whose relationship is predicted using the relationship model according to the equation (1) for the measurement data of each sensor.

In step S720, the main control unit 65 calculates a difference value between the measurement data of each sensor and the predicted value.
In step S725, the main control unit 65 calculates the collapse of the invariant (invariant relationship) that occurs when the difference value exceeds the allowable range. Here, the allowable range represents the range from the lower limit value to the upper limit value of the predicted value, and an abnormality occurs when the difference (difference value) between the measured data of each sensor and the predicted value exceeds the allowable range. Suppose that there is.
In step S730, the main control unit 65 calculates the total value (anomaly score) of the collapsed invariant. Next, the process in the subroutine is terminated and the process returns.

  According to the present embodiment, in correspondence with the steady operation process of the plant 10, a plurality of relationship models of measurement data during normal operation in a device representing the mutual relationship between the measurement data of the sensors are stored in the model storage unit. Store the measured data of each sensor, calculate the predicted value of each sensor whose relationship is predicted using the relationship model, calculate the difference value between the measured data of each sensor and the predicted value, Because it is possible to detect the failure sign of each device by detecting the collapse of the invariant (invariable relationship) that occurs when the value exceeds the allowable range, the failure sign of the device equipped in the plant can be detected by the person in charge. There is no dependence variation, there is a certain detection accuracy, and it is possible to quickly detect a failure sign of a device.

FIG. 11 is a flowchart showing a subroutine (S900) of equipment inspection processing by the analysis server 53 according to the embodiment of the present invention.
In the equipment inspection process, in step S905, the main control unit 65 calls a relationship model creation process (S400) which is a subroutine.
When the process returns from the subroutine, the process proceeds to step S910.
In step S910, the main control unit 65 calls a real-time monitoring process (S700) based on invariant monitoring, which is a subroutine.
When the process returns from the subroutine, the process proceeds to step S915.

In step S915, the main control unit 65 determines whether a problem has occurred.
If there is a problem (S915, Yes), the process proceeds to step S940. On the other hand, if there is no problem (S915, No), the process proceeds to step S920.
If there is no problem, in step S920, the main control unit 65 displays a message for prompting equipment inspection on the display unit 73. For example, the main control unit 65 displays a message “please check the equipment” on the display unit 73 via the display control unit 71.
In step S925, the main control unit 65 determines whether or not the equipment inspection is finished.
Here, when equipment inspection is complete | finished (S925, Yes), it progresses to step S930, and when equipment inspection is not complete | finished (S925, No), it returns to step S920.
In step S930, the main control unit 65 calls a relationship model creation process (S400) which is a subroutine.
When returning from the subroutine, the process proceeds to step S935.
In step S935, the main control unit 65 stores the relationship model created by the relationship model creation process (S400) in the database unit 77 via the disk control unit 75.
Next, the process in the subroutine is terminated and the process returns.

If there is a problem, in step S940, the main control unit 65 calls a problem location identification process (S1100) which is a subroutine.
When the process returns from the subroutine, the process proceeds to step S945.
In step S <b> 945, the main control unit 65 displays a message that prompts the problem portion to deal with the problem on the display unit 73. For example, the main control unit 65 displays a message “There is a problem part, please deal with the problem” on the display unit 73 via the display control unit 71.
In step S950, the main control unit 65 determines whether the problem handling has ended.
If the problem handling has been completed (S950, Yes), the process proceeds to step S910. On the other hand, if the problem handling has not been completed (S950, No), the process returns to step S945.

FIG. 12 is a flowchart showing a subroutine (S1000) of real-time monitoring processing by invariant monitoring by the analysis server 53 according to the embodiment of the present invention.
In the real-time monitoring process by invariant monitoring, in step S1005, the main control unit 65 acquires the relationship model corresponding to the equipment inspection process from the database unit 77 to the data storage unit 69 via the disk control unit 75.
In step S <b> 1010, the main control unit 65 acquires measurement data from the sensor monitoring device 51.
In step S <b> 1015, the main control unit 65 calculates a predicted value of each sensor whose relationship is predicted using the relationship model according to the equation (1) for the measurement data of each sensor.
In step S1025, the main control unit 65 calculates a difference value between the measurement data of each sensor and the predicted value.
In step S1030, the main control unit 65 detects an invariant (invariant relationship) collapse that occurs when the difference value exceeds an allowable range set in the data storage unit 69 in advance.
In step S <b> 1035, the main control unit 65 calculates a total value (anomaly score) of the invariants that have collapsed.
In step S1040, the main control unit 65 displays the result on the display unit 73.
As a result, as shown in FIGS. 14A to 14E, the display screen at each time point can be displayed on the display unit 73, and the person in charge can be visually confirmed.
Next, the process in the subroutine is terminated and the process returns.

  According to this embodiment, with respect to the measurement data of each sensor Se1 to Sen, the predicted value of each sensor whose relationship is predicted using the relationship model is calculated, and the measurement data and the predicted value of each sensor are calculated. Equipment that is provided in the plant, because it is possible to detect a failure sign of each equipment by calculating the difference value and detecting the invariant (invariable relationship) collapse that occurs when the difference value exceeds the allowable range. Therefore, there is no variation depending on the person in charge, there is a certain detection accuracy, and it is possible to quickly detect a failure sign of a device.

  According to the present embodiment, as the relationship model, the first relationship model to the nth relationship model different from each other with the correlation of the sensor group grouped for each characteristic of the sensors Se1 to Sen as the monitoring range, and Is stored in the database unit 77, and the measurement data of each sensor is simultaneously monitored in real time based on the measurement data of each sensor and the first relationship model to the nth relationship model for each sensor. Therefore, there is no variation depending on the person in charge of the failure sign of the equipment provided in the plant, there is a certain detection accuracy, and the failure sign of the equipment can be detected promptly.

  According to the present embodiment, the display positions of the correlated sensors are respectively arranged at the positions in the vertical axis direction and the horizontal axis direction, and the presence / absence of the invariant (invariant relationship) collapse is displayed at each intersection position. Therefore, there is no variation depending on the person in charge of the failure sign of the equipment provided in the plant, there is a certain detection accuracy, and the failure sign of the equipment can be detected promptly.

  According to the present embodiment, when the total value (anomaly score) of the collapsed invariant is calculated, it is determined whether or not the total value exceeds the allowable range, and it is determined that the total value exceeds the allowable range In addition, the alarm can be reported, so there is no variation depending on the person in charge of the failure sign of the equipment provided in the plant, there is a certain detection accuracy, and the sign of failure of the equipment can be detected promptly. .

FIG. 13 is a flowchart showing a subroutine (S1100) of the problem location specifying process by the analysis server 53 according to the embodiment of the present invention. Hereinafter, the main control unit 65 performs parallel processing in the processing from steps S1105-1 to S1105-n to steps S1115-1 to S1115-n, and description of similar processing contents is omitted.
In step S1105-1, the main control unit 65 acquires the first relationship model from the database unit 77 to the data storage unit 69 via the disk control unit 75.
In step S1110-1, the main control unit 65 calls a failure sign detection process (S600) which is a subroutine.
When returning from the subroutine, the process proceeds to step S1115-1.

  In step S1115-1, the main control unit 65 generates a determination flag based on the detection result. That is, when the detection result is abnormal, an abnormality flag (NG) is set in the data storage unit 69 as a determination flag. As a result, in the data storage unit 69, the first relationship model to the nth relationship model and the respective determination flags are set.

  Next, in step S <b> 1125, the main control unit 65 displays the result on the display unit 73. Next, the process in the subroutine is terminated and the process returns.

  According to the present embodiment, the analysis server 53 detects a failure sign of each device by monitoring measurement data of each sensor in real time in a trial operation process of the plant, and detects any one failure sign of a plurality of devices. When detected, by confirming the appropriateness of the behavioral state based on the measurement data, the failure signs of each device can be displayed. There is no dependence variation, there is a certain detection accuracy, and it is possible to quickly detect a failure sign of a device.

FIGS. 14A to 14E are diagrams showing analysis results by the analysis server 53 according to the embodiment of the present invention. FIG. 14A is an example of a display screen showing a display screen 101, a display target time and display button 103, an anomaly score graph 103a, a search condition 105, a list of all invariants or a list of defect invariants 107. When a desired point on the anomaly score graph 103a shown in FIG. 14A is clicked, the display shifts to the two-dimensional matrices (b) to (e) at the time of the click point.
In the two-dimensional matrix display processing, when the fit value is larger than the reference value, the intersection indicating the relationship of the two-dimensional matrix table is displayed in red, and when the fit value is not larger than the reference value, the two-dimensional matrix table is displayed. The intersections showing the relationship are displayed in white.
FIG. 14B is an example of a display screen 109a in which intersections displayed in red at a certain point in time start to appear a little, and FIG. 14C is displayed in red with time slightly advanced from the point of FIG. 14B. FIG. 14D is a display screen example 109c showing the detection timing (S1030) by the analysis server 53, and FIG. 14E is a display screen showing the detection timing by the person in charge. Example 109d.
In the present embodiment, the two-dimensional matrix table that is color-coded into red and white is configured to be displayed. However, other two colors may be used for display.

In the prior art, when monitoring the observed data and detecting anomalies by comparing with the set threshold, the threshold is set by paying attention to the physical quantity to be measured. It was difficult and sometimes overlooked.
On the other hand, according to the present embodiment, the pre-failure point of each device can be displayed from the slight displacement of the measurement data before the abnormality detection timing based on the threshold value set in the prior art. Therefore, there is no variation depending on the person in charge of the failure sign of the device being used, there is a certain detection accuracy, and the failure sign of the device can be detected quickly.
As a result, it is possible to reduce the burden on the person in charge such as time and labor required for analyzing the influence range. At the same time, it is possible to reduce the burden on each device provided in the plant.

<Configuration, operation and effect of exemplary embodiment of the present invention>
<First aspect>
The failure sign monitoring method according to the present aspect includes a plurality of devices arranged in the plant 10, sensors Se1 to Sen that measure the behavior of each device, and measurement data measured by each sensor. An analysis server 53 (failure sign monitoring device) for monitoring a sign, and is a failure sign monitoring method by the analysis server 53, and the analysis server 53 is configured as shown in the flowcharts of FIGS. Each device is divided into a plurality of periods t0 to t1 based on the operation contents in the starting process, and the validity of the behavior state is checked each time each period ends based on the measurement data. The problem location display processing step (Fig. 4) for displaying the pre-failure location, and the process management step that moves to the next period when it is confirmed that the behavior state in each period is appropriate Tsu and up (S235), characterized in that it run.
According to this aspect, the analysis server 53 divides the inside of the starting process into a plurality of periods t0 to t1 based on the operation content in the starting process of the plant 10, and each time period ends based on the measurement data. By confirming the appropriateness of the behavioral state, the failure sign of each device is displayed, and when the behavioral state in each period is confirmed to be valid, the failure of each device is confirmed by moving to the next period. Since the sign location can be displayed, there is no variation depending on the person in charge of the failure sign of the equipment provided in the plant, there is a certain detection accuracy, and the failure sign of the equipment can be detected quickly.
As a result, when it is necessary to monitor a plurality of events continuously for a long period of time, such as an activation process, a great effect can be obtained in strengthening the monitoring function.

<Second aspect>
The failure sign monitoring method according to the present aspect includes a plurality of devices arranged in the plant 10, sensors Se1 to Sen that measure the behavior of each device, and measurement data measured by each sensor. An analysis server 53 (failure sign monitoring device) for monitoring a sign, and a failure sign monitoring method by the analysis server 53, wherein the analysis server 53 stores the measurement data of each sensor as shown in the flowchart of FIG. A failure sign detection step (S600) for detecting a failure sign of each device by monitoring in real time and displaying a problem location is performed.
According to this aspect, the analysis server 53 can detect a failure sign of each device by monitoring the measurement data of each sensor in real time and display the problem location. Therefore, there is no variation depending on the person in charge, there is a certain detection accuracy, and it is possible to quickly detect a failure sign of a device.

<Third aspect>
The failure sign monitoring method according to the present aspect includes a plurality of devices arranged in the plant 10, sensors Se1 to Sen that measure the behavior of each device, and measurement data measured by each sensor. An analysis server 53 (failure sign monitoring device) that monitors a sign, and is a failure sign monitoring method by the analysis server 53. The analysis server 53 is a CR pattern of a plant as shown in the flowcharts of FIGS. By dividing the inside of the process into a plurality of periods t40 to t5 based on the operation content in the change process or the stop process, and confirming the validity of the behavior state every time the period ends based on the measurement data When the problem location display processing step (Fig. 4) for displaying the pre-failure location of each device and the behavior state in each period is confirmed to be valid, And executes a process to row management step (S235), the.
According to this aspect, the analysis server 53 divides the inside of the process into a plurality of periods t40 to t5 based on the operation content in the CR pattern changing process or the stopping process of the plant, and the period based on the measurement data. By confirming the appropriateness of the behavioral state every time is completed, the failure sign of each device is displayed, and when the behavioral state in each period is confirmed to be valid, by moving to the next period, Since it can be confirmed that the behavior state in each period is appropriate, there is no variation depending on the person in charge of the failure sign of the equipment provided in the plant, there is a certain detection accuracy, and the failure sign of the equipment is detected quickly. be able to.

<4th aspect>
The failure sign monitoring method according to the present aspect includes a plurality of devices arranged in the plant 10, sensors Se1 to Sen that measure the behavior of each device, and measurement data measured by each sensor. An analysis server 53 (failure sign monitoring device) for monitoring a sign, and is a failure sign monitoring method by the analysis server 53, and the analysis server 53 is a test run of a plant as shown in the flowcharts of FIGS. In the process, a failure sign detection step (S900) for detecting a failure sign of each device by monitoring measurement data of each sensor in real time, and a failure sign of any one of a plurality of devices is detected by the failure sign detection step. In this case, it is possible to check the appropriateness of the behavioral state based on the measurement data, and to display the failure point of each device. And it shows processing steps (S1100), characterized by the execution.
According to this aspect, the analysis server 53 detects the failure sign of each device by monitoring the measurement data of each sensor in real time in the trial operation process of the plant, and detects any one failure sign of the plurality of devices. In this case, by confirming the appropriateness of the behavioral state based on the measurement data, it is possible to display the failure signs of each device, so the failure signs of the devices installed in the plant depend on the person in charge. There is no variation, there is a certain detection accuracy, and it is possible to quickly detect a failure sign of the device.

<5th aspect>
The problem location display processing step of this aspect is based on the acquisition step (S105) for acquiring measurement data measured by the sensors Se1 to Sen and the measurement data, as in the flowcharts shown in FIGS. An extraction step (S110) for extracting a monitoring parameter group, a fitting value calculation step (S125) for calculating a fitting value indicating the strength of correlation between measurement data of each sensor included in the monitoring parameter group, and a reference A calculation step (S130) for calculating an average value and a standard deviation of a plurality of fit values acquired in the past normal state, an average value and a standard deviation value of the fit values in the normal state, and a fit value for the period The validity of the behavior state is confirmed by executing a comparison step (S215) for comparison.
According to this aspect, the measurement data measured by each sensor Se1 to Sen is acquired, the monitoring parameter group is extracted based on the measurement data, and the correlation between the measurement data of each sensor included in the monitoring parameter group is calculated. Calculate the fit value indicating strength, calculate the average value and standard deviation of the fit values obtained multiple times in the past normal state as a reference, calculate the average value and standard deviation value of the fit value in the normal state, and the period By comparing with the fit value of the plant, the validity of the behavioral state can be confirmed, so there is no variation depending on the person in charge of the failure sign of the equipment provided in the plant, there is a certain detection accuracy, equipment It is possible to quickly detect a failure sign.

<Sixth aspect>
In the failure sign detection step (S600) of this aspect, as shown in the flowcharts of FIG. 9 and FIG. 10, corresponding to the steady operation process of the plant 10, the device representing the mutual relationship between the measurement data of the sensors. Storage step (S655) for storing a plurality of relationship models of measurement data during normal operation in the model storage means, and for each sensor whose relationship is predicted using the relationship model for the measurement data of each sensor A predicted value calculating step (S715) for calculating the predicted value of the sensor, a difference value calculating step (S720) for calculating a difference value between the measurement data of each sensor and the predicted value, and when the difference value exceeds the allowable range. A failure detection step (S725) for detecting an invariant (invariant relationship) collapse is detected, and a failure sign of each device is detected. To.
According to this aspect, in correspondence with the steady operation process of the plant 10, a plurality of relationship models of measurement data at the time of normal operation in a device representing the mutual relationship between the measurement data of the sensors are stored in the model storage means. And calculate the predicted value of each sensor whose relationship is predicted using the relationship model for the measured data of each sensor, calculate the difference value between the measured data of each sensor and the predicted value, Because it is possible to detect a failure sign of each device by detecting the collapse of the invariant (invariable relationship) that occurs when the value exceeds the allowable range, it depends on the person in charge of the failure sign of the equipment provided in the plant There is no variation, there is a certain detection accuracy, and it is possible to quickly detect a failure sign of the device.

<Seventh aspect>
In the failure sign detection step (S900) of this aspect, as shown in the flowcharts of FIGS. 11 and 12, each sensor whose relationship is predicted using the relationship model with respect to the measurement data of each sensor Se1 to Sen. This occurs when a predicted value calculation step (S1015) for calculating a predicted value, a difference value calculation step (S1025) for calculating a difference value between measurement data of each sensor and a predicted value, and when the difference value exceeds an allowable range. A failure sign of each device is detected by executing a collapse detection step (S1030) for detecting an invariant (invariant relationship) collapse.
According to this aspect, with respect to the measurement data of each sensor Se1 to Sen, the predicted value of each sensor whose relationship is predicted using the relationship model is calculated, and the difference between the measured data of each sensor and the predicted value By calculating the value and detecting the invariant (invariable relationship) collapse that occurs when the difference value exceeds the allowable range, it is possible to detect a failure sign of each device. There is no variation depending on the person in charge of the failure sign, there is a certain detection accuracy, and the failure sign of the device can be detected quickly.

<Eighth aspect>
The failure sign monitoring method according to the present embodiment includes data that can be acquired in the process of executing each step, failure point display information for displaying a failure sign point, and an abnormality when an abnormality is detected, as shown in the flowchart of FIG. A database generation step (S525) for generating a database that stores detection information and display information of a failure sign point together with a tag representing each process and a time stamp is executed.
According to this aspect, data that can be acquired in the process of executing each step, failure point display information for displaying a failure sign point, abnormality detection information when an abnormality is detected, display information of a failure sign point, By generating a database that stores a tag representing a process and a time stamp, it is possible to improve the accuracy of identifying future failure sign points.

<Ninth aspect>
In the model storing step (S930, S400) of this aspect, as shown in the flowcharts of FIGS. 11 to 13, as a relationship model, the correlation of sensor groups grouped for each characteristic of each sensor Se1 to Sen is monitored. The first relationship model to the nth relationship model that are different from each other as the range are stored in the database unit 77 (S935), and the problem location display step (S1100) is performed for the measurement data of each sensor and each sensor. Based on the first relationship model to the n-th relationship model, the measurement data of each sensor is simultaneously monitored in real time.
According to this aspect, as the relationship model, the first relationship model to the n-th relationship model that are different from each other with the correlation of the sensor group grouped for each characteristic of the sensors Se1 to Sen as the monitoring range are obtained. Based on the measurement data of each sensor stored in the database unit 77 and the first to nth relationship models for each sensor, the measurement data of each sensor is simultaneously monitored in real time. Therefore, there is no variation depending on the person in charge of the failure sign of the equipment provided in the plant, there is a certain detection accuracy, and the failure sign of the equipment can be detected promptly.

<10th aspect>
In the problem location display processing step of this aspect, as shown in the flowchart of FIG. 12, the display positions of the correlated sensors are arranged at the positions in the vertical axis direction and the horizontal axis direction, respectively, and are inserted at the respective intersection positions. A display step (S1000) for displaying whether or not a variant (invariant relationship) has collapsed is executed.
According to this aspect, the display position of each sensor in correlation is arranged at the position in the vertical axis direction and the horizontal axis direction, and the presence or absence of invariant (invariant relation) collapse is displayed at each intersection position. Therefore, there is no variation depending on the person in charge of the failure sign of the equipment provided in the plant, there is a certain detection accuracy, and the failure sign of the equipment can be detected promptly.

<Eleventh aspect>
The failure sign detection step of this aspect includes a total value calculation step (S730) for calculating the total value (anomaly score) of the collapsed invariant, as shown in the flowcharts of FIGS. A determination step (S620) for determining whether or not the threshold value has been exceeded is executed, and an alarm is reported when it is determined by the determination step that the total value exceeds the allowable range.
According to this aspect, the total value (anomaly score) of the collapsed invariant is calculated, it is determined whether the total value exceeds the allowable range, and when it is determined that the total value exceeds the allowable range Since the alarm can be reported, there is no variation depending on the person in charge of the failure sign of the equipment provided in the plant, there is a certain detection accuracy, and the failure sign of the equipment can be detected promptly.

DESCRIPTION OF SYMBOLS 10 ... Plant, 11 ... Reactor building, 13 ... Reactor, 15 ... Reactor containment vessel, 17 ... Nuclear pressure vessel, 19 ... Steam dryer, 21 ... Steam separator, 23 ... Fuel assembly, 25 ... Control Rod, 26 ... Recirculation pump, 27 ... Pressure suppression chamber, 31 ... Turbine building, 33 ... Turbine, 35 ... Generator, 37 ... Condenser, 39 ... Drain, 41 ... Intake, 43 ... Pump, 45 ... Water supply pump, 51 ... sensor monitoring device, 50 ... system, 53 ... analysis server, 55 ... client terminal, 61 ... communication control unit, 65 ... main control unit, 67 ... operation unit, 69 ... data storage unit, 71 ... display control 73, display unit, 75 ... disk control unit, 77 ... database unit

Claims (11)

A plurality of devices arranged in the plant;
A sensor for measuring the behavior of each device;
A failure sign monitoring device that monitors a failure sign of each device based on measurement data measured by each sensor, and a failure sign monitoring method by the failure sign monitoring device,
The failure sign monitoring device is
By dividing the start-up process into a plurality of periods based on the operation contents in the start-up process of the plant, and confirming the appropriateness of the behavior state at the end of each period based on the measurement data , A problem location display processing step for displaying a failure sign location of each device,
And a process management step of shifting to the next period when the behavior state in each period is confirmed to be valid. A plurality of devices arranged in the plant;
A sensor for measuring the behavior of each device;
A failure sign monitoring device that monitors a failure sign of each device based on measurement data measured by each sensor, and a failure sign monitoring method by the failure sign monitoring device,
The failure sign monitoring device is
A failure sign monitoring method for detecting a failure sign of each device by monitoring measurement data of each sensor in real time, and executing a failure sign detection step of displaying a problem location. A plurality of devices arranged in the plant;
A sensor for measuring the behavior of each device;
A failure sign monitoring device that monitors a failure sign of each device based on measurement data measured by each sensor, and a failure sign monitoring method by the failure sign monitoring device,
The failure sign monitoring device is
Based on the operation contents in the CR pattern changing process or the stopping process of the plant, the process is divided into a plurality of periods, and the validity of the behavior state every time the period ends based on the measurement data. By confirming, the problem location display processing step of displaying the failure sign location of each device,
And a process management step of shifting to the next period when the behavior state in each period is confirmed to be valid. A plurality of devices arranged in the plant;
A sensor for measuring the behavior of each device;
A failure sign monitoring device that monitors a failure sign of each device based on measurement data measured by each sensor, and a failure sign monitoring method by the failure sign monitoring device,
The failure sign monitoring device is
In the trial operation process of the plant,
A failure sign detection step of detecting a failure sign of each device by monitoring measurement data of each sensor in real time;
When any one of the plurality of devices is detected in the failure sign detection step, the failure sign location of each device is displayed by checking the validity of the behavior state based on the measurement data. A failure sign monitoring method comprising: performing a problem location display processing step. The problem location display processing step includes:
An acquisition step of acquiring measurement data measured by each sensor;
An extraction step of extracting a monitoring parameter group based on the measurement data;
A fitting value calculating step for calculating a fitting value indicating the strength of correlation between measurement data of each sensor included in the monitoring parameter group;
A calculation step for calculating an average value and a standard deviation of a plurality of fit values acquired in the past normal state as a reference;
2. The validity of the behavior state is confirmed by executing a comparison step of comparing the average value and standard deviation value of the fit values in the normal state with the fit values of the period. The failure sign monitoring method according to any one of 3, 4 and 4. The failure sign detection step includes
Corresponding to the steady operation process of the plant, a model storage step of storing a plurality of relationship models of measurement data at the time of normal operation in the device representing a mutual relationship between the measurement data of the sensors in the model storage means When,
A predicted value calculation step for calculating a predicted value of each sensor whose relationship is predicted using the relationship model with respect to measurement data of each sensor;
A difference value calculating step for calculating a difference value between the measurement data of each sensor and the predicted value;
The failure detection method according to claim 2, wherein a failure sign of each of the devices is detected by executing a failure detection step of detecting a failure of an invariant that occurs when the difference value exceeds an allowable range. Predictive monitoring method. The failure sign detection step includes
A predicted value calculation step for calculating a predicted value of each sensor whose relationship is predicted using the relationship model with respect to measurement data of each sensor;
A difference value calculating step for calculating a difference value between the measurement data of each sensor and the predicted value;
5. The failure detection according to claim 4, wherein a failure symptom of each device is detected by executing a collapse detection step of detecting a collapse of an invariant that occurs when the difference value exceeds an allowable range. Predictive monitoring method.   Tags representing each step of data that can be acquired in the process of executing each step, failure location display information for displaying a failure sign location, abnormality detection information when an abnormality is detected, and display information of a failure indication location And a database generation step of generating a database to be stored together with a time stamp. 5. The failure sign monitoring method according to claim 1. In the model storing step, as the relationship model,
A first relationship model to a nth relationship model different from each other with the correlation of the sensor group grouped for each characteristic of each sensor as a monitoring range;
The problem location display step includes:
Based on the measurement data of each sensor and the first relationship model to the nth relationship model for each sensor, the measurement data of each sensor is monitored in parallel in real time. The failure sign monitoring method according to claim 4. The problem location display processing step includes:
The display step of displaying the presence / absence of the invariant collapse at each intersection position by disposing the display positions of the sensors in the correlation at the positions in the vertical axis direction and the horizontal axis direction, respectively. The failure sign monitoring method according to claim 1. The failure sign detection step includes
A total value calculating step for calculating a total value of the collapsed invariant,
Determining whether the total value exceeds an allowable range, and
The failure sign monitoring method according to claim 2, wherein an alarm is reported when it is determined in the determination step that the total value exceeds an allowable range.

Images