JP6523815B2 - Plant diagnostic device and plant diagnostic method - Google Patents

Description

The present invention relates to a plant diagnostic device and a plant diagnostic method for diagnosing a status abnormality of a plant.

  When an abnormal transient event or an accident or the like occurs in the plant, the plant diagnosis device detects the occurrence of the abnormality or the accident based on measurement data from the plant.

  Patent Document 1 discloses a diagnostic device using Adaptive Resonance Theory (ART), which is one of clustering techniques. Here, ART is a theory that classifies multi-dimensional data into categories according to their degree of similarity.

  In the above-described technology, first, measurement data in a normal state is classified into a plurality of categories (normal categories) using ART. Next, current measurement data is input to ART and classified into categories. If this measurement data can not be classified as a normal category, a new category (new category) is generated. The occurrence of a new category means that the state of the plant has changed. Therefore, the occurrence of an abnormality is determined on the basis of the occurrence of a new category, and the occurrence of a new category is diagnosed as an abnormality when it exceeds a threshold.

JP 2005-165375 A

  In clustering techniques, there are parameters that determine the size of the cluster (in ART, the size of the category). This parameter is called a resolution parameter. In general, when certain data is classified into clusters, setting the resolution roughly reduces the number of clusters, and setting the resolution finely increases the number of clusters.

  When clustering is used for abnormality diagnosis, the change width of the data tendency that a new category generates differs depending on whether the resolution is coarse or fine. If a new category is generated when the resolution is coarse, the data tendency is largely changed from that in the normal state, so the probability that the device is different is high. On the other hand, when the resolution is fine, there is a possibility that a slight tendency change such as measurement noise may be detected, so the probability of being abnormal is low. As described above, when the setting values of the parameters for determining the cluster size are different, the probability that an abnormality occurs at the time of abnormality detection is different.

  In general, when the diagnosis method is different, the abnormality detection performance is different, so the probability that an abnormality occurs at the time of abnormality detection is different.

  In addition, stopping the plant and performing maintenance / repair when detecting an abnormality is effective for failure prevention of the equipment, but costs for maintenance / repair and opportunity loss during a period when the plant is shut down occur. Therefore, if there is a minor failure, operation may be continued until the periodic inspection. On the other hand, as a result of leaving the abnormality, the device may be broken or damaged, and the loss may be larger than that in the case of maintenance or repair.

  In the present situation, when an abnormality is detected, it is judged based on the plant operation experience whether or not the abnormality should be dealt with, but it is desirable to judge based on the risk (loss expected amount) when leaving the abnormality.

  In order to solve the above problems, the present invention relates to a plant diagnosis apparatus comprising a plurality of diagnosis means for diagnosing a state abnormality of a plant, based on measurement signal data on the state of the plant and facility management information data on a past state abnormality. It is characterized in that it comprises comprehensive diagnostic means for obtaining the certainty related to detection of the condition abnormality of each of the plurality of diagnosis means, and evaluating the expected loss amount based on the certainty and the loss amount accompanying the condition abnormality.

  It is possible to obtain an expected loss amount at the time of abnormality detection, and to provide useful information for determining whether to cope with the detected abnormality.

It is a block diagram explaining the diagnostic device which is the 1st example of the present invention. It is a flowchart figure explaining operation | movement of the comprehensive diagnostic means in evaluation mode and diagnostic mode of a diagnostic device. It is a figure explaining the timing which operates evaluation mode and a diagnostic mode. It is a figure explaining the aspect of the data preserve | saved to a measurement signal database and an installation management information database. It is a figure explaining the aspect of the data preserve | saved at a diagnostic result database. It is explanatory drawing of an adaptive resonance theory. It is a figure which shows the example of a result which classify | categorized the measurement signal into a category. It is a figure explaining the relation between the size of a category, detection timing, accuracy, and a loss expected amount. It is a figure explaining the time-dependent change of the detection result of each diagnostic means, and the loss estimated amount. It is a figure explaining the correction method of accuracy. It is a figure explaining the Example of the screen displayed on a screen display apparatus. It is a figure explaining the Example of the screen displayed on a screen display apparatus. It is a figure explaining model diagnosis. It is a figure explaining the effect by combining clustering diagnosis and model diagnosis. It is a figure explaining the Example at the time of applying the diagnostic device of the present invention to a thermal power plant.

  A diagnostic device suitable for the implementation of the present invention is described below with reference to the drawings. The following is merely an example of the embodiment and is not intended to limit the invention itself to the following specific contents.

  FIG. 1 is a block diagram for explaining a diagnostic apparatus according to a first embodiment of the present invention. The diagnostic device 200 is connected to the plant 100, the screen display device 800, and the external input device 900, and monitors and diagnoses the plant 100. Further, the diagnostic device 200 is configured by a communication unit that executes communication among the devices or devices, a computer or computer server (CPU: Central Processing Unit), a memory, various databases DB, etc. by wired or wireless connection. Further, the external input device 900 is configured by a keyboard switch, a pointing device such as a mouse, a touch panel, a voice instruction device, and the like, and the screen display device 800 is configured by a display and the like.

  The diagnostic device 200 includes a comprehensive diagnostic unit 400 and a diagnostic unit 500 as an arithmetic device. A plurality of diagnostic means 500 are provided, and the number can be set arbitrarily. Further, the diagnostic device 200 includes a measurement signal database 300, an equipment management information database 310, and a diagnosis result database 320 as a database. In FIG. 1, the database is abbreviated as DB.

  The measurement signal database 300, the facility management information database 310, and the diagnosis result database 320 store digitized information, and save the information in a form generally called an electronic file (electronic data).

  The diagnostic device 200 also includes an external input interface 210 and an external output interface 220 as an interface with the outside.

  Then, measurement signals 1 obtained by measuring various state quantities, which are operating states of the plant 100, through the external input interface 210, and external input signals 2 generated by operating the keyboard 910 and the mouse 920 provided in the external input device 900. Are taken into the diagnostic device 200. Also, the integrated diagnosis result signal 12 is output to the screen display device 800 via the external output interface 220.

  In the diagnostic device 200 shown in FIG. 1, measurement signals 1 obtained by measuring various state quantities of the plant 100 are taken in via the external input interface 210. The measurement signal 3 taken into the diagnostic device 200 is stored in the measurement signal database 300. Further, facility management information such as failure information and maintenance information generated in the plant 100 is taken into the diagnostic device 200 by the external input signal 2 generated by the operation of the keyboard 910 and the mouse 920. The facility management information signal 4 taken into the diagnostic device 200 is stored in the facility management information database 310.

  The diagnostic device 200 has two processing modes, an evaluation mode and a diagnostic mode. The flowcharts of the evaluation mode and the diagnosis mode and the operations of the comprehensive diagnosis means 400 and the diagnosis means 500 will be described later with reference to FIGS.

  In the diagnostic device 200 of the present embodiment, the comprehensive diagnostic means 400, the diagnostic means 500, the measurement signal database 300, the equipment management information database 310, and the diagnostic result database 320 are provided inside the diagnostic device 200. Some of the devices may be disposed outside the diagnostic device 200, and only data may be communicated between the devices.

  Further, all information stored in the database installed in the diagnostic device 200 can be displayed on the screen display device 100, and such information is generated by operating the external input device 900 with the external input signal 1 It can be corrected.

  In the present embodiment, the external input device 900 is configured of a keyboard and a mouse, but any device for inputting data, such as a microphone for voice input or a touch panel may be used.

  Moreover, it goes without saying that the present invention can also be implemented as an information providing service that provides information obtained by operating the diagnostic method and the diagnostic device 200 as an embodiment of the present invention.

  FIG. 2 is a flow chart for explaining the operation of the comprehensive diagnostic means 400 in the evaluation mode and the diagnostic mode of the diagnostic device 200.

  FIG. 2A is a flowchart of the evaluation mode.

  First, in step 2000, the comprehensive diagnostic means 400 extracts the measurement signal 5 in a predetermined period stored in the measurement signal database 300.

  In step 2010, the comprehensive diagnostic means 400 transmits the measurement signal 9 to the diagnostic means 500. The diagnostic means 500 processes the measurement signal 9 to diagnose the state of the plant 100, and transmits the diagnostic result 10 to the comprehensive diagnostic means 400. The comprehensive diagnostic means 400 collects the received diagnostic results 10, transmits the diagnostic result database information 8 to the diagnostic result database 320, and stores it.

  In step 2020, the comprehensive diagnostic means 400 extracts the facility management information signal 6 stored in the facility management information database 310.

  In step 2030, the detection result of each diagnosis means of the diagnosis result database information 7 stored in the diagnosis result database 320 is compared with the facility management information signal 6 extracted in step 2020 to calculate the accuracy and the average lead time. Here, the accuracy is obtained by dividing the number of failures by the number of detections. The average lead time is a time obtained by subtracting the time detected by the corresponding diagnostic means from the time detected by the threshold determination, and is a time indicating how early the detection is performed. The accuracy and average lead time of each diagnostic means determined in step 2030 are stored in the diagnostic result database 320.

  At step 2040, the comprehensive diagnostic means 400 extracts the diagnostic result database information 7 stored in the diagnostic result database 320 and transmits it as the comprehensive diagnostic result signal 11 to the external output interface 220. The comprehensive diagnosis result signal 12 is transmitted to the image display device 800 and displayed on the screen display device 800.

  FIG. 2 (b) is a flow chart for explaining the operation of the diagnostic mode.

  In step 2100, the comprehensive diagnostic means 400 extracts the operation data 5 of the diagnosis period stored in the measurement signal database.

  At step 2110, the comprehensive diagnostic means 400 transmits the measurement signal 9 to the diagnostic means 500. The diagnostic means 500 processes the measurement signal 9 to diagnose the state of the plant 100, and transmits the diagnostic result 10 to the comprehensive diagnostic means 400. The comprehensive diagnostic means 400 collects the received diagnostic results 10, transmits the diagnostic result database information 8 to the diagnostic result database 320, and stores it.

  In step 2120, the presence or absence of abnormality detection is evaluated, and if there is a diagnosis unit that detects an abnormality, the process proceeds to step 2130, and if not, the process proceeds to step 2160.

  At step 2130, the comprehensive diagnostic means 400 extracts the diagnostic result database information 7 stored in the diagnostic result database 320, and at step 2120 grasps the information on the certainty about the diagnostic means which has detected the abnormality.

  In step 2140, the comprehensive diagnostic means 400 extracts the facility management information 6 stored in the facility management information database 310, and grasps the loss amount due to failure.

  In step 2150, the comprehensive diagnostic means 400 calculates the expected loss amount based on the accuracy extracted in step 2130 and the loss amount extracted in step 2140. It is needless to say that there are a plurality of ways to calculate the expected loss amount, such as multiplying the accuracy and the loss amount, or evaluating using a predetermined parameter.

  At step 2160, the detection result of each diagnostic means and the expected loss calculated at step 2150 are displayed on the screen display device 800 if there are any diagnostic means detected as abnormal.

  As described above, the diagnostic device 200 of the present invention can provide information useful for judging whether or not the detected abnormality is to be dealt with by displaying the expected loss amount when the abnormality is detected by the diagnostic means 500.

  FIG. 3 is a diagram for explaining the timing for operating the evaluation mode and the diagnostic mode.

  In the method shown in FIG. 3A, after accumulating operation data for a fixed period, the evaluation mode is operated once and the diagnosis mode is operated at a fixed cycle.

  In the method shown in FIG. 3B, the evaluation mode is operated at constant intervals, the data of the accuracy and the average lead time stored in the diagnosis result database 320 are updated, and then the diagnosis mode is operated.

  In the method shown in FIG. 3C, the evaluation mode is operated when instructed by the user. Execute evaluation mode at any timing, update accuracy, average lead time, and operate diagnostic mode.

  In addition to the timing described in the present embodiment, the timing for operating the evaluation mode and the diagnostic mode can be set arbitrarily.

  FIG. 4 is a diagram for explaining an aspect of data stored in the measurement signal database 300 and the facility management information database 310. As shown in FIG.

  As shown in FIG. 4A, in the measurement signal database 300, the values of the measurement signal 1 (data items A, B, and C are shown in the figure), which are operation data measured for the plant 100, are sampled. It is stored for each cycle (time on the vertical axis).

  A wide range of data can be scrolled by using the scroll boxes 302 and 303 which can move vertically and horizontally on the display screen 301.

  As shown in FIG. 4 (b), the facility management information database 310 stores fault information such as fault contents, countermeasure cost, lead time necessary for fault avoidance, number of days of outage due to fault, and opportunity loss amount caused by plant shutdown. Be done.

  Further, as shown in FIG. 4C, the facility management information database 310 stores maintenance information such as the contents of maintenance, the cost required for maintenance, the number of days required for maintenance, and the amount of opportunity loss due to maintenance.

  FIG. 5 is a view for explaining an aspect of data stored in the diagnosis result database 320. As shown in FIG.

  As shown in FIG. 5A, in the diagnosis result database 320, the detection results of the respective diagnosis means (in the figure, the diagnosis means A, B and C are described) are stored for each sampling cycle (time on the vertical axis) Be done.

  A wide range of data can be scrolled by using the scroll boxes 312 and 313 which can move vertically and horizontally on the display screen 311.

  In the diagnosis result database 320, the detection results of the respective diagnosis means are stored. For example, the diagnosis result is replaced with digital information and stored as 1 for abnormality determination and 0 for normal determination.

  As shown in FIG. 5B, in the diagnostic result database, the accuracy and the average lead time calculated in the evaluation mode are stored for each diagnostic means.

  FIG. 6 describes the case where adaptive resonance theory (ART) is applied as an example of the diagnostic means 500. Note that other clustering methods such as vector quantization and support vector machines can also be used.

  As shown in FIG. 6A, the data classification function comprises a data preprocessing unit 610 and an ART module 620. The data preprocessing unit 610 converts operation data into input data of the ART module 620.

  Hereinafter, the procedure of the data preprocessing unit 610 and the ART module 620 will be described.

  First, in the data preprocessing device 610, data is normalized for each measurement item. Data including normalized data Nxi (n) of the measurement signal and complement CNxi (n) (= 1 to Nxi (n)) of the normalized data is set as input data Ii (n). The input data Ii (n) is input to the ART module 620.

  The ART module 620 classifies the measurement signal 10 or the operation signal 11 as input data into a plurality of categories.

  The ART module 620 comprises an F0 layer 621, an F1 layer 622, an F2 layer 623, a memory 624 and a selection subsystem 625, which are coupled to one another. The F1 layer 622 and the F2 layer 623 are connected via weighting factors. The weighting factor represents a prototype of the category into which the input data is classified. Here, a prototype is a representative value of a category.

  Next, the algorithm of the ART module 620 will be described.

  An outline of the algorithm when input data is input to the ART module 620 is as shown in the following processes 1 to 5.

  Process 1: The input vector is normalized by the F0 layer 621 to remove noise.

  Process 2: By comparing the input data input to the F1 layer 622 with the weighting factor, a candidate of an appropriate category is selected.

  Process 3: The validity of the category selected in the selection subsystem 625 is evaluated by the ratio to the parameter ρ. If it is determined that the data is valid, the input data is classified into the category, and the process proceeds to processing 4. On the other hand, if it is not determined that the category is determined to be valid, the category is reset, and a candidate of an appropriate category is selected from other categories (the process 2 is repeated). As the value of the parameter ρ is increased, the classification of categories becomes finer. That is, the category size becomes smaller. Conversely, the smaller the value of 小 さ く, the coarser the classification. Category size increases. This parameter ρ is called a vigilance parameter.

  Process 4: When all existing categories are reset in Process 2, it is determined that the input data belongs to a new category, and a new weighting factor representing a prototype of the new category is generated.

  Process 5: When the input data is classified into category J, the weighting factor WJ (new) corresponding to the category J uses the past weighting factor WJ (old) and the input data p (or data derived from the input data) Is updated by the number 1.

(1)
WJ (new) = Kw p + (1-Kw) WJ (old)

  Here, Kw is a learning rate parameter (0 <Kw <1), which is a value for determining the degree of reflecting the input vector on a new weighting factor.

  Note that Equations 1 and Equations 2 to 12 described later are incorporated in the ART module 620.

  The feature of the data classification algorithm of the ART module 620 is the process 4 described above.

  In process 4, when input data different from the learned pattern is input, a new pattern can be recorded without changing the recorded pattern. For this reason, it is possible to record a new pattern while recording a pattern learned in the past.

  Thus, given pre-given operation data as input data, the ART module 620 learns the given pattern. Therefore, when new input data is input to the learned ART module 620, the above algorithm can determine which pattern in the past is close. Moreover, if it is a pattern which has not experienced in the past, it will be classified into a new category.

FIG. 6B is a block diagram showing the configuration of the F0 layer 621. The F0 layer 621 re-normalizes the input data I _i at each time to create a normalized input vector u _i ⁰ to be input to the F 1 layer 621 and the selection subsystem 625.

First, W _i ⁰ is calculated from the input data I _i according to Equation 2. Here, a is a constant.

Next, X _i ⁰ obtained by normalizing W _i ⁰ is calculated using Equation 3. Here, || W ⁰ || represents the norm of W ⁰ .

Then, using equation 4, to calculate the V _i ⁰ obtained by removing noise from the X _i ^0. Here, θ is a constant for removing noise. By the calculation of Equation 4, since the minute value is 0, the noise of the input data is removed.

Finally, the normalized input vector u _i ⁰ is obtained using Equation 5. u _i ⁰ is an input of the F1 layer.

FIG. 6C is a block diagram showing the configuration of the F1 layer 622. The F1 layer 622 holds u _i ⁰ obtained in Equation 5 as short-term memory, and calculates P _i to be input to the F 2 layer 722. Formulas for the F2 layer are summarized in Equations 6 to 12. Here, a and b are constants, f (·) is the function shown in equation 4, and T _j is the fitness calculated by the F2 layer 623.

However,

  FIG. 7 is a diagram showing an example of the result of classifying measurement signals into categories.

  Fig.7 (a) is a figure which shows an example of the classification result which classify | categorized the measurement signal 1 of the plant 100 into the category.

  FIG. 7A shows, as an example, two items of the measurement signal, and is represented by a two-dimensional graph. Moreover, the vertical axis and the horizontal axis normalized and showed the measurement signal of each item.

  The measurement signal is divided into a plurality of categories 630 (circles shown in FIG. 4 (c)) by the ART module 620 of FIG. 3 (a). One circle corresponds to one category.

  In the present embodiment, the measurement signals are classified into four categories. Category number 1 is a group in which the value of item A is large and the value in item B is small. Category number 2 is a group in which the values of item A and item B are both small. Category number 3 is small in the value of item A, item B The category number 4 is a group in which the values of item A and item B are both large.

  FIG.7 (b) is a figure explaining the result of having classified measurement signal 1 acquired from plant 100 into a category. The horizontal axis is time, and the vertical axis is a measurement signal and a category number.

  As shown in FIG. 7 (b), data of the normal period before the start of diagnosis was classified into categories 1 to 3. The first half of the data after the start of monitoring is classified into category 2 and is the same category as model data. In this case, it is determined that the state has not changed since the tendency of the data is the same. On the other hand, data in the second half after the start of monitoring is classified into category 4 and is classified into a category different from model data. Since the tendency of the data is different, it is judged that the state of the plant has changed.

  As described above, the diagnostic technology using the clustering technology has a feature of detecting a change in data tendency.

  FIG. 8 is a diagram for explaining the relationship between the category size and the detection timing, the accuracy, and the estimated loss.

  As shown in FIG. 8A, if the parameter す る for determining the resolution is set large and the category size is reduced, even a minute change is detected. It can detect early. On the other hand, the accuracy decreases because a minute change such as measurement noise is detected.

  On the other hand, if the parameter ρ is set small and the category size is increased, a new category occurs when the deviation from the normal state is large.

  It is far from the normal state and the probability of being abnormal is high. On the other hand, the timing of detection is delayed.

  Thus, as the category size increases, the accuracy increases. Since the higher the certainty, the higher the expected loss, the category size and the expected loss have an exponential relationship as shown in FIG. 8 (b).

  At step 2030 in FIG. 2, the past diagnostic data are analyzed by the comprehensive diagnostic means 400 to obtain the relationship of FIG. 8B and stored in the diagnosis result database 320. At step 2040, the relationship of FIG. It may be displayed on the device 800.

  FIG. 9 is a view for explaining the detection results of the respective diagnostic means and the temporal change of the expected loss amount.

  The diagnostic means A, B, C are composed of three types of ART with different category sizes. The diagnostic means A detects at time 2200, the diagnostic means B detects at time 2210, and the diagnostic means C detects at time 2220. Further, the expected loss amount is calculated by multiplying the maximum value of the accuracy of the detected diagnostic means by the damage amount (10 million yen in the present embodiment).

  As described above, during the time 2200 to 2210, the change in the measured value is small, the time for reaching the failure is long, the accuracy is low, and the estimated loss amount is also low. As time passes, the change in the measured value becomes large, and a highly accurate diagnostic means detects an abnormality, and the loss expected amount also increases.

  As described above, the diagnostic device 200 of the present invention can acquire information for determining whether to cope with an abnormality based on the estimated loss amount at each time.

  FIG. 10 is a diagram for explaining the accuracy correction method.

  Depending on the degree and content of the failure, the possibility of damage changes.

  For example, a device failure or a failure leading to a trip is corrected with a high degree of certainty and a high expected loss, and a minor failure not noticed until the periodic inspection is corrected with a low degree of certainty.

  By correcting the accuracy according to the degree of influence of the fault content in this manner, it is possible to estimate the estimated loss more accurately.

  FIG. 11 is a view for explaining an embodiment of a screen displayed on the screen display device 800. As shown in FIG.

  FIG. 11A is a view for explaining an embodiment of a screen displayed on the screen display device 800 when the diagnosis mode is executed. The diagnostic means that detected the abnormality and the expected loss are displayed on the screen. As described above, by displaying the estimated loss amount on the screen display device, it is possible to provide information for determining whether to cope with the loss.

  FIG. 11B is a view for explaining an embodiment of a screen displayed on the screen display device 800 when the evaluation mode is executed. It is assumed that the failures detected earlier than the lead time are the failures that can be prevented by introducing a diagnostic plan, and the loss amount of these failures is added and displayed as a cost merit. It is possible to display the calculated cost merit and the service price of the diagnosis plan, and to judge whether or not to purchase this service.

  FIG. 12 is a view for explaining an embodiment of a screen displayed on the screen display device 800. As shown in FIG.

  Assuming that maintenance will be carried out when it is detected, we propose a diagnostic plan that minimizes the expected loss against the maintenance cost target value. If maintenance is performed based on diagnosis results with low detection accuracy, the expected loss (risk) can be lowered, but the number of maintenances will increase, and the maintenance cost will increase.

  When the maintenance cost target value (annual maintenance cost target value) is input, a suitable diagnostic plan is output. As described above, the present invention can also be used as a system that proposes a diagnostic plan that minimizes the expected loss amount in response to the input of the maintenance cost target value.

  In a second embodiment of the present invention, a case where model diagnosis and clustering are used as the diagnosis technique 500 will be described. The clustering described in the first embodiment is used.

  FIG. 13 is a diagram for explaining model diagnosis. In model diagnosis, an equipment model that simulates the characteristics of the equipment that constitutes the plant 100 is used. As a method of constructing a model that simulates the plant 100, there are physical models using physical formulas such as mass conservation formula and heat transfer formula, and statistical models such as neural network, and there is JP-A-2006-57595 as a known technology. .

  The input / output information of the devices constituting the plant 100 is measured as a signal A and a signal B, respectively. In the device model, the predicted value of the signal B with respect to the input of the signal A is output. In the model diagnosis technology, an abnormality is detected when an error between a model predicted value of the signal B and an actual measurement value exceeds a threshold.

  FIG. 14 is a diagram for explaining the effect of using both clustering and model diagnosis.

  Equipment A and equipment B are connected to the plant. In clustering (ART) diagnosis for diagnosing the device B, data B and data C are used as input data to the ART, and it is detected that the data tendency changes. In model diagnosis, data B is input and a predicted value of data C is output, and an error is detected when an error between the predicted value and the actual value of data C exceeds a threshold.

  In this example, at time 2300, a problem has occurred in which the plant A does not reach the plant stoppage. The flow rate, pressure, and temperature flowing from the device A to the device B change due to the occurrence of a trouble in the device A, and the signal B changes. Between time 2300 and time 2310, the device B is operating normally. The trouble occurred in the device B because the flow rate, pressure, and temperature of the fluid flowing to the device B changed at time 2310.

  In this case, since the change of the signal B is detected in the ART diagnosis, the ART diagnosis detects an abnormality at the timing of time 2300. On the other hand, since the device B is in a normal state, no abnormality is detected in model diagnosis.

  A problem occurs in the device B, and the model diagnosis is detected at the timing of time 2310.

  Thus, ART diagnosis detects abnormalities earlier than model diagnosis. In addition, no problem occurs in the device B when detected by ART, and a problem occurs when detected by model diagnosis. That is, the probability of being abnormal is higher when detected by the model diagnosis, and the diagnostic device 200 of the present invention calculates the expected loss amount high in consideration of this probability.

  Information useful for judging whether to cope with a detected abnormality by calculating and displaying the expected loss amount based on diagnosis results using different diagnostic methods such as clustering and model diagnosis with detection timing and accuracy. Can provide

  An effect when the diagnostic device 200 of the present invention is applied to a C / C plant will be described.

  FIG. 15 is a diagram showing an apparatus configuration of a C / C plant which is an embodiment of the plant 1000. As shown in FIG. The gas turbine 1080 includes a compressor 1010, an expander 1020, and a combustor 1030. In the gas turbine 1080, the compressor 1010 takes in and compresses air, and then the combustor 1030 takes in compressed air and fuel to generate combustion gas, and the expander 1020 takes in combustion gas to obtain motive power. The output of the gas turbine 1080 is the difference between the power output from the expander 1020 and the power used by the compressor 1010. The exhaust heat recovery boiler 1050 is provided with a heat exchanger 1060 and generates high temperature steam using high temperature exhaust gas from the gas turbine 1080. In the steam turbine 1070, the high temperature steam generated by the exhaust heat recovery boiler 1050 is taken in to obtain motive power. In the condenser 1090, the exhaust of the steam turbine 1070 is taken in and heat-exchanged with the cooling water to condense the steam into water. The generator 1040 generates power using the outputs of the gas turbine 1080 and the steam turbine 1070.

  In this plant, the fuel flow rate is controlled so that the exhaust gas temperature becomes a target value.

  As an abnormal event generated in the present plant, it is mentioned that a hole (blade surface cooling hole) for flowing cooling air of the wing in the expander 1020 becomes large. When this abnormality occurs, the amount of cooling air increases, the exhaust gas temperature decreases, and the fuel flow rate of the combustor 1030 increases. The combustion temperature rises due to the increase in fuel flow rate, and the combustor 1030 is broken. Thus, the abnormality of the expander 1020 propagates to the combustor 1030.

  When an abnormal event spreads, as described in the second embodiment, is it possible to cope with the detected abnormality by calculating and displaying the expected loss amount based on the diagnosis result using the diagnostic means having different detection timing and accuracy? It is possible to provide useful information to judge whether or not it is not.

  The present invention is widely applicable as a plant diagnostic device.

Reference Signs List 1 measurement signal 2 external input signal 3 measurement signal 4 facility management information signal 5 measurement signal 6 facility management information signal 7 diagnosis result database information 8 diagnosis result database information 9 measurement signal 10 diagnosis result 11 comprehensive diagnosis result signal 12 comprehensive diagnosis result signal 100 Plant 200 diagnostic device 210 data input interface 220 data output interface 300 measurement signal database 310 facility management information database 320 diagnosis result database 400 comprehensive diagnostic means 500 diagnostic means 800 surface display device 900 external input device 910 keyboard 920 mouse

Claims (10)

In a plant diagnostic apparatus comprising a plurality of diagnostic means for diagnosing an abnormal condition of a plant,
Based on the measurement signal data on the status of the plant and the facility management information data on the past status abnormality, the accuracy of detection of the status abnormality of each of the plurality of diagnostic means is determined, and A plant diagnostic apparatus comprising: integrated diagnostic means for evaluating an expected loss based on the basis of the total diagnostic means. The plant diagnostic device according to claim 1 is
A plant diagnosis apparatus further comprising display means for displaying the detection result of the diagnosis means and the expected loss amount. In the plant diagnostic device according to claim 1,
The plant diagnosis system according to claim 1, wherein said comprehensive diagnostic means determines said accuracy by dividing the number of state abnormalities in a predetermined period by the number of state abnormality detections by said diagnosis means. In the plant diagnostic device according to claim 1,
The facility management information data includes fault information including fault contents, countermeasure cost, lead time necessary for preventing fault occurrence, number of days of plant shutdown in case of fault, and opportunity loss amount generated by the plant shutdown. A plant diagnostic device characterized by In the plant diagnostic device according to claim 1,
The comprehensive diagnostic means detects that the diagnostic means has generated a status abnormality from the time when the measurement signal data deviates from a predetermined threshold value to be diagnosed as a status abnormality set based on the facility management information data. A plant diagnosis apparatus characterized by determining an average lead time obtained by subtracting the calculated time. In the plant diagnostic device according to claim 1,
A plant diagnosis apparatus characterized by using, as the diagnosis means, at least one diagnosis of model diagnosis using an instrument model simulating the characteristics of a device constituting a plant, or clustering diagnosis using adaptive resonance theory. In the plant diagnostic device according to claim 1,
A plant diagnosis apparatus, wherein the plurality of diagnosis means classify the measurement signal data into a plurality of categories according to the degree of similarity. In the plant diagnostic device according to claim 1,
The plant diagnostic apparatus according to claim 1, wherein the comprehensive diagnostic unit corrects the accuracy in accordance with the degree of influence of the state abnormality. In the plant diagnostic device according to claim 2,
The said display means displays the detection result by the diagnostic means by which the said loss estimated amount becomes the minimum with respect to the target value of the cost which maintains the said abnormal condition, The plant diagnostic apparatus characterized by the above-mentioned. In a plant diagnosis method for diagnosing a state abnormality of a plant by a plurality of methods,
The plant diagnosis device determines the accuracy of detection of the status abnormality of each of the plurality of methods based on the measurement signal data on the status of the plant and the facility management information data on the status abnormality in the past, A plant diagnostic method characterized by evaluating an expected loss amount based on the accompanying loss amount.

Images