JP6943698B2 - Plant abnormality location estimation system - Google Patents

Description

The present disclosure relates to a technique for estimating abnormal locations in a plurality of devices constituting a plant.

In the plant, abnormality monitoring is performed to prevent the occurrence of failures. For example, the measured values (sensor values) of a plurality of sensors installed for various devices constituting the plant are monitored and the sensors are monitored. A monitoring method is known in which an alarm is issued to a driver and an administrator when a value exceeds a certain threshold value (for example, Patent Documents 1 to 3). For example, in the flue that guides the exhaust gas discharged from the combustion chamber of the boiler, a plurality of heat exchangers are sequentially installed from the upstream side to the downstream side where the exhaust gas flows. If the heat transfer tube of the heat exchanger is damaged due to high temperature corrosion or wear, and a water supply leak (leakage) occurs from the damaged part, the surrounding heat transfer tube will also be damaged by the leaked water supply (steam) over time. The importance of early detection of abnormalities is great, such as the expansion of the damage range (see Patent Document 3).

For example, Patent Document 3 discloses a tube leak detection device that detects a tube leak that realizes early detection of a boiler tube leak (leakage of steam from a damaged portion of a heat transfer tube) and early identification of a leak position (abnormal portion). Has been done. This detection device is detected by a measurement signal database that stores measurement signals that measure the state quantity of the boiler plant for each data item, a state change detection unit that detects changes in the operating state of the boiler plant, and a state change detection unit. It is equipped with a detection content evaluation unit that evaluates whether changes are leaks. The above state change detection unit is a monitoring data extraction unit that inputs the first measurement signal data from the measurement signal database and groups some of the data items as a monitoring group, and an operation pattern that identifies the operation pattern of the boiler plant. An evaluation unit, a classification unit that classifies the first measurement signal data belonging to the grouped data items for each identified operation pattern and each monitoring group, and constructs a diagnostic model, a diagnostic model, and a second. It is equipped with a detection unit that detects that the operating state has changed by comparing the measurement signals.

International Publication No. 2017/051576 Japanese Unexamined Patent Publication No. 6-331507 Japanese Unexamined Patent Publication No. 2015-7509

For example, a water supply leak due to damage to a heat exchanger can be detected by measuring the metal temperature of the heat transfer tube with a plurality of temperature sensors arranged apart from each other in the wavy heat transfer tube. However, since almost all temperature sensors are affected by abnormalities due to the above water supply leak (see the vicinity of time t1 in FIG. 6 described later), it is difficult to identify which heat exchanger and where the damage occurred. Is. In response to such problems, the inventors of the present invention have diligently studied the effects of abnormalities such as damage to the heat transfer tube on the degree of abnormality such as the Maharanobis distance with respect to the direction in which the exhaust gas flows (flow path direction) and each heat exchange. When analyzed in consideration of the relationship with the arrangement direction of the heat transfer tubes (width direction of the flue) in the vessel, it is found that the position in the flow path direction and the width direction differs depending on the abnormal part (damaged part, etc.), and will be described later. It was found that it is possible to narrow down the damage position based on the degree of abnormality for each line and the degree of abnormality for each device.

In view of the above circumstances, at least one embodiment of the present invention is a plant abnormality location estimation system capable of quickly estimating an abnormality location in a plurality of devices installed in a flow path forming member such as a boiler flue. The purpose is to provide.

(1) The plant abnormality location estimation system according to at least one embodiment of the present invention is
It is a plant abnormality location estimation system that estimates an abnormality location in a plurality of devices installed in the flow path forming member based on the detection values of a plurality of sensors installed in the flow path forming member of the plant.
A plurality of abnormalities which are detection values of the plurality of sensors installed along the flow path direction and the width direction in the flow path forming member and which are the detection values when an abnormality of the plant is detected. An abnormal sensor value acquisition unit that acquires the hour sensor value, and
Each abnormality of the plurality of devices is based on the abnormality sensor value of the device-specific sensor group, which is a part of the plurality of sensors and is composed of a plurality of sensors installed in each of the plurality of devices. An abnormality degree calculation unit for each device that calculates the abnormality degree for each of a plurality of devices, which is a degree, and an abnormality degree calculation unit for each device.
A part of the plurality of sensors belonging to each of the plurality of line regions, assuming a plurality of line regions that spread along the flow path direction and are arranged in the width direction in the flow path forming member. A group of sensors for each line area, each of which is composed of at least one sensor installed in each portion of the plurality of devices belonging to each of the plurality of line areas. A line region-specific anomaly calculation unit that calculates a plurality of line-specific anomalies, which are the anomalies of each of the plurality of line regions, based on the abnormal sensor values of the group.
It is provided with an abnormality location estimation unit that estimates the abnormality location based on the plurality of device-specific abnormality degrees and the plurality of line-specific abnormality degrees.

For example, in a flue through which exhaust gas such as a boiler flows, a plurality of heat exchangers, such as a superheater and a reheater, each having a plurality of heat transfer tubes folded back in a wavy shape are installed along the flue. Damage caused by high-temperature corrosion or wear in the heat transfer tube can be detected by measuring the metal temperature of the heat transfer tube with, for example, a plurality of temperature sensors. However, the plurality of sensors are arranged apart from each other in a wavy heat transfer tube extending in the width direction of the flue and in the flow path direction (direction orthogonal to the width direction) in which the flue guides the exhaust gas. In particular, if the heat transfer tube is damaged at a location away from each temperature sensor, almost all temperature sensors are affected by the abnormality (see the vicinity of time t1 in FIG. 6 described later). It was difficult to identify where the damage occurred.

According to the configuration of (1) above, the degree of abnormality such as the Mahalanobis distance (degree of abnormality for each device) is calculated for each of a plurality of devices sequentially arranged in the flow path forming member along the flow path direction, and the flow path direction. A plurality of line regions each having a line-shaped region shape extending (extending) along the width direction, and the degree of abnormality for each of a plurality of virtual line regions (abnormality for each line) arranged along the width direction. calculate. Then, the abnormal portion (abnormal part) is specified based on the abnormality degree for each of a plurality of devices and the abnormality degree for each of a plurality of lines. As a result, at the time of abnormality detection, for example, there is an abnormality location on the upstream side of the device having the maximum abnormality degree for each device and around the line area having the maximum abnormality degree for each line. The region where the abnormal portion exists in the flow path forming member can be narrowed down to a narrower region. That is, by being able to quickly estimate the abnormal location, it is possible to quickly perform recovery work from an abnormality such as repair or replacement, and it is possible to improve the operating rate of the plant.

(2) In some embodiments, in the configuration of (1) above,
The abnormality location estimation unit
The target abnormality degree group including the plurality of device-specific abnormality degrees and the plurality of line-specific abnormality degrees, and the plurality of device-specific abnormality degrees calculated based on the past sensor values at the time of abnormality when an abnormality occurs. It has a matching rate calculation unit that calculates the matching rate with the reference abnormality group including the plurality of line-specific abnormalities.
The abnormal location in the plurality of devices is estimated based on the information of the past abnormal location associated with the reference abnormality degree group in which the matching rate is equal to or higher than the matching determination threshold value.

According to the configuration of (2) above, the matching rate between the target abnormality degree group and the reference abnormality degree group including the abnormality degree by device and the abnormality degree by line when an abnormality occurred in the past is calculated, and the matching rate is calculated. The abnormal part is estimated based on the past abnormal part included in the reference abnormality degree group in which is equal to or higher than the match judgment threshold. A reference anomaly group that matches or is similar to the target anomaly group in terms of device-specific anomaly and line-specific anomaly is likely to match or resemble the cause of the anomaly indicated by the target anomaly group to be estimated. .. Therefore, a reference abnormality degree group whose matching rate is equal to or higher than the matching judgment threshold is obtained, and the target abnormality degree group is corresponded to the position indicated by the information of the past abnormality portion associated with this reference abnormality degree group. It is possible to further narrow down the abnormal parts based on the reference abnormality degree group, such as presuming that there are abnormal parts.

(3) In some embodiments, in the configuration of (2) above,
The matching rate calculation unit compares the top N devices having a large degree of abnormality for each device and the top M line regions in both the target abnormality group and the reference abnormality group. , The matching rate is calculated.
According to the configuration of (3) above, the top N devices and the top M line areas of the target abnormality degree group, and the plurality of top N devices having a large abnormality degree for each reference device included in the reference abnormality group. The matching rate can be appropriately obtained based on the comparison with the upper M line regions having a large degree of abnormality for each reference line.

(4) In some embodiments, in the configuration of (3) above,
The matching rate is based on the number of matching devices belonging to each rank in the top N devices and each rank in the top M line regions in both the target abnormality degree group and the reference abnormality degree group. The ratio of the total number of matching line regions to which the line regions belong to the total of the N and the M.
According to the configuration of (4) above, the match rate can be appropriately calculated.

(5) In some embodiments, in the configurations (3) to (4) above,
With respect to the matrix corresponding to the arrangement of the plurality of line regions and the plurality of devices in the flow path forming member, the upper N devices, the upper M line areas, and the abnormality location estimation unit are used. An estimated map information generator that generates estimated map information, which is map information that maps the estimated abnormal locations, and an estimated map information generator.
An output unit for outputting the estimated map information is further provided.
According to the configuration of (5) above, the estimation result of the abnormal part can be visually shown to the driver, the manager, etc. by the estimation map information, and the suspected part of the abnormality can be easily grasped by the driver, the manager, etc. You can try to do it.

(6) In some embodiments, in the configurations (2) to (5) above,
A past abnormality that stores a plurality of past abnormality sensor values used for calculating the reference abnormality degree group or the reference abnormality degree group in association with information on the past abnormality location corresponding to the reference abnormality degree group. It is further equipped with a time information storage unit.
According to the configuration of (6) above, the information of the reference abnormality degree group and the past abnormality location corresponding to the reference abnormality degree group can be surely stored as the information indicating the abnormal event that occurred in the past.

(7) In some embodiments, in the configurations (2) to (6) above,
The reference abnormality degree group is calculated based on the detection values of a plurality of other sensors installed in other flow path forming members of another plant different from the plant from which the plurality of abnormality sensor values have been acquired. Will be done.
According to the configuration of (7) above, the estimation of the anomaly location is executed using the reference anomaly degree group corresponding to the anomaly occurring in another plant. That is, the abnormality cases are shared between the plants, and it is possible to estimate the abnormality location even for the abnormality cases that have already occurred in other plants but have not occurred in the own plant.

(8) In some embodiments, in the configurations (1) to (7) above,
The degree of abnormality is the Mahalanobis distance.
According to the configuration of (8) above, the abnormal portion can be appropriately estimated by the Mahalanobis distance (MD).

(9) The method for estimating a plant abnormality location according to at least one embodiment of the present invention is
It is a plant abnormality location estimation method for estimating an abnormality location in a plurality of devices installed in the flow path forming member based on the detection values of a plurality of sensors installed in the flow path forming member of the plant.
A plurality of abnormalities which are detection values of the plurality of sensors installed along the flow path direction and the width direction in the flow path forming member and which are the detection values when an abnormality of the plant is detected. The step of acquiring the sensor value at the time of abnormality and the step of acquiring the sensor value at the time,
A plurality of devices having an abnormality degree of each of the plurality of devices based on the abnormality sensor value of the device-specific sensor group each composed of a part of the plurality of sensors installed in each of the plurality of devices. The step of calculating the degree of abnormality for each device and the step for calculating the degree of abnormality for each device,
Assuming a plurality of line regions that spread along the flow path direction and are arranged in the width direction in the flow path forming member, a part of the plurality of sensors belonging to each of the plurality of line regions, respectively. A group of sensors for each of a plurality of line regions, each of which is composed of at least one of the sensors installed in each portion of the plurality of devices belonging to each of the plurality of line regions. A line area-specific abnormality calculation step for calculating each of the plurality of line-specific abnormality degrees, which is the abnormality degree of each of the plurality of line regions, based on the abnormality sensor value of the above.
The present invention includes an abnormality location estimation step for estimating the abnormality location based on the plurality of device-specific abnormality degrees and the plurality of line-specific abnormality degrees.

According to the configuration of (9) above, the same effect as that of (1) above is obtained.

(10) In some embodiments, in the configuration of (9) above,
The abnormality location estimation step is
The target abnormality degree group including the plurality of device-specific abnormality degrees and the plurality of line-specific abnormality degrees, and the plurality of device-specific abnormality degrees calculated based on the past sensor values at the time of abnormality when an abnormality occurs. It has a matching rate calculation step for calculating a matching rate with a reference abnormality group including the plurality of line-specific abnormalities.
The abnormal location in the plurality of devices is estimated based on the information of the past abnormal location associated with the reference abnormality degree group in which the matching rate is equal to or higher than the matching determination threshold value.
According to the configuration of the above (10), the same effect as the above (2) is obtained.

(11) In some embodiments, in the configuration of (10) above,
In the matching rate calculation step, the top N devices having a large degree of abnormality for each device and the top M line regions in both the target abnormality group and the reference abnormality group are compared with each other. , The matching rate is calculated.
According to the configuration of the above (11), the same effect as the above (3) is obtained.

(12) In some embodiments, in the configuration of (11) above,
The matching rate is based on the number of matching devices belonging to each rank in the top N devices and each rank in the top M line regions in both the target abnormality degree group and the reference abnormality degree group. The ratio of the total number of matching line regions to which the line regions belong to the total of the N and the M.
According to the configuration of the above (12), the same effect as the above (4) is obtained.

(13) In some embodiments, in the configurations (11) to (12) above,
With respect to the matrix corresponding to the arrangement of the plurality of line regions and the plurality of devices in the flow path forming member, the upper N devices, the upper M line areas, and the abnormality location estimation step An estimated map information generation step for generating estimated map information, which is map information that maps the estimated abnormal location, and an estimated map information generation step.
An output step for outputting the estimated map information is further provided.
According to the configuration of the above (13), the same effect as the above (5) is obtained.

(14) In some embodiments, in the configurations (10) to (13) above,
A past abnormality that stores a plurality of past abnormality sensor values used for calculating the reference abnormality degree group or the reference abnormality degree group in association with information on the past abnormality location corresponding to the reference abnormality degree group. Further prepare for the time information storage step.
According to the configuration of (14) above, the same effect as that of (6) above is obtained.

(15) In some embodiments, in the configurations (10) to (14) above,
The reference abnormality degree group is calculated based on the detection values of a plurality of other sensors installed in other flow path forming members of another plant different from the plant from which the plurality of abnormality sensor values have been acquired. Will be done.
According to the configuration of the above (15), the same effect as the above (7) is obtained.

(16) In some embodiments, in the configurations (9) to (14) above,
The degree of abnormality is the Mahalanobis distance.
According to the configuration of the above (16), the same effect as the above (8) is obtained.

According to at least one embodiment of the present invention, there is provided a plant abnormality location estimation system capable of quickly estimating an abnormality location in a plurality of devices installed in a flow path forming member such as a boiler flue.

It is a figure which shows schematic the plant abnormality part estimation system which estimates the abnormality part of a plurality of heat exchangers installed in the boiler which concerns on one Embodiment of this invention. It is a schematic view which looked at the cross section shown by AA line of FIG. 1 in the vertical direction. It is a block diagram which shows the function of the plant abnormality part estimation system which concerns on one Embodiment of this invention. It is a block diagram which shows the function of the plant abnormality part estimation system which concerns on one Embodiment of this invention. It is a figure which shows the line area and the device area set in the flue of a boiler in one Embodiment of this invention, and shows the case assumed with respect to the flue 82 of FIG. It is a figure which shows the time transition before and after the time of abnormality detection (time t2) of MD value by (a) equipment and (b) line area which concerns on one Embodiment of this invention. It is a figure which shows the time transition before and after the time of abnormality detection (time t2) of the detection value of the temperature sensor for each device which concerns on one Embodiment of this invention. It is a figure for demonstrating the estimation logic of the abnormality part which concerns on one Embodiment of this invention, (a) is the reference map information, (b) is the estimation map information, (c) is the figure which shows the calculation example of the matching rate. Is. It is a figure which shows the plant abnormality part estimation method which concerns on one Embodiment of this invention.

Hereinafter, some embodiments of the present invention will be described with reference to the accompanying drawings. However, the dimensions, materials, shapes, relative arrangements, etc. of the components described as embodiments or shown in the drawings are not intended to limit the scope of the present invention to this, but are merely explanatory examples. No.
For example, expressions that represent relative or absolute arrangements such as "in a certain direction", "along a certain direction", "parallel", "orthogonal", "center", "concentric" or "coaxial" are exact. Not only does it represent such an arrangement, but it also represents a state of relative displacement with tolerances or angles and distances to the extent that the same function can be obtained.
For example, expressions such as "same", "equal", and "homogeneous" that indicate that things are in the same state not only represent exactly the same state, but also have tolerances or differences to the extent that the same function can be obtained. It shall also represent the existing state.
For example, an expression representing a shape such as a quadrangular shape or a cylindrical shape not only represents a shape such as a quadrangular shape or a cylindrical shape in a geometrically strict sense, but also an uneven portion or chamfering within a range in which the same effect can be obtained. The shape including the part and the like shall also be represented.
On the other hand, the expressions "equipped", "equipped", "equipped", "included", or "have" one component are not exclusive expressions that exclude the existence of other components.

FIG. 1 is a diagram schematically showing a plant abnormality location estimation system 1 that estimates abnormality locations of a plurality of heat exchangers 9 installed in the boiler 8 according to the embodiment of the present invention. Further, FIG. 2 is a schematic view of the cross section shown by the line AA of FIG. 1 as viewed in the vertical direction.

The plant abnormality location estimation system 1 converts abnormal locations (abnormal locations) in a plurality of devices (equipment) constituting the plant 7, such as a thermal power plant having a commercial boiler, a waste incineration plant, and a chemical plant, into the plant 7. It is a system (device) that estimates based on the detection values of each of a plurality of installed sensors (hereinafter, appropriately, sensor values). In the plant 7, the state of a plurality of devices constituting the plant 7 is measured by installing a plurality of sensors, and the sensor values of the plurality of sensors and the on / off of various devices including the valve are measured. For example, the state of is periodically acquired (operation data D described later), and operation control and abnormality monitoring are performed. For example, the above-mentioned plurality of devices constituting a coal-cooking thermal power plant include a boiler 8, a steam turbine (high-pressure turbine, low-pressure turbine, etc.), a superheater 91, a heat exchanger 9 such as a reheater 92, and steam. There are valves and dampers that adjust the flow rate and pressure of steam sent to the turbine, and various devices (denitration device, electrostatic dust collector, etc.) for treating the exhaust gas G discharged from the boiler 8.

The boiler 8 and the heat exchanger 9 will be described. As shown in FIG. 1, the boiler 8 includes a furnace 81 and a flue 82 connected to an upper portion of the furnace 81. Further, as shown in FIGS. 1 and 2, the flue 82 has one or more heat exchangers for recovering the thermal energy of the exhaust gas G (combustion gas) generated by the combustion of fuel such as coal in the furnace 81. 9 (equipment) is installed. Examples of the type of heat exchanger 9 installed in the boiler 8 include a superheater 91 (SH: Superheater), a reheater 92 (RH: ReHeter), and an economizer (economizer).

Further, the heat exchanger 9 has a heat transfer tube 9p through which water is supplied (see FIG. 2), and the heat transfer tube 9p and the exhaust gas G come into contact with each other inside the flue 82, and the temperature is relatively low. The above-mentioned water supply is heated by heat exchange between the water supply and the exhaust gas G having a relatively high temperature through the wall surface of the heat transfer tube 9p, and steam is generated. Further, the heat transfer tube 9p constitutes a linear portion extending along the vertical direction (gravity direction) of the boiler 8 and a portion connected to the linear portion and folded back at the upper end and the lower end of the linear portion. By having a plurality of bent portions, the flue 82 is installed inside the flue 82 in a state of being folded back in a wavy shape. Therefore, with the heat transfer tube 9p installed inside the flue 82, the vertical direction of the boiler 8, the flow path direction in which the flue 82 guides the exhaust gas (the direction in which the exhaust gas G flows), and the flow. It is in a state of being widely installed in a certain space (hereinafter, equipment area R) over the width direction (hereinafter, simply the width direction) of the flue 82 which is a direction orthogonal to the road direction. Then, as shown in FIGS. 1 and 2, one or more heat exchangers 9 having such a heat transfer tube 9p are sequentially installed in the flue 82 along the flow path direction, so that the exhaust gas G is generated. When flowing inside the flue 82, it passes through one or more heat exchangers 9 installed in the flue 82 in order. Further, as shown in FIGS. 1 and 2, in the flue 82, a plurality of temperature sensors 84 are provided for each heat exchanger 9 in order to monitor the state of each part of the heat transfer tube 9p of each heat exchanger 9. Will be installed.

In the embodiment shown in FIGS. 1 and 2, the heat transfer tube 9p has a plurality of linear portions extending along the vertical direction of the boiler 8, and the plurality of linear portions extend in the flow path direction and the width direction. It has a portion installed in the flue 82 so as to be arranged along the line. Therefore, when the AA cross section of FIG. 1 is viewed in the vertical direction, there are innumerable cross sections of the heat transfer tube 9p as shown in FIG. Further, inside the flue 82, in order from the upstream side along the flow path direction, the secondary superheater 91b (2SH), the tertiary superheater 91c (3SH), the quaternary superheater 91d (4SH), and the secondary superheater 91d (4SH). The reheater 92b (2RH), the primary reheater 92a (1RH), and the primary superheater 91a (1SH) are installed at intervals from each other. Further, as shown in FIG. 2, the above-mentioned equipment region R by each heat exchanger 9 includes the wall surface 82w on the right side of the flue 82 (the front side of the paper surface in FIG. 1) along the width direction of the flue 82. It extends from near the edge to near the edge between the wall surface 82w on the left side (the back side of the paper in FIG. 1). Therefore, the exhaust gas G flows inside the flue 82 in the order of 2SH, 3SH, 4SH, 2RH, 1RH, and 1SH.

Further, as shown in FIGS. 1 and 2, a plurality of temperature sensors 84 for monitoring the metal temperatures of these heat exchangers 9 (91a to 91d, 92a to 92b) are provided inside the flue 82. , Each heat exchanger 9 is installed in the heat transfer tube 9p in a state of being separated from each other in the width direction. More specifically, as shown in FIG. 2, a plurality of temperature sensors 84 are installed in a line in the heat transfer tube 9p of each heat exchanger 9 along the width direction, and 2SH, 3SH, and 4SH. Eight temperature sensors 84 are installed in each of the 2RH, 1RH, and 1SH. The positions of the plurality of temperature sensors 84 arranged in a row along the width direction do not have to be exactly the same in the flow path direction. However, the present invention is not limited to the present embodiment. In the above-described embodiment, the number of temperature sensors 84 installed in all the heat exchangers 9 is the same, but in some other embodiments, the temperature sensors 84 installed in each heat exchanger 9 are the same number. The numbers do not have to be the same.

Then, the plant abnormality location estimation system 1 of the embodiment shown in FIGS. 1 and 2 detects the metal temperature of each of the heat transfer tubes 9p of the plurality of heat exchangers 9 installed in the flue 82 described above. By connecting to the temperature sensor 84, the above-mentioned abnormal portion is estimated based on the detected values of the plurality of temperature sensors 84.

Next, the plant abnormality location estimation system 1 will be described in detail with reference to FIGS. 1 to 7. FIG. 3 is a block diagram showing a function of the plant abnormality location estimation system 1 according to the embodiment of the present invention. FIG. 4 is a diagram showing a line region L and an equipment region R assumed in the flue 82 of the boiler 8 in one embodiment of the present invention, and shows a case assumed for the flue of FIG. FIG. 5 is a diagram showing the time transition before and after the time of abnormality detection (time t2) of the MD value for each device (a) and (b) line region according to the embodiment of the present invention. FIG. 6 is a diagram showing a time transition before and after the abnormality detection (time t2) of the detection value of the temperature sensor 84 for each device according to the embodiment of the present invention. 7A and 7B are diagrams for explaining the estimation logic of the abnormal portion according to the embodiment of the present invention, in which FIG. 7A is reference map information, FIG. 7B is estimation map information M, and FIG. 7C is match rate C. It is a figure which shows the calculation example of.

The plant abnormality location estimation system 1 shown in FIG. 1 has an abnormality location in a plurality of devices installed in the flow path forming member based on the detection values of a plurality of sensors installed in the flow path forming member of the plant 7. It is a system that estimates.
In the following, the plant abnormality location estimation system 1 is installed in the flue 82 based on the detection values of the plurality of temperature sensors 84 installed in the flue 82 of the boiler 8 of the plant 7. A case of estimating an abnormal portion in the heat exchanger 9 will be described as an example.

As shown in FIG. 3, the plant abnormality location estimation system 1 includes an abnormality sensor value acquisition unit 13, an abnormality degree calculation unit 2 for each device, an abnormality degree calculation unit 3 for each line area, and an abnormality location estimation unit 4. To be equipped. The plant abnormality location estimation system 1 is composed of a computer, and includes a CPU (processor) (not shown), a storage device 15 including a memory such as ROM and RAM, and an external storage device. Then, the CPU operates (data calculation, etc.) according to the instructions of the program loaded in the memory (main storage device) to realize each of the above-mentioned functional units included in the plant abnormality location estimation system 1.
Each of the above functional parts will be described.

As shown in FIG. 4 (FIG. 2), the abnormal sensor value acquisition unit 13 is provided in each of the flow path direction and the width direction inside the flue 82 (corresponding to the inside of the above-mentioned flow path forming member; the same applies hereinafter). A plurality of abnormality sensor values S, which are detection values of a plurality of temperature sensors 84 (corresponding to the above sensors; the same applies hereinafter) installed along the line and are detection values when an abnormality of the plant 7 is detected. get. In the embodiment shown in FIG. 3, the plant abnormality location estimation system 1 is connected to the plant 7 via a communication network or the like, and is configured to receive the operation data D indicating the operation state of the plant 7 from the plant 7. As a result, the abnormality sensor value acquisition unit 13 acquires a plurality of abnormality sensor values S from the plurality of temperature sensors 84 directly from the plant 7. However, the present invention is not limited to this embodiment, and in some other embodiments, the abnormality sensor value acquisition unit 13 acquires a plurality of abnormality sensor values S acquired by another system (device). The sensor value S at the time of abnormality may be indirectly acquired.

More specifically, in the plant abnormality location estimation system 1 of the embodiment shown in FIG. 3, the operation data collection unit 11 for acquiring the above operation data D sent from the plant 7 side and the operation data collection unit 11 acquire the operation data. For example, the abnormality degree T is calculated based on the detection values of the plurality of temperature sensors 84 described above included in the operation data D, and the calculated abnormality degree T is compared with the abnormality determination threshold for detecting the abnormality. It includes an abnormality monitoring unit 12 for detecting an abnormality. The above-mentioned abnormality degree T changes so as to deviate from the normal value (normal range) when an abnormality occurs (see FIG. 5), but the abnormality monitoring unit 12 uses the abnormality determination threshold value to change the abnormality degree T from the normal value. A deviation event is detected, and when this is detected, it is determined to be abnormal. When the abnormality monitoring unit 12 detects an abnormality, the device-specific abnormality degree calculation unit 2 described below sets the sensor value used for calculating the abnormality degree T as the abnormality sensor value S, and the device-specific abnormality degree calculated below is described. It is transmitted to the calculation unit 2 and the abnormality degree calculation unit 3 for each line area, respectively.

In some embodiments, the degree of abnormality T may be the Mahalanobis distance (MD) used in a pattern recognition technique called the MT method (Mahalanobis Taguchi method). In this MT method, a normal group is defined as a unit space based on normal multivariate data (here, multiple sensor values detected by a plurality of sensors), and the distance of the target data from the unit space (here). Mahalanobis distance) is calculated to determine the abnormality. This makes it possible to comprehensively diagnose the plant 7 using only one index, the Mahalanobis distance. In addition, the MT method makes it possible to detect abnormalities at an early stage before equipment damage progresses, compared to the method of diagnosing whether various operating parameters are within the control values, and equipment damage can be prevented. It is known as a method that can be prevented or minimized. However, the present invention is not limited to the present embodiment. The degree of abnormality T may be calculated by another method based on multivariate data, for example, the K-nearest neighbor method, as long as the abnormality can be detected.

When the device-specific abnormality degree calculation unit 2 acquires the plurality of abnormality sensor values S acquired by the above-mentioned abnormality sensor value acquisition unit 13, the device-specific abnormality degree calculation unit 2 is a part of the plurality of temperature sensors 84 and is a part of the plurality of heat exchangers 9. As shown in FIG. 5 (a), based on the abnormal sensor value S of the device-specific sensor group 85 composed of the plurality of temperature sensors 84 installed in each of the above devices (corresponding to the above devices. In addition, the abnormality degree Tr for each of the plurality of devices, which is the abnormality degree (MD) of each of the plurality of heat exchangers 9, is calculated. In FIG. 5, FIG. 5A shows the abnormality degree Tr for each device. However, assuming that the abnormality monitoring unit 12 detects an abnormality based on the abnormality degree T at time t1, the device-specific abnormality degree calculation unit 2 has this. A plurality of device-specific abnormality degrees Tr are calculated based on the plurality of abnormal sensor values S at time t1.

In the embodiment shown in FIG. 3, the device-specific abnormality degree calculation unit 2 uses all the sensor values of the plurality of temperature sensors 84 included in the device-specific sensor group 85 of each heat exchanger 9 for each heat exchanger 9. The abnormality degree Tr for each device is calculated. That is, the abnormality degree Tr for each device is calculated based on eight abnormal sensor values S for each of 2SH, 3SH, 4SH, 2RH, 1RH, and 1SH. However, the present invention is not limited to this embodiment, and in some other embodiments, the degree of abnormality Tr of each heat exchanger 9 for each device is, for example, 8 for 1SH and 7 for 4SH. It may not be calculated using the abnormal sensor values S of all the temperature sensors 84 belonging to the separate sensor group 85, or may be calculated based on the partial abnormal sensor values S. Further, a plurality of device-specific abnormality degrees Tr may be calculated based on the abnormality sensor value S when an abnormality occurs at a time when a time has elapsed from the time t1 in FIG.

Similarly, when a plurality of abnormal sensor values S are acquired, the line region-specific abnormality degree calculation unit 3 spreads along the flow path direction and is arranged in the width direction in the flue 82, as shown in FIG. It is a plurality of line region-specific sensor group 86 composed of a part of the above-mentioned plurality of temperature sensors 84, which are assumed to be a plurality of line regions L and belong to each of the plurality of line regions L, and are a plurality of line regions. A plurality of line regions based on the abnormal sensor value S of the line region-specific sensor group 86 each composed of at least one temperature sensor 84 installed in each portion of the plurality of heat exchangers 9 belonging to each of L. A plurality of line-specific abnormality degrees Tl, which are the respective abnormality degrees (MD) of L, are calculated. That is, the plurality of line regions L intersect with the plurality of devices (equipment area R) by being arranged along the flue 82 (extending) and in the width direction of the flue 82, respectively. A plurality of lines inside the flue 82 so that at least one temperature sensor 84 exists in each of the intersecting regions (hereinafter, the intersecting region D _{LR ; only D 81} is represented in FIG. 4). Assume region L. When a plurality of temperature sensors 84 are present in each intersection region _DLR , the abnormality sensor value S of at least one of the temperature sensors 84 is used for calculating the abnormality degree Tl for each line. Assuming that the number of the plurality of heat exchangers 9 is x and the number of the plurality of line regions L is y, the number of intersection regions D _LR is xx y.

In the embodiment shown in FIG. 4, inside the flue 82, eight line regions L (L1 to L8) extending in the flue 82 along the flow path direction and parallel to each other in the width direction are formed in the flow path. It is assumed to intersect each of the six device regions R arranged along the direction (x = 6, y = 8). Therefore, the number of intersection regions D _LR is 48 (D _{11 to} D _yx ). Then, by selecting one temperature sensor 84 from each intersection region D _LR , all the line regions L (L1 to L8) are line-based based on the abnormal sensor values S of the six temperature sensors 84, respectively. The degree of abnormality Tl is calculated.

The abnormality location estimation unit 4 estimates the abnormality location based on a plurality of (x) device-specific abnormality degrees Tr and a plurality (y) line-specific abnormality degrees Tl. Here, an abnormality such as a water supply leak due to damage to the heat transfer tube 9p of the heat exchanger 9 is caused by the abnormality monitoring unit 12 as described above, somewhere in any of the heat transfer tubes 9p of the plurality of heat exchangers 9. Although it can be detected as having occurred, it is difficult to specify which part of the heat transfer tube 9p of which heat exchanger 9 is occurring as it is. In particular, if the heat transfer tube 9p is damaged at any location away from each temperature sensor 84, an abnormal effect appears on the values of almost all temperature sensors 84 as shown at time t1 in FIG. Even by looking at the sensor values of each temperature sensor 84, it is difficult to identify the abnormal portion.

On the other hand, the inventors of the present invention have diligently examined the influence of the abnormality such as the damage of the heat transfer tube 9p on the abnormality degree T such as the Mahalanobis distance (MD) from the position where the damage occurred in the flue 82. Was found to appear strongly on the downstream side. It was also found that it is possible to narrow down the damage position in the width direction based on the degree of abnormality Tl for each line. According to these findings, by obtaining the abnormality degree Tr for each device and the abnormality degree Tr for each of a plurality of lines when an abnormality is detected, for example, it is upstream from the device having the maximum abnormality degree Tr for each device. It is possible to narrow down the area where the abnormal part exists in the flue 82 to a narrower area at the time of abnormality detection, such as around the line area L where the abnormality degree Tl for each line is the maximum on the side. Become.

This will be described in more detail with reference to FIG. As shown in FIG. 7, x devices arranged along the flow path direction and M line regions L arranged along the width direction inside the flue 82 are respectively arranged in the flue 82. When shown in a two-dimensional table in the order of arrangement, a table (estimated map information M) corresponding to the arrangement of _{xxy intersection regions DLR in the flue 82 can be obtained as it is in the arrangement of each cell (Fig.).} 7 (a), (b)). The tables of FIGS. 7 (a) to 7 (b) reflect the calculation results of the abnormality degree Tr for each device and the abnormality degree Tl for each line at time t1 as shown in FIG. 5, and are for each device. The top two abnormalities Tr and the top two abnormalities Tl for each line are marked.

FIG. 7 (b) reflects the contents of FIG. 5, and the description will be continued with reference to FIG. 7 (b). As shown in FIG. 5A, at time t1, the degree of abnormality Tr for each device was 1Rh, 4SH, 1SH, 3SH, 2RH, and 2SH in descending order. As shown in FIG. 5B, at time t1, the degree of abnormality Tl for each line is the fifth line (L5), the fourth line (L4), the sixth line (L6), the third line (L3), in descending order. It was the second line (L2), the eighth line (L8), the first line (L1), and the seventh line (L7).

Then, according to the above-mentioned findings of the inventors of the present invention, based on the estimated map information M (FIG. 7 (b)), for example, the abnormality degree Tr for each device is on the upstream side of the highest 2RH, and among them. It is presumed that there is an abnormal part in the line region L up to both sides of the sixth line (L6) having the highest degree of abnormality Tl for each line, for example. That is, out of the 48 crossing regions D _LR existing in total, 9 crossing regions D _LR (D _{51 ) which are crossing regions D LR} at which the 5th to 7th lines and 2SH, 3SH, and 4SH each intersect. , D ₅₂ , D ₅₃ , D ₆₁ , D ₆₂ , D ₆₃ , D ₇₁ , D ₇₂ , D ₇₃ ). At this time, the heat transfer tube 9p was actually damaged (abnormal part) in the intersection region D ₅₃ where the fifth line (L5) and 4SH intersect, so from the 48 intersection regions D _LR. abnormal location is an example that could be narrowed down to the appropriate areas occurring on the twelve intersection region D _LR.
In some other embodiments, the abnormal portion may be estimated based on the reference abnormality degree group P (described later, see FIG. 7A) selected based on the matching rate C as described later. ..

According to the above configuration, a plurality of devices are sequentially arranged in the flow path forming member (inside the flue 82 in the above embodiment) along the flow path direction (separate heat exchangers 9 in the above embodiment). A plurality of line regions L each having a line-shaped region shape extending (extending) along the flow path direction while calculating the degree of abnormality (abnormality Tr for each device) such as the Mahalanobis distance, and along the width direction. The anomaly degree T (abnormality degree Tl for each line) for each of a plurality of virtual line areas L arranged in each is calculated. Then, the abnormality location is specified based on the abnormality degree Tr for each device and the abnormality degree Tl for each line. As a result, at the time of abnormality detection, for example, there is an abnormality location on the upstream side of the device having the maximum abnormality degree Tr for each device and around the line region L where the abnormality degree Tl for each line is maximum. The region where the abnormal portion exists in the flow path forming member can be narrowed down to a narrower region. That is, since the abnormal portion can be quickly estimated, the recovery work from the abnormality such as repair and replacement can be performed quickly, and the operating rate of the plant 7 can be improved.

In some embodiments, the abnormal location estimation unit 4 may estimate the abnormal location by using a past abnormal case (reference abnormality degree group P described later). That is, the abnormality location estimation unit 4 sets the target abnormality degree group E (estimation target) including the abnormality degree Tr for each device and the abnormality degree Tl for each line and the sensor value at the time of the past abnormality when the abnormality occurs. It has a matching rate calculation unit 41 that calculates a matching rate C with a reference abnormality group P including a plurality of device-specific abnormality degrees Tr and a plurality of line-specific abnormality degrees Tl calculated based on the above. Then, the abnormality location estimation unit 4 determines the abnormality locations in the plurality of heat exchangers 9 based on the information of the past abnormality locations associated with the reference abnormality degree group P in which the match rate C is equal to or higher than the match determination threshold value Vc. presume. As shown in FIG. 3, the matching rate calculation unit 41 is connected to the device-specific abnormality degree calculation unit 2 and the line area-specific abnormality degree calculation unit 3, and is calculated by the device-specific abnormality degree calculation unit 2 for each of a plurality of devices. It is configured to acquire the abnormality degree Tr and a plurality of line-specific abnormality degree Tl (target abnormality degree group E) calculated by the line area-specific abnormality degree calculation unit 3. Further, the match rate calculation unit 41 is connected to the storage device 15 and acquires the reference abnormality degree group P from the storage device 15.

The reference abnormality degree group P is calculated based on a plurality of abnormality sensor values S used for calculating the past abnormality degree T when an abnormality is detected in the past based on the abnormality degree T such as the Maharanobis distance. The heat transfer tube 9p of which heat exchanger 9 installed in the flue 82 has damage to the heat transfer tube 9p that includes a plurality of device-specific abnormality levels Tr and a plurality of line-specific abnormality degrees Tl and causes the abnormality at this time. Information on past abnormal parts indicating which part of 9p was damaged is associated with it. In some embodiments, the plant abnormality location estimation system 1 stores the information of the past abnormality location corresponding to the reference abnormality degree group P and the reference abnormality degree group P in association with each other. May be further prepared. In some other embodiments, the plant anomaly location estimation system 1 uses a plurality of past anomaly sensor values S used to calculate the reference anomaly group P and past anomaly locations corresponding to the reference anomaly group P. A past abnormality information storage unit 16 that stores the information in association with the above information may be further provided. In this case, the abnormality location estimation unit 4 may obtain a plurality of past information storage units 16 from the past abnormality information storage unit 16. The reference abnormality degree group P is calculated based on the abnormality sensor value S of. The information storage unit 16 at the time of past abnormality is formed in a storage device 15 such as an external storage device, and the information storage unit 16 at the time of past abnormality indicates the past abnormality points corresponding to the reference abnormality degree group P and the reference abnormality degree group P. Information can be reliably stored as information indicating an abnormal event that has occurred in the past.

Further, the matching rate C is an index that quantitatively indicates how much the target abnormality degree group E and the reference abnormality degree group P match. For example, the larger the value, the more the target abnormality degree group E and the reference abnormality degree group E and the reference abnormality degree. It is an index showing that the group P matches (there are many common items). Then, in the present embodiment, the reference abnormality degree group P having a high match rate C with the target abnormality degree group E from the viewpoint of the abnormality degree Tr for each device and the abnormality degree Tl for each line corresponds to the target abnormality degree group E to be estimated. It is presumed that there is a high possibility that it matches or resembles the cause of the problem, and that there is an abnormal part in the vicinity of the past abnormal part associated with the reference abnormality group P. In the embodiment shown in FIG. 7, FIG. 7A shows the reference abnormality degree group P with map information, and the past abnormality portion associated with the reference abnormality degree group P is the intersection region D. It was _53. The reference abnormality group P corresponding to the map information shown in FIG. 7 (a) has a high matching rate C with the target abnormality group E corresponding to the estimated map information M shown in FIG. 7 (b). , based on the reference degree of abnormality group P, target the abnormal degree group E intersecting region D ₅₃ or anomaly in the periphery is estimated to occur. In the example of FIG. 7B, the abnormality was actually found in the intersection region D ₅₃ , and the abnormality location in the target abnormality degree group E was based on the information of the past abnormality location corresponding to the reference abnormality degree group P. This is an example in which the area where is occurring can be narrowed down appropriately.

For example, in some embodiments, the matching rate calculation unit 41 has a plurality of upper N (N ≦ x) devices having a large degree of abnormality Tr for each device in both the target abnormality degree group E and the reference abnormality degree group P. The matching rate C may be calculated by comparing the upper M line regions (M ≦ y) with each other (see FIG. 7). More specifically, in some embodiments, as shown in FIG. 7 (c), the matching rate C is determined in each of the top N devices in both the target anomaly group E and the reference anomaly group P. It may be a ratio of the total number of matching devices belonging to the rank and the number of matching line areas L belonging to each rank in the upper M line regions L to the total of N and M. In the embodiment shown in FIG. 7, N = M = 2. Further, as shown in FIG. 7 (c), the ranking of the abnormality degree T is as follows in the reference abnormality degree group P in the 5th line (1st place), the 4th line (2nd place), 1RH (1st place), and 4SH (2). In the target abnormality degree group E, the order is 6th line (1st place), 7th line (2nd place), 1RH (1st place), and 2RH (2nd place). Therefore, of the four items, only 1RH (1st place of the device) matches in both the target abnormality degree group E and the reference abnormality degree group P, so that the match rate C is C = 1/4 = 0.25. Calculated as (25%).

According to the above configuration, the matching rate C between the target abnormality degree group E and the reference abnormality degree group P including the device-specific abnormality degree Tr and the line-specific abnormality degree Tl when an abnormality has occurred in the past is calculated and matched. The abnormality location is estimated based on the reference abnormality degree group P in which the rate C is equal to or higher than the match determination threshold value Vc. The reference abnormality group P that matches or is similar to the target abnormality group E in terms of the device-specific abnormality Tr and the line-specific abnormality Tl matches or is similar to the cause of the abnormality indicated by the target abnormality group E to be estimated. There is a high possibility that it will be done. Therefore, the reference abnormality degree group P in which the match rate C is equal to or higher than the match determination threshold is obtained, and the target abnormality degree group is located near the position indicated by the information of the past abnormality portion associated with the reference abnormality degree group P. It is possible to further narrow down the abnormal parts based on the reference abnormality degree group P, such as presuming that there is an abnormal part corresponding to E.

Further, in some embodiments, as shown in FIG. 3, the plant anomaly location estimation system 1 has a matrix corresponding to the arrangement of the plurality of line regions L and the plurality of heat exchangers 9 in the flue 22. , Estimated to generate estimated map information M (FIG. 7 (b)) which is map information mapping the upper N devices, the upper M line areas L, and the abnormal parts estimated by the abnormal part estimation unit 4. A map information generation unit 5 and an output unit 6 for outputting the estimated map information M are further provided. In the embodiment shown in FIG. 3, the output unit 6 is connected to the estimation map information generation unit 5 and the display device 18 (display device in FIG. 3), respectively, and the estimation map information M generated by the estimation map information generation unit 5. Is output to the display device 18. As shown in FIG. 7B, in the display device 18, the estimated map information M visually displays the upper N devices and the upper M line areas L used for calculating the matching rate C by, for example, color coding. _{The intersection area (D 53 in the} present embodiment) including the abnormal part estimated by the abnormal part estimation unit 4 is visually identifiablely displayed. Along with the estimated map information M, map information may be generated and output from the matching rate C, the reference abnormality degree group P, and the information of the abnormal portion corresponding to the reference abnormality degree group P.

According to the above configuration, the estimation map information M can visually show the estimation result of the abnormal part to the driver, the manager, etc., so that the driver, the manager can easily grasp the suspected part of the abnormality. Can be planned.

Further, in some embodiments, the above-mentioned reference abnormality degree group P is different from the plant 7 (for example, the plant A in FIG. 3) in which the plurality of abnormality sensor values S are acquired. For example, it is calculated based on the detection values of a plurality of other sensors installed in the other flow path forming members of the plant B) in FIG. In the embodiment shown in FIG. 3, the plant abnormality location estimation system 1 is used to calculate the reference abnormality group P or the reference abnormality group P corresponding to the abnormalities that have occurred in the past in plants A and B. A plurality of abnormality sensor values, information on the abnormal location of the past abnormality, and the information storage unit 16 at the time of the past abnormality are registered and used for estimating the abnormal location of the plant A and the plant B. That is, trouble cases are shared by a plurality of plants 7.

According to the above configuration, the estimation of the abnormality location is executed using the reference abnormality degree group P corresponding to the abnormality occurring in the other plant 7. That is, the abnormality case is shared among the plants 7, and the abnormality location can be estimated even for the abnormality case that has already occurred in the other plant 7 but has not occurred in the own plant 7.

Next, a plant abnormality location estimation method corresponding to the processing of the plant abnormality location estimation system 1 described above will be described with reference to FIG. FIG. 8 is a diagram showing a method for estimating a plant abnormality location according to an embodiment of the present invention. The plant abnormality location estimation method is based on the detection values of a plurality of sensors (temperature sensors 84) installed in the flow path forming member (smoke path 82) of the plant 7, and a plurality of methods installed in the flow path forming member. This is a method of estimating an abnormal part in the equipment (heat exchanger 9) of the above, and is a sensor value acquisition step (S1) at the time of abnormality, an abnormality degree calculation step (S2) for each equipment, and an abnormality degree calculation step (S3) for each line area. And the abnormality location estimation step (S4). This will be described according to the flow of FIG.

In FIG. 8, in step S0, the past abnormality information storage step is executed. The past abnormality information storage step includes information on a plurality of past abnormality sensor values S used for calculating the reference abnormality group P or the reference abnormality group P, and information on the past abnormality location corresponding to the reference abnormality group P. This is a step of associating and storing a set of. By executing the past abnormal time information storage step, one or more of the above sets are stored in the past abnormal time information storage unit 16 or the like described above.

In step S1, the error sensor value acquisition step is executed. The abnormality sensor value acquisition step is a detection value of a plurality of temperature sensors 84 installed along the flow path direction and the width direction inside the flue 82, and is a detection value when an abnormality of the plant 7 is detected. This is a step of acquiring a plurality of abnormal sensor values S, which are detected values. Since the abnormal sensor value acquisition step is the same as the process performed by the abnormal sensor value acquisition unit 13, detailed description thereof will be omitted.

In step S2, the device-specific abnormality degree calculation step is executed. The device-specific abnormality degree calculation step is an abnormality sensor of the device-specific sensor group 85, which is a part of the plurality of temperature sensors 84 and is composed of a plurality of temperature sensors 84 installed in each of the plurality of heat exchangers 9. Based on the value S, it is a step of calculating the abnormality degree Tr for each of the plurality of devices, which is the abnormality degree (MD) of each of the plurality of heat exchangers 9. Since the device-specific abnormality degree calculation step is the same as the process performed by the device-specific abnormality degree calculation unit 2 described above, detailed description thereof will be omitted.

In step S3, the step of calculating the degree of abnormality for each line area is executed. The line region-specific abnormality calculation step assumes a plurality of line regions L that spread along the flow path direction and are arranged in the width direction in the flue 82, and a plurality of temperature sensors belonging to each of the plurality of line regions L. A plurality of line region-specific sensor groups 86 each composed of a part of 84, and at least one temperature sensor 84 installed in each portion of a plurality of heat exchangers 9 belonging to each of the plurality of line regions L. This is a step of calculating a plurality of line-specific abnormality degrees Tl, which are the abnormality degrees (MD) of each of the plurality of line areas L, based on the abnormality sensor value S of the line area-specific sensor group 86 configured by the above. .. Since the line area-specific abnormality calculation step is the same as the process performed by the line area-specific abnormality calculation unit 3, detailed description thereof will be omitted.

In step S4, the abnormality location estimation step is executed. The abnormality location estimation step is a step of estimating an abnormality location based on a plurality of device-specific abnormality degrees Tr and a plurality of line-specific abnormality degrees Tl. Since the abnormality location estimation step is the same as the process performed by the abnormality location estimation unit 4 described above, detailed description thereof will be omitted.

In step S5, the estimation map information generation step is executed. In the estimation map information generation step, the upper N devices, the upper M line areas L, and the upper M line areas L, and the upper M line areas L, and the matrix corresponding to the arrangement of the plurality of line areas L and the plurality of heat exchangers 9 in the flue 22 are performed. This is a step of generating estimated map information M (FIG. 7 (b)), which is map information that maps the abnormal locations estimated by the abnormal location estimation unit 4. Since the estimation map information generation step is the same as the processing performed by the estimation map information generation unit 5 described above, detailed description thereof will be omitted.

In step S6, the output step is executed. The output step is a step of outputting the estimation result, and in the present embodiment, it is a step of outputting the estimation map information M. Since the output step is the same as the process performed by the output unit 6 described above, detailed description thereof will be omitted.

As described above, in the above-described embodiment, the plant abnormality location estimation system 1 is installed in the flue 82 based on the detection values of the plurality of temperature sensors 84 installed in the flue 82 of the boiler 8. The case of estimating the abnormal portion in the heat exchanger 9 has been described as an example. However, the present invention is not limited to the present embodiment. According to the present invention, when a plurality of devices are installed in a flow path through which a fluid such as exhaust gas G flows (a flow path formed by a flow path forming member), a plurality of devices for detecting temperature and other physical quantities are detected. It can also be applied when identifying an abnormal part based on the sensor value of the sensor.
Further, the present invention is not limited to the above-described embodiment, and includes a modification of the above-described embodiment and a combination of these embodiments as appropriate.

1 Plant abnormality location estimation system 11 Operation data collection unit 12 Abnormality monitoring unit 13 Abnormality sensor value acquisition unit 15 Storage device 16 Past abnormality information storage unit 18 Display device 2 Device-specific abnormality degree calculation unit 3 Line area-specific abnormality degree calculation unit 4 Abnormal location estimation unit 41 Match rate calculation unit 5 Estimated map information generation unit 6 Output unit 7 Plant 8 Boiler 81 Fire furnace 82 Smoke path 82w Smoke path wall surface 84 Temperature sensor 85 Device-specific sensor group 86 Line area-specific sensor group 9 Heat exchange Instrument 9p Heat transfer tube 91 Superheater 92 Reheater G Exhaust gas D Operation data S Abnormal sensor value R Equipment area L Line area T Abnormality Tl Line-specific abnormality Tr Equipment-specific abnormality D _LR Crossing area E Target abnormality group P Reference anomaly group C Match rate Vc Match judgment threshold M Estimated map information

Claims (11)

It is a plant abnormality location estimation system that estimates an abnormality location in a plurality of devices installed in the flow path forming member based on the detection values of a plurality of sensors installed in the flow path forming member of the plant.
A plurality of abnormalities which are detection values of the plurality of sensors installed along the flow path direction and the width direction in the flow path forming member and which are the detection values when an abnormality of the plant is detected. An abnormal sensor value acquisition unit that acquires the hour sensor value, and
Each abnormality of the plurality of devices is based on the abnormality sensor value of the device-specific sensor group, which is a part of the plurality of sensors and is composed of a plurality of sensors installed in each of the plurality of devices. An abnormality degree calculation unit for each device that calculates the abnormality degree for each of a plurality of devices, which is a degree, and an abnormality degree calculation unit for each device.
A part of the plurality of sensors belonging to each of the plurality of line regions, assuming a plurality of line regions that spread along the flow path direction and are arranged in the width direction in the flow path forming member. A group of sensors for each line area, each of which is composed of at least one sensor installed in each portion of the plurality of devices belonging to each of the plurality of line areas. A line region-specific anomaly calculation unit that calculates a plurality of line-specific anomalies, which are the anomalies of each of the plurality of line regions, based on the abnormal sensor values of the group.
It is provided with an abnormality location estimation unit that estimates the abnormality location based on the plurality of device-specific abnormality degrees and the plurality of line-specific abnormality degrees.
The abnormality location estimation unit
The target abnormality degree group including the plurality of device-specific abnormality degrees and the plurality of line-specific abnormality degrees, and the plurality of device-specific abnormality degrees calculated based on the past sensor values at the time of abnormality when an abnormality occurs. It has a matching rate calculation unit that calculates the matching rate with the reference abnormality group including the plurality of line-specific abnormalities.
Based on the information of the past abnormal locations associated with the reference abnormality degree group in which the matching rate is equal to or higher than the matching determination threshold value, the abnormal locations in the plurality of devices are estimated.
The matching rate calculation unit compares the top N devices having a large degree of abnormality for each device and the top M line regions in both the target abnormality group and the reference abnormality group. , A plant abnormality location estimation system characterized by calculating the matching rate. The matching rate is based on the number of matching devices belonging to each rank in the top N devices and each rank in the top M line regions in both the target abnormality degree group and the reference abnormality degree group. The plant abnormality location estimation system according to claim 1, wherein the line region to which the line region belongs is a ratio of the total number of matching numbers to the total of the N and the M. With respect to the matrix corresponding to the arrangement of the plurality of line regions and the plurality of devices in the flow path forming member, the upper N devices, the upper M line areas, and the abnormality location estimation unit are used. An estimated map information generator that generates estimated map information, which is map information that maps the estimated abnormal locations, and an estimated map information generator.
The plant abnormality location estimation system according to claim 1 or 2, further comprising an output unit that outputs the estimation map information. A past abnormality that stores a plurality of past abnormality sensor values used for calculating the reference abnormality degree group or the reference abnormality degree group in association with information on the past abnormality portion corresponding to the reference abnormality degree group. The plant abnormality location estimation system according to any one of claims 1 to 3, further comprising a time information storage unit. The reference abnormality degree group is calculated based on the detection values of a plurality of other sensors installed in other flow path forming members of another plant different from the plant from which the plurality of abnormality sensor values have been acquired. The plant abnormality location estimation system according to any one of claims 1 to 4, wherein the plant abnormality location is estimated. It is a plant abnormality location estimation system that estimates an abnormality location in a plurality of devices installed in the flow path forming member based on the detection values of a plurality of sensors installed in the flow path forming member of the plant.
A plurality of abnormalities which are detection values of the plurality of sensors installed along the flow path direction and the width direction in the flow path forming member and which are the detection values when an abnormality of the plant is detected. An abnormal sensor value acquisition unit that acquires the hour sensor value, and
Each abnormality of the plurality of devices is based on the abnormality sensor value of the device-specific sensor group, which is a part of the plurality of sensors and is composed of a plurality of sensors installed in each of the plurality of devices. An abnormality degree calculation unit for each device that calculates the abnormality degree for each of a plurality of devices, which is a degree, and an abnormality degree calculation unit for each device.
A part of the plurality of sensors belonging to each of the plurality of line regions, assuming a plurality of line regions that spread along the flow path direction and are arranged in the width direction in the flow path forming member. A group of sensors for each line area, each of which is composed of at least one sensor installed in each portion of the plurality of devices belonging to each of the plurality of line areas. A line region-specific anomaly calculation unit that calculates a plurality of line-specific anomalies, which are the anomalies of each of the plurality of line regions, based on the abnormal sensor values of the group.
It is provided with an abnormality location estimation unit that estimates the abnormality location based on the plurality of device-specific abnormality degrees and the plurality of line-specific abnormality degrees.
A plant abnormality location estimation system characterized in that the degree of abnormality is the Mahalanobis distance. It is a plant abnormality location estimation method for estimating an abnormality location in a plurality of devices installed in the flow path forming member based on the detection values of a plurality of sensors installed in the flow path forming member of the plant.
A plurality of abnormalities which are detection values of the plurality of sensors installed along the flow path direction and the width direction in the flow path forming member and which are the detection values when an abnormality of the plant is detected. The step of acquiring the sensor value at the time of abnormality and the step of acquiring the sensor value at the time,
A plurality of devices having an abnormality degree of each of the plurality of devices based on the abnormality sensor value of the device-specific sensor group each composed of a part of the plurality of sensors installed in each of the plurality of devices. The step of calculating the degree of abnormality for each device and the step for calculating the degree of abnormality for each device,
Assuming a plurality of line regions that spread along the flow path direction and are arranged in the width direction in the flow path forming member, a part of the plurality of sensors belonging to each of the plurality of line regions, respectively. A group of sensors for each of a plurality of line regions, each of which is composed of at least one of the sensors installed in each portion of the plurality of devices belonging to each of the plurality of line regions. A line area-specific abnormality calculation step for calculating each of the plurality of line-specific abnormality degrees, which is the abnormality degree of each of the plurality of line regions, based on the abnormality sensor value of the above.
An abnormality location estimation step for estimating the abnormality location based on the plurality of device-specific abnormality degrees and the plurality of line-specific abnormality degrees is provided.
The abnormality location estimation step is
The target abnormality degree group including the plurality of device-specific abnormality degrees and the plurality of line-specific abnormality degrees, and the plurality of device-specific abnormality degrees calculated based on the past sensor values at the time of abnormality when an abnormality occurs. It has a matching rate calculation step for calculating a matching rate with a reference abnormality group including the plurality of line-specific abnormalities.
Based on the information of the past abnormal locations associated with the reference abnormality degree group in which the matching rate is equal to or higher than the matching determination threshold value, the abnormal locations in the plurality of devices are estimated.
In the matching rate calculation step, the top N devices having a large degree of abnormality for each device and the top M line regions in both the target abnormality degree group and the reference abnormality degree group are compared with each other. A plant abnormality location estimation method characterized by calculating the matching rate. The matching rate is based on the number of matching devices belonging to each rank in the top N devices and each rank in the top M line regions in both the target abnormality degree group and the reference abnormality degree group. The plant abnormality location estimation method according to claim 7, wherein the total number of matching line regions to which the line regions belong is a ratio to the total of N and M. With respect to the matrix corresponding to the arrangement of the plurality of line regions and the plurality of devices in the flow path forming member, the upper N devices, the upper M line areas, and the abnormality location estimation step An estimated map information generation step for generating estimated map information, which is map information that maps the estimated abnormal location, and an estimated map information generation step.
The plant abnormality location estimation method according to claim 7 or 8, further comprising an output step for outputting the estimated map information. A past abnormality that stores a plurality of past abnormality sensor values used for calculating the reference abnormality degree group or the reference abnormality degree group in association with information on the past abnormality portion corresponding to the reference abnormality degree group. The method for estimating a plant abnormality location according to any one of claims 7 to 9, further comprising a time information storage step. It is a plant abnormality location estimation method for estimating an abnormality location in a plurality of devices installed in the flow path forming member based on the detection values of a plurality of sensors installed in the flow path forming member of the plant.
A plurality of abnormalities which are detection values of the plurality of sensors installed along the flow path direction and the width direction in the flow path forming member and which are the detection values when an abnormality of the plant is detected. The step of acquiring the sensor value at the time of abnormality and the step of acquiring the sensor value at the time,
A plurality of devices having an abnormality degree of each of the plurality of devices based on the abnormality sensor value of the device-specific sensor group each composed of a part of the plurality of sensors installed in each of the plurality of devices. The step of calculating the degree of abnormality for each device and the step for calculating the degree of abnormality for each device,
Assuming a plurality of line regions that spread along the flow path direction and are arranged in the width direction in the flow path forming member, a part of the plurality of sensors belonging to each of the plurality of line regions, respectively. A group of sensors for each of a plurality of line regions, each of which is composed of at least one of the sensors installed in each portion of the plurality of devices belonging to each of the plurality of line regions. A line area-specific abnormality calculation step for calculating each of the plurality of line-specific abnormality degrees, which is the abnormality degree of each of the plurality of line regions, based on the abnormality sensor value of the above.
An abnormality location estimation step for estimating the abnormality location based on the plurality of device-specific abnormality degrees and the plurality of line-specific abnormality degrees is provided.
A method for estimating a plant abnormality location, wherein the degree of abnormality is a Mahalanobis distance.

Images