JP6037954B2 - Boiler tube leak detection device, boiler tube leak detection method, data monitoring center using these, information providing service, and boiler plant. - Google Patents

Description

The present invention relates to a boiler tube leak detection device and a boiler tube leak detection method. The present invention also relates to a data monitoring center, an information providing service, and a boiler plant using these.

  In a boiler plant, steam is generated by heating feed water with a plurality of heat exchangers using high-temperature gas generated by coal combustion. Since heat exchangers come into contact with high-temperature, highly corrosive gases, metal materials may be damaged due to creep, thermal fatigue, or corrosion. When the metal material is damaged, steam leaks from the damaged part. This phenomenon is called tube leak.

  Since the feed water flow rate is controlled so that the amount of steam circulating in the boiler is constant, the feed water flow rate increases when a tube leak occurs. An increase in the water supply flow rate causes an increase in power generation cost.

  When the tube leak occurs and the feed water flow rate increases, the site where the leak occurs is visually confirmed by on-site patrol. When the plant is stopped, it is not possible to confirm the location where the leak has occurred, so it is necessary to visually check the location where the leak has occurred during plant operation.

  On the other hand, when the leaked vapor collides with a surrounding tube, secondary damage that damages the tube occurs. For this reason, the damage range expands as time elapses from the occurrence of the leak. As damage increases, the repair period becomes longer, which increases cost loss.

  Therefore, early detection of tube leak occurrence and early identification of the leak occurrence position contribute to a reduction in plant maintenance costs.

  As a technique for realizing early detection of tube leak occurrence or specifying a leak occurrence position, there are techniques disclosed in Patent Documents 1 to 3.

Although patent document 1 is not a heat exchanger of a boiler plant, it uses the measured value of the make-up water flow rate and the measured value of the temperature sensor provided on one pipe of the leak detection point, from the increase in make-up water flow rate and the temperature change. Detects tube leaks. In patent document 2, the drain pot for accommodating a liquid is provided, and tube leak generation | occurrence | production is detected when a liquid is accommodated in a drain pot. In Patent Document 3, a sound sensor is installed in a boiler building, and when a leak sound is detected, the occurrence of leak is detected. Further, a leak sound source is obtained by cross-correlation processing of acoustic data, and the leak position is specified.

JP 2008-144959A JP 2011-11085A Japanese Patent Laid-Open No. 9-229811

  The technique of Patent Document 1 detects the occurrence of a leak when the increase in the feed water flow rate and the temperature change width exceed a threshold value. However, there are various operation patterns in boiler plants, such as changing the load, burner pattern, and coal type. Since the temperature reference value is different for each operation pattern, the threshold value for detecting tube leak occurrence is also different. Therefore, in order to apply this technique, it is necessary to set a threshold value for every driving pattern.

  In the techniques of Patent Document 2 and Patent Document 3, new hardware is required to detect tube leaks such as the installation of a drain pot and the installation of a sound sensor, which causes an increase in cost.

An object of the present invention is to provide a boiler tube leak detection device that realizes early detection of a boiler tube leak and early specification of a leak position and that suppresses erroneous detection.

  A plurality of means for solving the above-described problems are included, and as an example, the boiler tube leak detection device of the present invention has the following configuration.

A measurement signal database in which measurement signals obtained by measuring the state quantity of the boiler plant are stored for each data item, a state change detection unit for detecting a change in the operation state of the boiler plant, and a change detected by the state change detection unit are leaked. In the boiler tube leak detection device including a detection content evaluation unit for evaluating, the state change detection unit receives first measurement signal data from the measurement signal database, and a part of the data items is set as a monitoring group. A monitoring data extraction unit for grouping, an operation pattern evaluation unit for identifying an operation pattern of the boiler plant, a first belonging to the grouped data item for each identified operation pattern and for each monitoring group A classifying unit that classifies the measurement signal data of each of them to construct a diagnostic model; and A detection unit that detects that the operating state has changed by comparing the two is included, and the data item grouped by the monitoring data extraction unit includes the metal temperature of a plurality of heat exchangers in the boiler plant. Boiler tube leak detection device.

  Provided is a boiler tube leak detection device that realizes early detection of a boiler tube leak and early identification of a leak position, in which erroneous detection is suppressed.

Problems, configurations, and effects other than those described above will be clarified by the following description of embodiments.

It is a block diagram explaining the boiler tube leak detection apparatus which is 1st Example of this invention. It is an operation | movement flowchart figure explaining operation | movement of a boiler tube leak detection apparatus. It is the figure which showed embodiment of the boiler plant. It is a figure explaining the mode of the data preserve | saved at a measurement signal database, and the operation | movement of a monitoring data extraction part. It is a flowchart figure explaining operation | movement of a driving | running pattern evaluation part. It is a figure explaining the function which classifies a measurement signal in a classification part and a detection part. It is a figure explaining the result of having classified the data signal for classification in a classification part, and the result of having classified the signal for detection in a detection part. It is a figure explaining the time-dependent change of the category number which is the feed water flow volume at the time of tube leak generation | occurrence | production, the time of ash fall | offset | occurrence | production, metal temperature, and a classification result. It is a flowchart figure explaining operation | movement of the detection content estimation part. It is a figure explaining operation | movement of the step of a detection content estimation part. It is a figure explaining the aspect of the data preserve | saved in the past example database. It is a figure explaining the Example of the screen displayed on an image display apparatus. It is a block diagram explaining the boiler tube leak detection apparatus which is the 2nd Example of this invention. It is a figure explaining the calculation result of a boiler characteristic calculation part. It is a block diagram explaining the 3rd Example of the present invention. It is an operation | movement flowchart figure of a transmission information determination part.

Next, a boiler tube leak detection apparatus according to an embodiment of the present invention will be described below with reference to the drawings.

  FIG. 1 is a block diagram for explaining a boiler tube leak detection apparatus 400 according to the first embodiment of the present invention. Boiler plant 100 is monitored using boiler tube leak detection device 400. The configuration of the boiler plant 100 will be described later with reference to FIG. The boiler tube leak detection device 400 includes a monitoring data extraction unit 710, an operation pattern evaluation unit 720, a classification unit 730, a detection unit 750, and a detection content that constitutes a detection content evaluation unit 800, which constitute a state change detection unit 700 as an arithmetic device. An estimation unit 810 is provided. The boiler tube leak detection apparatus 400 includes a measurement signal database 510, a diagnostic model database 740, and a past case database 820 as databases. In FIG. 1, the database is abbreviated as DB.

  The measurement signal database 510, the diagnostic model database 740, and the past case database 820 store computerized information, and the information is stored in a form called a normal electronic file (electronic data).

  The boiler tube leak detection apparatus 400 includes an external input interface 410 and an external output interface 420 as interfaces with the outside.

  And the measurement signal 1 which measured the various state quantities which are the operating states of the boiler plant 100 via the external input interface 410, and the external input comprised by the operation management room 900, for example, comprised with the keyboard 920 and the mouse 930, for example. The external input signal 2 created by the operation of the device 910 is taken into the boiler tube leak detection device 400. Further, the image display information 7 is output to the image display device 940 provided in the operation management room 900 via the external output interface 420.

  In the boiler tube leak detection apparatus 400 shown in FIG. 1, the measurement signal 1 obtained by measuring various state quantities of the boiler plant 100 is taken in via the external input interface 410. The measurement signal 3 is stored in the measurement signal database 510.

  The boiler tube leak detection apparatus 400 has two processing modes: model construction processing and diagnostic processing. In the model construction process, a diagnostic model is constructed using a measurement signal in a period determined to be normal in the measurement signal database. The diagnostic model is constructed by clustering technology, and the measurement signals in the normal state are classified into several data groups. Next, in the diagnosis process, the measurement signal at the time to be diagnosed is processed. If the measurement signal has the same characteristics as in the normal state, it is classified into one of the data groups of the diagnostic model. If the characteristics are different, they do not belong to the diagnostic model data group. A data group construction method will be described later with reference to FIGS.

  When tube leak occurs in the boiler, the characteristics of the measurement signal are different from the normal state. Therefore, the boiler tube leak detection apparatus 400 according to the present embodiment detects the occurrence of tube leak when the measurement signal to be diagnosed is not classified into the data group of the diagnosis model.

  However, the characteristics of the boiler vary depending on the operation pattern such as the load, the coal type, and the burner pattern. Moreover, it changes also by disturbances, such as omission of the ash adhering to a heat exchanger.

  The boiler tube leak detection apparatus 400 of this embodiment distinguishes and detects operation pattern changes, disturbances, and boiler tube leaks. This is realized by the state change detection unit 700 and the detection content evaluation unit 800.

  The state change detection unit 700 diagnoses the boiler plant 100 using the measurement signal 4 stored in the measurement signal database 510 and evaluates whether the state of the boiler plant 100 has changed. The detection result 5 obtained by the operation of the state change detection unit 700 is output to the detection content evaluation unit 800 and the external output interface 420.

  First, the operation of the state change detection unit 700 in the model construction processing mode will be described. In the model construction processing mode, the monitoring data extraction unit 710, the driving pattern evaluation unit 720, the classification unit 730, and the diagnostic model database 740 are operated.

  The monitoring data extraction unit 710 extracts a predetermined data item and data for a period defined as normal from the measurement signal database 510. The data for the period defined as normal is referred to herein as first measurement signal data. The monitoring data group signal 701 extracted and grouped in units of data items by the monitoring data extraction unit 710 is output to the operation pattern evaluation unit 720.

  The driving pattern evaluation unit 720 identifies driving patterns and distinguishes the data of the monitoring data group signal 701 for each driving pattern. Here, the operation pattern is a load, a coal type, a burner pattern, and the like, and is evaluated based on data read from, for example, coal flow rate data included in data extracted as a monitoring group. A classification data signal 702 composed of the operation pattern evaluation result and the monitoring data group signal is transmitted to the classification unit 730.

  The classification unit 730 classifies the monitoring data group signal included in the classification data signal 702 using a clustering technique, and constructs a diagnostic model. The diagnostic model 703 is generated for each monitoring pattern and each driving pattern. The diagnostic model 703 constructed by the classification unit 730 is stored in the diagnostic model database 740.

  Next, the operation of the state change detection unit 700 in the diagnostic processing mode will be described. In the diagnosis processing mode, the monitoring data extraction unit 710, the operation pattern evaluation unit 720, and the detection unit 750 are operated.

  The monitoring data extraction unit 710 extracts predetermined data items and data for a diagnosis period from the measurement signal database 510. Here, the data of the period to be diagnosed is referred to as second measurement signal data. The monitoring data group signal 701 extracted by the monitoring data extraction unit 710 is output to the operation pattern evaluation unit 720.

  The driving pattern evaluation unit 720 distinguishes the data of the monitoring data group signal 701 for each driving pattern. A detection data signal 706 including the operation pattern evaluation result and the monitoring data group signal is transmitted to the detection unit 750.

  The detection unit 750 extracts a diagnostic model corresponding to the current driving pattern from the diagnostic model database 740 as diagnostic model database information 704. Moreover, it is diagnosed whether the state of the boiler plant 100 changed using the detection data signal 706 and the extracted diagnostic model.

  Thus, in the boiler tube leak detection apparatus 400 of the present embodiment, the diagnosis model is switched according to the operation pattern such as the load, the coal type, the burner pattern, etc., so that the change in the plant characteristics due to the operation pattern change is considered. Diagnosis is possible. Details of the state change detection unit 700 and a diagnosis method will be described later with reference to FIGS.

  The detection content evaluation unit 800 is operated in the diagnosis processing mode. The detection content evaluation unit 800 evaluates the detection content using the measurement signal 4 and the detection result 5. As an example of the detected content, there is content that specifies the occurrence position of the tube leak. The detection content estimation result 6 obtained by the operation of the detection content evaluation unit 800 is output to the external output interface 420. The outline of the detection content evaluation unit 800 will be described below.

  The detection content estimation unit 810 estimates the detection content based on the past case database information 802, the measurement signal 4, and the diagnosis result 5 stored in the past case database 820. The detection content estimation result 6 is output to the external output interface 420. The contents of detection include information on the occurrence / non-occurrence of boiler tube leak and information on the occurrence position when tube leak occurs. Details of the detection content evaluation unit 800 will be described later with reference to FIGS.

  The diagnosis result 5 and the detection content estimation result 6 are converted into image display information 7 by the external output interface 420 and transmitted to the image display device 940.

  Thus, in the boiler tube leak detection apparatus 400 of the present embodiment, when a tube leak occurs in the boiler plant 100, the detection result of the leak occurrence and the leak occurrence position are displayed on the image display device 940, and information is provided to the operator. I will provide a.

  In the boiler tube leak detection device 400 of this embodiment, the state change detection unit 700, the detection content evaluation unit 800, and the measurement signal database 510 are provided in the boiler tube leak detection device 400. May be arranged outside the boiler tube leak detection device 400 so that only data is communicated between the devices.

  Further, FIG. 1 is a diagram showing the relationship between the functions, and the implementation and the mode of the apparatus are not limited to the divisions and inclusion relationships shown in the figure. For example, the diagnostic model DB 740 may be included in the state detection unit 700 as shown in FIG. 1, or the effects of this embodiment can be obtained even when used in combination with other DBs.

  In addition, information stored in the measurement signal database 510, the diagnostic model 740, and the past case database 820 installed in the boiler tube leak detection device 400 can be arbitrarily displayed on the image display device 940 of the operation management room 900. ing. These pieces of information can be corrected by an external input signal 2 generated by operating an external input device 910 including a keyboard 920 and a mouse 930.

  Although not shown, as an embodiment of the present embodiment, an information providing service for providing information obtained by operating the tube leak detection device 400 to the operator, and an operation control device equipped with the tube leak detection device 400 Boiler equipment, boiler plant, etc. are also included.

  FIG. 2 is an operation flowchart illustrating the operation of the boiler tube leak detection apparatus 400.

  First, in step 1000, it is determined that the model construction mode is operated when the following conditions are satisfied, and a diagnostic model is constructed. In other cases, it is determined to operate in the diagnosis mode.

  When the boiler tube leak detection device 400 is used for the first time, that is, when there is no diagnostic model.

  -When the driving pattern evaluation unit 720 detects a new driving pattern and needs to add a diagnostic model.

  -When there is a request for model construction by input from the external input device 910.

  If it is in the model construction mode, the process proceeds to step 1010. If it is in the diagnosis mode, the process proceeds to step 1020.

  In step 1010, the monitoring data extraction unit 710, the operation pattern evaluation unit 720, and the classification unit 730 of the state change detection unit 700 are operated to construct a diagnostic model.

  In Step 1020, it is determined whether or not a predetermined diagnosis cycle time has elapsed since the end of the diagnosis one cycle before. If the time has elapsed, the process returns to Step 1020. Proceed to step 1030.

  In step 1030, the monitoring data extraction unit 710, the operation pattern evaluation unit 720, and the detection unit 750 of the state change detection unit 700 are operated to diagnose the boiler plant 100.

  In Step 1040, it is evaluated whether or not a plant abnormality is detected by the detection unit 750 operated in Step 1030. If detected, the process proceeds to step 1050, and if not detected, the process proceeds to step 1060.

  In step 1050, the detected content evaluation unit 800 is operated to evaluate the detected content.

  In step 1060, when there is a request to end the boiler tube leak detection device 400 by the external input signal 2 from the external input device 910, the process proceeds to the end, and otherwise returns to step 1000.

  FIG. 3 is a diagram showing an embodiment of the boiler plant 100.

  The present embodiment is a thermal power plant having a boiler 200 and a steam turbine 300 driven by steam generated by the boiler 200 as main components (a generator is not shown). The boiler plant 100 controls the specified load (power generation output) based on the load request command. By adjusting the valve opening degree of the steam control valve 290, the steam flow rate 261 guided to the turbine 300 changes and the power generation output changes.

  In addition, the water / steam system includes a condenser 310 that cools the steam emitted from the steam turbine 300 into a liquid, and a water supply pump 320 that feeds water cooled by the condenser 310 back to the boiler 200 as boiler feed water. There is. Although not shown in the drawings, an actual plant also includes a feed water heater that preheats boiler feed water using a part of steam extracted from the middle stage of the steam turbine 300 as a heating source.

  On the other hand, in the system of the combustion gas 201 discharged from the boiler, there are an exhaust gas treatment device 330 for purifying exhaust gas and a chimney 340 for discharging the purified gas 331.

  Coal 381 as fuel is sent to a coal pulverizer (mill) 350 via a fuel supply amount adjustment valve 380. In addition, air 382 used for coal conveyance and combustion adjustment is supplied to the coal pulverizer 350 and the burner 210 via an air amount adjustment valve 370. Coal that has been powdered (pulverized coal) by the coal pulverizer 350 is conveyed by air and supplied to the burner 210. An after air port 220 is disposed on the upper portion of the burner 210, and air 383 is supplied to the after air port 220 via an air amount adjustment valve 360.

  Next, the configuration of the boiler 200 will be described.

  A furnace having a burner 210 for burning fuel has a cooling wall called a water wall 230 that cools the entire wall surface and collects the heat of the combustion gas because the inside of the furnace becomes hot. In the boiler 200, there are other heat exchangers including a economizer 280, a primary superheater 270, a secondary superheater 240, a tertiary superheater 250, and a fourth superheater 260. Is recovered to produce high-temperature steam.

  Although not shown in the figure, the plant has many sensors for measuring gas composition, temperature, pressure, steam temperature, pressure, heat exchanger metal temperature, etc. The measurement result is transmitted as measurement information 1 from the data transmission device 390 to the boiler tube leak detection device 400. Although not shown, it is common to install a plurality of boiler burners 210 in the horizontal direction before and after the furnace and a plurality of stages in the height direction, and a plurality of after airports in the horizontal direction before and after the furnace. is there.

  FIG. 3 (b) is a diagram showing a steam path from the feed water to the turbine. As shown in FIG. 3 (b), the boiler feed water is first guided to the economizer 280, and then the water wall 230, the primary superheater 270, the secondary superheater 240, the tertiary superheater 250, and the fourth superheater 260. In this order, the main steam 261 flows into the steam turbine 300. The steam that has worked in the high-pressure steam turbine 300 becomes liquid in the condenser 310 and is sent again to the boiler by the feed water pump 320.

  FIG. 3C is a top view of the tertiary superheater 250. A plurality of tubes 251 (thin lines) constituting the superheater are arranged in the width direction and the depth direction of the boiler. As a shape of the tube, for example, it is U-shaped in the depth direction of FIG. 3 (c), and the steam entering from one side returns from the outlet on the opposite side. Further, a tube metal temperature measuring device 252 is attached to the superheater (for example, at a thick line portion steam outlet portion in the figure). In general, every several to several tens of metal temperature measuring instruments are attached.

  FIG. 4 is a diagram for explaining the mode of data stored in the measurement signal database 510 and the operation of the monitoring data extraction unit 710.

  FIG. 4A is a diagram illustrating a mode of data stored in the measurement signal database 510. As shown in FIG. 4A, in the measurement signal database 510, the value of the measurement signal 1 (data items A, B, and C are shown in the figure) that is operation data measured for the plant 100 is sampled. Stored for each period (time on the vertical axis).

  By using scroll boxes 512 and 513 that can move vertically and horizontally on the display screen 511, a wide range of data can be scroll-displayed.

  FIG. 4B is a block diagram of the monitoring data extraction unit 710. Data items are divided into a plurality of groups according to the diagnosis location and range. For example, it is divided into a monitoring group 1 for evaluating the operation pattern, a monitoring group 2 for monitoring the main feed water flow rate, and a monitoring group 3 for monitoring the primary superheater (1SH) outlet metal temperature.

  FIG. 4C shows the data items of each group. Such a monitoring group can be arbitrarily added / deleted using the external input device 910. In this embodiment, the metal temperature measurement values are grouped for each heat exchanger, but the metal temperature measurement values may be grouped along the gas flow.

  Different effects can be obtained depending on the grouping method. For example, data items corresponding to metal temperature measurement values measured by a large number of tubes included in each heat exchanger are grouped for each heat exchanger. By looking at the positional relationship and temperature correlation between these tubes, it is possible to quickly detect which tube in the specific heat exchanger has leaked with less errors. In addition, for example, a data item corresponding to a metal temperature measurement value of a tube of each of a plurality of heat exchangers in the same width direction position of the boiler can and having the same gas flow upstream and downstream positional relationship. , Group according to regularity such as gas flow direction. By evaluating the positional relationship and temperature correlation of the tubes located in these different heat exchangers from the viewpoint of gas flow, accurate leak judgment is performed (for example, errors due to other accidents such as ash dropping, abnormalities in specific thermometers, etc.). Detection can be suppressed), and the leak location heat exchanger and tube can be identified early. As will be described later, detection results and data are displayed on the image display device, and there are cases where the operator visually judges from the display of the data and its graph. Judgment is possible and the effect of improving the judgment accuracy can be expected.

  FIG. 5 is a flowchart for explaining the operation of the driving pattern evaluation unit 720.

  First, the purpose of the driving pattern evaluation unit 720 will be described. When the operation state of the boiler plant 100 is a transient state, the measurement signal changes irregularly. Moreover, the characteristics of the plant change according to the operation pattern such as the burner pattern, the coal type, and the load. Therefore, when operating in a transient state and an operation pattern that has not been experienced in the past, there is a possibility that a false alarm for detecting an abnormality in the state change detection unit 700 may occur even if no abnormality has occurred in the plant.

  Therefore, the state change detection unit 700 according to the present embodiment does not perform diagnosis in a transient state. In addition, by constructing and diagnosing a diagnostic model for each driving pattern, the occurrence of false alarms is suppressed. In order to realize this function, a function for determining whether the operation state of the plant is a transient state or a steady state and a function for determining the operation pattern are required. The operation pattern evaluation unit 720 of this embodiment is required. Is equipped with these functions. Hereinafter, the operation content of each step of the flowchart will be described.

  In step 1100, using the measurement signal for operation pattern monitoring extracted by the monitoring data extraction unit 710, it is determined whether the operation state of the plant is a steady state or a transient state. The transient state is a state within one of the following predetermined periods, and the rest is a steady state.

  -A predetermined period from the start of soot blower injection. In the boiler plant 100, there is a soot blower facility that injects steam into a tube in order to remove ash adhering to the heat exchanger. The metal temperature of the heat exchanger varies due to the soot blower.

  ・ Predetermined period from the start of burner ignition / extinguishing. In the boiler plant 100, the burner is ignited and extinguished in accordance with a load request signal in order to obtain a desired load. Also, the burner pattern is changed for burner maintenance. When the burner is ignited and extinguished, the flow rate of coal flowing through the burner changes greatly, so the temperature of the gas generated by coal combustion also varies. As the gas temperature varies, the metal temperature also varies.

  -A predetermined period after the load change and after the load change ends. In the boiler plant 100, the power generation output of the plant is changed using a load request signal based on a command from the central power supply command station. During the load change, the coal flow rate, feed water flow rate, and air flow rate are changed. As a result, since the gas temperature and the steam temperature fluctuate, the metal temperature also fluctuates.

  In step 1110, based on the coal flow rate supplied to each burner, it is evaluated whether each burner is in an ignition state or a fire extinguishing state, and a burner pattern is determined. In step 1120, the type of coal supplied to the burner is determined. The type of coal is determined from, for example, a coal type code assigned to each type of coal. In step 1130, the load is determined based on the measured value of the generator output. In the present embodiment, a leak detection method corresponding to fluctuation of each value depending on these operation patterns is made possible.

  FIG. 6 is a diagram illustrating a function of classifying the classification data signal 702 and the detection data signal 706 by the classification unit 730 and the detection unit 750. Whether the classification unit 730 operates or the detection unit 750 operates depends on the operation mode of the state change detection unit 700 as described above.

  In the present embodiment, a case where adaptive resonance theory (ART) is applied as a technique for classifying signals will be described. It should be noted that other clustering methods such as vector quantization and support vector machine can be used.

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

  Hereinafter, those procedures performed by the data preprocessing device 610 and the ART module 620 will be described.

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

  In the ART module 620, the classification data signal 702 or the detection data signal 706 that is input data is classified into a plurality of categories.

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

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

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

  Process 1: The input vector is normalized by the F0 layer 621, and noise is removed.

  Process 2: A suitable category candidate is selected by comparing the input data input to the F1 layer 622 with a weighting factor.

  Process 3: The validity of the category selected by the selection subsystem 625 is evaluated by the ratio with the parameter ρ. If it is determined to be valid, the input data is classified into the category, and the process proceeds to process 4. On the other hand, if it is not judged to be valid, the category is reset, and an appropriate category candidate is selected from the other categories (repeat processing 2). Increasing the value of parameter ρ makes the category classification finer, and decreasing the value of ρ makes the classification coarse. This parameter ρ is referred to as a vigilance parameter.

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

  Process 5: When input data is classified into category J, weight coefficient WJ (new) corresponding to category J uses past weight coefficient WJ (old) and input data p (or data derived from input data). And updated by the following equation (1).

  Here, Kw is a learning rate parameter (0 <Kw <1), and is a value that determines the degree to which the input vector is reflected in the new weighting factor.

  It should be noted 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 processing 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. Therefore, it is possible to record a new pattern while recording a pattern learned in the past.

  As described above, when the operation data given in advance is given as input data, the ART module 620 learns the given pattern. Therefore, when new input data is input to the learned ART module 620, it is possible to determine which pattern in the past is close by the above algorithm. If the pattern has never been experienced before, it is classified into a new category.

FIG. 6B is a block diagram showing the configuration of the F0 layer 621. In the F0 layer 621, the input data I _i is normalized again at each time, and a normalized input vector u _i ⁰ to be input to the F1 layer 621 and the selection subsystem 625 is created.

First, w _i ⁰ is calculated from the input data I _{i according} to the equation (2). Here, α is a constant.

Next, x _i ⁰ obtained by normalizing w _i ⁰ is calculated using equation (3). Here, || || is a symbol representing a norm.

Then, using equation (4), calculates the v _i ⁰ obtained by removing noise from x _i ^0. However, θ is a constant for removing noise. Since the minute value becomes 0 by the calculation of the equation (4), noise of the input data is removed.

Finally, a normalized input vector u _i ⁰ is obtained using Equation (5). u _i ⁰ is input to the F1 layer.

FIG. 6C is a block diagram showing the configuration of the F1 layer 622. In the F1 layer 622, u _i ⁰ obtained by the equation (5) is held as a short-term memory, and p _i input to the F2 layer 722 is calculated. The formulas for calculating the F2 layer are collectively shown in formulas (6) to (12). Here, a and b are constants, f () is a function shown in Equation (4), and T _j is a fitness calculated by the F2 layer 722.

  However,

  FIG. 7 is a diagram for explaining the result of classifying the classification data signal 702 by the classification unit 730 and the result of classifying the detection signal 706 by the detection unit 750. As described above, the classification unit 730 operates when the state change detection unit 700 operates in the model construction mode, and the detection unit 750 operates when it operates in the diagnosis mode.

  FIG. 7A is a diagram for explaining the result of classifying the measurement signal 1 acquired from the boiler plant 100 into categories. The horizontal axis is time, and the vertical axis is measurement signal and category number. In FIG. 7A, the normal period and the diagnostic period are shown to be continuous on the time axis, but the normal period and the diagnostic institution do not have to be continuous in time. For example, a certain time period determined to be in the normal state on the previous day may be used in the model construction mode to create a diagnostic model, and a certain time period on another day may be diagnosed. Fig. 7 (a) shows an example of the data when comparing the measured signal data of the period (left side of the figure) measured in the model construction mode and the measured signal data of the diagnosis period (right side of the figure). It is a thing. The former measurement signal data may be distinguished as first measurement signal data, and the latter measurement signal data may be distinguished as second measurement signal data.

  FIG. 7B is a diagram illustrating an example of a classification result obtained by classifying the measurement signal 1 of the plant 100 into a category. FIG. 7B shows, as an example, two items of the measurement signal, which are represented by a two-dimensional graph. In addition, the vertical axis and the horizontal axis indicate the measurement signals of the respective items normalized.

  The measurement signal is divided into a plurality of categories 630 (circles shown in FIG. 7B) by the ART module 620 in FIG. One circle corresponds to one category.

  In this embodiment, measurement signals are classified into four categories. Category number 1 is a group in which item A has a large value and item B has a small value, category number 2 is a group in which both items A and B have small values, category number 3 has a small value in item A, and item B A group with a large value of, category number 4 is a group with a large value for both items A and B.

  As shown to Fig.7 (a), the data of the normal period were classified into the categories 1-3. The first half of the data after the start of monitoring in the diagnosis mode is classified into category 2, which is the same category as the model data. In this case, since the data trends are the same, it is determined that the state has not changed. On the other hand, data in the latter half after the start of monitoring is classified into category 4, and is classified into a category different from the diagnostic model data. Since the data trends are different, it is determined that the state of the plant has changed.

  In this embodiment, an example in which two items of measurement signals are classified into categories has been described. However, three or more items of measurement signals can be classified into categories using multidimensional coordinates. In that case, the determination can be made more finely by looking at the correlation of a large number of data items having different tendency depending on the state quantity of the plant, such as the metal temperature, the feed water flow rate, and the combustion gas flow rate.

  In the diagnostic model database 740, as shown in FIG. 7C, the relationship between the category number and the weighting coefficient is stored. Here, the weighting factor is the center coordinate of the category.

  FIG. 8 is a diagram for explaining the temporal change of the feed water flow rate, the metal temperature, and the category number as the classification result when the tube leak occurs and the ash drop occurs.

  FIG. 8A is a diagram for explaining a change with time when a tube leak occurs. If steam leaks when a tube leak occurs, the feedwater flow rate will begin to increase slightly to maintain the power output. Thereafter, the leaked steam causes damage to the surrounding tubes. As a result, the amount of leaking steam increases and the feed water flow rate also increases.

  The metal temperature of the tube around the location where the breakage occurs is lowered because it is cooled by the leaked steam. On the other hand, the metal temperature of the tube apart from the damaged part rises. This is because the cooling effect is weakened due to the influence of less steam flowing in the tube due to leakage.

  In the monitoring group 2 that monitors the feed water flow rate, if the increase in the feed water flow rate immediately after the occurrence of the leak is small, a change in state may not be detected. On the other hand, in the monitoring group 3 that monitors the metal temperature, since the measurement value changes as described above after the occurrence of the leak, a new category is generated and a state change is detected. Thereafter, when the damage range is widened, the feed water flow rate is greatly increased, so that the monitoring group 2 also detects a change in state.

  FIG. 8 (b) is a diagram for explaining the change over time when the ash is dropped.

  As the ash adhering to the heat exchanger falls off, the amount of heat transferred from the gas increases, and the metal temperature rises. Thereafter, as the ash gradually reattaches to the metal, the metal temperature decreases. As a result, in the monitoring group 3, when an abnormality is detected at the timing of ash dropping, and then the metal temperature returns to the base state, the normal category is reached.

  Moreover, the ash drop has almost no effect on the feed water flow rate. Therefore, a new category does not occur in the monitoring group 2.

  As described above, the occurrence of tube leak can be detected at an early stage from the change in metal temperature (up or down depending on the location) by monitoring the metal temperature, and the accuracy of detecting the occurrence of tube leak can be improved by monitoring the feed water flow rate. On the other hand, an abnormality is detected because the metal temperature changes even when the ash is dropped, which is a typical example of disturbance, but by monitoring both the metal temperature and the feed water flow rate, the tube leak is as described in the explanation of FIG. There is a difference. Thereby, the detection content evaluation unit 800 of the present embodiment has a function of distinguishing a disturbance represented by ash drop and a tube leak. Hereinafter, the operation of the detection content evaluation unit 800 will be described.

  FIG. 9 is a flowchart for explaining the operation of the detection content estimation unit 810 in the detection content evaluation unit 800.

  In step 1200, the diagnostic cycle is confirmed. It is determined whether or not a predetermined diagnosis cycle time has elapsed since the end of the diagnosis one cycle before. If the time has elapsed, the process returns to step 1200. If the time has elapsed, the process proceeds to step 1210. .

  In step 1210, it is evaluated whether the detection unit 750 has detected a state change. If it has been detected, the process proceeds to step 1220. If not, the process returns to step 1200.

  Step 1220 distinguishes between tube leaks and disturbances. In the case of tube leak, the process proceeds to step 1230, and in the case of disturbance, the process proceeds to step 1240.

  In step 1230, the occurrence position and the size of the tube leak are estimated. Moreover, the operation guidance of the boiler plant 100 is determined.

  Details of step 1220 and step 1230 will be described with reference to FIG.

  In step 1240, the detection content estimation result 6 is output to the external output interface 420.

  In step 1250, when there is a request to end the boiler tube leak detection device 400 by the external input signal 2 from the external input device 910, the process proceeds to the end, and otherwise returns to step 1200.

  FIG. 10 is a diagram for explaining the operations of Step 1220 and Step 1230 of the detection content estimation unit 810. In step 1220, tube leak and ash drop are distinguished based on the normal state immediately before detection and the change width of the metal temperature after detection. FIGS. 10A, 10B, and 10C show the metal temperature change width when the tube leak occurs in the central portion of the can, and changes in the order of (a), (b), and (c) as time passes.

  As shown in FIG. 10 (a), the event heat exchanger has a part where the metal temperature rises and a part where it falls (circle in FIG. 10 (a)). The reason for this is as described in FIG.

  This effect also affects the metal temperature of the heat exchanger downstream of the gas flow (square in FIG. 10 (a)). The reason is as follows. Because the gas temperature that passes through the tube part where the metal temperature has increased in the event-generating heat exchanger increases, the metal temperature of the tube located immediately downstream of the event-generating tube among the tubes of the heat exchanger located downstream Also rises. Moreover, since the gas temperature which passes the site | part where the metal temperature fell with the heat exchanger of event generation | occurrence | production falls, the downstream metal temperature also falls.

  Further, when the leaked steam flows back into the gas flow and is ejected, the metal on the upstream side of the gas flow is cooled, so that the metal temperature decreases (triangle in FIG. 10 (a)).

  The decrease width of the metal temperature increases around the site where the leak occurs, increases in the heat exchanger where the leak occurs, and in many cases, the decrease width becomes the maximum. Based on this tendency, the detection content estimation unit 810 calculates the metal temperature decrease width as the tube leak occurrence location around the metal temperature measurement tube portion of the heat exchanger in which the decrease width is the maximum in many cases. Extract.

  Since the scale of the leak increases due to secondary damage as time passes after the occurrence of the leak, as shown in FIGS. 10 (b) and 10 (c), the range of change in the metal temperature increases, and the region where the metal temperature changes Become wider.

  FIGS. 10D, 10E, and 10F show the metal temperature change width when ash dropping occurs, and change in the order of (d), (e), and (f) with the passage of time.

  As shown in FIG. 10 (d), the metal temperature at the site where the ash has fallen rises (circle in FIG. 10 (d)). This effect also affects the downstream heat exchanger (square in FIG. 10 (d)). This is because the gas temperature passing through the portion where the metal temperature has risen in the eventual heat exchanger rises, so that the downstream metal temperature also rises. On the other hand, the heat exchanger upstream of the gas flow is not affected (triangle in FIG. 10 (d)).

  Thereafter, as the ash adheres with the passage of time, the state returns to the original state as shown in FIGS.

  In step 1220, the tube leak and the disturbance are distinguished from each other by utilizing the above-described characteristic difference in the metal temperature change width in the ash dropping that is a typical example of the disturbance when the tube leak occurs.

  Immediately after the event occurs, if both the part where the metal temperature rises and the part where it falls are diagnosed, the tube leak is diagnosed. Moreover, when the metal temperature of the heat exchanger arrange | positioned in the upstream of gas is changing with respect to the heat exchanger with the largest metal temperature change width | variety, it diagnoses that tube leak generate | occur | produces.

  If the change width of the metal temperature increases as time elapses from the abnormality detection, a tube leak is diagnosed. By adopting the above diagnostic criteria, it is possible to distinguish disturbances such as ash drop and to detect tube leaks.

  Such cases are stored in the past case database 820.

In step 1220, tube leak and disturbance may be distinguished from similar cases by comparing with information stored in the past case database 820. By displaying and presenting information related to past cases to the operator, it is possible to use past knowledge for leak determination, and it is possible to reduce time and labor for making a leak determination. Here, the similar case is a case where Equation (13) is minimized.
Σ (Metal temperature change width of target case-metal temperature change width of past case database) ²
(13)

  In step 1230, a portion where the change width of the metal temperature is maximum is extracted as a leak occurrence position. Further, the size of the tube leak is estimated according to the maximum change width of the metal temperature. Furthermore, an operation guidance recommended for each maximum change width of the metal temperature (plant stop, operation with reduced output, etc.) is associated in advance, and the associated operation guidance is determined. By having the function of determining the boiler tube leak detection device and the function of determining the guidance, accurate tube leak determination in which human error is suppressed becomes possible.

  FIG. 11 is a diagram for explaining a mode of data stored in the past case database 820.

  As shown in FIG. 11A, the past case database 820 stores events such as tube leaks and ash drop, the maximum metal temperature change width, and the change width of each metal temperature in association with each other.

  Further, as shown in FIG. 11B, the relationship between the structure and the measurement position is stored, and it is possible to search where the position where the tube leak has occurred is on the design drawing.

  Further, although not shown, the past case database 820 stores 3D-CAD data of the boiler plant 100.

  FIG. 12 is a diagram illustrating an example of a screen displayed on the image display device 940.

  The metal temperature change width at the current time before detection as shown in FIG. 10 can be displayed, and the state of the plant can be confirmed. In addition, the position of the measuring instrument where the metal temperature drop width is maximized is displayed on the 3D-CAD, and a place where there is a high possibility that a tube leak has occurred can be confirmed. By being displayed as a CAD diagram, it becomes information useful for facilitating the recognition of the position of the tube leak and for predicting the spread of leaks that may occur in a chain.

  In addition, operation guidance corresponding to past similar cases and the maximum metal temperature change width is displayed, and operation determination materials are provided to the operator. By providing data that is effective judgment material according to the present embodiment through an interface that is easy to visually recognize, the operator can visually recognize leak detection at an early stage and can take an early action.

  By using the boiler tube leak detection device 400 described above, early detection of tube leaks and early identification of tube leak occurrence positions are realized without the need to set threshold values for each operation pattern or install new hardware. And the expansion of secondary damage can be suppressed.

  In addition, a service for providing the obtained information to a plant operating company for a power plant using the boiler tube leak detection apparatus 400 is also assumed as a business form. In that case, the plant operation company has the advantage of being able to obtain the economic effect that it is not necessary to have personnel with the knowledge necessary for judgment, and that the company that provides information can gather and know-how. Occurs.

The boiler tube leak detection device described in the present embodiment is a device having a function of detecting boiler tube leak, for example, a boiler control device having the configuration of the present embodiment, and data measured by the boiler. A device located at a remote place that originally has the configuration of the present embodiment and processes to determine and detect a leak also corresponds to this.

  FIG. 13 is a block diagram illustrating a boiler tube leak detection apparatus 400 according to the second embodiment of the present invention. It differs from the first embodiment of the present invention (FIG. 1) in that a boiler characteristic calculation unit 450 is provided.

  The boiler characteristic calculation unit 450 is a model that simulates the characteristics of the boiler plant 100, and uses a numerical analysis method such as a difference method, a finite volume method, and a finite element method for the combustion (reaction), gas flow, and heat transfer processes. To calculate. Although it is desirable that the analysis accuracy of the numerical analysis is high, this embodiment is not characterized by the analysis method, so the description of the numerical analysis method is omitted, but generally the shape of the boiler to be calculated is a calculation grid (mesh). And calculate the physical quantity in the lattice. Using at least one of the fuel flow rate, air flow rate, or feed water flow rate stored in the measurement signal database 510 as an input, the gas temperature, gas component concentration, gas flow rate and flow direction by numerical analysis, The metal temperature etc. of each heat exchanger is output as a calculation result. Calculate the phenomena under various operating conditions by numerical analysis.

  The boiler characteristic calculation unit 450 can calculate the metal temperatures of all the tubes of the heat exchanger, and the calculation result is output as the calculation result 9. The calculation result 9 is output to one or more of the state change detection unit 700 and the detection content evaluation unit 800, where it is used to supplement the measurement signal 4 from the measurement signal database or instead of the measurement signal 4. The In the state change detection unit 700, the monitoring data extraction unit 710 extracts and groups data items used for monitoring from the measurement signal database and the calculation results of the boiler characteristic calculation unit. The subsequent operations of the state change detection unit 700 and the detection content evaluation unit 800 are the same as those in the first embodiment.

FIG. 14 is a diagram for explaining a calculation result of the boiler characteristic calculation unit 450. It is the figure which displayed the measured value and calculated value of the metal temperature superimposed. Although the number of metal temperature measurement points is limited among many tubes in each heat exchanger, the metal temperature of all tubes is output as calculation results by the boiler characteristic calculation unit 450, and the calculation results are the data items to be diagnosed. Can be used. As a result, diagnosis in consideration of the metal temperature of all the tubes can be performed, and the state change can be detected with higher accuracy. Further, when the operator determines the leak detection result, it is displayed as smoother and more detailed visual information, so that the determination accuracy can be improved.

  FIG. 15 is a block diagram for explaining a third embodiment of the present invention.

  In this embodiment, a data monitoring center 950, a power plant 970, and a load adjustment department 980 are connected to each other via an information communication network 960.

  Although there are a plurality of power plants 970 and two power plants are described in this embodiment, the power plants 970 may actually be configured to be connected to three or more power plants.

  The data monitoring center 950 includes the boiler tube leak detection device 400 and the transmission information determination unit 951 described in the first or second embodiment. The transmission information determination unit 951 processes data using the diagnosis result 8 and the measurement signal 21, and transmits the transmission information 22 to the power plant 970 and the load adjustment department 980.

  The load adjustment department 980 outputs a signal 10 including a load request signal (output request signal) of each power plant using the external input device 981. The signal 9 including the load request signal is displayed on the image display device 940, and the output is controlled at each power plant according to the displayed information.

  The measurement signal 1 measured at the power plant is transmitted to the data monitoring center 950 via the information communication network 960. The data monitoring center 950 monitors the operating state of each power plant using the received measurement signal 21 and evaluates whether tube leak has occurred.

  By gathering the data monitoring center 980 in one department separately from each power plant, operators with the knowledge necessary to determine leaks from plant measurement signals with higher accuracy can be obtained. This eliminates the need to place them at each power plant, enabling cost reduction and integration of know-how. This is because the power plant 970a, b of the present embodiment has the boiler tube leak detection device 400 of the first embodiment or the second embodiment, so that the display data is less dependent on the individual characteristics of each power plant by applying the clustering technology. This is because it was possible to judge from the above, and because it was possible to detect tube leaks at an early stage, it was possible to create a grace period to respond from a remote location. In addition, the data monitoring center and the monitoring information providing service of this embodiment can be implemented in which the above problem of monitoring these from a remote place is improved.

  When the occurrence of tube leak is detected, the operational duration of the plant where the tube leak occurred, the degree of damage spread, the loss cost due to the plant shutdown, whether there is a margin for increasing the output of other plants, starting or increasing the load Considering the time required, additional cost, etc., an operation schedule that minimizes the cost is obtained, and transmission information 22 including operation schedule information is transmitted to the power plant 970 and the load adjustment department 980.

Each power plant can obtain an operation schedule plan before the load request signal arrives from the load adjustment department, so that it is possible to prepare for operation such as output increase and output decrease.
FIG. 16 is an operation flowchart of the transmission information determination unit 951.

  First, in step 1300, it is determined whether or not a predetermined diagnosis period has elapsed since the end of the diagnosis one cycle before. If the time has elapsed, the process returns to step 1300, and the time has elapsed. Proceeds to step 1310.

  In step 1310, when the tube leak detection is detected by the boiler tube leak detection device 400, the process proceeds to step 1320. Otherwise, the process returns to step 1300.

  In step 1320, an operation schedule that minimizes the evaluation function of equation (14) is determined.

  However, 1 ≦ i ≦ P, P is the total number of power plants, α i is a weighting factor, and Ci is an additional cost generated in each power plant.

  In step 1330, the operation schedule determined in step 1320 is transmitted to the power plant 970 and the load adjustment department 980.

  In step 1340, the presence / absence of a command to stop the tube leak detection apparatus 400 is evaluated. If there is a stop command, the process proceeds to the end, and if not, the process returns to step 1300.

It is possible to automatically create an operation schedule that minimizes the cost loss associated with tube leak occurrence, and it is possible to operate the plant according to this operation schedule. In addition, a service that provides each power plant with information on an operation schedule including a load requirement value of each plant has an effect of providing the above-described merit that enables a plant operation company to prepare for operation in advance.

DESCRIPTION OF SYMBOLS 1 ... Measurement signal 2 ... External input signal 3 ... Measurement signal 4 ... Measurement signal 5 ... Diagnosis result 6 ... Detection content estimation result 7 ... Image display information 100 ... Plant 400 ... Boiler tube leak detection device 410 ... External input interface 420 ... External output interface 510 ... Measurement signal database 700 ... State change detection unit 710 ... Monitoring data extraction unit 720 Driving pattern evaluation unit 730 Classification unit 740 Diagnosis model database 750 Detection unit 800 Detection content evaluation unit 810 Detection factor estimation unit 820 Past case database 701 Monitoring data group signal 702 ... Classification data signal 703 ... Diagnosis model 704 ... Diagnosis model Database information 705 ... Diagnostic model database information 706 ... Detection data signal 801 ... Past case database information 802 ... Past case database information 900 ... Operation management room 910 ... External input device 920・ ・ ・ Keyboard 930 ・ ・ ・ Mouse

Claims (14)

A measurement signal database in which measurement signals measuring the state quantity of the boiler plant are stored by data item;
A state change detector that detects a change in the operating state of the boiler plant;
In the boiler tube leak detection device provided with the detection content evaluation unit for evaluating whether the change detected by the state change detection unit is a leak,
A boiler characteristic calculator that calculates a metal temperature from at least one condition of a fuel flow rate, an air flow rate, or a feed water flow rate stored in the measurement signal database;
In the state change detection unit,
A monitoring data extraction unit that inputs first measurement signal data that is data of a period defined as normal from the measurement signal database, and groups a part of the data items as a monitoring group;
An operation pattern evaluation unit for identifying an operation pattern of the boiler plant;
Said each identified operation pattern and for each of the monitoring group, the classification unit to construct a diagnostic model to classify the first measurement signal data belonging to the grouped data item,
A detection unit that detects that the driving state has changed by comparing second measurement signal data that is data of a period to be diagnosed with the diagnostic model is provided,
The data item grouped by the monitoring data extraction unit includes the metal temperature of a plurality of heat exchangers in the boiler plant ,
The boiler tube leak detection device, wherein the monitoring data extraction unit inputs data from the measurement signal database and calculation results of the boiler characteristic calculation unit . In the boiler tube leak detection device according to claim 1,
The boiler tube leak detection apparatus characterized in that the data item extracted and grouped by the monitoring data extraction unit includes a feed water flow rate. In the boiler tube leak detection device according to any one of claims 1 to 2,
The boiler is characterized in that the second measurement signal data to be compared with the diagnostic model in the detection unit is data that is extracted from the measurement signal database in units of data items, grouped, and subjected to driving pattern evaluation. Tube leak detection device. In the boiler tube leak detection device according to any one of claims 1 to 3 ,
The boiler tube leak detection device characterized by not operating the detection unit when the operation pattern evaluation unit determines that the operation state of the plant is a transient state. In the boiler tube leak detection device according to any one of claims 1 to 4 ,
The metal temperature grouping performed by the monitoring data extraction unit is
A boiler tube leak detection device comprising one or more of grouping of metal temperature measurement values for each heat exchanger or grouping of metal temperature measurement values along a gas flow. In the boiler tube leak detection apparatus according to any one of claims 1 to 5 ,
In the detection content evaluation unit,
Calculate the metal temperature change width before and after detecting the change of state in the detector, and extract the metal temperature measurement tube part of the heat exchanger where the metal temperature decrease width is calculated to be the maximum as the vicinity of the tube leak occurrence point A boiler tube leak detection device characterized in that a detection content estimation unit is provided. In the boiler tube leak detection device according to any one of claims 1 to 6 ,
In the detection content evaluation unit,
If both the part where the metal temperature rises and the part where it falls are included,
Or when the metal temperature of the heat exchanger arranged upstream of the gas is changing with respect to the heat exchanger with the largest metal temperature change width,
Or when the change width of the metal temperature becomes larger as time passes from the abnormality detection,
A boiler tube leak detection apparatus characterized by determining that tube leak has occurred. In the boiler tube leak detection device according to any one of claims 1 to 7 ,
In the detection content evaluation unit, a past case database in which events that occurred in the past and a change width of each metal temperature are stored in association with each other, and a metal temperature change width from cases stored in the past case database are stored. A boiler tube leak detection device comprising a detection content estimation unit for extracting a case where a square error is minimized. In the boiler tube leak detection device according to any one of claims 1 to 8 ,
The detection content evaluation unit is equipped with a function of evaluating the degree of tube leak based on the change width of the metal temperature, and determining whether the operation of the plant is continued, reduced in output, or stopped based on the degree of tube leak. Boiler tube leak detection device. In the boiler tube leak detection apparatus according to any one of claims 1 to 9 ,
In the detection content evaluation unit,
A detection content estimation unit is provided that calculates a change range of the metal temperature before and after detection by the detection unit, and extracts a portion where the metal temperature decrease width is maximum as a tube leak occurrence location,
A boiler characterized by displaying at least one of information on a metal temperature change width calculated by the detection content estimation unit or information for confirming an extracted tube leak occurrence location on a CAD drawing on an image display device. Tube leak detection device. In the data monitoring center provided with the boiler tube leak detection device according to any one of claims 1 to 10 ,
The data monitoring center, the plurality of power plants and the load adjustment department are connected to each other by an information communication network,
The data monitoring center includes a transmission information determination unit that evaluates the possibility of an increase in output of another power plant and determines a load demand value of each plant when a boiler tube leak occurs in a specific power plant. A data monitoring center characterized by In the information provision service using the boiler tube leak detection device according to any one of claims 1 to 10 ,
At least one of the boiler tube leak detection information from the boiler tube leak detection device to the corresponding boiler plant, or the operation schedule information including the load request value of each plant obtained based on the detection information from the data monitoring center. Information service characterized by providing. Using a measurement signal obtained by measuring the state quantity of the boiler plant, a state change detection step for detecting a change in the operating state of the boiler plant;
A boiler tube leak detection method including a detection content evaluation step for evaluating whether the change detected in the state change detection step is a leak,
A boiler characteristic calculation step of calculating a metal temperature from at least one condition of a fuel flow rate, an air flow rate, or a feed water flow rate that is a measurement signal of the state quantity;
The state change detection step includes:
A monitoring data extraction step of grouping first measurement signal data, which is data in a period defined as normal, from the past measurement signal as a monitoring group in units of data items;
An operation pattern evaluation step for identifying an operation pattern of the boiler plant;
A classification step of the each monitoring group and for each of the operation pattern, to construct a diagnostic model to classify the first measurement signal data belonging to the grouped data item,
A detection step of detecting that the driving state has changed by comparing the second measurement signal data which is data of a period to be diagnosed with the diagnostic model;
Look containing a metal temperature of a plurality of heat exchangers as a data item to be used for the monitoring group,
The boiler tube leak detection method characterized in that the monitoring data extraction step inputs data from the measurement signal of the state quantity and the calculation result of the boiler characteristic calculation step . In a boiler plant having a plurality of heat exchangers, a device for measuring a state quantity of the boiler plant, and an operation control device for controlling the boiler plant,
The operation control device includes:
A measurement signal database in which measurement signals transmitted from the device for detecting the state quantity are stored for each data item;
A boiler characteristic calculator that calculates a metal temperature from at least one condition of a fuel flow rate, an air flow rate, or a feed water flow rate stored in the measurement signal database;
A state change detection unit that outputs a change in the operating state of the boiler plant as diagnosis result data based on the measurement signal input from the measurement signal database;
The diagnosis result data is input, the detection state evaluation unit that evaluates whether the operating state change is a leak, and outputs the detection content estimation result data; and
An image display device for pre-displaying the dangerous intellectual content estimated data,
The state change detection unit
Monitoring data extraction unit that outputs first measurement signal data that is data of a period defined as normal from the measurement signal database, and outputs monitoring group data obtained by grouping a part of the data items as a monitoring group;
The monitoring group data is input, an operation pattern evaluation unit that identifies the operation pattern of the boiler plant based on the monitoring group data, and outputs operation pattern evaluation result data;
The operation pattern evaluation result data and the monitoring group data is input, for each of the operation pattern for each and the monitoring group, it outputs a diagnostic model to classify the first measurement signal data belonging to the grouped data items A classification unit to
Second measurement signal data that is data stored in the measurement signal database, grouped by the monitoring data extraction unit, and identified by the operation pattern evaluation unit is input, and the diagnosis model is further input. It is, detects that the operation state has changed by comparing said second measurement signal data and the diagnostic model, the detection unit is provided for outputting the diagnosis result data,
The data item grouped by the monitoring data extraction unit includes the metal temperature of the plurality of heat exchangers of the boiler plant ,
The boiler plant characterized in that the monitoring data extraction unit inputs data from calculation results of the measurement signal database and the boiler characteristic calculation unit .