Steam trap diagnostic system

Abstract

To provide a diagnostic device or the like for improving accuracy of gas leakage determination of a steam trap.SOLUTION: A diagnostic device includes: measurement means that measures vibration of a trap to be diagnosed and calculates first vibration data from measurement data; estimation means that estimates a drain amount of the trap to be diagnosed on the basis of the first vibration data; acquisition means that acquires a pressure value of the trap to be diagnosed; storage means that stores first relationship information in which a pressure value of the trap in a normal state in which there is no leakage of gas is associated with a determination threshold value, and second relationship information in which a pressure value of the trap in a state in which there is leakage of gas, and a drain amount is equal to or greater than a predetermined amount is associated with the determination threshold value; first determination means that specifies a determination threshold value based on the acquired pressure value on the basis of the first relationship information and performs leakage determination of the gas to be diagnosed on the basis of the first vibration data and the determination threshold value; and display means that displays a determination result by the first determination means and the drain amount. The first determination means executes the leakage determination again on the basis of the second relationship information in response to the satisfaction of a predetermined condition.SELECTED DRAWING: Figure 10

Description

[Technical Field]

[0001] The present invention relates to a diagnostic device for a steam trap. [Background technology]

[0002] In steam piping systems such as steam plants, steam condenses and generates drain (condensate). The generated drain is discharged to the outside using a steam trap or similar device. Steam traps can sometimes develop abnormalities such as steam leaks. For this reason, inspectors move to each steam trap and perform a diagnosis using diagnostic equipment.

[0003] One diagnostic device is a quality determiner that detects vibrations associated with steam trap operation and determines whether the trap is operating properly, such as for steam leakage (see, for example, Patent Document 1). The quality determiner described in Patent Document 1 pre-stores the relationship between vibration level and steam system pressure, and automatically determines whether or not there is a steam leakage by comparing the detected vibration level with this relationship. The quality determiner described in Patent Document 1 also has a configuration in which the relationship is corrected based on the condensate load factor. The condensate load factor is the ratio between the maximum amount of drain that a steam trap can discharge and the actual amount of drain.

[0004] That is, the above-mentioned automatic steam leak detection is performed based on vibration values, the amount of drain, etc. This is because vibrations (ultrasonic vibrations) occur in a steam trap when drain flows, and vibrations also occur when gas such as steam leaks. Some automatic steam leak detection systems use, for example, the amount of drain calculated (estimated) based on the measured vibration values.

[0005] Regarding flow rate, there is a simple flow rate measuring device that stores the relationship between flow rate and vibration in advance, and converts and displays the approximate flow rate flowing down a valve with a specified opening from the measured vibration and the above relationship (see, for example, Patent Document 2). [Prior art documents] [Patent documents]

[0006] [Patent Document 1] Japanese Patent Application Publication No. 08-004993 [Patent Document 2] Japanese Patent Application Publication No. 09-196716 Summary of the Invention [Problem to be solved by the invention]

[0007] In the automatic steam leak detection described above, the detection is based on the magnitude of the measured vibration. However, because the magnitude of the vibration is also affected by the amount of drain, there are cases where the detection result changes depending on the amount of drain even when a steam leak actually occurs. In other words, there are cases where the detection result is normal even when a steam leak actually occurs. There are also cases where the amount of drain cannot be accurately estimated from the measured vibration.

[0008] An object of the present invention is to provide a diagnostic device or the like that improves the accuracy of gas leakage determination in a steam trap. [Means for solving the problem]

[0009] A first aspect of the present invention provides a steam trap diagnostic device that includes: a measuring means for measuring vibrations of a steam trap to be diagnosed and calculating first vibration data from the measured data; an estimating means for estimating the amount of drainage of the target trap based on the first vibration data; an acquiring means for acquiring a pressure value of the target trap; a memory means for storing first relationship information correlating the pressure value of the steam trap in a normal state with no gas leakage with a judgment threshold and second relationship information correlating the pressure value of the steam trap in a state with gas leakage and a predetermined amount of drainage or more with the judgment threshold; a first determining means for identifying the judgment threshold based on the acquired pressure value based on the first relationship information and determining whether the target trap is leaking gas based on the first vibration data and the judgment threshold; and a display means for displaying the result of the determination by the first determining means, i.e., the amount of drainage. When a predetermined condition is met, the first determining means performs a leakage determination again based on the second relationship information instead of the first relationship information.

[0010] The diagnostic device may further include a first input receiving means for receiving an input for executing a judgment based on the second relationship information, and the predetermined condition may include that the input for executing a judgment has been received.

[0011] The diagnostic device may further include a second determination means for determining the validity of executing a leak determination based on the second relationship information of the object to be diagnosed from the diagnostic data related to the object to be diagnosed, based on a learning model trained with diagnostic data related to leak determination, including second vibration data and a pressure value related to the steam trap, and teacher data including the validity of executing a leak determination based on the second relationship information of the steam trap, wherein the measurement means calculates the second vibration data from the measurement data, and the display means displays the determination result by the second determination means in addition to the determination result and drain amount by the first determination means.

[0012] The diagnostic device may further include a second determination means for determining the validity of execution of a leak determination based on the second relationship information of the object to be diagnosed from the diagnostic data related to the object to be diagnosed, based on a learning model trained with teacher data including diagnostic data related to leak determination, which includes second vibration data and a pressure value related to the steam trap, and validity of execution of a leak determination based on the second relationship information of the steam trap, and the measurement means may calculate the second vibration data from the measurement data, and the predetermined condition may include being determined to be valid by the second determination means.

[0013] The storage means may store the first relationship information for each drain amount, and the determination means may make a leakage determination based on the first relationship information corresponding to the estimated drain amount.

[0014] The above-mentioned diagnostic device may further include a specifying means for specifying, based on the first relationship information, whether or not the first vibration data belongs to a region in which the determination result by the determining means varies depending on the magnitude of the drain amount, and a second input accepting means for accepting an input to change the drain amount of the object to be diagnosed, wherein the display means displays the determination result by the specifying means in addition to the determination result and the drain amount by the first determining means, and when an input to change the drain amount is accepted, the determining means may re-execute the leakage determination based on the first relationship information corresponding to the drain amount for which the input to change has been accepted, instead of the estimated drain amount.

[0015] A second aspect of the present invention provides a steam trap diagnostic program that causes a computer of a steam trap diagnostic device to function as: a measuring means that measures the vibration of the steam trap to be diagnosed and calculates first vibration data from the measurement data; an estimating means that estimates the amount of drainage of the steam trap based on the first vibration data; an acquiring means that acquires the pressure value of the steam trap; a memory means that stores first relationship information correlating the pressure value of the steam trap in a normal state with no gas leakage with a judgment threshold and second relationship information correlating the pressure value of the steam trap in a state with gas leakage and a predetermined amount of drainage or more with the judgment threshold; a first determining means that identifies the judgment threshold based on the acquired pressure value based on the first relationship information and determines whether the steam trap is leaking gas based on the first vibration data and the judgment threshold; and a display means that displays the result of the determination by the first determining means, i.e., the amount of drainage. When a predetermined condition is met, the first determining means re-executes the leakage determination based on the second relationship information instead of the first relationship information.

[0016] A third aspect of the present invention provides a steam trap diagnostic system comprising: a measuring means for measuring vibrations of a steam trap to be diagnosed and calculating first vibration data from the measured data; an estimating means for estimating the amount of drainage of the target trap based on the first vibration data; an acquiring means for acquiring a pressure value of the target trap; a memory means for storing first relationship information correlating the pressure value of the steam trap in a normal state with no gas leakage with a judgment threshold and second relationship information correlating the pressure value of the steam trap in a state with gas leakage and a predetermined amount of drainage or more with the judgment threshold; a first determining means for identifying the judgment threshold based on the acquired pressure value based on the first relationship information and for determining whether the target trap is leaking gas based on the first vibration data and the judgment threshold; and a display means for displaying the result of the determination by the first determining means, i.e., the amount of drainage. When a predetermined condition is met, the first determining means performs a leakage determination again based on the second relationship information instead of the first relationship information. [Effects of the Invention]

[0017] According to this invention, after a leak determination is made for the object to be diagnosed based on first relationship information correlating the pressure value of a steam trap in a normal state with no gas leakage with a determination threshold, a second leak determination is made for the object to be diagnosed based on second relationship information correlating the pressure value of a steam trap in a state where there is gas leakage and the amount of drain is equal to or greater than a predetermined amount with a determination threshold, depending on whether a predetermined condition is met. In other words, the second leak determination is made based on second relationship information optimized for a steam trap in a state where there is gas leakage and the amount of drain is equal to or greater than a predetermined amount. This makes it possible to perform the above-mentioned second leak determination for the object to be diagnosed that is suspected to be in the above state, thereby improving the accuracy of the leak determination. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a configuration diagram of a diagnostic system according to an embodiment of the present invention. [Figure 2] 1 is an external view of a diagnostic machine according to an embodiment of the present invention; [Figure 3]1 is a schematic diagram showing a state during diagnosis by a diagnostic machine according to an embodiment of the present invention; [Figure 4] 10 is a graph illustrating first relationship information in which pressure values ​​of a steam trap are associated with determination thresholds. [Figure 5] 10 is a graph illustrating second relationship information in which the pressure value of the steam trap is associated with the determination threshold value. [Figure 6] 1 is a table for explaining the vibration state of a steam trap. [Figure 7] 10 is a graph illustrating the relationship between first relationship information in which pressure values ​​of a steam trap are associated with determination thresholds, and the relationship between pressure values ​​and regions. [Figure 8] FIG. 1 is a diagram showing an overview of a learning model according to an embodiment of the present invention. [Figure 9] FIG. 4 is a diagram showing an example of a diagnosis result screen displayed on a diagnostic machine (liquid crystal display) according to an embodiment of the present invention. [Figure 10] 3 is a flowchart showing a diagnostic process according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0019] A diagnostic system (diagnostic device, diagnostic program) according to an embodiment of the present invention will be described with reference to the drawings. Note that the configuration of the present invention is not limited to the embodiment. Furthermore, the order of various processes constituting the flow described below may be random as long as no inconsistencies occur in the process content.

[0020] 1 is a schematic diagram of a diagnostic system 100 according to an embodiment of the present invention. The diagnostic system 100 includes a diagnostic machine 10, a terminal device (management terminal) 20, and a server device 30. The diagnostic machine 10 and the terminal device 20 can communicate with each other wirelessly within a communication range using a communication method such as Bluetooth (registered trademark). The terminal device 20 and the server device 30 are connected to each other so as to be able to communicate with each other via a communication network N such as the Internet.

[0021] Diagnostic system 100 diagnoses steam traps. In the diagnosis, a leak determination (automatic determination) of steam (gas) from the steam trap is performed. The steam trap is, for example, a float-type steam trap, and is arranged in a steam piping system of a steam plant. The steam trap is configured to automatically discharge drain (condensate) generated by steam condensation downstream, but to confine the steam within the steam trap so that it does not escape. The leak determination by diagnostic system 100 determines whether steam within the steam trap is leaking to the outside. In the diagnosis, the vibration value and other parameters of the steam trap to be diagnosed are measured, and then the leak determination is performed. For example, the diagnosis is performed when an inspector inputs a diagnosis request into terminal device 20. Hereinafter, the steam trap to be diagnosed may be simply referred to as the diagnosis target.

[0022] In this embodiment, the diagnostic device 10 performs the leak determination. The diagnostic device 10 performs the leak determination based on the ultrasonic vibration (vibration value), pressure value, drain amount, etc. of the diagnostic object. In the leak determination, if it is determined that no steam leak has occurred, the determination result is "normal," and if it is determined that a steam leak has occurred, the determination result is "leak." The vibration value is measured by the diagnostic device 10. The drain amount is the amount of drain discharged per predetermined time in the steam trap. There are two types of drain amount used in the diagnosis of this embodiment: a "large" drain amount and a "small" drain amount. In this embodiment, the drain amount (estimated drain amount) estimated (calculated) by the diagnostic device 10 is used for the leak determination.

[0023] The diagnostic system 100 of this embodiment includes a first leakage determination that is always performed in the diagnosis, and a second leakage determination and a third leakage determination that can be performed after the first leakage determination. After performing the first leakage determination, the inspector (user) can perform the second leakage determination and / or the third leakage determination as needed. In the first leakage determination, first relationship information optimized for a steam trap in a normal state is used for the determination. In the second leakage determination, the first relationship information is used as in the first leakage determination, but the drain amount changed and input by the inspector is used instead of the estimated drain amount. In the third leakage determination, second relationship information is used for the determination instead of the first relationship information. The second relationship information is relationship information optimized for a steam trap that is leaking steam and has a drain amount equal to or greater than a predetermined amount. Details will be described later.

[0024] <Diagnostic machine configuration> 2 is an external view of diagnostic machine 10. Diagnostic machine (diagnostic device) 10 performs steam leakage determination (first leakage determination to third leakage determination) of the object to be diagnosed. Diagnostic machine 10 has a vibration measurement unit 11, a temperature measurement unit 12, a memory unit 13, a calculation unit 14, a communication unit 15, input buttons 16, a liquid crystal display 17, etc.

[0025] The vibration measurement unit 11 measures ultrasonic vibrations (vibrations) of the diagnostic object. As shown in FIG. 2, the vibration measurement unit 11 is provided at the tip of a rod-shaped probe 10a. Vibration measurement by the vibration measurement unit 11 can be performed by bringing the probe 10a into contact with the diagnostic object (see, for example, FIG. 3). The vibration measurement unit 11 includes a known ultrasonic detection element (for example, a piezoelectric element). In this embodiment, in one vibration measurement, measurement of ultrasonic vibrations is performed once for a predetermined period (for example, 15 seconds). The measurement data measured by the vibration measurement unit 11 is stored in the memory unit 13. Furthermore, the calculation unit 14 calculates the RMS (Root Mean Square) of the vibration from the measurement data as a vibration value (first vibration data). Note that a value other than the RMS may be used as the vibration value as long as it can be used for leak detection, etc.

[0026] The temperature measuring unit 12 measures the temperature (surface temperature) of the diagnostic object. As shown in FIG. 2, the temperature measuring unit 12 is provided at the tip of a rod-shaped probe 10a. By bringing the probe 10a into contact with the diagnostic object (see, for example, FIG. 3), the temperature measuring unit 12 can measure the temperature. The temperature measuring unit 12 includes a known temperature measuring element (for example, a thermocouple). The measurement data measured by the temperature measuring unit 12 is stored in the memory unit 13. The calculation unit 14 calculates the temperature value from the measurement data.

[0027] The memory unit 13 is, for example, a semiconductor memory (such as a flash memory). The memory unit 13 stores, for each drain amount, first relationship information in which the pressure value of the steam trap in a normal state where there is no steam leakage is associated with a judgment threshold. The first relationship information is used for leak judgment (first leak judgment, second leak judgment). FIG. 4 is a graph for explaining first relationship information in which the pressure value is associated with the judgment thresholds α and β. That is, FIG. 4 is a graph for explaining first relationship information in which the pressure value is associated with the judgment threshold α (corresponding to a drain amount of "small"), and first relationship information in which the pressure value is associated with the judgment threshold β (corresponding to a drain amount of "large"). The horizontal axis of the graph indicates the vibration value, and the vertical axis indicates the pressure value.

[0028] The judgment threshold value α is used for the first and second leak judgments when the drain amount is "small." The judgment threshold value β is used for the first and second leak judgments when the drain amount is "large." As shown in FIG. 4, the judgment threshold values ​​α and β become larger as the pressure value of the steam trap increases. Furthermore, even for the same pressure value, the values ​​of the judgment threshold values ​​α and β differ. In other words, the judgment threshold value is determined based on the pressure value and the drain amount. Then, if the measured vibration value of the diagnosis object exceeds the judgment threshold value, it is determined that a steam leak has occurred in the diagnosis object.

[0029] For example, if the object to be diagnosed has a pressure value P1 and a drain amount "small," a judgment threshold α1 is determined. If the vibration value exceeds the judgment threshold α1, it is determined to be a "leak." On the other hand, if the vibration value is equal to or less than the judgment threshold α1, it is determined to be "normal." Also, if the steam trap has a pressure value P1 and a drain amount "large," a judgment threshold β1 is determined. If the vibration value exceeds the judgment threshold β1, it is determined to be a "leak." On the other hand, if the vibration value is equal to or less than the judgment threshold β1, it is determined to be "normal."

[0030] The first relationship information is, for example, received from the terminal device 20 and stored in the storage unit 13. The relationship information is, for example, function information.

[0031] The memory unit 13 also stores second relationship information that correlates the pressure value of a steam trap in a state where there is a gas leak and the amount of drain is equal to or greater than a predetermined amount with a judgment threshold. The second relationship information is used for the third leakage judgment. The above-mentioned first relationship information is relationship information optimized for a steam trap in a normal state where there is no gas leak. On the other hand, the second relationship information is relationship information optimized for a steam trap in a state where there is a gas leak and the amount of drain is equal to or greater than a predetermined amount. Figure 5 is a graph for explaining the second relationship information that correlates the pressure value with the judgment threshold γ. The judgment threshold γ is used for the third leakage judgment regardless of the amount of drain. In other words, the amount of drain is not referenced in the third leakage judgment. Figure 5 also displays the judgment thresholds α and β of the first relationship information.

[0032] The state in which there is a gas leak and the amount of drain is equal to or greater than a predetermined amount is state S4 shown in Figure 6. That is, the third leakage determination (second relationship information) is a determination for a steam trap in state S4 shown in Figure 6. Figure 6 is a table showing the relationship between the state of the steam trap and the state of the drain, and the relative magnitude of the vibration (vibration value) of the steam trap. In the table of Figure 6, the horizontal axis represents the state of the steam trap (presence or absence of leakage) and the vertical axis represents the state of the drain in the steam trap (amount of drain). Figure 6 shows the results of measuring actual vibration (vibration value) by changing the amount of drain at the same pressure value P1 using a steam trap with and without leakage of the same model.

[0033] 6 indicates that the ratio of the drain amount to the maximum processing flow rate of the steam trap is less than 10%. Also, the drain amount of "medium to large" in FIG. 6 indicates that the ratio is 10% or more, which corresponds to the drain amount of "large" in this embodiment.

[0034] In a normal steam trap, the vibration value for a drain amount of "none to small" is "small" (state S1), and the vibration value for a drain amount of "medium to large" is "relatively small" (state S3). The magnitude of the vibration is such that state S3 > state S1. In other words, even in a normal steam trap, vibration occurs when drain flows, and the vibration increases as the drain amount increases.

[0035] On the other hand, in a steam trap with a leak, the vibration value when the amount of drain is "none to small" is "relatively large" (state S2), and the vibration value when the amount of drain is "medium to large" is "relatively small to medium" (state S4). In other words, in a steam trap with a leak, vibration occurs due to the flow of leaking steam and drain. However, the magnitude of the vibration is in state S2 > state S4. In other words, in a steam trap with a leak, the vibration does not increase even if the amount of drain increases. When the amount of drain is "medium to large," the vibration due to the vibration caused by the steam and the vibration caused by the drain are buffered, so the vibration value does not increase beyond state S2 and fluctuates within the "relatively small to medium" range.

[0036] The states S1 to S4 of the steam trap described above have the relationship shown in Figure 5, for example, at pressure value P1. Figure 5 shows the range of vibrations (vibration values) that occur in states S1 to S4. In states S1 and S3, the first leakage determination is performed with the determination thresholds α1 and β1 or less, regardless of the amount of drainage. Therefore, the determination result is "normal." In addition, in state S2, the first leakage determination is performed with the determination thresholds α1 and β1 exceeded, regardless of the amount of drainage. Therefore, the determination result is "leak."

[0037] Furthermore, in the case of state S4, the range of vibration values ​​that occurs is wide, partially overlapping with the range of state S3. Therefore, even if a steam leak occurs in the steam trap, the first leak determination may result in a "normal" determination.

[0038] For example, in the case of a portion S4-1 of state S4 that overlaps with state S3, the first leakage determination will determine that the drain amount is equal to or less than the determination thresholds α1 and β1 regardless of the amount of drain. Therefore, the determination result of the first leakage determination will be determined as "normal." Also, even in the case of a portion S4-2 of state S4 that does not overlap with state S3, if the amount of drain is large, the value may be equal to or less than the determination threshold β1. Therefore, the determination result of the first leakage determination will be determined as "normal."

[0039] Therefore, the first leakage determination may result in an erroneous determination for a steam trap in state S4 as described above. Therefore, in this embodiment, when the object to be diagnosed is suspected to be in state S4 as described above, the third leakage determination is performed to improve the accuracy of the leakage determination. In the third leakage determination, the second relationship information is used to perform the leakage determination instead of the first relationship information. As described above, the second relationship information is relationship information that associates the pressure value of a steam trap in a state (state S4) where gas is leaking and the drain amount is equal to or greater than a predetermined amount (e.g., drain amount "medium" in FIG. 6 ) with a determination threshold. More specifically, the second relationship information is relationship information that associates the pressure value with a determination threshold so that when the third leakage determination is performed on an object to be diagnosed in state S4, the determination result will be "leak."

[0040] In the third leak determination, a determination threshold is identified based on the pressure value using the second relationship information, and if the vibration value exceeds the identified determination threshold, a "leak" is determined. For example, in FIG. 5, if the object to be diagnosed is a pressure value P1, a determination threshold γ1 is determined. If the vibration value exceeds the determination threshold γ1, a "leak" is determined. In other words, even if the object to be diagnosed is in state S4, the leak determination result will be "leak" by performing the third leak determination. Note that the drain amount is not referenced in the third leak determination. Therefore, even if the drain amount is not accurately estimated, the third leak determination is not affected.

[0041] In this embodiment, after the first leakage determination is performed, the third leakage determination is performed when a predetermined condition is met. The predetermined condition in this embodiment is that an input to perform the third leakage determination is received from an inspector. In addition, the third leakage determination is the same as the first leakage determination in terms of pressure values, vibration values, etc., except that the second relationship information is used.

[0042] The second relationship information is, for example, received from the terminal device 20 and stored in the storage unit 13. The relationship information is, for example, function information.

[0043] The storage unit 13 also stores relationship information in which the surface temperature (temperature value) and vibration value are associated with the amount of drainage. The relationship information is used to calculate the amount of drainage (estimated amount of drainage). The relationship information is received from the terminal device 20 and stored in the storage unit 13, for example. The relationship information is, for example, function information.

[0044] Furthermore, a program module of a learning model DL, which will be described later, is stored in the storage unit 13. As will be described later, the calculation unit 14 of the diagnostic machine 10 functions as the learning model DL.

[0045] The calculation unit 14 includes a CPU, memory (RAM), etc. The calculation unit 14 executes processing related to the diagnosis of the diagnosis object. Specifically, the calculation unit 14 calculates a vibration value from the measurement data of the vibration measured by the vibration measurement unit 11. The calculation unit 14 also calculates second vibration data from the measurement data of the vibration measured by the vibration measurement unit 11. The second vibration data is data obtained by subjecting the measurement data to a Fourier transform and breaking it down into frequency components. The calculation unit 14 calculates a temperature value from the measurement data measured by the temperature measurement unit 12.

[0046] The calculation unit 14 also calculates the magnitude of the drain amount (estimated drain amount) of the diagnosis target. Specifically, the calculation unit 14 first calculates the drain amount (amount of drain discharged per predetermined time) from the measured vibration value and temperature value based on relationship information in which temperature values ​​and vibration values ​​are associated with drain amounts. Note that the drain amount may be calculated based on the measured vibration value without using the temperature value, by referring to relationship information in which vibration values ​​are associated with drain amounts.

[0047] Next, the calculation unit 14 determines whether the calculated drain amount is large (second drain amount) or small (first drain amount). For example, the determination may be based on the ratio of the calculated drain amount to the maximum processing flow rate of the steam trap. Specifically, if the ratio is less than a reference value (10%), the estimated drain amount is determined as a "small" drain amount (first drain amount). If the ratio is equal to or greater than the reference value (10%), the estimated drain amount is determined as a "large" drain amount (second drain amount).

[0048] The magnitude of the drain amount (estimated drain amount) may be calculated using a value of 10% of the maximum processing flow rate as a reference value. In this case, if the calculated drain amount is less than the reference value, the estimated drain amount is specified as a "small" drain amount. If the calculated drain amount is equal to or greater than the reference value, the estimated drain amount is specified as a "large" drain amount.

[0049] The above-mentioned maximum processing flow rate and reference value may be received from the terminal device 20 and stored in the storage unit 13. Furthermore, since the vibration value, second vibration data, temperature value, and estimated drain amount are calculated by known methods, detailed explanations will be omitted.

[0050] The calculation unit 14 also performs a leak judgment (first leak judgment) for the object to be diagnosed based on the vibration value, pressure value, and drain amount. The vibration value used is the measured (calculated) vibration value described above. The pressure value is, for example, a value indicating the pressure (inlet pressure) inside the steam trap. The pressure value used is, for example, a value input by an inspector via the terminal device 20. For example, the inspector may input a pressure value measured by another device or an estimated pressure value. The drain amount used is the estimated drain amount calculated above. The calculation unit 14 determines a judgment threshold from the first relationship information, the pressure value, and the drain amount (estimated drain amount), and performs a first leak judgment by comparing the vibration value. As described above, if the vibration value is equal to or less than the judgment threshold, it is judged as "normal," and if the vibration value is greater than the judgment threshold, it is judged as "leak."

[0051] Furthermore, the calculation unit 14 identifies the region to which the measured vibration value belongs. Specifically, as shown in FIG. 7, it is identified which of the regions R1 to R3 the vibration value belongs to. Region R1 is a region in which the first leakage determination results in a normal determination regardless of the amount of drainage. Region R2 is a region in which the determination result in the first leakage determination differs depending on the amount of drainage. Region R3 is a region in which the first leakage determination results in a leakage determination regardless of the amount of drainage. As shown in FIG. 7, regions R1 to R3 are formed based on relationship information correlating pressure values ​​with determination thresholds α and β and the pressure value of the diagnosis target. FIG. 7 is a graph for explaining the relationship between the relationship information correlating pressure values ​​with determination thresholds α and β, the pressure value, and the region. FIG. 7 shows an example of regions R1 to R3 for the graph shown in FIG. 4.

[0052] The calculation unit 14 identifies which of the regions R1 to R3 the vibration value belongs to based on the pressure value and first relationship information in which the pressure value is associated with the determination thresholds α and β. Note that the result of the calculation unit 14 identifying the region to which the vibration value belongs may be referred to as an identification result.

[0053] An example will be described where the diagnosis target is a pressure value P1. In this case, region R1 is the range where the vibration value is equal to or less than the judgment threshold value α1. Region R2 is the range where the vibration value is greater than the judgment threshold value α1 and equal to or less than the judgment threshold value β1. Region R3 is the range where the vibration value is greater than the judgment threshold value β1.

[0054] For example, let us consider a case where the vibration value of the diagnostic object belongs to region R1. In this case, the judgment result will be "normal" whether the drain amount of the diagnostic object is large or small. This is because vibration values ​​that belong to region R1 are equal to or smaller than the judgment threshold values ​​α1 and β1. In other words, when the vibration value belongs to region R1, the judgment result will be "normal" regardless of the amount of drain.

[0055] Next, we will explain the case where the vibration value of the steam trap belongs to region R2. In this case, if the amount of drainage to be diagnosed is large, the judgment threshold value becomes β1 and the judgment result is "normal". This is because vibration values ​​belonging to region R2 are equal to or smaller than the judgment threshold value β1. On the other hand, if the amount of drainage to be diagnosed is small, the judgment threshold value becomes α1 and the judgment result is "leak". This is because vibration values ​​belonging to region R2 are greater than the judgment threshold value α1. Therefore, when the vibration value belongs to region R2, the judgment result will differ depending on the amount of drainage to be diagnosed.

[0056] Next, we will explain the case where the vibration value of the diagnostic object belongs to region R3. In this case, the judgment result will be "leak" whether the drain amount of the diagnostic object is large or small. This is because the vibration values ​​that belong to region R3 are larger than the judgment threshold values ​​α1 and β1. In other words, when the vibration value belongs to region R3, the judgment result will be "leak" regardless of the size of the drain amount.

[0057] As described above, the calculation unit 14 identifies the region to which the vibration value belongs, allowing the inspector to identify whether or not a change in the amount of drainage is likely to change the judgment result. For example, the inspector can take the judgment result, the amount of drainage, and the identification result into consideration and subsequently select a course of action, such as changing the amount of drainage and conducting a leak judgment again (second leak judgment). Details will be described later.

[0058] Furthermore, after performing the first leakage determination, the calculation unit 14 performs another leakage determination (second leakage determination and third leakage determination). The second leakage determination is performed when an input for changing the drain amount is received. The calculation unit 14 performs the second leakage determination using the changed drain amount instead of the estimated drain amount. The input for changing the drain amount is performed, for example, by the inspector operating the input button 16 of the diagnostic machine 10. In the case of the second leakage determination, the first relationship information is used, and the previous values ​​for the vibration value, pressure value, etc. are used. The determination method is the same as that of the first leakage determination.

[0059] The third leak determination is performed when a predetermined condition is met. In this embodiment, the predetermined condition is that an input to perform the third leak determination has been received from the inspector. The input to perform the third leak determination is performed, for example, by the inspector operating the input button 16 of the diagnostic machine 10. The calculation unit 14 performs the third leak determination using the second relationship information instead of the first relationship information. In the case of the third leak determination, the same values ​​as those used for the first leak determination are used for the vibration value, pressure value, etc. The calculation unit 14 determines a determination threshold from the second relationship information and the pressure value, and performs a leak determination by comparing it with the vibration value. As described above, if the vibration value is equal to or less than the determination threshold, it is determined to be "normal," and if the vibration value is greater than the determination threshold, it is determined to be "leak."

[0060] Furthermore, the calculation unit 14 determines the validity of executing the third leakage determination for the object to be diagnosed from the diagnostic data related to the leakage determination for the object to be diagnosed based on the learning model DL. That is, it determines whether or not it is valid to execute the third leakage determination for the object to be diagnosed. As described above, the third leakage determination is a leakage determination for a steam trap in state S4. Therefore, the calculation unit 14 determines the determination result as "valid" when the steam trap to be diagnosed is estimated to be in state S4.

[0061] The learning model DL is a neural network that has undergone machine learning (e.g., deep learning) using a large amount of training data. For example, as shown in FIG. 8, the learning model DL is composed of an input layer DL11, an intermediate layer DL12, and an output layer DL13. Diagnostic data related to leak determination of the object to be diagnosed is input to the input layer DL. The diagnostic data is data acquired by measurement or the like in diagnosing the leak determination. In this embodiment, the model, second vibration data, and pressure value of the object to be diagnosed are included in the diagnostic data.

[0062] In the intermediate layer DL12, parameters (weights, etc.) tuned by the above-mentioned learning are set so that the validity of the third leak determination of the diagnosis target is output from the output layer DL13. When the above-mentioned diagnostic data is input to the input layer DL11, the output layer DL13 outputs the validity of the third leak determination. For example, information specifying either "valid" or "invalid" (for example, as a numerical value, valid: 1, invalid: 0) is output

[0063] The learning model DL is generated, for example, by using training data in the server device 30. The training data is data including, for example, diagnostic data related to leak determination, including the steam trap model, second vibration data, and pressure values, and the effectiveness of executing leak determination based on the second relationship information for the steam trap. The process of generating the learning model will be described later.

[0064] Furthermore, the diagnostic data input to the learning model DL is not limited to the above-mentioned type, second vibration data, etc. For example, first vibration data (vibration value) may be used instead of the second vibration data. Furthermore, for example, the drain amount may be included in the diagnostic data. Furthermore, if there are not multiple types of steam traps, the type need not be included in the diagnostic data.

[0065] Note that the learning model DL may be a model based on various learning algorithms, such as a convolution neural network (CNN), a support vector machine (SVM), or a decision tree.

[0066] The vibration measurement unit 11 and calculation unit 14 described above correspond to a measurement means that measures the vibration of the steam trap to be diagnosed and calculates first vibration data and second measurement data from the measurement data. The calculation unit 14 also corresponds to an estimation means that estimates the amount of drain and a first determination means that performs a leakage determination. Furthermore, the calculation unit 14 also corresponds to a second determination means that determines the validity of the third leakage determination and a determination means that identifies the region to which the vibration value belongs.

[0067] The calculation unit 14 also controls the display of the liquid crystal display 17. For example, the calculation unit 14 causes the liquid crystal display 17 to display the determination results and the like.

[0068] The communication unit 15 has a communication circuit compatible with Bluetooth (registered trademark) or the like, and transmits and receives various information to and from the terminal device (communication unit 24). For example, information relating to the performed diagnosis (vibration value, second vibration data, temperature value, pressure value, drain amount, vibration and temperature measurement data, determination results, etc.) is transmitted to the terminal device 20 (communication unit 24). In this embodiment, when the second leakage determination and the third leakage determination are performed, information specifying that they have been performed is also transmitted to the terminal device 20 (communication unit 24) as information relating to the above diagnoses. For example, flag A is transmitted as information specifying that they have been performed. Flag A is set to a value of 1 when the second leakage determination is performed, and a value of 2 when the third leakage determination is performed. Flag A: 0 indicates that the first leakage determination has been performed. The initial value of flag A may be set to 0.

[0069] Furthermore, for example, the communication unit 15 receives a diagnosis request including various parameters, pressure values, etc. based on the model of the object to be diagnosed from the terminal device 20 (communication unit 24). The received information is stored in the memory unit 13. The various parameters based on the model include the first relationship information, second relationship information, etc. exemplified in FIG. 4, etc. The communication unit 15 corresponds to an acquisition means for acquiring the pressure value of the steam trap.

[0070] Although the communication method used is Bluetooth (registered trademark), it is not limited to this. As long as it is possible to communicate with the terminal device 20, various communication methods such as Wi-Fi can be applied.

[0071] The input button 16 accepts inputs such as operations to switch the information displayed on the liquid crystal display 17. The input button 16 also corresponds to a first input accepting means for accepting an input to execute a third leakage determination, and a second input accepting means for accepting an input to change the drain amount. Furthermore, the input button 16 accepts an input to request another diagnosis of the diagnosis target, and an input to confirm the diagnosis of the diagnosis target (save input). The save input is performed to end the diagnosis, confirm the leakage determination result, and save information related to the diagnosis, including the determination result, etc.

[0072] The liquid crystal display (display means) 17 displays various information necessary for the work. For example, when a diagnosis of a diagnostic object is performed, the liquid crystal display 17 displays various information related to the diagnosis as shown in FIG. 9. FIG. 9 is a diagram showing an example of a diagnostic result screen displayed on the liquid crystal display 17. The diagnostic result screen includes, for example, display areas 301 to 304. The display area 301 displays the result of the leak determination (normal, leak) and the temperature (temperature value) of the diagnostic object. The result of the leak determination most recently performed is displayed as the result of the leak determination. For example, when a first leak determination is performed, the result of the first leak determination is displayed. When a third leak determination is subsequently performed, the result of the third leak determination is displayed. The display area 302 displays the pressure (pressure value) of the diagnostic object. The display area 303 displays the drain amount (large, small) used in the leak determination and the identification result (the area to which the vibration value belongs). The display area 304 displays the result of the determination of the validity (valid, invalid) of the execution of the third leak determination of the diagnostic object.

[0073] For example, the inspector can input a change to the drain amount, input an input to execute a third leakage determination, input a request for another diagnosis, and input a save input while the diagnosis result screen is displayed on the liquid crystal display 17. When a change to the drain amount is input, the display of the drain amount in the display area 303 is also updated.

[0074] The identification results in the display area 303 are displayed in a different color (e.g., red) from the other characters and in bolder font than the other characters. That is, the identification results are highlighted. Also, the identification results may be highlighted only when the vibration value belongs to area R2. The determination results in the display area 304 are also highlighted. Also, the vibration value may be displayed on the diagnosis result screen.

[0075] <Configuration of terminal device> The terminal device 20 is, for example, a portable tablet computer. The inspector carries the terminal device 20 together with the diagnostic machine 10. The terminal device 20 executes an application program in the storage unit 22 to cause the diagnostic machine 10 to perform a diagnosis or the like in response to inputs from the inspector, and also transmits (uploads) information such as the leak determination results to the server device 30. The terminal device 20 has a touch panel 21, a storage unit 22, a calculation unit 23, a communication unit 24, etc.

[0076] The touch panel 21 is composed of a display unit such as a liquid crystal panel and an input unit such as a touchpad. The touch panel 21 functions as an input / output interface for the inspector. For example, the inspector can input the steam trap model, pressure value, diagnostic request, etc. into the touch panel 21, which displays an operation input screen. The touch panel 21 also displays a diagnostic result screen for the steam trap. The diagnostic result screen displays information such as the leak determination results.

[0077] The storage unit 22 stores the above-mentioned application program, various steam trap parameters, etc., for each steam trap model. For example, first relationship information, second relationship information, and relationship information in which the surface temperature and vibration values ​​are associated with the drain amount are stored in the storage unit 22 for each steam trap model. Also, for example, the above-mentioned maximum processing flow rate, reference values, etc. are stored in the storage unit 22 for each steam trap model. The storage unit 22 also stores various information related to diagnosis, such as the leakage determination results received from the diagnostic machine 10. The storage unit 22 is a semiconductor memory (for example, a flash memory).

[0078] The calculation unit 23 controls the display of the touch panel 21. The calculation unit 23 displays, for example, the above-mentioned operation input screen and diagnosis result screen on the touch panel 21. The calculation unit 23 includes a CPU, a memory (RAM), and the like.

[0079] The communication unit 24 has a communication circuit compatible with Bluetooth (registered trademark), Wi-Fi, etc. The communication unit 24 transmits and receives various information to and from the diagnostic machine 10 (communication unit 15). For example, the communication unit 24 transmits to the diagnostic machine 10 a diagnosis request including various parameters, pressure values, etc. based on the model of the diagnostic target. Furthermore, for example, the communication unit 24 receives information related to the executed diagnosis (vibration value, second vibration data, temperature value, pressure value, drain amount, vibration and temperature measurement data, determination result, flag A, etc.) from the diagnostic machine 10. The terminal device 20 stores the received various information in the storage unit 22. Furthermore, the communication unit 24 transmits and receives various information to and from the server device 30 (communication unit 33) via the network N. For example, the communication unit 24 transmits information related to the diagnosis, such as the leakage determination result, to the server device 30. For example, information related to the diagnosis for one day is transmitted collectively to the server device 30 after the diagnostic work for that day is completed.

[0080] <Configuration of Server Device> The server device 30 transmits and receives various types of information to and from the terminal device 20 (communication unit 24) via the communication unit 33, and stores and manages various types of information about the steam trap, such as the determination results. The server device 30 is, for example, a cloud server existing on a network (in a cloud environment). The server device 30 includes a storage unit 31, a calculation unit 32, a communication unit 33, etc.

[0081] The storage unit 31 is a large-capacity storage device such as a hard disk. The storage unit 31 stores various types of information about the object to be diagnosed (the steam trap). In this embodiment, in the diagnostic system 100, the information stored in the storage unit 31 of the server device 30 is positioned as master data. The various types of information about the steam trap are stored, for example, in association with the management number of the steam trap.

[0082] The calculation unit 32 updates various information stored in the storage unit 31. For example, when a new judgment result of a diagnostic object is received, the calculation unit 32 adds the new judgment result to the information of the corresponding diagnostic object. The calculation unit 32 includes a CPU, memory (RAM), etc. The calculation unit 32 also generates a learning model DL using training data. The generation of the learning model DL will be described later.

[0083] The communication unit 33 has a communication circuit compatible with Wi-Fi, etc. The communication unit 33 transmits and receives various information to and from the terminal device 20 (communication unit 24) via the network N.

[0084] The server device 30 can be accessed from terminal devices (not shown) other than the terminal device 20, and various information stored in the storage unit 31 can be viewed from the other terminal devices.

[0085] <Operation of the diagnostic system> During the diagnostic work, an inspector moves around carrying the diagnostic device 10 and the terminal device 20, and diagnoses (determines leaks in) each steam trap installed in the steam plant one by one. The following describes the diagnostic work, focusing mainly on the work related to leak determination.

[0086] When the inspector reaches the steam trap to be diagnosed, he first inputs the model and pressure value of the steam trap to be diagnosed into terminal device 20. Next, the inspector inputs a diagnosis request into terminal device 20. As a result, terminal device 20 (communication unit 24) transmits a diagnosis request including various parameters based on the model of the steam trap, pressure values, etc. to diagnostic machine 10. Furthermore, upon receiving the diagnosis request, diagnostic machine 10 is ready to start the diagnosis.

[0087] Thereafter, the diagnosis is initiated by the inspector pressing probe 10a of diagnostic device 10 against the steam trap to be diagnosed. For example, as shown in FIG. 3, probe 10a of diagnostic device 10 is pressed against the primary side of steam trap ST. This causes diagnostic device 10 to start measuring vibration, temperature, etc., and ultimately makes a first leak determination (normal, leak). The determination results, etc. are then displayed on liquid crystal display 17, as shown in FIG. 9. The determination results, etc. are stored in memory unit 13, and are also transferred (transmitted) to terminal device 20 and displayed.

[0088] On the liquid crystal display 17, the inspector checks the leak determination result, drain amount, identification result, validity determination result, etc. Taking the leak determination result, etc. into consideration, the inspector can select a course of action, such as adopting the current (displayed) determination result (end of diagnosis), changing the drain amount and performing a leak determination again (second leak determination), performing a leak determination again using the second relationship information (third leak determination), or performing a diagnosis again.

[0089] The reason for checking the determination result is that it is possible to determine whether or not there is a possibility that the determination result will change due to a change in the drain amount, as described above.

[0090] For example, if the vibration value belongs to region R1 or region R3, the determination result does not change depending on the drain amount, so the inspector does not need to select an action to change the drain amount and perform a leak determination again. In this case, the inspector can select an action other than changing the drain amount and performing a leak determination again. For example, if the inspector himself / herself believes that the leak determination result is correct, the inspector can select an action to adopt the current (displayed) leak determination result. In this case, the inspector inputs a save instruction for the diagnosis in the diagnostic device 10. This causes the diagnostic device 10 to end the diagnosis. In addition, the diagnostic device 10 transmits information related to the diagnosis, including the leak determination result, to the terminal device 20. This causes the information related to the diagnosis to be saved in the terminal device 20. In addition, if the determination result of validity is "valid," for example, the inspector can select an action to perform a third leak determination. In this case, the inspector inputs a command to perform a third leak determination in the diagnostic device 10. This causes the diagnostic device 10 to perform a second leak determination (third leak determination). Furthermore, if the inspector himself / herself has doubts about the judgment results, for example, the inspector may choose to perform a re-diagnosis. In this case, the inspector inputs a request for a re-diagnosis into the diagnostic device 10. This puts the diagnostic device 10 in a state where it can start a re-diagnosis. The inspector again presses the probe 10a of the diagnostic device 10 against the steam trap, and the execution of the re-diagnosis begins.

[0091] Next, for example, if the vibration value belongs to region R2, the inspector can choose to adopt the current (displayed) judgment result, change the drain amount and make a leak judgment again, make a leak judgment again using the second relationship information, or make a diagnosis again.

[0092] For example, a case will be described in which the leakage determination result is "leakage," the drain amount (estimated drain amount) is "small," and the vibration value belongs to region R2, as shown in FIG. 9. In this case, for example, if the inspector himself thinks that the determination result is actually incorrect, or if he himself wants to change the drain amount to "large" to confirm and try a leakage determination again, the inspector can select the response of changing the drain amount and performing a leakage determination again (second leakage determination). Specifically, he can input to change the drain amount to "large" into the diagnostic device 10. As a result, the diagnostic device 10 performs a leakage determination again (second leakage determination) with the drain amount set to "large." Thereafter, the inspector can check the results of the leakage determination again, and again consider which of the above-mentioned responses to select.

[0093] Furthermore, for example, even if the vibration value belongs to region R2, if the inspector himself / herself believes that the judgment result is correct, the inspector may select the response of adopting the current (displayed) judgment result. Also, for example, if the validity judgment result is "valid," the inspector may select the response of executing a third leakage judgment. Also, for example, if the inspector wishes to perform a re-diagnosis, including an estimation of the drain amount, the inspector may select the response of performing a re-diagnosis.

[0094] As described above, by understanding the region to which the vibration value belongs, the inspector can determine whether or not changing the drain amount is likely to change the judgment result. Therefore, if the vibration value belongs to region R1 or region R3, the inspector does not need to consider changing the drain amount. This prevents the inspector's workload from increasing.

[0095] The confirmation of the validity determination result on the LCD display 17 is because, as described above, the steam trap to be diagnosed is estimated to be in state S4, and it is possible to identify whether it is valid to perform the third leakage determination.

[0096] For example, if the validity determination result is "invalid," it is unlikely that the steam trap to be diagnosed is in state S4. If the inspector also believes that it is unlikely that it is in state S4, the inspector may select an action other than performing the third leak determination. Note that even if the validity determination result is "invalid," if the inspector believes that it is highly likely that it is in state S4, the inspector may select an action other than performing the third leak determination. Also, for example, if the validity determination result is "valid," it is highly likely that the steam trap to be diagnosed is in state S4. If the inspector also believes that it is highly likely that it is in state S4, the inspector may select an action other than performing the third leak determination. Note that even if the validity determination result is "valid," if the inspector believes that it is highly likely that it is not in state S4, the inspector may select an action other than performing the third leak determination.

[0097] Also, for example, after the first leakage determination is performed, both the second leakage determination and the third leakage determination may be performed sequentially. In this case, the order of execution may be any. For example, if the second leakage determination is performed but the inspector does not obtain the leakage determination result he or she desires, and there is a possibility that the state S4 may also apply, then the third leakage determination may be performed.

[0098] In addition to checking the leak determination results, drain volume, and identification results on the screen, the inspector may select the above-mentioned response by listening to the vibration sound of the steam trap with earphones connected to the diagnostic device 10, or by visually checking the condition of the surroundings (appearance) of the steam trap. Note that the diagnostic device 10 may output to the earphones a vibration sound that has been frequency converted so that ultrasonic vibrations can be heard by a human.

[0099] 10 shows a flowchart of the diagnostic process. In the diagnostic process, the vibration value and the like of the steam trap to be diagnosed are mainly measured to determine whether there is a leak. The calculation unit 14 starts executing the diagnostic process, for example, when the diagnostic machine 10 receives a diagnostic request from the terminal device 20. As described above, the diagnostic request includes various parameters, pressure values, and the like based on the model of the object to be diagnosed.

[0100] The calculation unit 14 executes a first calculation process (step S10). Specifically, the calculation unit 14 instructs the vibration measurement unit 11 to measure the vibration, and calculates a vibration value (first vibration data) and second vibration data from the acquired measurement data, etc. As described above, the vibration measurement unit 11 starts measurement with the probe 10a of the diagnostic device 10 pressed against the steam trap.

[0101] Next, the calculation unit 14 executes a second calculation process (step S11). Specifically, the calculation unit 14 instructs the temperature measurement unit 12 to measure the temperature, and calculates the temperature value from the acquired measurement data, etc. As described above, the temperature measurement unit 12 starts measurement with the probe 10a of the diagnostic device 10 pressed against the steam trap.

[0102] Thereafter, the calculation unit 14 executes a third calculation process (step S12). In the third calculation process, a drain amount (estimated drain amount) is calculated from the measured vibration value, temperature value, etc. Next, the calculation unit 14 executes an identification process (step S13). In the identification process, a region to which the measured vibration value belongs is identified. Thereafter, the calculation unit 14 executes a validity determination process (step S14). In the validity determination process, the validity of executing the third leakage determination for the diagnosis target is determined.

[0103] Next, the calculation unit 14 executes a leakage determination process (step S15). In the leakage determination process, leakage determination is performed based on the pressure value received from the terminal device 20, the measured (calculated) vibration value, the drain amount, etc. In the leakage determination process, first, a first leakage determination process is executed based on flag A:0. Next, the calculation unit 14 executes an output process (step S16). In the output process, information related to the executed diagnosis is saved in the memory unit 13. In addition, in the output process, a diagnosis result screen is displayed on the liquid crystal display 17.

[0104] Thereafter, the calculation unit 14 determines whether or not to execute a second leakage determination (a second leakage determination) (step S17). The calculation unit 14 makes this determination depending on whether or not a change input for the drain amount has been made to the diagnostic device 10. If the second leakage determination is to be executed (a change input for the drain amount has been made) (step S17: YES), the calculation unit 14 sets (changes) the drain amount to be used in the second leakage determination, and sets flag A to 1 (step S18). For example, the drain amount to be used in the leakage determination is changed from the estimated drain amount to the changed drain amount. Thereafter, the calculation unit 14 executes the leakage determination process of step S15 again. In this case, in the leakage determination process of step S15, the second leakage determination is executed using the changed drain amount based on flag A: 1. Note that in the second leakage determination, as described above, the changed drain amount is used, but the vibration value and other parameters other than the drain amount are not changed.

[0105] On the other hand, if the second leakage determination is not to be performed (if there is no input to change the drain amount) (step S17: NO), the calculation unit 14 determines whether or not to perform a third leakage determination (a second leakage determination) (step S19). The calculation unit 14 makes this determination depending on whether or not there is an input to perform the third leakage determination from the diagnostic device 10. If the third leakage determination is to be performed (step S19: YES), the calculation unit 14 sets flag A to 2 (step S20). Thereafter, the calculation unit 14 performs the leakage determination process of step S15 again. In this case, the third leakage determination is performed based on flag A: 2 in the leakage determination process of step S15. Note that in the third leakage determination, the second relationship information is used instead of the first relationship information, as described above, but the vibration value, etc. are not changed. Furthermore, the drain amount is not referenced in the third leakage determination.

[0106] On the other hand, if the third leakage determination is not to be performed (step S19: NO), the calculation unit 14 determines whether or not to perform a re-diagnosis (step S21). The calculation unit 14 makes this determination depending on whether or not a request for another diagnosis has been input to the diagnostic device 10. If a re-diagnosis is to be performed (step S21: YES), the calculation unit 14 proceeds to the first calculation process of step S10. This causes vibration value measurements and the like to be performed again to perform a leakage determination. Note that the pressure values ​​and the like included in the initial diagnosis request are used and are not changed for various parameters based on the steam trap model, pressure values, and the like. Also, although not shown, flag A is reset to its initial value: 0.

[0107] On the other hand, if re-diagnosis is not to be performed (step S21: NO), the calculation unit 14 determines whether to save the determination result and end the diagnosis (step S22). The calculation unit 14 makes this determination depending on whether or not a save input has been made to the diagnostic machine 10. If the diagnosis is not to be ended (step S22: NO), the calculation unit 14 proceeds to the processing of step S17. On the other hand, if the diagnosis is to be ended (step S22: YES), the calculation unit 14 executes a saving process (step S23). In the saving process, the calculation unit 14 causes the communication unit 15 to transmit information related to the confirmed diagnosis to the terminal device 20. That is, information related to the diagnosis including the determination result of the last leak determination is transmitted to the terminal device 20 and stored in the memory unit 22. In this embodiment, information related to the flag A is also transmitted as information related to the diagnosis. For example, if the first leak determination is performed and the diagnosis is ended without performing the second leak determination and the third leak determination, flag A: 0 is transmitted. Furthermore, for example, if the first leakage determination is performed, then the second leakage determination and the third leakage determination are performed in this order, and the diagnosis is terminated, flag A:2 is transmitted. Furthermore, for example, if the first leakage determination is performed, then the second leakage determination is performed, and the diagnosis is terminated, flag A:1 is transmitted. That is, flag A is transmitted as information on the type of determination adopted in the finalized diagnosis. Thereafter, the calculation unit 14 terminates the diagnostic processing.

[0108] <Generation of learning models> The learning model DL is generated, for example, by the server device 30 using training data. The training data is data including, for example, the steam trap model, diagnostic data related to leak determination including the second vibration data and pressure value, and the validity (valid, invalid) of the execution of the third leak determination for this steam trap. For example, multiple training data are prepared for each of multiple steam trap models.

[0109] The training data may be prepared, for example, by an inspector actually performing a diagnosis. Specifically, the inspector diagnoses the steam trap using a diagnostic device that does not have the function of performing a validity determination. During the diagnosis, the inspector takes into consideration the condition of the steam trap, etc., and performs a third leakage determination if necessary. As a result, information related to the diagnosis is stored in the server device 30. The information related to the diagnosis includes the steam trap model, second vibration data, pressure value, and flag A.

[0110] The steam trap model, second vibration data, and pressure value contained in the above diagnostic information are used as diagnostic data for the teacher data. Furthermore, data on the validity (valid, invalid) of the execution of the third leak judgment in the teacher data is generated using flag A contained in the diagnostic information. Flag A is information on the type of judgment applied to finalize the diagnosis. In other words, if the inspector actually executed the third leak judgment (flag A: 2), it is set to valid: 1, and if the third leak judgment was not executed (flag A: 1 or 0), it is set to invalid: 0.

[0111] In this embodiment, the training data is data from an actual diagnosis, but data generated by a simulator may also be used. The diagnostic data used as the training data is not limited to the above-mentioned type, second vibration data, etc.

[0112] The server device 30 executes a generation process using the training data stored in the memory unit 31. In the generation process, a learning model DL is generated. In the generation process, the model of the steam trap, the second vibration data, and the pressure value of the training data are input into the learning model DL, and the effectiveness of this training data is obtained as an output. The server device 30 compares the obtained effectiveness with the correct value (correct effectiveness) and optimizes parameters such as the weights of the intermediate layer DL12. After the above process is completed for all training data, the generation process ends. This completes the learning of the learning model DL. The trained learning model DL (program module) is then installed in the diagnostic machine 10.

[0113] As described above, after a leak determination (first leak determination) of the object to be diagnosed is made based on the first relationship information correlating the pressure value of a steam trap in a normal state with no gas leakage with a determination threshold, a second leak determination (third leak determination) of the object to be diagnosed is made based on the second relationship information correlating the pressure value of a steam trap in a state with gas leakage and a drain amount equal to or greater than a predetermined amount with a determination threshold, depending on whether a predetermined condition is met. That is, the third leak determination is made based on the second relationship information optimized for a steam trap in a state with gas leakage and a drain amount equal to or greater than a predetermined amount. This makes it possible to perform the third leak determination on the object to be diagnosed that is suspected to be in the above state, thereby improving the accuracy of the leak determination.

[0114] Furthermore, by referring to the effectiveness determination result by the learning model, it is possible to determine whether or not to perform a leak determination based on the second relational information (third leak determination). Therefore, the inspector can determine whether or not to perform a leak determination based on the second relational information (third leak determination) without being affected by the inspector's own ability. This also reduces the workload of the inspector in determining whether or not to perform a leak determination based on the second relational information (third leak determination).

[0115] In the above-described embodiment, the validity of executing the third leak determination for the diagnosis target is determined using a learning model, but the validity determination does not have to be performed. In this case, after executing the first leak determination, the inspector can determine whether to execute the third leak determination by, in addition to checking the leak determination results, listening to the vibration sound of the steam trap with earphones connected to the diagnostic machine, visually checking the condition of the surroundings (appearance) of the steam trap, etc.

[0116] In the above-described embodiment, the predetermined condition for executing the third leak determination is receiving an input from the inspector to execute the third leak determination, but this is not particularly limited. Multiple conditions may be included in the predetermined condition. For example, the predetermined condition may include (A) receiving an input from the inspector to execute the third leak determination, and (B) the validity determination result being “valid.” Condition (B) means that the validity of the execution of the third leak determination of the diagnosed object has been determined to be “valid.” In this case, the predetermined condition may be satisfied when either one of conditions (A) or (B) is satisfied. In this case, even if the inspector does not input an input for the execution of the third leak determination, if the validity determination result of condition (B) is “valid,” the third leak determination is automatically executed. Alternatively, the predetermined condition may be satisfied when all of the multiple conditions (A) and (B) are satisfied. Furthermore, only condition (B) may be the predetermined condition. Note that if the validity determination result is “valid” and the third leak determination is automatically executed, the validity does not need to be displayed on the display means.

[0117] In the above-described embodiment, first relationship information is stored for each drain amount ("large" and "small"), and the first leakage determination is performed based on the first relationship information corresponding to the drain amount, but this is not particularly limited to this. For example, it is not necessary to store first relationship information for each drain amount. In this case, a single piece of first relationship information may be saved in the storage unit, and the first leakage determination may be performed by identifying the determination threshold from the pressure value based on the single piece of first relationship information. In this case, the drain amount does not need to be referenced. Also, while there are two types of drain amount, "large" and "small," this is not particularly limited to this. Three or more types may also be used.

[0118] In the above-described embodiment, the server device generates the learning model, but this is not a limitation and the learning model may be generated by another device such as a terminal device.

[0119] In the above embodiment, the configuration in which the region to which the vibration value belongs is specified and the configuration in which the second leakage determination is executed are described, but these configurations may be omitted.

[0120] In the above-described embodiment, it is possible to change the drain amount used in the leakage determination, but it is also possible to change the leakage determination result. For example, this is effective when the inspector's judgment is prioritized when the result of the leakage determination remains unchanged even after the second and third leakage determinations are performed. In this case, the inspector can simply input a change to the determination result on the diagnostic machine, similar to inputting a change to the drain amount. When a change to the determination result is input, the terminal device transmits a diagnosis completion signal to the diagnostic machine. The terminal device also transmits information regarding the diagnosis, including the changed determination result, to the server device.

[0121] In the above-described embodiment, various inputs related to the diagnosis, such as pressure values, are made at the terminal device, but inputs may also be made directly to the diagnostic machine. For example, inputs may be made by operating the input buttons on the diagnostic machine. Also, in the above-described embodiment, inputs to change the drain amount, inputs to execute the third leakage determination, inputs to request another diagnosis, inputs to save, etc. are made at the diagnostic machine, but these inputs may also be made at the terminal device. In this case, the terminal device may transmit to the diagnostic machine a request to change the amount (a request to execute the second leakage determination), a request to execute the third leakage determination, a request to repeat the diagnosis, and an indication that the diagnosis is complete.

[0122] In the above embodiment, the pressure value of the steam trap is input by an inspector, but this is not a limitation. For example, the diagnostic device may acquire the pressure value by communicating with a pressure measurement device.

[0123] In the above-described embodiment, various parameters such as the first relationship information are transmitted from the terminal device to the diagnostic machine, but the parameters may be stored in advance in a storage unit of the diagnostic machine. For example, the first relationship information and the like may be stored in the storage unit of the diagnostic machine for each model, and only the model of the vehicle to be diagnosed may be received from the terminal device.

[0124] In the above embodiment, the vibration value is specified to belong to one of three regions, but the present invention is not limited to this. It is sufficient to at least specify whether the vibration value belongs to a region where the determination result differs depending on the amount of drainage.

[0125] In the above-described embodiment, the determination results and the like are displayed on the diagnostic machine and the terminal device, but they may be displayed on only one of the diagnostic machine and the terminal device.

[0126] In the above-described embodiment, the diagnostic machine determines whether there is a leak, but this is not a limitation. A terminal device or a server device constituting the diagnostic system may also perform the determination. In this case, for example, the diagnostic machine transmits ultrasonic vibration and temperature measurement data, etc. to a device that performs leak determination. The device that performs leak determination may calculate vibration values, temperature values, estimated drain amounts, etc., and perform the leak determination. Also, for example, the diagnostic machine may calculate vibration values, temperature values, estimated drain amounts, etc. from the measurement data, etc., and transmit the calculated values ​​to the device that performs leak determination. The device that performs leak determination may perform the leak determination based on the received vibration values, temperature values, estimated drain amounts, etc.

[0127] In the above-described embodiment, the diagnostic machine identifies the region to which the vibration value belongs and determines the effectiveness of the execution of the third leakage determination, but this is not particularly limited. The determination may be made by a terminal device or a server device constituting the diagnostic system. For example, the server device may have a trained learning model and execute the above-described effectiveness determination.

[0128] In the above-described embodiment, the diagnostic device and the terminal device are distinguished from each other, but the diagnostic device and the terminal device may be integrated into one device.

[0129] In the above-described embodiment, the diagnosis is performed using a diagnostic device carried by the inspector, but the diagnostic device does not have to be portable. For example, a diagnostic device may be installed on the steam trap and periodically performed. In this case, the diagnostic device may transmit the results of the diagnosis to a server device via a communication network.

[0130] In the above-described embodiment, a diagnostic system configuration including a server device, a terminal device, and a diagnostic machine is described. However, a configuration without a server device or a terminal device, in which the diagnostic machine alone functions as the diagnostic machine, is also possible. In this case, for example, a diagnosis is performed by operating input buttons on the diagnostic machine to input the steam trap model, pressure value, etc., and information related to the diagnosis, such as the determination results, is stored in the memory unit of the diagnostic machine. In addition, various parameters, such as the first relationship information, may also be stored in advance in the memory unit of the diagnostic machine. [Industrial Applicability]

[0131] This is useful for improving the accuracy of determining gas leakage from a steam trap. [Explanation of symbols]

[0132] 10 Diagnostic equipment 11 Vibration measurement section 12 Temperature measurement part 13 Storage section 14 Arithmetic section 15 Communications Department 17 LCD display 20 Terminal equipment 21 Touch Panel 30 Server device 100 Diagnostic Systems DL learning model

Claims

1. a measuring means for measuring vibration of the steam trap to be diagnosed and calculating first vibration data from the measurement data; an estimation means for estimating the amount of drainage of the diagnostic object based on the first vibration data; an acquisition means for acquiring a pressure value of the diagnosis target; a storage means for storing first relationship information correlating the pressure value of a steam trap in a normal state with no gas leakage with a determination threshold value, and second relationship information correlating the pressure value of a steam trap in a state with gas leakage and a drain amount equal to or greater than a predetermined amount with a determination threshold value; a first determination means for specifying the determination threshold based on the acquired pressure value based on the first relationship information, and for determining leakage of the gas to be diagnosed based on the first vibration data and the determination threshold; a display means for displaying the determination result by the first determination means and the drain amount; Equipped with the first determination means executes the leakage determination again based on the second relationship information instead of the first relationship information in response to establishment of a predetermined condition; A diagnostic device for a steam trap characterized by:

2. a first input receiving means for receiving an input for executing a determination based on the second relationship information; Furthermore, the predetermined condition includes that an input for executing the determination has been received.

2. The steam trap diagnostic device according to claim 1.

3. a second determination means for determining the validity of execution of leakage determination based on the second relationship information of the object to be diagnosed from the diagnostic data of the object to be diagnosed, based on a learning model trained with teacher data including diagnostic data related to leakage determination, which includes second vibration data and pressure values ​​related to the steam trap, and validity of execution of leakage determination based on the second relationship information of the steam trap; Furthermore, the measuring means calculates the second vibration data from the measurement data, the display means displays the determination result by the second determination means in addition to the determination result by the first determination means and the drain amount.

3. The steam trap diagnostic device according to claim 2.

4. a second determination means for determining the validity of execution of leakage determination based on the second relationship information of the object to be diagnosed from the diagnostic data of the object to be diagnosed, based on a learning model trained with teacher data including diagnostic data related to leakage determination, which includes second vibration data and pressure values ​​related to the steam trap, and validity of execution of leakage determination based on the second relationship information of the steam trap; Furthermore, the measuring means calculates second vibration data from the measurement data, the predetermined condition includes being determined to be valid by the second determination means; 2. The steam trap diagnostic device according to claim 1.

5. the storage means stores the first relationship information for each of the drain amounts, the determination means performs the leakage determination based on the first relationship information corresponding to the estimated drain amount.

2. The steam trap diagnostic device according to claim 1.

6. a determination means for determining, based on the first relationship information, whether the first vibration data belongs to a region in which the determination result by the determination means differs depending on the magnitude of the drain amount; a second input receiving means for receiving an input for changing the drain amount of the diagnosis target; Furthermore, the display means displays the determination result by the first determination means and the drain amount, as well as the determination result by the determination means; When an input to change the drain amount is received, the determination means executes the leakage determination again based on the first relationship information corresponding to the drain amount for which the input to change has been received, instead of the estimated drain amount.

6. The steam trap diagnostic device according to claim 5.

7. The steam trap diagnostic equipment computer a measuring means for measuring vibration of the steam trap to be diagnosed and calculating first vibration data from the measurement data; an estimation means for estimating the amount of drainage of the diagnostic object based on the first vibration data; an acquisition means for acquiring a pressure value of the diagnosis target; a storage means for storing first relationship information correlating the pressure value of a steam trap in a normal state with no gas leakage with a determination threshold value, and second relationship information correlating the pressure value of a steam trap in a state with gas leakage and a drain amount equal to or greater than a predetermined amount with a determination threshold value; a first determination means for specifying the determination threshold based on the acquired pressure value based on the first relationship information, and for determining leakage of the gas to be diagnosed based on the first vibration data and the determination threshold; a display means for displaying the determination result by the first determination means and the drain amount; It functions as the first determination means executes the leakage determination again based on the second relationship information instead of the first relationship information in response to establishment of a predetermined condition; A diagnostic program for a steam trap, comprising:

8. a measuring means for measuring vibration of the steam trap to be diagnosed and calculating first vibration data from the measurement data; an estimation means for estimating the amount of drainage of the diagnostic object based on the first vibration data; an acquisition means for acquiring a pressure value of the diagnosis target; a storage means for storing first relationship information correlating the pressure value of a steam trap in a normal state with no gas leakage with a determination threshold value, and second relationship information correlating the pressure value of a steam trap in a state with gas leakage and a drain amount equal to or greater than a predetermined amount with a determination threshold value; a first determination means for specifying the determination threshold based on the acquired pressure value based on the first relationship information, and for determining leakage of the gas to be diagnosed based on the first vibration data and the determination threshold; a display means for displaying the determination result by the first determination means and the drain amount; Equipped with the first determination means executes the leakage determination again based on the second relationship information instead of the first relationship information in response to establishment of a predetermined condition; A diagnostic system for a steam trap, comprising:

Images