Determination method

Abstract

To provide a determination method capable of accurately determining signs of water leakage from cooling water flowing inside an induction coil.SOLUTION: A determination method for determining signs of water leakage from cooling water flowing inside an induction coil 10 for induction heating includes the steps of (a) acquiring data indicating the state of the induction coil 10, and (b) performing a Welch's t-test based on the data, and determining that there are signs of water leakage when a significant difference is determined to exist.SELECTED DRAWING: Figure 5

Description

[Technical field]

[0001] The present invention relates to a method for determining whether there is a sign of water leakage from cooling water flowing inside an induction coil for induction heating. [Background technology]

[0002] An induction heating device for induction heating an object to be heated is known (see, for example, Patent Document 1). This type of induction heating device includes a power supply unit, a matching unit, and an induction coil. The power supply unit is an inverter power supply having multiple switching elements, and generates a high-frequency current by turning the multiple switching elements on and off at high speed. The matching unit is a parallel resonant circuit electrically connected between the power supply unit and the induction coil. The induction coil is formed in a pipe shape and is arranged so as to cover the periphery of the object to be heated. Cooling water is supplied inside the induction coil to cool the induction coil.

[0003] A high-frequency current from a power supply is supplied to an induction coil via a matching unit. The alternating magnetic flux generated by this high-frequency current penetrates the inside of the object to be heated, causing eddy currents to flow inside the object. The Joule heat generated by this eddy current induces heating of the object to be heated. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2000-208240 A Summary of the Invention [Problem to be solved by the invention]

[0005] In the induction heating device described above, it is desired to accurately determine signs of leakage of the cooling water flowing inside the induction coil.

[0006] An object of the present invention is to provide a method for accurately determining signs of water leakage from the cooling water flowing inside an induction coil. [Means for solving the problem]

[0007] A determination method according to a first aspect of the present invention is a method for determining signs of water leakage of cooling water flowing inside an induction coil for induction heating, and includes the steps of (a) acquiring data indicating a state of the induction coil, and (b) performing a Welch's t-test based on the data, and determining that there are signs of water leakage if it is determined that there is a significant difference.

[0008] According to this embodiment, a Welch's t-test is performed based on the data showing the state of the induction coil, and if a significant difference is determined, it is determined that there is a sign of water leakage. This makes it possible to accurately determine the sign of water leakage from the cooling water flowing inside the induction coil.

[0009] For example, in the determination method of the second aspect, in the first aspect, (b) may be configured to calculate a first average value, which is the average value of the data for each day in a first period in which no water leakage occurred, calculate a second average value, which is the average value of the data in the first period, using the first average value, calculate a third average value, which is the average value of the data in a second period after the first period, and compare the second average value with the third average value using the Welch's t-test to determine whether there is a significant difference.

[0010] According to this aspect, signs of leakage of the cooling water flowing inside the induction coil can be accurately determined.

[0011] For example, in the judgment method according to the third aspect, in the first or second aspect, the judgment method may be further configured to include a step of (c) calculating an average value of the data for each day, and determining that there are signs of water leakage if the average value decreases for a predetermined number of consecutive days or more.

[0012] According to this aspect, it is possible to more accurately determine signs of leakage of the cooling water flowing inside the induction coil.

[0013] For example, in the judgment method according to the fourth aspect, in any one of the first to third aspects, the judgment method may further include a step (d) of performing an F-test based on the data, and determining that there is a sign of water leakage if it is determined that there is a significant difference.

[0014] According to this aspect, it is possible to more accurately determine signs of leakage of the cooling water flowing inside the induction coil.

[0015] For example, in the determination method of the fifth aspect, in the fourth aspect, (d) may be configured to calculate a third average value, which is the average value of the data in a third period in which no water leakage occurred, calculate a fourth average value, which is the average value of the data in a fourth period after the third period, and use the F-test to calculate the ratio of variation between the third average value and the fourth average value, thereby determining whether or not there is a significant difference.

[0016] According to this aspect, it is possible to more accurately determine signs of leakage of the cooling water flowing inside the induction coil.

[0017] For example, in the determination method according to the sixth aspect, in any one of the first to fifth aspects, the determination method may further include (e) a step of determining that there are signs of water leakage based on an output result obtained by inputting the data into a machine learning model.

[0018] According to this aspect, it is possible to more accurately determine signs of leakage of the cooling water flowing inside the induction coil.

[0019] For example, in the determination method according to the seventh aspect, in any one of the first to sixth aspects, the determination method may further include a step (f) of determining that there are signs of a water leak if the data deviates from a predetermined threshold range.

[0020] According to this aspect, it is possible to more accurately determine signs of leakage of the cooling water flowing inside the induction coil.

[0021] For example, in the judgment method according to the eighth aspect, in any one of the first to seventh aspects, the judgment method may further include a step of (g) calculating an average value of the data for each day, and determining that there is a sign of water leakage if the absolute value of the change between the average value of the data on the current day and the average value of the data on the previous day falls below a threshold value.

[0022] According to this aspect, it is possible to more accurately determine signs of leakage of the cooling water flowing inside the induction coil.

[0023] For example, in the judgment method according to the ninth aspect, in any one of the first to eighth aspects, the judgment method may be further configured to include a step of (h) calculating a moving average of the average values ​​of the data for each specified time period in a day, and determining that there are signs of a water leak if the average value decreases a specified number of times or more.

[0024] According to this aspect, it is possible to more accurately determine signs of leakage of the cooling water flowing inside the induction coil.

[0025] For example, in the determination method according to the tenth aspect, in any one of the first to ninth aspects, the data may be configured to be at least one of the flow rate of the cooling water, the temperature of the cooling water, the pressure of the cooling water, and the temperature of the induction coil.

[0026] According to this aspect, the presence or absence of signs of water leakage can be determined by using various data indicating the state of the induction coil.

[0027] Furthermore, these comprehensive or specific aspects may be realized by a system, a method, an integrated circuit, a computer program, or a recording medium such as a computer-readable CD-ROM, or may be realized by any combination of the system, the method, the integrated circuit, the computer program, and the recording medium. Effect of the Invention

[0028] According to the determination method according to one aspect of the present invention, signs of water leakage of the cooling water flowing inside the induction coil can be accurately determined. [Brief description of the drawings]

[0029] [Figure 1] 1 is a schematic diagram showing a configuration of an induction heating device according to an embodiment; [Diagram 2] 1 is a block diagram showing a configuration of an induction heating device maintenance system according to an embodiment; [Diagram 3] FIG. 2 is a block diagram showing a configuration of a server according to the embodiment. [Figure 4] 4 is a sequence diagram showing the flow of operations of the induction heating device maintenance system according to the embodiment. FIG. [Diagram 5] 4 is a flowchart showing the flow of a method for determining a sign of water leakage according to an embodiment. [Figure 6] 11 is a graph showing an example of a transition of an average value of a flow rate. [Figure 7] 10 is a flowchart showing the flow of a method for determining a sign of water leakage according to Modification 1. [Figure 8] 10 is a flowchart showing the flow of a method for determining a sign of water leakage according to Modification 2. [Figure 9] 13 is a flowchart showing the flow of a method for determining a sign of water leakage according to Modification 3. [Figure 10] 13 is a flowchart showing the flow of a method for determining a sign of water leakage according to Modification 4. [Figure 11]13 is a flowchart showing the flow of a method for determining a sign of water leakage according to Modification 5. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0030] Hereinafter, the embodiment will be specifically described with reference to the drawings.

[0031] The embodiments described below are all comprehensive or specific examples. The numerical values, shapes, materials, components, component arrangement and connection forms, steps, and order of steps shown in the following embodiments are merely examples and are not intended to limit the scope of the claims. Furthermore, among the components in the following embodiments, components that are not described in an independent claim showing a top concept are described as optional components.

[0032] In addition, the drawings are not necessarily strict illustrations. In the drawings, the same reference numerals are used for substantially the same configurations, and duplicated explanations are omitted or simplified.

[0033] (Embodiment) [1. Configuration of induction heating device] First, the configuration of an induction heating device 2 according to an embodiment will be described with reference to Fig. 1. Fig. 1 is a schematic diagram showing the configuration of an induction heating device 2 according to an embodiment.

[0034] As shown in Fig. 1, the induction heating device 2 is a device for induction heating (so-called high-frequency hardening) an object 4 to be heated with a high frequency of, for example, several kHz to several hundred kHz. Here, high-frequency hardening is a heat treatment in which the surface of the object 4 to be heated is heated and hardened by generating high-frequency electromagnetic induction. The object 4 to be heated is induction heated to a hardening temperature, and then quenched by injecting quenching water onto the object 4 to rapidly cool it, thereby performing high-frequency hardening. The object 4 to be heated is, for example, a metal part used in a vehicle, a machine tool, or the like.

[0035] The induction heating device 2 includes a power supply unit 6, a matching unit 8, an induction coil 10, a cooling water tank 12, and a flow rate sensor 14.

[0036] The power supply unit 6 is an oscillator for generating a high-frequency current having a frequency of, for example, several kHz to several hundred kHz, and has multiple switching elements. The power supply unit 6 generates the high-frequency current by turning the multiple switching elements on and off at high speed.

[0037] The matching unit 8 is a parallel resonant circuit composed of a capacitor 16 and a matching transformer 18, and is electrically connected between the power supply unit 6 and the induction coil 10. The matching unit 8 serves to supply the active power generated by the power supply unit 6 to the induction coil 10 with high efficiency.

[0038] The induction coil 10 is formed in a pipe shape (hollow cylinder shape) and is disposed so as to surround the object to be heated 4. High-frequency current from the power supply unit 6 is supplied to the induction coil 10 via a matching unit 8. An alternating magnetic flux generated by this high-frequency current penetrates the inside of the object to be heated 4, causing an eddy current to flow inside the object to be heated 4. The object to be heated 4 is induction-heated by Joule heat due to this eddy current.

[0039] Cooling water tank 12 is a tank that stores cooling water for cooling induction coil 10. Cooling water tank 12 is in communication with the inside of induction coil 10 via supply pipe 20. Supply pipe 20 is provided with supply pump 22. The cooling water stored in cooling water tank 12 is supplied to the inside of induction coil 10 through supply pipe 20 by supply pump 22. The cooling water supplied to the inside of induction coil 10 cools induction coil 10 by flowing through the inside of induction coil 10.

[0040] The flow rate sensor 14 is a sensor for detecting the flow rate (liters / minute) of the cooling water flowing inside the induction coil 10 (an example of data indicating the state of the induction coil 10).

[0041] [2. Configuration of induction heating equipment maintenance system] Next, the configuration of induction heating device maintenance system 24 according to the embodiment will be described with reference to Fig. 2 and Fig. 3. Fig. 2 is a block diagram showing the configuration of induction heating device maintenance system 24 according to the embodiment. Fig. 3 is a block diagram showing the configuration of server 26 according to the embodiment.

[0042] The induction heating device maintenance system 24 according to the embodiment is an IoT (Internet of Things) system for supporting the maintenance of the induction heating device 2 described above. As shown in Fig. 2, the induction heating device maintenance system 24 according to the embodiment includes the induction heating device 2, a server 26, a terminal device 28, and a terminal device 30. The induction heating device 2, the server 26, the terminal device 28, and the terminal device 30 are connected to each other so as to be able to communicate with each other via a network 32. The network 32 is, for example, the Internet.

[0043] The induction heating device 2 is installed in a factory or the like of a client company that uses the induction heating device maintenance system 24. The flow sensor 14 of the induction heating device 2 is connected to a communication adapter 34, for example, via a wired LAN (Local Area Network) or a wireless LAN. The communication adapter 34 connects the flow sensor 14 to a network 32. The communication adapter 34 transmits data from the flow sensor 14 (i.e., data indicating the flow rate of the cooling water flowing inside the induction coil 10) to the server 26 via the network 32.

[0044] The server 26 is, for example, a cloud server, and is operated by a management company that manages the induction heating device maintenance system 24. As shown in FIG.

[0045] The acquiring unit 36 ​​acquires data from the flow rate sensor 14 via the network 32. The acquiring unit 36 ​​acquires data at predetermined time intervals (for example, every minute).

[0046] The storage unit 38 is a memory for storing (accumulating) the data acquired by the acquisition unit 36.

[0047] The analysis unit 40 reads data from the storage unit 38 and executes a Welch's t-test based on the read data to determine whether or not there is a sign of water leakage from the cooling water flowing inside the induction coil 10. In this specification, the term "sign of water leakage" is a concept that includes not only a sign of water leakage but also a situation in which water leakage actually occurs. When the analysis unit 40 determines that there is a sign of water leakage, it notifies the terminal device 28 and the terminal device 30 via the network 32 of an alert to notify that there is a sign of water leakage.

[0048] The terminal device 28 is, for example, a personal computer or a smartphone, and is operated by an operator belonging to the client company. The terminal device 28 receives the alert notified from the server 26. Specifically, when the terminal device 28 is a personal computer, the terminal device 28 receives the alert notified from the server 26 by email. Also, when the terminal device 28 is a smartphone, the terminal device 28 receives the alert notified from the server 26 by push notification.

[0049] The terminal device 30 is, for example, a personal computer or a smartphone, and is operated by an administrator belonging to a management company. The terminal device 30 receives an alert notified from the server 26, similar to the terminal device 28.

[0050] [3. Operation of induction heating equipment maintenance system] Next, the operation of the induction heating device maintenance system 24 according to the embodiment will be described with reference to Fig. 4. Fig. 4 is a sequence diagram showing the flow of the operation of the induction heating device maintenance system 24 according to the embodiment.

[0051] 4, the flow sensor 14 of the induction heating device 2 installed in a factory of a client company detects data (S101). Next, the communication adapter 34 transmits the data from the flow sensor 14 to the server 26 via the network 32 (S102).

[0052] Next, the acquisition unit 36 ​​of the server 26 acquires data from the flow rate sensor 14 of the induction heating device 2 via the network 32 (S103). Next, the acquisition unit 36 ​​stores the acquired data in the storage unit 38 (S104).

[0053] Next, the analysis unit 40 executes Welch's t-test based on the data read from the storage unit 38, and determines that there is a sign of leakage of the cooling water flowing inside the induction coil 10 (S105).

[0054] Next, the analysis unit 40 notifies the terminal device 28 of an alert to notify that there is a sign of water leakage via the network 32 (S106). Although not shown, the analysis unit 40 also notifies the terminal device 30 of an alert to notify that there is a sign of water leakage via the network 32.

[0055] Next, the terminal device 28 receives the alert notified from the server 26 (S107) and displays the contents of the alert. By looking at the contents of the notified alert, the worker of the client company can know that there is a sign of a water leak and can take appropriate action, such as replacing the induction coil 10.

[0056] [4. How to determine if there is a water leak] Next, a method for determining signs of water leakage by the analysis unit 40 will be described with reference to Fig. 5 and Fig. 6. Fig. 5 is a flowchart showing the flow of a method for determining signs of water leakage according to an embodiment. Fig. 6 is a graph showing an example of the transition of the average value of the flow rate.

[0057] As shown in FIG. 5, first, the analysis unit 40 calculates the average daily flow rate (hereinafter referred to as the "first average value") in a month in which no water leakage occurred (an example of a first period) based on the data read from the memory unit 38 (S201).

[0058] Next, the analysis unit 40 uses the first average value to calculate an average value of the flow rate in that month (hereinafter referred to as a "second average value") (S202).

[0059] Next, the analysis unit 40 calculates the average flow rate for each week (an example of the second period) after the month (hereinafter referred to as the "third average value") and compares the second average value with the third average value using a Welch's t-test with a two-sided significance level of 5% (S203). Note that the Welch's t-test is a method for verifying whether there is a significant difference between the average values ​​of two populations. By using this Welch's t-test, it is possible to compare the average values ​​of the first period and the second period even if the number of data items differs between the two periods.

[0060] Specifically, the analysis unit 40 compares the second average value with the third average value by calculating a statistic t using the following formula 1. In the following formula 1, the normal data indicates, for example, data detected by the flow sensor 14 in a month in which no water leakage occurred, and the comparison data indicates, for example, data detected by the flow sensor 14 every week after that month.

[0061]

number

[0062] When no significant difference is found as a result of comparing the second average value with the third average value (No in S204), the analysis unit 40 determines that there is no sign of water leakage (S205).

[0063] On the other hand, when a significant difference is found as a result of comparing the second average value with the third average value (Yes in S204), the analysis unit 40 determines that there are signs of a water leak (S206). In this case, the change in the average flow rate may be as shown in FIG. 6, for example. In FIG. 6, the vertical axis represents the average flow rate (liters / minute) and the horizontal axis represents the date. In the example shown in FIG. 6, during periods when no water leaks occurred, the average flow rate remains roughly stable, whereas during periods when there are signs of a water leak, the average flow rate continues to decline.

[0064] [5. Effects] In this embodiment, as described above, the analysis unit 40 executes the Welch's t-test based on the data read from the storage unit 38, and if it is determined that there is a significant difference, it determines that there is a sign of water leakage. This makes it possible to accurately determine the sign of water leakage of the cooling water flowing inside the induction coil 10.

[0065] [6. Variations of the method for determining signs of water leakage] In the present embodiment, the analysis unit 40 performs the determination method shown in the flowchart of Fig. 5 as a method for determining signs of water leakage, but is not limited to this. For example, instead of the determination method shown in the flowchart of Fig. 5 or in addition to the determination method shown in the flowchart of Fig. 5, the analysis unit 40 may perform a method for determining signs of water leakage according to each of the following modified examples.

[0066] [6-1. Variation 1] A method for determining whether there is a sign of water leakage according to the first modification will be described with reference to Fig. 7. Fig. 7 is a flow chart showing the flow of the method for determining whether there is a sign of water leakage according to the first modification.

[0067] 7, in the first modification, the analysis unit 40 first calculates the average daily flow rate (S301) based on the data read from the storage unit 38. Then, if the average flow rate continues to decrease for a predetermined number of days (e.g., seven days) or more (Yes in S302), the analysis unit 40 determines that there is a sign of a water leak (S303).

[0068] On the other hand, if the average flow rate has not decreased for a predetermined number of consecutive days or more (No in S302), the analysis unit 40 determines that there is no sign of a water leak (S304).

[0069] [6-2. Variation 2] A method for determining whether there is a sign of water leakage according to the second modification will be described with reference to Fig. 8. Fig. 8 is a flow chart showing the flow of the method for determining whether there is a sign of water leakage according to the second modification.

[0070] As shown in FIG. 8, in the second modification, first, the analysis unit 40 calculates an average flow rate (hereinafter referred to as the "third average value") for a month in which no water leakage occurred (an example of a third period) based on the data read from the memory unit 38 (S401).

[0071] Next, the analysis unit 40 calculates the average value (hereinafter referred to as the "fourth average value") for each week (an example of a fourth period) after the month, and compares the third average value with the fourth average value using an F-test with a two-sided significance level of 5% (S402). Specifically, the analysis unit 40 calculates the ratio of the variations between the third average value and the fourth average value. The F-test is a method for verifying whether or not there is a significant difference between the variations of the two populations by calculating the ratio of variations (= the variation of the data to be compared / the variation of the normal data). The normal data indicates, for example, data detected by the flow sensor 14 in a month in which no water leakage occurred, and the comparison data indicates, for example, data detected by the flow sensor 14 for each week after the month.

[0072] If no significant difference is found as a result of calculating the ratio of the variations between the third average value and the fourth average value (No in S403), the analysis unit 40 determines that there is no sign of water leakage (S404).

[0073] On the other hand, when a significant difference is found as a result of calculating the ratio of the variations between the third average value and the fourth average value (Yes in S403), the analysis unit 40 determines that there is a sign of water leakage (S405).

[0074] [6-3. Variation 3] A method of determining whether there is a sign of water leakage according to Modification 3 will be described with reference to Fig. 9. Fig. 9 is a flow chart showing the flow of the method of determining whether there is a sign of water leakage according to Modification 3.

[0075] 9, in the third modification, first, the analysis unit 40 calculates the average daily flow rate (S501) based on the data read from the storage unit 38. Then, the analysis unit 40 sets a range of 5% above and below the flow rate in a normal period (a period during which it can be guaranteed that no water leakage is occurring) as a predetermined threshold range, and compares the average daily flow rate with the predetermined threshold range.

[0076] If the average value of the daily flow rate is outside the predetermined threshold range (Yes in S502), the analysis unit 40 determines that there is a sign of a water leak (S503).

[0077] On the other hand, if the average value of the daily flow rate does not deviate from the predetermined threshold range (No in S502), the analysis unit 40 determines that there is no sign of a water leak (S504).

[0078] [6-4. Variation 4] A method of determining whether there is a sign of water leakage according to the fourth modification will be described with reference to Fig. 10. Fig. 10 is a flow chart showing the flow of the method of determining whether there is a sign of water leakage according to the fourth modification.

[0079] 10, in the fourth modification, the analysis unit 40 first calculates the average flow rate for each day based on the data read from the storage unit 38 (S601). Next, the analysis unit 40 compares the average flow rate for the current day with the average flow rate for the previous day (S602).

[0080] If the absolute value of the change between the average flow rate of the day and the average flow rate of the previous day falls below a threshold value (e.g., 0.2) (Yes in S603), the analysis unit 40 determines that there is a sign of a water leak (S604).

[0081] On the other hand, if the absolute value of the amount of change between the average flow rate of the day and the average flow rate of the previous day is not below the threshold value (No in S603), the analysis unit 40 determines that there are no signs of water leakage (S605).

[0082] [6-5. Variation 5] A method for determining whether there is a sign of water leakage according to the fifth modification will be described with reference to Fig. 11. Fig. 11 is a flow chart showing the flow of the method for determining whether there is a sign of water leakage according to the fifth modification.

[0083] 11, in the fifth modification, the analysis unit 40 first calculates a moving average of the average flow rate for each time period of a day (S701) based on the data read from the storage unit 38. Then, if the average flow rate drops a predetermined number of times (e.g., seven times) or more consecutively (Yes in S702), the analysis unit 40 determines that there is a sign of a water leak (S703).

[0084] On the other hand, if the average flow rate does not drop consecutively for a predetermined number of times or more (No in S702), the analysis unit 40 determines that there is no sign of a water leak (S704).

[0085] [6-6. Variation 6] Finally, a method for determining whether there is a sign of water leakage according to the sixth modification will be described. In the sixth modification, the analysis unit 40 determines whether there is a sign of water leakage based on an output result obtained by inputting data into a machine learning model. The machine learning model is a trained logical model for determining whether there is a sign of water leakage. For example, the machine learning model receives data indicating the flow rate of the cooling water flowing inside the induction coil 10 as input, and outputs information indicating whether there is a sign of water leakage.

[0086] The machine learning model is constructed by performing supervised learning using, for example, data from a normal period (a period during which it can be guaranteed that there is no water leakage) and data from an abnormal period (a period from the time the water leakage is discovered to one month prior) as training data. For example, a neural network or a random forest is used to construct a logical model in machine learning.

[0087] Alternatively, the machine learning model may be constructed by performing unsupervised learning to determine that there are signs of a water leak when data indicating the flow rate of the cooling water flowing inside the induction coil 10 deviates from data during a normal period.

[0088] (Variations, etc.) Although the determination method according to one or more aspects of the present invention has been described based on the above embodiment, the present invention is not limited to the above embodiment. As long as it does not deviate from the spirit of the present invention, various modifications conceived by a person skilled in the art to this embodiment and forms constructed by combining components in different embodiments may also be included within the scope of one or more aspects of the present invention.

[0089] In the above embodiment, data indicating the flow rate of the cooling water is used when determining whether or not there is a sign of water leakage, but this is not limiting, and for example, data indicating any one of the flow rate of the cooling water, the temperature of the cooling water, the pressure of the cooling water, and the temperature of the induction coil 10 may be used. Alternatively, data indicating a combination of two or more of the flow rate of the cooling water, the temperature of the cooling water, the pressure of the cooling water, and the temperature of the induction coil 10 may be used.

[0090] In the above embodiment, each component may be realized by a dedicated hardware or by executing a software program suitable for each component. Each component may be realized by a program execution unit such as a CPU or a processor reading and executing a software program recorded on a recording medium such as a hard disk or a semiconductor memory. [Industrial Applicability]

[0091] The present invention can be applied, for example, as a method for determining leakage of cooling water flowing inside an induction coil used in an induction heating device. [Explanation of symbols]

[0092] 2 Induction heating device 4 Object to be heated 6 Power supply section 8 Matching section 10 Induction Coil 12 Cooling water tank 14 Flow Sensor 16 Capacitor 18 Matching transformer 20 Supply pipe 22 Supply pump 24 Induction heating equipment maintenance system 26 Server 28,30 Terminal equipment 32 Network 34 Communication adapter 36 Acquisition Department 38 Memory section 40 Analysis Department

Claims

1. A method for determining whether there is a sign of leakage of cooling water flowing inside an induction coil for induction heating, comprising: (a) acquiring data indicative of a condition relating to the induction coil; (b) performing a Welch's t-test based on the data, and determining that there is a sign of water leakage when a significant difference is determined. Judgment method.

2. In the step (b), a first average value is calculated as an average value of the data for each day in a first period in which no water leakage occurred, a second average value is calculated as an average value of the data in the first period using the first average value, a third average value is calculated as an average value of the data in a second period after the first period, and the second average value and the third average value are compared using the Welch's t-test to determine whether there is a significant difference. The method according to claim 1 .

3. The determination method further comprises: (c) calculating an average value of the data for each day, and determining that there is a sign of a water leak when the average value has decreased for a predetermined number of consecutive days or more; The method according to claim 1 .

4. The determination method further comprises: (d) performing an F-test based on the data, and determining that there is a sign of water leakage when it is determined that there is a significant difference. The method according to claim 1 .

5. In the step (d), a third average value is calculated, which is the average value of the data in a third period in which no water leakage occurred, and a fourth average value is calculated, which is the average value of the data in a fourth period after the third period. The F-test is used to calculate a ratio of variation between the third average value and the fourth average value, thereby determining whether or not there is a significant difference. The method according to claim 4.

6. The determination method further comprises: (e) determining that there is a sign of a water leak based on an output result obtained by inputting the data into a machine learning model. The method according to claim 1 .

7. The determination method further comprises: (f) determining that there is a sign of a water leak when the data deviates from a predetermined threshold range. The method according to claim 1 .

8. The determination method further comprises: (g) calculating an average value of the data for each day, and determining that there is a sign of water leakage when the absolute value of the amount of change between the average value of the data for the day and the average value of the data for the previous day falls below a threshold value. The method according to claim 1 .

9. The determination method further comprises: (h) calculating a moving average of the average value of the data for each predetermined time period in one day, and determining that there is a sign of a water leak when the average value drops a predetermined number of times or more in succession. The method according to claim 1 .

10. The data is at least one of the flow rate of the cooling water, the temperature of the cooling water, the pressure of the cooling water, and the temperature of the induction coil. The method according to any one of claims 1 to 9.

Images