Method and system for identifying leakage phenomena using machine learning

Abstract

To provide a method and system for identifying leakage phenomenon with which it is possible to measure AE waves by a single sensor and identify the leakage phenomenon of a fluid in a pressure pipeline, including a water sending-distributing pipeline, by machine learning.SOLUTION: Provided is a leakage phenomenon identification method capable of identifying the leakage phenomenon of a fluid in a pressure pipeline by AE waves measured with a single leakage sensor, said method including at least: a measurement step for measuring AE waves with a single leakage sensor that is installed in the pressure pipeline; a learning step for training the system by machine learning using the measured AE waves; an extraction step for extracting AE parameters in the learning step; and a leakage phenomenon identification step for identifying the leakage phenomenon of a fluid in the pressure pipeline on the basis of the extracted AE parameters.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a leakage phenomenon identification method and identification system that is capable of measuring AE waves with a single sensor and identifying a fluid leakage phenomenon in a pressurized pipeline through machine learning. [Background technology]

[0002] In recent years, many water leakage accidents due to deterioration have occurred in water transmission and distribution pipelines that utilize internal water pressure, such as those for drinking water and industrial water, and methods for identifying water leakage phenomena are being developed.Specifically, as a method for identifying the presence or absence of leakage and its location, many methods have been proposed in which sensors are installed at multiple points and the leakage location is estimated from the difference in the measured leakage waveforms.For example, Patent Document 1 discloses a method for estimating the leakage location by calculating the ratio of high-frequency components to low-frequency components.

[0003] Furthermore, Patent Document 2 discloses an invention of a water leakage location estimation system that estimates a water leakage path and location by installing a single sensor at one point. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2019-039858 A [Patent Document 2] JP 2021-183936 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, the method disclosed in Patent Document 1 has the problem that it is necessary to detect leakage waves with the same accuracy using sensors installed at two locations, and the workload is greater than that of a single sensor. Also, even in the system disclosed in Patent Document 2, a method for identifying the scale of leakage has not been confirmed, and furthermore, useful waveform parameters for identifying the presence or absence of leakage and the location of the leakage have not been fully clarified.

[0006] In other words, in the prior art, there is still no established method for accurately identifying the presence or absence of a leak, the location of the leak, and the scale of the leak using a single sensor.

[0007] Therefore, an object of the present invention is to provide a leakage phenomenon identification method and identification system that can measure AE waves using a single sensor and identify fluid leakage phenomena in pressurized pipelines, including water transmission and distribution pipelines, using machine learning. [Means for solving the problem]

[0008] The present invention provides a method for identifying a leakage phenomenon using machine learning, which is capable of identifying a fluid leakage phenomenon in a pressurized pipeline by AE waves measured by a single leakage sensor, and is characterized by having at least a measurement step of measuring AE waves by the single leakage sensor installed in the pressurized pipeline, a learning step of machine learning the measured AE waves, an extraction step of extracting AE parameters in the learning step, and a leakage phenomenon identification step of identifying a fluid leakage phenomenon in the pressurized pipeline based on the extracted AE parameters.

[0009] According to the configuration of the present invention, by identifying AE parameters that are effective in identifying the presence or absence of a leak, the location of the leak, and the size of the leak, which have not been clearly identified until now, it is possible to identify each leakage phenomenon with high accuracy using a single leakage sensor. [Brief description of the drawings]

[0010] [Figure 1] 4 is a flow chart showing a procedure for identifying a water leakage phenomenon in an embodiment of the present invention. [Diagram 2] FIG. 2 is a schematic plan view showing the arrangement of water leakage sensors in a model water distribution pipeline in an embodiment of the present invention. [Diagram 3] These are examples of the waveforms of continuous AE waves detected, where (a) is the waveform when there is a leak in the model water distribution pipeline, and (b) is the waveform when there is no leak in the model water distribution pipeline. [Figure 4] 2 shows waveforms of AE waves for explaining AE parameters that are explanatory variables in an embodiment of the present invention. [Diagram 5] 11 is a table showing an F value, which indicates the accuracy of a model, for the determination result of the presence or absence of water leakage in an embodiment of the present invention. [Figure 6] This is a table showing the top three AE parameters with high importance in the decision tree and random forest that had the highest accuracy in discriminating whether or not there was a leak. [Figure 7] 11 is a table showing an F value, which indicates the accuracy of a model, for the results of identifying a water leakage position in an embodiment of the present invention. [Figure 8] This is a table showing the top three important AE parameters in the decision tree and random forest that had the highest accuracy in identifying the leak location. [Figure 9] This is a table showing the AE parameters with the highest importance in the decision tree and random forest that had high accuracy in identifying the leak location. [Figure 10] 11 is a table showing an F value, which indicates the accuracy of a model, for the results of identification of the scale of leakage in an embodiment of the present invention. [Figure 11] This is a table showing the top three important AE parameters in the decision tree and random forest that had the highest accuracy in identifying the leak scale. [Figure 12] This is a table showing the AE parameters with the highest importance in the decision tree and random forest that had high accuracy in identifying the leak scale. [Figure 13](a) is a graph showing the importance of explanatory variables in a decision tree obtained by verification on an actual structure, and (b) is a graph showing the importance of explanatory variables in a random forest. [Figure 14] This is a photograph of the leakage state at a leak point in a water transmission pipeline, which is an actual structure. [Figure 15] 1 is a schematic block diagram of a water leakage phenomenon identification system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, with reference to the drawings, an embodiment of a leakage phenomenon identification method and identification system using machine learning according to the present invention will be described, taking a method for identifying a leakage phenomenon in a water transmission / distribution pipeline as an example.

[0012] The method and system for identifying a water leakage phenomenon in a water transmission / distribution pipeline of this embodiment uses machine learning to learn acoustic emission waves (hereinafter simply referred to as "AE waves") in the water transmission / distribution pipeline, making it possible to identify the presence or absence of a leakage in the water transmission / distribution pipeline, as well as the location and magnitude of the leakage, using a single water leakage sensor 1.

[0013] In other words, by identifying AE parameters that are effective in identifying the presence or absence, location, and magnitude of a leak, which have not been clearly defined until now, it is possible to identify each leakage phenomenon with high accuracy using a single water leakage sensor 1.

[0014] (Leakage phenomenon identification flow) The flow of identifying a water leakage phenomenon in this embodiment is shown in Figure 1. To briefly explain the flow, in step S100, AE waves in a water transmission / distribution pipeline are measured using a water leakage sensor 1 that is composed of a known elastic wave measuring device and a resonance type sensor.

[0015] In the next step S101, it is determined whether or not AE waves have been detected, and if AE waves have not been detected, the measurement conditions are reset in step S102. In resetting the measurement conditions, in addition to adjusting the frequency band, adjustments to the preamplifier, and adjustments to the amplitude detection threshold shown in Fig. 4 are performed. If it is determined in step S101 that AE waves have been detected, a class label is assigned in step S103.

[0016] Next, in step S104, the machine learning model of this embodiment determines whether or not there is a water leak. If it is determined that there is a water leak, AE parameters effective for that determination are extracted in step S105.

[0017] Next, in step S106, it is determined whether or not the leak location has been identified by the machine learning model of this embodiment. If it is determined that the leak location has been identified, AE parameters effective for this determination are extracted in step S107. If it is determined that the leak location cannot be identified, the measurement conditions are reset in step S102 as described above.

[0018] Next, in step S108, it is determined whether or not the scale of the water leakage has been identified by the machine learning model of this embodiment. If it is determined that the scale of the water leakage has been identified, AE parameters effective for this determination are extracted in step S109. If it is determined that the scale of the water leakage cannot be identified, the measurement conditions are reset in step S102 as described above.

[0019] (Investigation and verification of a model water distribution pipeline) In this embodiment, in order to identify various water leakage phenomena and to verify effective AE parameters, a model water distribution pipeline P as shown in FIG. 2 was installed and verified. A stand 2.9 m above ground was installed on the upstream side of the model water distribution pipeline P, and a water tank (not shown) was installed on the stand. A terminal valve (not shown) was installed on the downstream side, and was configured to be able to switch between discharging and not discharging. That is, the model water distribution pipeline P is assumed to be a relatively low-pressure water distribution pipeline branching off from a high-pressure water transmission pipeline. The arrangement relationship between each water leakage sensor 1 and the water leakage hole H is as shown in FIG. 2. When measuring AE waves in the model water distribution pipeline P, AE waves were measured on the model water distribution pipeline P with the water leakage hole H and the undamaged model water distribution pipeline P without the water leakage hole H. For reference, the model water distribution pipeline P in this embodiment uses a VP pipe with an inner diameter of 100.8 mm.

[0020] The measurement cases are as shown in Table 1 below. "Case A" is a case in which the end valve (not shown) of the model water distribution pipeline P was blocked and water was only drained from leak hole H. "Case B" is a case in which the end valve was opened to 11.3° and water was drained from both leak hole H and the end valve. "Case C" is a case in which the end valve was opened to 11.3° in an undamaged model pipeline P without leak hole H and water was drained only from the end valve.

[0021] [Table 1]

[0022] In addition, each water leakage sensor 1 is positioned relative to the water leakage hole H as shown in Figure 2, with a 150 kHz resonant type sensor (R15α) attached to "ch1", "ch4", "ch5", and "ch8", a 60 kHz resonant type sensor (R6α) attached to "ch2" and "ch6", and a 30 kHz resonant type sensor (R3α) attached to "ch3" and "ch7".

[0023] Each of the water leakage sensors 1 is adhered to the lower part of the pipe of the model water distribution pipeline P using a high vacuum sealing oil compound, and further fixed to the pipe by wrapping a band around it.

[0024] Additionally, the measurement conditions were a preamplifier amplification value of 40db and a detection threshold of 30db, described below. The measurement interval for AE waves was 1MHz. To confirm the effects of water pressure, pressure sensors were placed at both the upstream and downstream parts of the model water distribution pipeline P, and the water pressure at each point was measured as a synchronous signal in addition to the measurement of AE waves. The measurement conditions for AE waves are as shown in Table 2.

[0025] [Table 2]

[0026] Then, it is possible to identify each leakage phenomenon and extract effective AE parameters by applying machine learning to the AE waves detected by the water leakage sensor 1 in the model water distribution pipeline P. For reference, Fig. 3 shows an example of the waveform of detected continuous AE waves, where (a) shows the waveform when there is a water leakage hole H in the model water distribution pipeline P, and (b) shows the waveform when there is no leakage in the model water distribution pipeline P.

[0027] (Analysis methods in machine learning) Next, we explain the analysis method for identifying the presence or absence of water leakage and extracting effective AE parameters by machine learning. Figure 4 shows the waveform of the AE wave to explain the AE parameters, which are explanatory variables.

[0028] As shown in the figure, in this embodiment, the AE parameters extracted from the measured AE wave include "AMP", which is the maximum amplitude value, "RISE", which is the rise time, "DURATION", which is the duration, and "COUNT", which is the count value of the intersection with a predetermined detection threshold, as well as "A-FRQ", which is the average frequency, "C-FRQ", which is the centroid frequency, "RMS", which is the effective voltage, and "P-FRQ", which is the peak frequency.

[0029] Next, the class labels set for "determining the presence or absence of leakage," "identifying the leakage location," and "identifying the leakage scale (leak hole diameter)" are shown in Tables 3 to 5.

[0030] [Table 3]

[0031] [Table 4]

[0032] [Table 5]

[0033] The measurement data obtained by measuring AE waves was divided into training data and evaluation data to build an algorithm and verify the evaluation accuracy of the algorithm. For "determining the presence or absence of a leak," the training data was set at 70, and the evaluation data at 50. For "identifying the location of the leak" and "identifying the scale of the leak (leak hole diameter)," two training data cases were used, 40 and 200, and the evaluation data was set at 200, to examine the effect of data size on the evaluation accuracy.

[0034] When constructing the algorithm, we use "decision trees," "random forests," and "support vector machines (hereinafter referred to as "linear SVMs")," which are types of supervised learning.

[0035] The machine learning model was constructed as described above, and the accuracy of identifying various water leakage phenomena using this machine learning model and the identification of effective AE parameters are explained below.

[0036] (1) Determining whether there is a leak Figure 5 shows the F-value, which indicates the accuracy of the model, for the results of machine learning to determine the presence or absence of leakage based on measurement data taken from a model water distribution pipeline P with no leakage after discharging (terminal valve opening angle 11.3°) and a model water distribution pipeline P with a leakage hole H. As shown in the figure, when comparing the accuracy of each algorithm, it can be seen that decision trees and random forests achieve higher accuracy than linear SVM.

[0037] Comparing the accuracy for each diameter of the leak hole H, it can be seen that the larger the diameter of the leak hole H, the higher the discrimination accuracy (dashed line A in the figure), and when the diameter of the leak hole H is 3 mm or more, the F value is 0.9 or more, and it is possible to accurately determine whether or not there is a leak. Furthermore, regardless of the resonant frequency of the water leak sensor 1, the discrimination accuracy of "ch5," "ch6," and "ch7," which are close to the leak hole H, tends to be higher than that of the other water leak sensors 1 (solid line B in the figure).

[0038] In addition, the top three AE parameters with high importance in the discrimination of the decision tree and random forest, which had high discrimination accuracy, are shown in Figure 6. As shown in the figure, it is clear that the parameters with high importance common to both algorithms are "RMS", which is the effective voltage, "P-FRQ", which is the peak frequency, and "C-FRQ", which is the center of gravity frequency.

[0039] Since the majority of the AE parameters with the highest importance in the decision tree are “RMS,” which is the effective voltage, it is clear that a certain level of discrimination accuracy can be obtained with just one AE parameter.

[0040] In addition, the important AE parameters differ depending on the diameter of the leak hole H. When the diameter of the leak hole H is 1 mm, the peak frequency "P-FRQ" is more important, and when the diameter of the leak hole H is 5 mm, the effective voltage "RMS" is more important.

[0041] From the above, it became clear that the presence or absence of water leakage can be determined with high accuracy by using decision trees or random forests. In addition, it became clear that the AE parameters effective for discrimination are mainly "RMS", which is the effective voltage, and "P-FRQ", which is the peak frequency.

[0042] (2) Identifying the leak location We examined whether it was possible to identify the leak location under two conditions: "Case B" with discharge (terminal valve opening of 11.3°) and "Case A" with no discharge. Figure 7 shows the F-value, which indicates the model accuracy, for the results of leak location identification using machine learning for each of the above conditions. Comparing the identification accuracy of each algorithm, it can be seen that decision trees and random forests achieve higher accuracy than linear SVM, just as in determining the presence or absence of a leak.

[0043] Also, when comparing identification accuracy by data size, although there is a tendency for a data size of 200 to provide higher identification accuracy, it is clear that by using a 30 kHz resonant sensor (R3α), a high identification accuracy with an F value of 0.9 or more can be obtained regardless of the data size (solid line A in the figure). Furthermore, it was confirmed that there is a tendency for identification accuracy to be high in the "no discharge" case, and in addition, it was shown that when the diameter of the leak hole H is 1 mm, the identification accuracy decreases with the 60 kHz and 150 kHz resonant sensors.

[0044] The top three important AE parameters in the decision tree and random forest that showed high identification accuracy are shown in Figure 8. As shown in the figure, the important parameters common to both algorithms are "RMS" which is the effective voltage, "P-FRQ" which is the peak frequency, "C-FRQ" which is the center of gravity frequency, and "COUNT" which is the count value of the intersection with a predetermined threshold.

[0045] The important AE parameters differ depending on whether or not current is discharged. As shown in Fig. 9, in the case of "no current discharge," the important AE parameter is "RMS," which is the effective voltage, and in the case of "current discharge," the important parameter is "P-FRQ," which is the peak frequency.

[0046] From the above, it was clarified that the leak location can be identified with high accuracy by using the 30 kHz resonant sensor (R3α). In addition, it was shown that "RMS", "P-FRQ", "C-FRQ", and "COUNT" are effective AE parameters.

[0047] (3) Identification of the scale of leakage We examined whether the diameter of leak hole H could be identified under two conditions: "Case B" with discharge (terminal valve opening of 11.3°) and "Case A" without discharge. Comparing the identification accuracy of each algorithm, as shown in Figure 10, decision tree and random forest achieved higher identification accuracy than linear SVM, as in the previously examined cases (1) and (2).

[0048] Furthermore, when comparing the identification accuracy by data size, a higher identification accuracy was obtained with a data size of 200. When comparing the identification accuracy by the presence or absence of discharge, it was shown that "no discharge" was more accurate. In particular, when the data size was 200 and "no discharge" was present, the identification accuracy of the decision tree and random forest showed extremely high identification accuracy with an F-value of 0.94 or higher for all resonant sensors. As shown by the solid line A in Figure 10, the identification accuracy of "ch5," "ch6," and "ch7" is higher than that of the other resonant sensors, so even in the case of "discharge," the size of leak hole H can be identified if the resonant sensor is close to leak hole H.

[0049] The top three important AE parameters in the decision tree and random forest that showed high identification accuracy are shown in Figure 11. The important parameters common to both algorithms are "RMS" which is the effective voltage, "P-FRQ" which is the peak frequency, and "COUNT" which is the count value of the intersection with a predetermined threshold.

[0050] Furthermore, as shown in Fig. 12, the AE parameter "RMS" was shown to be an important indicator regardless of whether or not there was release, while the importance of "COUNT" was also high when there was release, and "P-FRQ" was also high when there was no release.

[0051] From the above, it became clear that the scale of the leak could be identified with high accuracy, and it was found that the AE parameters that were effective in this case were "RMS", "P-FRQ", and "COUNT".

[0052] (Verification on actual structures) Using the machine learning model described above, the accuracy of identifying water leakage phenomena was verified for a cast iron water transmission pipeline (φ250 mm) that is actually buried and in common use. In the water transmission pipeline being verified, a water leakage hole H with a diameter of 3 mm was confirmed at a position 3.0 m from the measurement point of water leakage sensor 1. In addition, the internal water pressure of the water transmission pipeline was measured under water stop conditions, ranging from an extremely high state of 0.8 MPa (maximum value: water head 78 m) to 0.01 MPa (water head 1 m) during the measurement period. Note that Figure 14 shows a photograph of water leaking vigorously from water leakage hole H in the water transmission pipeline, which is an actual structure, and the AE waves accompanying this jet flow were measured.

[0053] The water inside the water transmission pipeline was drained only from leak hole H, and it took 33 hours for the water to be drained from a full-water state to leak hole H. AE wave measurements were taken at the pumping station near leak hole H and near leak hole H, at 15-minute intervals. Each measurement was taken for 30 seconds, and the measurement conditions were a detection threshold of 20db and an amplification value by the preamplifier of 60db. As AE wave measurements were taken at the pumping station, the internal water pressure of the water transmission pipeline was evaluated simultaneously with the AE wave measurements using a water pressure meter installed in the nearby pump equipment. Note that in this verification, a wideband sensor was used as leak sensor 1.

[0054] Next, the analysis method used in the verification will be explained. As explanatory variables, eight AE parameters were extracted: "AMP" which is the maximum amplitude value, "RISE" which is the rise time, "DURATION" which is the duration, and "COUNT" which is the count value of the intersection with the specified detection threshold, as well as "A-FRQ" which is the average frequency, "C-FRQ" which is the center of gravity frequency, "RMS" which is the effective voltage, and "P-FRQ" which is the peak frequency.

[0055] Furthermore, in order to examine the differences in AE waves due to the water head, the class labels were set as shown in Table 6 below, and the acquired AE wave measurement data was divided into training data and evaluation data to construct an algorithm and verify the evaluation accuracy of the algorithm. The data size was set to 75 for training data and 58 for evaluation data, and similar to the model pipeline P described above, linear SVM, decision tree, and random forest were used to construct algorithms and compare the evaluation accuracy.

[0056] [Table 6]

[0057] Table 7 shows the verification results for a water transmission pipeline of an actual structure. Regarding the evaluation accuracy for each algorithm, a high evaluation accuracy of 0.98 or more was obtained for all indices in the decision tree and random forest. From this, it can be seen that the method for identifying a water leakage phenomenon in a water transmission / distribution pipeline using machine learning according to the present embodiment is effective not only for low-pressure water distribution pipelines such as the above-mentioned model water distribution pipeline P, but also for high-pressure water transmission pipelines. It can also be seen that the leakage phenomenon can be identified with high accuracy even in an actual structure that is significantly affected by noise.

[0058] [Table 7]

[0059] In addition, Figure 13(a) shows the importance of explanatory variables in the decision tree obtained in this verification, and Figure 13(b) shows the importance of explanatory variables in the random forest. As shown in the figure, it can be seen that "COUNT" is the most important AE parameter in both algorithms. This means that by using "COUNT" as an index, it can be said that leakage phenomena for each head difference can be identified with high accuracy.

[0060] (System Configuration) The method for identifying a water leakage phenomenon using machine learning according to this embodiment has been described above, but it is needless to say that this series of processes can be systematized. For example, Fig. 15 shows a schematic block diagram of a water leakage phenomenon identification system 100 according to this embodiment. The water leakage phenomenon identification system 100 has a single water leakage sensor 1 and a preamplifier 2 that are installed in a water transmission and distribution pipeline, and the measurement data measured by the water leakage sensor 1 is input to a PC or application server that serves as an analysis means via communication means (wired or wireless).

[0061] The PC or application server includes at least a measurement data analysis unit 101 that analyzes the measurement data measured by the water leakage sensor 1, a measurement condition setting unit 102 that sets the measurement conditions as shown in Table 2 above, a parameter extraction unit 103 that extracts AE parameters for identifying the water leakage phenomenon, a machine learning unit 104 that constructs a predetermined algorithm by supervised learning, a water leakage information output unit 106 that outputs identification information such as the presence or absence of a leak, the location of the leak, and the scale of the leak, and a measurement facility information input unit 105 that inputs facility information such as the pipe diameter and water pressure of the water transmission and distribution pipeline to be measured.

[0062] By executing the above-mentioned method for identifying a water leakage phenomenon using the device configuration or program configuration described above, it becomes possible to identify a water leakage phenomenon with high accuracy.

[0063] In addition, in an actual structure currently in use and investigated by the leakage phenomenon identification system 100, information such as the position of the actually confirmed leakage hole H (distance from the leakage sensor 1), the diameter of the leakage hole H, and the water pressure is input to the machine learning unit 104 as supervised data each time, thereby making it possible to gradually improve the accuracy of identifying the leakage phenomenon.

[0064] (Other embodiments) The above describes an embodiment of the leakage phenomenon identification method and identification system using machine learning of the present invention, taking as an example a method for identifying a leakage phenomenon in a water transmission / distribution pipeline. However, the present invention is not necessarily limited to the configuration described above, and various modifications such as those described below are possible.

[0065] For example, the leakage phenomenon identification method and identification system using machine learning of the present invention is not necessarily limited to water supply and distribution pipelines, but can be applied to pressurized pipelines that transport various fluids, such as fuel pipes, gas pipes, and steam pipes. By taking into account the characteristics of the fluid and installing a single leakage sensor in the pressurized pipeline, it is possible to identify fluid leakage phenomena (presence or absence of leakage, leakage location, leakage scale (diameter of leakage hole), etc.) with high accuracy.

[0066] Although the embodiments of the present invention have been described above based on the drawings, the specific configuration is not limited to these embodiments. The scope of the present invention is indicated by the claims, not by the description of the above embodiments, and further includes all modifications within the meaning and scope of the claims. In addition, the specific materials, dimensions, shapes, etc. described in the above examples can be modified within the scope of the present invention. [Explanation of symbols]

[0067] 1. Water leakage sensor (leakage sensor) 2 Preamplifier 100 Leakage phenomenon identification system 101 Measurement Data Analysis Section 102 Measurement condition setting section 103 Parameter Extraction Unit 104 Machine Learning Department 105 Measurement facility information input section 106 Leakage information output section

Claims

1. A method for identifying leakage phenomena by machine learning, capable of identifying a fluid leakage phenomenon in a pressurized pipeline by an AE wave measured by a single leakage sensor, comprising: a measuring step of measuring an AE wave by the single leak sensor installed in the pressurized pipeline; A learning step of machine learning the measured AE waves; A leakage phenomenon identification step of identifying the presence or absence of a leakage phenomenon, a leakage position, and a leakage scale (diameter of a leakage hole) by a machine learning model constructed based on the learning step, In the leakage phenomenon identifying step, Extraction of at least one of RMS and P-FRQ, which are AE parameters effective for determining the presence or absence of the leakage phenomenon; Extracting at least one of RMS, P-FRQ, and C-FRQ, which are AE parameters effective for determining the leak location; Identifying a fluid leakage phenomenon in the pressurized pipeline based on extraction of at least one of RMS, P-FRQ, and COUNT, which are AE parameters effective for determining the leakage magnitude. A method for identifying leakage phenomena using machine learning, comprising:

2. In the learning step, the algorithm is a decision tree or a random forest. The method for identifying leakage phenomena using machine learning according to claim 1.

3. The pressurized pipeline is a water distribution pipeline, and the fluid is water. The method for identifying leakage phenomena by machine learning according to claim 1 or 2.

4. A machine learning leak phenomenon identification system capable of identifying a fluid leak phenomenon in a pressurized pipeline, comprising: a single leak sensor installed in the pressurized pipeline; a measurement data analysis unit that analyzes measurement data measured by the single leak sensor; a measurement condition setting unit that sets measurement conditions for the single leak sensor; A parameter extraction unit extracts AE parameters for identifying a leakage phenomenon in the pressurized pipeline; A machine learning unit that constructs a predetermined algorithm through supervised learning; A leakage information output unit that outputs identification information of a leakage phenomenon in the pressurized pipeline; The measuring facility information input unit inputs facility information of the pressurized pipeline to be measured. The parameter extraction unit Extraction of at least one of RMS and P-FRQ, which are AE parameters effective for determining the presence or absence of a leakage phenomenon; Extraction of at least one of RMS, P-FRQ, and C-FRQ, which are AE parameters effective for determining a leak location; Extraction of at least one of RMS, P-FRQ, and COUNT, which are AE parameters effective for determining the leak size. A leakage phenomenon identification system using machine learning.

Images