Computing device, water leakage detection method, and water leakage detection system

Abstract

To detect water leakage whose location may be discovered with high accuracy.SOLUTION: A computing device comprises: a data acquisition section for acquiring a plurality of items of measured waveform data measured in different time zones by a vibration sensor installed in a fluid pipeline network; a water leakage determination section for calculating a plurality of time-series autocorrelation coefficients from the plurality of items of measured waveform data, calculating a water leakage score representing a relationship between the plurality of time-series autocorrelation coefficients, and executing water leakage determination processing for determining the presence or absence of a water leakage on the basis of the water leakage score; a discoverability determination section for acquiring a vibration intensity equal to or less than a predetermined value for each frequency from the plurality of items of measured waveform data, calculating a feature quantity of the vibration intensity equal to or less than the predetermined value for each frequency, and executing discoverability determination processing for determining discoverability of water leakage on the basis of the feature quantity; and an output section for outputting at least one of a result of the water leakage determination processing and a result of the discoverability determination processing.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to a computing device, a water leakage detection method, and a water leakage detection system. [Background technology]

[0002] As a technology for detecting leaks in pipeline networks such as water supply and sewerage systems and drainage pipes installed in factories as part of social infrastructure, for example, Patent Document 1 describes a "water pipeline monitoring device comprising a plurality of data collection devices and a data analysis device capable of wirelessly transmitting data to and receiving data from these data collection devices, the data collection devices measuring and recording sound pressure values ​​at predetermined intervals over a predetermined period of time each day, extracting and saving the minimum sound pressure value during the measured time, comparing the minimum sound pressure value data with an arbitrarily set sound pressure threshold, and determining whether or not an abnormality such as a leak has occurred depending on whether the minimum sound pressure value data is larger or smaller than the sound pressure threshold." [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2015-75440 A Summary of the Invention [Problem to be solved by the invention]

[0004] In the technology described in Patent Document 1, the sound pressure value of the water leakage sound at night, when the environmental sound is considered to be the quietest in a day, is compared with a threshold value to determine the presence or absence of a water leakage. Therefore, for example, in a busy shopping district or the like where there is always a loud environmental sound regardless of the time of day or night, it may not be possible to accurately determine the presence or absence of a water leakage.

[0005] In addition, the volume of the leak sound varies depending on the structure of the pipeline network and the leak flow rate, and the environmental sounds that become noise in leak detection also vary. Therefore, the threshold value to be compared with the leak sound needs to be set to an optimal value depending on the installation location and the environmental sounds.

[0006] Furthermore, even if the occurrence of a water leak can be detected based on the leak sound, if the amount of water leakage is small, the location of the leak may not be found even if an acoustic survey is carried out manually.

[0007] The present invention has been made in consideration of the above-mentioned points, and has an object to make it possible to detect water leakage with high accuracy so that the location of the leakage can be found. [Means for solving the problem]

[0008] The present application includes a number of means for solving at least some of the above problems, examples of which are as follows.

[0009] In order to solve the above problem, a calculation device according to one embodiment of the present invention includes a data acquisition unit that acquires multiple measurement waveform data measured at different time periods by a vibration sensor installed in a fluid pipeline network; a leakage determination unit that calculates autocorrelation coefficients of multiple time series from the multiple measurement waveform data, calculates a leakage score representing the relationship between the autocorrelation coefficients of the multiple time series, and executes a leakage determination process to determine whether or not a leakage has occurred based on the leakage score; a detectability determination unit that acquires vibration intensity below a predetermined value for each frequency from the multiple measurement waveform data, calculates a feature value of the vibration intensity below a predetermined value for each frequency, and executes a detectability determination process to determine the detectability of a leakage based on the feature value; and an output unit that outputs at least one of the results of the leakage determination process or the results of the detectability determination process. Effect of the Invention

[0010] According to the present invention, it is possible to detect water leakage with high accuracy, the location of which can be found.

[0011] Problems, configurations, and effects other than those described above will become apparent from the following description of the embodiments. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram showing the difference between steady water leakage vibration and sudden environmental vibration. [Diagram 2] FIG. 2 is a diagram showing the transition of the leakage score at the location where the leakage was found. [Diagram 3] FIG. 3 is a diagram showing an overview of a water leakage detection system according to an embodiment of the present invention. [Figure 4] FIG. 4 is a diagram showing an example of the configuration of a water leakage detection system according to the first embodiment of the present invention. [Diagram 5] FIG. 5 is a diagram illustrating an example of a functional block configuration of the water leakage detection device according to the first embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of a hardware configuration of a water leakage detection device. [Figure 7] FIG. 7 is a diagram illustrating an example of a functional block configuration of the management server in the first embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of the configuration of a general computer that realizes the management server. [Figure 9] FIG. 9 is a diagram showing an outline of the water leakage determination process. [Figure 10] FIG. 10 is a diagram showing an overview of the discoverability determination process. [Figure 11] FIG. 11 is a flowchart illustrating an example of the water leakage determination process in the first embodiment. [Figure 12] FIG. 12 is a flowchart illustrating an example of the measured waveform data acquisition process in step S1. [Figure 13] FIG. 13 is a flowchart illustrating an example of the water leakage determination process in step S2. [Figure 14] FIG. 14 is a diagram showing the change over time of the autocorrelation coefficient calculated from the measured waveform data including the water leakage signal. [Figure 15]FIG. 15 is a flowchart illustrating an example of the discoverability determination process in step S4. [Figure 16] FIG. 16 is a flowchart illustrating an example of the minimum vibration strength acquisition process in step S41. [Figure 17] FIG. 17 is a diagram for explaining an example of the minimum vibration strength acquisition process. [Figure 18] FIG. 18 is a diagram showing the relationship between the estimated leakage water flow rate and the detectability feature amount. [Figure 19] FIG. 19 is a diagram showing the distribution of detectability features for the results of an audio listening survey. [Figure 20] FIG. 20 is a flowchart illustrating an example of the determination result output process in step S5. [Figure 21] FIG. 21 is a diagram showing a first display example of the water leakage management screen. [Figure 22] FIG. 22 is a diagram showing a second display example of the water leakage management screen. [Figure 23] FIG. 23 is a diagram showing a third display example of the water leakage management screen. [Figure 24] FIG. 24 is a diagram showing a fourth display example of the water leakage management screen. [Diagram 25] FIG. 25 is a diagram illustrating an example of a functional block configuration of a water leakage detection device according to the second embodiment. [Figure 26] FIG. 26 is a diagram illustrating an example of a functional block configuration of a management server according to the second embodiment. As illustrated in FIG. [Figure 27] FIG. 27 is a flowchart illustrating an example of the water leakage determination process in the second embodiment. [Figure 28] FIG. 28 is a diagram showing an example of the functional block configuration of a water leakage detection device according to the third embodiment. [Figure 29] FIG. 29 is a diagram illustrating an example of a functional block configuration of a management server according to the third embodiment. As illustrated in FIG. [Diagram 30] FIG. 30 is a flowchart illustrating an example of the water leakage determination process in the third embodiment. [Diagram 31]FIG. 31 is a diagram showing an example of the functional block configuration of a water leakage detection device according to the fourth embodiment. As shown in FIG. [Diagram 32] FIG. 32 is a diagram illustrating an example of a functional block configuration of a management server according to the fourth embodiment. As illustrated in FIG. [Diagram 33] FIG. 33 is a flowchart illustrating an example of the water leakage determination process in the fourth embodiment. [Diagram 34] FIG. 34 is a flowchart illustrating a first modified example of the water leakage determination process in the first embodiment. [Diagram 35] FIG. 35 is a flowchart illustrating a first modified example of the water leakage determination process in the second embodiment. [Diagram 36] FIG. 36 is a flowchart illustrating a modification of the minimum vibration strength acquisition process in step S41. [Figure 37] FIG. 37 is a flowchart illustrating a first modified example of the discoverability determination process. [Figure 38] FIG. 38 is a diagram showing the relationship between frequency and minimum vibration strength when the amount of water leakage is different. [Figure 39] FIG. 39 is a flowchart illustrating a second modified example of the discoverability determination process. [Diagram 40] FIG. 40 is a flowchart illustrating an example of a minimum vibration strength acquisition process in the third modified example of the discoverability determination process. [Diagram 41] FIG. 41 is a diagram for explaining the process of updating the autocorrelation coefficient for each delay time. [Diagram 42] FIG. 42 is a flowchart illustrating an example of a minimum vibration strength acquisition process in the fourth modified example of the discoverability determination process. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] Hereinafter, a number of embodiments of the present invention will be described with reference to the drawings. Each embodiment is an example for explaining the present invention, and is omitted and simplified as appropriate for clarity of explanation. The present invention can be implemented in various other forms. Unless otherwise limited, each component may be singular or plural. The position, size, shape, range, etc. of each component shown in the drawings may not represent the actual position, size, shape, range, etc. in order to facilitate understanding of the invention. For this reason, the present invention is not necessarily limited to the position, size, shape, range, etc. disclosed in the drawings. As examples of various information, descriptions may be given using expressions such as "table", "list", and "queue", but various information may be expressed in other data structures. For example, various information such as "XX table", "XX list", and "XX queue" may be expressed as "XX information". When describing identification information, expressions such as "identification information", "identifier", "name", "ID", and "number" are used, but these are interchangeable. In all drawings for explaining the embodiments, the same members are generally given the same reference numerals, and repeated descriptions thereof will be omitted. In the following embodiments, the components (including element steps, etc.) are not necessarily essential unless otherwise specified or considered to be clearly essential in principle. When "consisting of A," "made of A," "having A," or "including A" is used, other elements are not excluded unless otherwise specified to mean only that element. Similarly, in the following embodiments, when referring to the shape, positional relationship, etc. of components, etc., it includes those that are substantially similar or similar to that shape, etc., unless otherwise specified or considered to be clearly not essential in principle.

[0014] <Outline of the water leakage detection system according to this embodiment> The water leakage detection system detects water leakage from pipes based on vibrations measured by a vibration sensor installed in a pipeline network, such as a water supply and sewerage system as part of social infrastructure, or a drainage channel installed in a factory.

[0015] The vibration sensor installed in the pipe can be installed at various locations, such as water control valves in the pipeline network, to measure vibrations caused by water leakage. Note that the vibration sensor can measure not only vibrations transmitted through the pipe, but also vibrations caused by sounds transmitted through air or liquid.

[0016] The cause of vibration caused by leakage from a pipe is considered to be turbulence at the leakage hole outlet. The leakage hole outlet is a hole that occurs in a pipe and the leakage water is spouting from the hole. Hereinafter, the leakage hole outlet is also simply called the leakage hole. When a leakage hole occurs in a pipe where water or the like flows at high pressure and water leaks, localized steep pressure fluctuations occur near the tiny leakage hole. At this time, a cavitation phenomenon occurs in the vicinity of the leakage hole, where tiny bubbles are repeatedly generated and destroyed due to pressure fluctuations in the water. The repeated motion of periodic generation and destruction of bubbles caused by the cavitation phenomenon generates a specific impulse sound in the vicinity. The generated impulse sound propagates through the pipe and the water flowing inside the pipe. It is possible to detect the occurrence of a leakage by measuring this periodic impulse sound with a vibration sensor. In order to accurately identify the occurrence of a leakage, it is necessary to accurately extract the periodic component observed when the leakage occurs.

[0017] Figure 1 is a diagram showing the difference between steady water leakage vibrations that occur in a pipeline network and sudden environmental vibrations. As shown in the figure, vibrations caused by water leakage generally occur continuously regardless of the time of day. In contrast, vibrations caused by the environment, such as vehicle traffic, occur suddenly. Therefore, if vibrations with the same periodic characteristics (steadiness) can be captured in different time periods, it is possible to determine that there is a water leak.

[0018] In this embodiment, an autocorrelation function is used to grasp the periodic characteristics (stationarity) of the vibration measured by the vibration sensor, that is, the periodic characteristics of the signal itself. The autocorrelation function G(τ) is a function that obtains the correlation between a certain signal p(t) and a signal p(t+τ) obtained by shifting the signal in time, and is defined by the following equation (1).

[0019]

number

[0020] When a signal p(t) has a periodic component with a period τ0, the autocorrelation function G(τ) shows a peak at G(τ0). Therefore, by obtaining the peak information of the autocorrelation function, it is possible to determine whether the signal p(t) is periodic.

[0021] In this embodiment, by calculating the autocorrelation function of vibration data measured at different time periods over multiple days, it is possible to make a leak judgment that is not dependent on the magnitude of the leak vibration while avoiding the false detection of sudden vibrations caused by vehicle traffic, etc. as a leak.

[0022] In actual operation, after determining that there is a leak based on the autocorrelation function, workers will search for the leak location by conducting an acoustic survey using a listening rod or similar. When conducting an acoustic survey, if the vibration is not loud enough for the worker to detect, the worker may not be able to find the leak even if it is occurring. From this perspective, in addition to determining the leak based on periodicity (steadiness), it is also important to determine whether the vibration at the location where the leak is determined to exist is loud enough to be detected by an acoustic survey.

[0023] FIG. 2 shows the transition of the judgment result when the water leakage judgment is performed based only on the periodicity of the vibration measured by the vibration sensor installed at a certain location. Here, the water leakage score is an index that indicates the high possibility of the occurrence of the water leakage. The installation location showed a high water leakage score for a long time after the vibration sensor was installed, but the water leakage point could not be found by the acoustic survey. On the other hand, after a certain period of time, water seepage onto the road surface occurred, and a nearby resident reported that the water leakage had occurred. The cause of this is thought to be that when the vibration sensor was first installed, the worker detected a minute water leakage that was too small to be heard by ear. In general, the magnitude of the water leakage vibration increases the closer it is to the water leakage point and the higher the leakage flow rate, and it is easier to find it by the acoustic survey. Therefore, if the presence or absence of the water leakage is judged using only the evaluation results regarding the periodicity (steadiness), it is not desirable because it will also report even a minute water leakage that cannot be found by the acoustic survey.

[0024] Therefore, the water leakage detection system according to the embodiment of the present invention is configured as follows. FIG. 3 shows an outline of the configuration of the water leakage detection system 1 according to the embodiment of the present invention. As shown in the figure, the water leakage detection system 1 according to the embodiment of the present invention is configured with a water leakage determination unit 112 having an autocorrelation function calculation unit 11201 that performs an extraction process of the peak position of the autocorrelation function and a water leakage determination processing unit 11202 that performs a water leakage determination based on the peak position of the autocorrelation function, a minimum vibration intensity feature amount calculation unit 11301 that calculates a minimum vibration intensity feature amount and a detectability determination processing unit 11302 that determines the detectability based on the minimum vibration intensity feature amount, a data acquisition unit 111 that acquires measured waveform data representing the measured time series vibration, and an output unit 114 that outputs the results of the water leakage determination process and the results of the detectability determination process. The water leakage determination unit 112 determines the presence or absence of water leakage based on the peak position information (periodicity) of the autocorrelation function from a plurality of measured waveform data measured at different time periods over several days. The detectability determination unit 113 determines whether or not a leak can be easily detected by an acoustic survey at a location where there is a possibility of a leak.

[0025] <Configuration example of the water leakage detection system 1 according to the first embodiment of the present invention> 4 shows an example of the configuration of a water leakage detection system 1 according to a first embodiment of the present invention. The water leakage detection system 1 includes a plurality of water leakage detection devices 10 installed at a plurality of locations (e.g., near water control valves) in a pipeline network 2, and a management server 20 to which each of the water leakage detection devices 10 is connected via a network N.

[0026] The pipeline network 2 is, for example, a water supply and sewerage system as social infrastructure, or a drainage channel installed in a factory, etc., and water flows through the pipes. The network N is a two-way communication network such as a WAN (Wide Area Network), a LAN (Local Area Network), the Internet, or a mobile phone communication network. The connection to the network N may be wireless or wired. In addition, the water leakage detection device 10 and the management server 20 may be directly connected wirelessly or wired without going through the network N.

[0027] The water leak detection device 10 corresponds to the arithmetic device of the present invention. The water leak detection device 10 has a built-in vibration sensor 108 (FIG. 6) that measures vibrations caused by a water leak that has occurred in the pipeline network 2, and executes a water leak determination process that determines the presence or absence of a water leak based on measured waveform data that represents a time-series vibration measured by the vibration sensor 108, and a detectability determination process that determines whether or not the location of the water leak that has been determined to have a water leak can be easily found by an operator through an acoustic investigation.

[0028] The management server 20 displays a UI screen including the results of the leakage determination process and the detectability determination process transmitted from each water leakage detection device 10, and presents it to a user of the management server 20 (such as the administrator of the pipeline network 2). The management server 20 may also be connected to the water leakage detection devices 10 via the network N to update the water leakage detection devices 10 and collect error log data.

[0029] <Configuration Example of Water Leak Detection Device 10 in First Embodiment> 5 shows an example of the configuration of functional blocks constituting the water leakage detection device 10 (hereinafter referred to as the water leakage detection device 101) in the first embodiment. The water leakage detection device 101 includes functional blocks of a processing unit 11, a storage unit 12, a measurement unit 13, and a communication unit 14. The processing unit 11 includes a data acquisition unit 111, a water leakage determination unit 112, a detectability determination unit 113, and an output unit 114.

[0030] 6 shows an example of the configuration of hardware constituting the water leakage detection device 101. The water leakage detection device 101 includes a microcontroller 101 incorporating a processor (not shown) such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit) and a memory (not shown) such as a DRAM (Dynamic Random Access Memory), a storage 103 such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive), an input device 104 such as a switch, an output device 105 such as a display, a communication module 106 such as a NIC (Network Interface Card), a battery 107, and a vibration sensor 108. However, a processor and a memory may be provided instead of the microcontroller 101.

[0031] The water leakage detection device 101, for example, realizes each of the functional blocks of a processing unit 11, a data acquisition unit 111, a water leakage determination unit 112, a detectability determination unit 113, and an output unit 114 by loading a program 102 stored in a storage 103 into the memory of the microcontroller 101 and having the processor of the microcontroller 101 execute the program 102 loaded into the memory.

[0032] The processing unit 11 controls the operation of each unit of the water leakage detection device 101. The data acquisition unit 111 acquires measured waveform data 121 representing the time series of vibrations measured by the measurement unit 13 and stores it in the memory unit 12. The water leakage determination unit 112 executes a water leakage determination process based on the measured waveform data 121. The detectability determination unit 113 executes a detectability determination process based on the measured waveform data 121. The output unit 114 controls the communication unit 14 to transmit a water leakage determination result 122, which is the result of the water leakage determination process, and a detectability determination result 124, which is the result of the detectability determination process, to the management server 20.

[0033] However, some or all of these functional blocks may be realized as hardware using integrated circuits or the like. Furthermore, these functional blocks may be realized by one microcontroller 101, or may be realized by multiple microcontrollers 101. When realized by multiple microcontrollers 101, the multiple microcontrollers 101 may be connected via a network N, or may be distributed and located in remote locations. Furthermore, instead of the microcontroller 101, a dedicated circuit such as a Field Programmable Gate Array (FPGA), an Application Specific Integrated Circuit (ASIC), or a Complex Programmable Logic Device (CPLD) may be used.

[0034] The memory unit 12 is realized by a memory resource consisting of the storage 103. The memory unit 12 stores measured waveform data 121 measured by the measurement unit 13 (vibration sensor 108), a water leakage determination result 122, a minimum vibration intensity for each frequency 123 acquired in the process of the detectability determination process, and a detectability determination result 124. Note that the measured waveform data 121, the water leakage determination result 122, the minimum vibration intensity for each frequency 123, and the detectability determination result 124 are provided with a time stamp, an identifier, or the like, for indicating a correspondence relationship between them. Note that the memory unit 12 may temporarily or permanently store data or information other than the measured waveform data 121, the water leakage determination result 122, the minimum vibration intensity for each frequency 123, and the detectability determination result 124.

[0035] The measurement unit 13 is realized by a vibration sensor 108. The measurement unit 13 intermittently measures vibrations at different time periods over several days. However, the measurement unit 13 may measure vibrations continuously at all times, rather than intermittently, and extract data from the results of the continuous constant measurement for a predetermined number of times measured at different time periods on different dates.

[0036] The communication unit 14 is realized by the communication module 106. The communication unit 14 connects to the management server 20 via the network N and transmits the water leakage determination result 122 and the detectability determination result 124. The communication unit 14 may also connect to a maintenance terminal (not shown) by short-distance wireless communication such as BLUETOOTH (trademark) or by wired communication to receive an update program for the water leakage detection device 101 and transmit error log data for the water leakage detection device 101. Note that maintenance and management of the water leakage detection device 101 using the maintenance terminal (not shown) can be performed by workers of the manufacturer of the water leakage detection device 101, a management organization (e.g., a waterworks bureau, etc.) that manages the pipeline network 2, a maintenance management company that undertakes maintenance and management of the water leakage detection device 101, etc.

[0037] <Configuration Example of Management Server 20 in First Embodiment> Fig. 7 shows an example of the functional block configuration of the management server 20 (hereinafter referred to as the management server 201) in the water leakage detection system 1. The management server 201 has functional blocks of a processing unit 21, a storage unit 22, and a communication unit 23. The management server 201 is realized by a general computer 200 (Fig. 8) such as a server computer or a personal computer.

[0038] 8 shows an example of the configuration of a general computer 200 that realizes a management server 201. The computer 200 includes a processor 201 such as a CPU or a GPU, a memory 202 such as a DRAM, a storage 203 such as an HDD or an SSD, an input device 204 such as a keyboard or a mouse, an output device 205 such as a display, and a communication module 206 such as a NIC.

[0039] The processing unit 21 of the management server 201 and the UI control unit 211 included in the processing unit 21 are realized by the processor 201 of the computer 200 executing a program 2021 loaded into the memory 202. The storage unit 22 is realized by the memory 202 and the storage 203 of the computer 200. The communication unit 23 is realized by the communication module 206 of the computer 200.

[0040] The processing unit 21 controls the overall operation of the management server 201. The UI control unit 211 displays a water leakage management screen on the display (output device 205) of the computer 200 based on the water leakage judgment result 122 and the detectability judgment result 124 stored in the memory unit 22. The memory unit 22 stores the judgment results (the water leakage judgment result 122 and the detectability judgment result 124) transmitted from the water leakage detection device 101. The communication unit 23 receives the judgment results transmitted from the water leakage detection device 101.

[0041] <Outline of leak detection process> 9 is a diagram showing an overview of the water leakage determination process. In the water leakage determination process, the autocorrelation function of each of a plurality of pieces of measured waveform data measured by the measuring unit 13 at different time periods over several days is calculated, period information of each piece of measured waveform data is obtained based on the autocorrelation function, and the presence or absence of water leakage is determined based on the degree to which the period information of each piece of measured waveform data matches.

[0042] <Outline of discoverability determination process> FIG. 10 is a diagram showing an outline of the detectability determination process. In the detectability determination process, the same multiple measured waveform data as in the above-mentioned water leakage determination process are used, and a fast Fourier transform (FFT) is performed on each measured waveform data to calculate the vibration intensity of each frequency component, which are then superimposed to obtain the minimum vibration intensity (minimum hold) for each frequency component. Here, the minimum vibration intensity for each frequency component is a value that is smaller than a predetermined value (for example, an average value) for each frequency component of multiple measured waveform data measured at different time periods over several days. Since vibration caused by water leakage occurs with a certain specific frequency and vibration intensity in any time period, by obtaining the minimum hold for each frequency component, it is possible to further emphasize the vibration characteristics specific to the water leakage vibration while removing the superimposed components of the environmental vibration. By using the minimum hold to convert it into a feature quantity, the detectability of water leakage can be determined.

[0043] <Leak detection processing by leak detection system 1> 11 is a flowchart illustrating an example of the water leakage detection process by the water leakage detection system 1. The water leakage detection process is periodically executed at a predetermined cycle.

[0044] First, the data acquisition unit 111 of the water leakage detection device 101 executes a measurement waveform data acquisition process (step S1).

[0045] FIG. 12 is a flow chart for explaining an example of the measured waveform data acquisition process. First, the data acquisition unit 111 controls the measurement unit 13 to start vibration measurement at different time periods over several days (step S11). The time periods for measuring vibration may be scheduled in advance or may be randomly determined. The number of measurements in one day may be fixed or may be changed every day. Furthermore, the number of measurements and the measurement time may be dynamically changed based on the result of the water leakage determination, such as increasing the number of measurements on the day after it is determined that there is a water leakage by the water leakage determination process (described later). Also, instead of measuring vibration intermittently as described above, it is possible to measure vibration continuously and extract measured waveform data for a predetermined number of times and for a predetermined time period from the measurement data that is continuous in time. Then, the data acquisition unit 111 acquires the measurement results from the measurement unit 13 and stores them in the storage unit 12 as measured waveform data 121 (step S12).

[0046] Next, the data acquiring unit 111 determines whether the number of measured waveform data 121 stored in the memory unit 12 has reached a predetermined number N (step S13), and if it determines that the number has not reached the predetermined number N (NO in step S13), the process returns to step S12 and steps S12 and S13 are repeated. Thereafter, if it determines that the number of measured waveform data 121 stored in the memory unit 12 has reached the predetermined number N (YES in step S13), the data acquiring unit 111 ends the measured waveform data acquisition process.

[0047] Returning to Fig. 11, next, the water leakage determination unit 112 of the water leakage detection device 101 executes a water leakage determination process based on the N pieces of measured waveform data 121 stored in the storage unit 12 (step S2).

[0048] 13 is a flowchart for explaining an example of the water leakage determination process. First, the water leakage determination unit 112 calculates a time-series autocorrelation coefficient for each of the N pieces of measured waveform data 121 (step S21). Note that one piece of measured waveform data 121 may be divided into multiple pieces in the time direction, and multiple autocorrelation coefficients may be calculated from one piece of measured waveform data 121.

[0049] FIG. 14 shows an example of autocorrelation coefficients calculated from N pieces of measured waveform data 121 in a superimposed manner. In the figure, the horizontal axis is time, and the unit is the same as the sampling interval of the vibration sensor 108. The vertical axis is the autocorrelation coefficient. As shown in the figure, a peak position information set having multiple peaks is observed over time in the autocorrelation coefficient. If the N pieces of measured waveform data 121 are observations of vibration caused by a water leak, the autocorrelation coefficients calculated from the N pieces of measured waveform data 121 observed at various time periods will match, and therefore the peak position information sets will also match.

[0050] Returning to Fig. 13, the leakage determination unit 112 then extracts a peak position set including multiple peak positions from each autocorrelation coefficient (step S22). At this time, the peak position set may be extracted by selecting an autocorrelation coefficient with less noise. The time width for extracting the peak position set can be set according to the sampling interval of the measured waveform data 121 so that the peak position set includes multiple peak positions.

[0051] For example, if one measured waveform data lasts for 4 seconds, the 4 seconds are divided into 16 periods, and the autocorrelation coefficients are calculated for every 250 ms to calculate 16 autocorrelation coefficients. Then, from the 16 autocorrelation coefficients, 6 autocorrelation coefficients with the least noise are selected, and 6 peak position information sets are extracted from the 6 autocorrelation coefficients. In this way, 6 x N peak position information sets can be extracted from N measured waveform data.

[0052] Next, the water leakage determination unit 112 compares all combinations of two peak position sets extracted in step S22, and calculates the coincidence rate of the peak positions (step S23). Note that instead of calculating the coincidence rate of the peak positions, the similarity rate may be calculated. The coincidence rate and similarity rate of the peak positions correspond to the water leakage score of the present invention.

[0053] Next, the water leakage determination unit 112 determines whether or not there is a water leakage based on the result of step S23 (step S24). For example, if the ratio of combinations of peak position sets in which the peak position coincidence rate is equal to or greater than a predetermined first threshold is equal to or greater than a predetermined second threshold, it is determined that there is a water leakage. Conversely, if the ratio of combinations of peak position sets in which the peak position coincidence rate is equal to or greater than the predetermined first threshold is less than the predetermined second threshold, it is determined that there is no water leakage.

[0054] Instead of the above-mentioned leakage determination, leakage determination may be performed using a graph network capable of grasping the relationship between the peak information of multiple autocorrelation coefficients. Here, a graph is a figure represented by multiple points and edges connecting them, and a graph network is a figure in which the points and edges are given physical meaning. In this case, each point can correspond to each measured waveform data to be compared, and each edge can correspond to the coincidence rate of the peak position. For example, a graph network is obtained in which points with a peak position coincidence rate of more than 80% are connected by lines to display the edges. By constructing a graph network between measured waveform data acquired at a leakage occurrence site, a large cluster is formed because the coincidence rate of the peak positions is high. On the other hand, peak positions acquired at a site where leakage does not occur are independent of each other and have little correlation, so a graph network having multiple clusters is obtained. Leaks may be determined based on such information.

[0055] Next, the water leakage determination unit 112 stores the water leakage score calculated in step S23 and the presence or absence of a water leakage determination determined in step S24 in the storage unit 12 as the water leakage determination result 122 (step S25). This concludes the description of the water leakage determination process by the water leakage determination unit 112.

[0056] Returning to Fig. 11, the detectability determination unit 113 of the water leakage detection device 101 then determines whether or not it is necessary to execute a detectability determination process (step S3). Specifically, if it is determined in step S2 that there is a water leak, it is determined that it is necessary to execute a detectability determination process. Alternatively, regardless of the determination result in step S2, it may be determined that it is necessary to execute a detectability determination process when a predetermined number of days have passed since the operation start date of the water leakage detection device.

[0057] Here, if it is determined that the discoverability determination process needs to be executed (YES in step S3), the discoverability determination section 113 executes the discoverability determination process (step S4) based on the N pieces of measured waveform data 121 stored in the storage section 12. Conversely, if the discoverability determination section 113 determines that the discoverability determination process does not need to be executed (NO in step S3), the discoverability determination process in step S4 is skipped.

[0058] 15 is a flowchart illustrating an example of the discoverability determination process. First, the discoverability determination unit 113 executes a minimum vibration strength acquisition process (step S41).

[0059] 16 is a flowchart illustrating an example of a minimum vibration strength acquisition process. First, the discoverability determination unit 113 initializes a parameter Y for designating one of the N pieces of measured waveform data 121 to 1 (step S411).

[0060] Next, the discoverability determination unit 113 acquires the Y-th measured waveform data 121 from the storage unit 12 among the N pieces of measured waveform data 121 (step S412). Next, the discoverability determination unit 113 executes a fast Fourier transform (FFT) on the Y-th measured waveform data 121 (step S413) and stores the result in the storage unit 12 (step S414).

[0061] Next, the discoverability determination unit 113 determines whether the parameter Y has reached the number N of measured waveform data 121 (step S415). If it is determined that the parameter Y has not reached the number N of measured waveform data 121 (NO in step S415), the discoverability determination unit 113 increments the parameter Y by 1 (step S416). Thereafter, the discoverability determination unit 113 returns the process to step S412 and repeats step S412 and subsequent steps.

[0062] Thereafter, if it is determined that the parameter Y has reached the number N of measured waveform data 121 (YES in step S415), then the discoverability determination unit 113 extracts the minimum vibration strength for each frequency from the N FFT results, and stores it in the storage unit 12 as the minimum vibration strength for each frequency 123 (step S417). This concludes the description of the minimum vibration strength acquisition process.

[0063] FIG. 17 is a diagram for explaining the process of extracting the minimum vibration intensity for each frequency from N FFT results in step S417. In addition, in the figure, the case of N=2 is shown for the sake of simplicity. The dashed line is the first (Y=1) FFT result, and the dotted line is the second (Y=2) FFT result. In this case, as the minimum vibration intensity for each frequency, in the band from 0 to 600 Hz, the FFT result of the second measured waveform is smaller in vibration intensity than the FFT result of the first measured waveform, so the FFT result of the second measured waveform is extracted. In the band above 600 Hz, the FFT result of the first measured waveform is smaller in vibration intensity than the FFT result of the second measured waveform, so the FFT result of the first measured waveform is extracted. By performing the above process on the N FFT results, the minimum vibration intensity for each frequency that is finally extracted will be a value below the average intensity for each frequency of the N FFT results, reducing the frequency components of environmental vibrations such as sudden noise and emphasizing the frequency components of steady water leakage vibration. Using the minimum vibration intensity for each frequency based on the above process makes it easier to identify the characteristics of steady water leakage vibration.

[0064] Returning to Fig. 15, the discoverability determination unit 113 then extracts a discoverability feature based on the minimum vibration strength 123 for each frequency acquired in step S41 (step S42). Specifically, for example, the minimum vibration strength for each frequency is integrated in a predetermined frequency band. This integrated value corresponds to the area of ​​the hatched region shown in Fig. 17. However, the frequency band to be integrated is not limited to the range shown in Fig. 17, and may be limited to a predetermined frequency band, or may be divided into a plurality of frequency bands and the integrated values ​​for each band may be used.

[0065] Next, the detectability determining unit 113 compares the detectability feature amount extracted in step S42 with a predetermined threshold value to determine whether or not a water leak can be detected by an acoustic survey (step S43).

[0066] Fig. 18 shows the relationship between the estimated leakage flow rate and the detectability feature, where the horizontal axis is the estimated leakage flow rate and the vertical axis is the detectability feature (a value normalized by a predetermined value). As shown in the figure, it can be confirmed that the larger the detectability feature is, the larger the leakage flow rate is.

[0067] FIG. 19 shows the distribution of detectability features (values ​​normalized by a predetermined value) for two types of results of an acoustic survey: when no leak is found (no leak sound) or when a leak is found (leak sound present). As shown in the figure, it can be seen that when no leak is found by an acoustic survey, the detectability feature is small, and when a leak is found by an acoustic survey, the detectability feature is large. Therefore, in the case of the figure, if the threshold value for the detectability feature (values ​​normalized by a predetermined value) is set to, for example, 0.1, it becomes possible to determine whether or not a leak can be found by an acoustic survey.

[0068] Returning to Fig. 15, the discoverability determination section 113 then stores the determination result in step S43 in the storage section 12 as the discoverability determination result 124 (step S44). The discoverability determination process by the discoverability determination section 113 has been described above.

[0069] Returning to Fig. 11, next, the output unit 114 of the water leakage detection device 101 executes a determination result output process (step S5).

[0070] 20 is a flow chart for explaining an example of the judgment result output process. First, the output unit 114 judges whether or not it is necessary to transmit the water leakage judgment result 122 and the detectability judgment result 124 stored in the storage unit 12 to the management server 201 based on the water leakage judgment result 122 and the detectability judgment result 124 stored in the storage unit 12 to the management server 201 (step S51). Specifically, for example, when the water leakage judgment result 122 indicates that there is a water leakage and the detectability judgment result 124 indicates that a water leakage can be detected, it is judged that it is necessary to transmit these judgment results to the management server 201.

[0071] However, even if the water leakage judgment result 122 indicates that there is no water leakage or the detection ease judgment result indicates that a water leakage cannot be detected, it may be periodically judged that it is necessary to transmit the judgment result to the management server 201 for the purpose of checking the aliveness of the water leakage detection device 101 (checking whether it is operating normally or not).

[0072] Then, when it is determined that transmission is necessary (YES in step S51), the output unit 114 then controls the communication unit 14 to transmit the determination results (the water leakage determination result 122 and the detectability determination result 124) stored in the memory unit 12 to the management server 201 via the network N (step S52). Note that, when the detectability determination process in step S4 has not been executed, it is sufficient to transmit only the water leakage determination result 122 stored in the memory unit 12.

[0073] On the other hand, if the output unit 114 determines that transmission is not necessary (NO in step S51), step S52 is skipped. This concludes the description of the determination result output process by the output unit 114.

[0074] Returning to Fig. 11, on the other hand, in the management server 201, the communication unit 23 receives the determination result transmitted from the water leakage detection device 101 and stores it in the memory unit 22. Next, the UI control unit 211 of the management server 201 displays a water leakage management screen based on the determination result stored in the memory unit 22 (step S6). This concludes the description of the water leakage detection process by the water leakage detection system 1.

[0075] <Leakage management screen displayed on management server 201> FIG. 21 shows a first display example of the water leakage management screen displayed on the management server 201.

[0076] A water leakage management screen 10001, which is a first display example, is provided with display areas 1001 to 1004. The display area 1001 displays the pipeline network 2 and the positions of the water leakage detection devices 101 installed in the pipeline network 2. The display area 1001 is provided with an "enlarge" button 1011 for enlarging the display of the pipeline network 2 in the display area 1001, a "reduce" button 1012 for reducing the display, and an input field 1013 for selecting the water leakage detection device 101. A user can select one of the multiple water leakage detection devices 101 installed in the pipeline network 2 by inputting identification information (sensor ID) of the water leakage detection device 101 in the input field 1013. Note that instead of inputting the identification information (sensor ID) of the water leakage detection device 101 in the input field 1013, the water leakage detection device 101 can also be selected by clicking on one of the water leakage detection devices 101 on the pipeline network 2 displayed in the display area 1001.

[0077] A display area 1002 displays the transition of the water leakage score over a predetermined period of the selected water leakage detection device 101. A display area 1003 displays the most recent water leakage judgment result of the selected water leakage detection device 101. A display area 1004 displays the most recent detectability judgment result of the selected water leakage detection device 101.

[0078] Instead of the user selecting the water leak detection device 101, for example, a water leak detection device 101 that has recently been determined to have a leak and is easy to detect may be automatically selected. The user can recognize the occurrence of a leak based on the information displayed on the water leak management screen 10001, and can comprehensively determine whether or not to conduct an acoustic inspection of the leak location.

[0079] FIG. 22 shows a second display example of the water leakage management screen displayed on the management server 201.

[0080] A water leakage management screen 10002, which is a second display example, is obtained by adding a display area 1005 to the water leakage management screen 10001 (FIG. 21). In the display area 1005, the horizontal axis is frequency and the vertical axis is minimum vibration intensity, and the minimum vibration intensity for each frequency corresponding to the date and time selected by the user on the curve representing the water leakage score in the display area 1002 is displayed. However, in order for the management server 201 to display the minimum vibration intensity for each frequency in the display area 1005, it is necessary to transmit the minimum vibration intensity 123 for each frequency from the water leakage detection device 101 to the management server 201. The user can confirm the validity of the judgment result of the ease of water leakage detection based on the relationship between each frequency and the minimum vibration intensity displayed in the display area 1005.

[0081] FIG. 23 shows a third display example of the water leakage management screen displayed on the management server 201.

[0082] The third display example, a water leakage management screen 10003, is obtained by adding a display area 1006 to the water leakage management screen 10001 (FIG. 21). In the display area 1006, the horizontal axis represents frequency, the vertical axis represents minimum vibration intensity, and the depth axis represents date and time, and the transition of the minimum vibration intensity for each frequency is displayed. However, in order for the management server 201 to display the minimum vibration intensity for each frequency in the display area 1006, the water leakage detection device 101 needs to transmit the minimum vibration intensity for each frequency 123 to the management server 201. The user can confirm the validity of the judgment result of the ease of water leakage detection based on the relationship between each frequency and the vibration intensity displayed in the display area 1005. In addition, for example, if a water leakage occurs at a certain time point, the minimum vibration intensity for each frequency also takes a different shape at the same time point. In addition, in cases where the corrosion of the water leakage hole progresses after the occurrence of the water leakage and the amount of water leakage gradually increases, the minimum vibration intensity for each frequency also changes over time. Therefore, the user can grasp information regarding the occurrence of a water leak and changes in the amount of water leaked over time based on the date and time changes in the minimum vibration intensity for each frequency, thereby improving the accuracy of estimating the ease of detection.

[0083] FIG. 24 shows a fourth display example of the water leakage management screen displayed on the management server 201.

[0084] A water leakage management screen 10004, which is a fourth display example, is obtained by adding a display area 1007 to the water leakage management screen 10001 (FIG. 21). The display area 1007 displays the transition of the detectability feature of the water leakage in a predetermined period in the selected water leakage detection device 101, with the horizontal axis representing date and time and the vertical axis representing the detectability feature. However, in order for the management server 201 to display the transition of the detectability feature in the display area 1007, it is necessary for the water leakage detection device 101 to transmit the detectability feature to the management server 201. The user can estimate the change in the amount of water leakage from the transition of the detectability feature displayed in the display area 1007, and the accuracy of the estimation of detectability can be improved.

[0085] The method of displaying the determination results transmitted from the water leakage detection device 101 is not limited to a GUI (Graphical User Interface) screen using figures and graphs like the water leakage management screens 10001-10004, but may be, for example, a CUI (Character User Interface) in which commands are entered on a text basis, or the determination results may be displayed on a text basis without using figures or graphs.

[0086] Moreover, the display of the water leakage management screens 10001 to 10004 is not limited to the management server 201, and may be displayed on a maintenance terminal (not shown) connected to the water leakage detection device 101, for example.

[0087] As described above, the water leakage detection system 1 makes it possible to determine leakage while avoiding false detections caused by sudden environmental vibrations such as the passing of automobiles, and furthermore, to obtain a judgment index regarding the ease of detecting leakage points by acoustic inspection. This makes it possible to avoid acoustic inspections of leakage events that are difficult to detect, and to limit or prioritize acoustic inspections to leakages that are easy to detect, thereby improving the efficiency of acoustic inspections.

[0088] <Water leakage detection system 12 according to a second embodiment of the present invention> Next, a water leakage detection system 12 (not shown) according to a second embodiment of the present invention will be described. The water leakage detection system 12 is configured such that most of the detectability determination process (step S4 (S41 to S44 in FIG. 15)) performed by the water leakage detection device 101 in the above-mentioned water leakage detection system 1 is performed by the management server 202.

[0089] The water leakage detection system 12 has the same configuration as the water leakage detection system 1 (FIG. 4). However, the configurations of the water leakage detection device 102 (FIG. 25) and the management server 202 (FIG. 26) in the water leakage detection system 12 are different from the configurations of the water leakage detection device 101 (FIG. 5) and the management server 201 (FIG. 19) in the water leakage detection system 1.

[0090] <Example of configuration of the water leakage detection device 102 in the water leakage detection system 12> 25 shows an example of the configuration of the water leakage detection device 102 in the water leakage detection system 12. Among the components of the water leakage detection device 102, those that are common to the components of the water leakage detection device 101 are given the same reference numerals and their description is omitted. The water leakage detection device 102 omits the detectability determination unit 113 from the processing unit 11 of the water leakage detection device 101 and provides a minimum vibration intensity acquisition unit 1132.

[0091] The minimum vibration intensity acquisition unit 1132 executes the minimum vibration intensity acquisition process of step S41 among the discoverability determination processes (steps S41 to S44 in FIG. 15) executed by the discoverability determination unit 113 of the water leakage detection device 101. Note that steps S42 to S44 in FIG. 15 will be executed by the discoverability determination unit 212 of the management server 202, as will be described later.

[0092] The storage unit 12 of the water leakage detection device 102 stores measured waveform data 121, a water leakage determination result 122, and a minimum vibration intensity 123 for each frequency.

[0093] <Example of configuration of the management server 202 in the water leakage detection system 12> Fig. 26 shows an example of the configuration of the management server 202 in the water leakage detection system 12. Among the components of the management server 202, those common to the components of the management server 201 (Fig. 7) are given the same reference numerals and their description will be omitted. The management server 202 is obtained by adding a discoverability determination unit 212 to the processing unit 21 of the management server 201.

[0094] The detectability determination unit 212 executes the determination of whether or not a detectability determination process is necessary (step S3 in FIG. 11) and steps S42 to S44 of the detectability determination process (steps S41 to S44 in FIG. 15), which were previously executed by the detectability determination unit 113 of the water leakage detection device 101 in the water leakage detection system 1.

[0095] The storage unit 22 of the management server 202 stores the water leakage determination result 122 transmitted from the water leakage detection device 102, the minimum vibration intensity 123 for each frequency, and the detectability determination result 224. The detectability determination result 224 is the processing result of steps S42 to S44 executed by the detectability determination unit 212 based on the minimum vibration intensity 123 for each frequency.

[0096] <Leak detection processing by the leak detection system 12> Fig. 27 is a flowchart for explaining an example of a water leakage detection process by the water leakage detection system 12. Each step of the water leakage detection process is given the same reference numeral as each step of the water leakage detection process (Fig. 11) by the water leakage detection system 1 that executes similar processing, and the explanation thereof will be appropriately simplified or omitted.

[0097] The water leakage detection process by the water leakage detection system 12 is periodically executed at a predetermined cycle. First, the data acquisition unit 111 of the water leakage detection device 102 executes a waveform data acquisition process (step S1). Next, the water leakage determination unit 112 of the water leakage detection device 102 executes a water leakage determination process based on the N pieces of measured waveform data 121 obtained in step S1 and stored in the storage unit 12 (step S2).

[0098] Next, the minimum vibration intensity acquisition unit 1132 of the water leakage detection device 102 executes the minimum vibration intensity acquisition process of the detectability determination process (step S4 (S41 to 44 in FIG. 15)) based on the N pieces of measured waveform data 121 stored in the memory unit 12 (step S41).

[0099] Next, the output unit 114 of the water leakage detection device 102 executes a judgment result output process (step S5). However, in this judgment result output process, the output unit 114 does not determine whether transmission is necessary, and instead controls the communication unit 14 to transmit the water leakage judgment result 122 stored in the memory unit 12 and the minimum vibration intensity 123 for each frequency to the management server 20 via the network N.

[0100] On the other hand, in the management server 202, the communication unit 23 receives the water leakage determination result 122 and the minimum vibration intensity 123 for each frequency transmitted from the water leakage detection device 102, and stores them in the storage unit 22. Then, the discoverability determination unit 212 determines whether or not it is necessary to execute the discoverability determination process (step S3). If it is determined that it is necessary to execute the process (YES in step S3), the discoverability determination unit 212 executes the discoverability determination process (steps S42 to S44 excluding step S41 in FIG. 15), and stores the result as the discoverability determination result 224 in the storage unit 22 of the management server 202 (step S4). If the discoverability determination unit 212 determines that it is unnecessary to execute the discoverability determination process (NO in step S3), step S4 is skipped.

[0101] Next, the UI control unit 211 of the management server 202 displays the water leakage management screen 10001 (FIG. 21) and the like based on the water leakage judgment result 122 and the detectability judgment result 224 stored in the memory unit 22 (step S6). This concludes the explanation of the water leakage detection process by the water leakage detection system 12.

[0102] According to the water leakage detection system 12, most of the detectability determination process is executed by the management server 202, so that the processing load on the water leakage detection device 102 can be reduced. Also, since the minimum vibration intensity 123 for each frequency, which has a smaller data amount than the measured waveform data 121, is transmitted to the management server 202, the transmission amount can be reduced compared to the case where the measured waveform data 121 is transmitted (the third embodiment described later).

[0103] <Water leakage detection system 13 according to a third embodiment of the present invention> Next, a water leakage detection system 13 (not shown) according to a third embodiment of the present invention will be described. The water leakage detection system 13 is configured to execute the detectability determination process (step S4) performed by the water leakage detection device 101 in the above-mentioned water leakage detection system 1 in a management server 203.

[0104] The water leakage detection system 13 has the same configuration as the water leakage detection system 1 (FIG. 4). However, the configurations of the water leakage detection device 103 (FIG. 28) and the management server 203 (FIG. 29) in the water leakage detection system 13 are different from the configurations of the water leakage detection device 101 (FIG. 5) and the management server 201 (FIG. 7) in the water leakage detection system 1.

[0105] <Example of configuration of the water leakage detection device 103 in the water leakage detection system 13> 28 shows an example of the configuration of the water leakage detection device 103 in the water leakage detection system 13. Among the components of the water leakage detection device 103, those that are common to the components of the water leakage detection device 101 are given the same reference numerals and their description will be omitted. The water leakage detection device 103 is a device in which the detectability determination unit 113 is omitted from the processing unit 11 of the water leakage detection device 101.

[0106] The discoverability determination process (step S4) executed by the discoverability determination unit 113 of the water leakage detection device 101 is executed by the discoverability determination unit 213 (FIG. 29) of the management server 203, as will be described later.

[0107] The storage unit 12 of the water leakage detection device 103 stores measured waveform data 121 and a water leakage determination result 122.

[0108] <Example of configuration of the management server 203 in the water leakage detection system 13> 29 shows a configuration example of the management server 203 in the water leakage detection system 13. Among the components of the management server 203, those common to the components of the management server 201 are given the same reference numerals and their description will be omitted. The management server 203 is obtained by adding a discoverability determination unit 213 to the processing unit 21 of the management server 201.

[0109] The detectability determination unit 213 executes the determination of whether or not the detectability determination process is required (step S3) and the detectability determination process (step S4 (steps S41 to S44 in FIG. 15)) that is executed by the detectability determination unit 113 of the water leakage detection device 101.

[0110] The memory unit 22 of the management server 203 stores the measured waveform data 121 and the water leakage judgment result 122 transmitted from the water leakage detection device 102, as well as the minimum vibration intensity 223 for each frequency and the detectability judgment result 224 obtained by the detectability judgment unit 213.

[0111] <Leak detection processing by leak detection system 13> Fig. 30 is a flowchart for explaining an example of a water leakage detection process by the water leakage detection system 13. Each step of the water leakage detection process is given the same reference numeral as each step of the water leakage detection process (Fig. 11) by the water leakage detection system 1 that executes the same process, and the description thereof will be omitted as appropriate.

[0112] The water leakage detection process by the water leakage detection system 13 is periodically executed at a predetermined cycle. First, the data acquisition unit 111 of the water leakage detection device 103 executes a waveform data acquisition process (step S1). Next, the water leakage determination unit 112 of the water leakage detection device 103 executes a water leakage determination process based on the N pieces of measured waveform data 121 obtained in step S1 and stored in the storage unit 12 (step S2).

[0113] Next, the output unit 114 of the water leakage detection device 103 executes a judgment result output process (step S5). However, in this judgment result output process, the output unit 114 does not determine whether transmission is necessary, and instead controls the communication unit 14 to transmit the measured waveform data 121 stored in the memory unit 12 and the water leakage judgment result 122 to the management server 20 via the network N.

[0114] Meanwhile, in the management server 203, the communication unit 23 receives the measured waveform data 121 and the water leakage determination result 122 transmitted from the water leakage detection device 103 and stores them in the storage unit 22. Then, the detectability determination unit 213 determines whether or not it is necessary to execute the detectability determination process (step S3). If it is determined that it is necessary to execute the process (YES in step S3), the detectability determination unit 213 executes the detectability determination process, stores the minimum vibration intensity 223 for each frequency acquired in the process in the storage unit 22, and stores the processing result as the detectability determination result 224 in the storage unit 22 of the management server 203 (step S4). Note that if the detectability determination unit 213 determines that it is unnecessary to execute the detectability determination process (NO in step S3), the process of step S4 is skipped.

[0115] Next, the UI control unit 211 of the management server 203 displays the water leakage management screen 10001 (FIG. 21) and the like based on the water leakage judgment result 122 and the detectability judgment result 224 stored in the memory unit 22 (step S6). This concludes the explanation of the water leakage detection process by the water leakage detection system 13.

[0116] According to the water leakage detection system 13, the detectability determination process is executed by the management server 203, so that the processing load on the water leakage detection device 103 can be reduced.

[0117] <Water leakage detection system 14 according to a fourth embodiment of the present invention> Next, a water leakage detection system 14 (not shown) according to a fourth embodiment of the present invention will be described. The water leakage detection system 14 is configured to execute in a management server 20 the water leakage determination process (step S2) and the detectability determination process (step S4) that are executed in the water leakage detection device 101 in the above-mentioned water leakage detection system 1.

[0118] The water leakage detection system 14 has the same configuration as the water leakage detection system 1 (FIG. 4). However, the configurations of the water leakage detection device 104 (FIG. 31) and the management server 204 (FIG. 32) in the water leakage detection system 14 are different from the configurations of the water leakage detection device 101 (FIG. 5) and the management server 201 (FIG. 7) in the water leakage detection system 1.

[0119] <Example of configuration of the water leakage detection device 104 in the water leakage detection system 14> 31 shows an example of the configuration of the water leakage detection device 104 in the water leakage detection system 14. Among the components of the water leakage detection device 104, those common to the components of the water leakage detection device 101 are given the same reference numerals and their description is omitted. The water leakage detection device 104 omits the leakage determination unit 112 and the detectability determination unit 113 from the processing unit 11 of the water leakage detection device 101, and further omits the memory unit 12.

[0120] The water leakage determination process performed by the water leakage determination unit 112 of the water leakage detection device 101 and the detectability determination process performed by the detectability determination unit 113 are executed by the water leakage determination unit 214 and the detectability determination unit 213 (both shown in FIG. 32) of the management server 204, as described below.

[0121] <Example of configuration of the management server 204 in the water leakage detection system 14> 32 shows an example of the configuration of the management server 204 in the water leakage detection system 14. Among the components of the management server 204, those common to the components of the management servers 201 to 203 are given the same reference numerals and their description will be omitted. The management server 204 is obtained by adding a water leakage determination unit 214 to the processing unit 21 of the management server 203.

[0122] The water leakage determination unit 214 executes the water leakage determination process (step S2) executed by the water leakage determination unit 112 of the water leakage detection device 101.

[0123] The memory unit 22 of the management server 204 stores the measured waveform data 121 transmitted from the water leak detection device 102, the water leak determination result 222 by the water leak determination unit 214, and the minimum vibration intensity 223 for each frequency and the detectability determination result 224 by the detectability determination unit 213.

[0124] <Leak detection processing by leak detection system 14> Fig. 33 is a flowchart for explaining an example of a water leakage detection process by the water leakage detection system 14. Each step of the water leakage detection process is given the same reference numeral as each step of the water leakage detection process (Fig. 11) by the water leakage detection system 1 that executes the same process, and the description thereof will be omitted as appropriate.

[0125] The water leakage detection process is periodically executed at a predetermined cycle by the water leakage detection system 14. First, the data acquisition unit 111 of the water leakage detection device 104 executes a waveform data acquisition process (step S1).

[0126] However, in the waveform data acquisition process by the water leak detection system 1 (FIG. 12), the measured waveform data 121 acquired from the measurement unit 13 is stored in the memory unit 12, but in the waveform data acquisition process by the water leak detection system 14, the measured waveform data 121 acquired from the measurement unit 13 is not saved, and the output unit 114 controls the communication unit 14 to transmit it to the management server 204 via the network N. Meanwhile, in the management server 204, the communication unit 23 receives the measured waveform data 121 transmitted from the water leak detection device 104 and stores it in the memory unit 22. This makes it possible to omit the memory unit 12 from the water leak detection device 104 or to reduce the capacity of the memory unit 12, thereby making it possible to reduce the housing size of the water leak detection device 104 and reduce manufacturing costs.

[0127] Next, the water leakage determination unit 214 of the management server 204 executes a water leakage determination process based on the N pieces of measured waveform data 121 stored in the storage unit 22, and stores the result in the storage unit 22 as a water leakage determination result 222 (step S2).

[0128] Next, the discoverability determination unit 213 of the management server 204 determines whether or not it is necessary to execute a discoverability determination process (step S3). If it is determined that the process is necessary (YES in step S3), the discoverability determination unit 213 executes the discoverability determination process, stores the minimum vibration strength 223 for each frequency acquired in the process in the storage unit 22, and stores the processing result as the discoverability determination result 224 in the storage unit 22 of the management server 202 (step S4). If the discoverability determination unit 212 determines that it is unnecessary to execute the discoverability determination process (NO in step S3), the process of step S4 is skipped.

[0129] Next, the UI control unit 211 of the management server 204 displays the water leakage management screen 10001 (FIG. 21) and the like based on the water leakage determination result 222 and the detectability determination result 224 stored in the storage unit 22 (step S6). This concludes the description of the water leakage detection process by the water leakage detection system 14.

[0130] According to the water leakage detection system 14, the water leakage determination process and the detectability determination process are executed by the management server 204, so that the processing load on the water leakage detection device 104 can be reduced. Also, since the storage unit 12 in the water leakage detection device 104 can be omitted or the capacity can be reduced, the housing size of the water leakage detection device 104 can be reduced and the manufacturing cost can be reduced.

[0131] <First Modification of Water Leak Detection Process by Water Leak Detection System 1> Fig. 34 is a flowchart for explaining a first modified example of the water leakage detection process by the water leakage detection system 1. Each step of the first modified example is given the same reference numeral as each step of the water leakage detection process (Fig. 11) by the water leakage detection system 1 that executes the same process, and the description thereof will be omitted as appropriate.

[0132] The first modified example swaps the execution order of the leak determination process (step S2) and the detectability determination process (step S4) in the leak detection process (Figure 11) by the leak detection system 1, and replaces the need for the detectability determination process (step S3) with a need for the leak determination process (step S3').

[0133] The first modified example is executed periodically at a predetermined cycle. First, the data acquisition unit 111 of the water leakage detection device 101 executes a waveform data acquisition process (step S1). Next, the detectability determination unit 113 executes a detectability determination process, stores the minimum vibration intensity 123 for each frequency obtained in the process in the storage unit 12, and stores the result of the detectability determination process in the storage unit 12 as a detectability determination result 124 (step S4).

[0134] Next, the water leakage determination unit 112 determines whether or not it is necessary to execute a water leakage determination process (step S3'). Specifically, for example, if it is determined in the above-mentioned step S4 that it is easy to detect, it is determined that it is necessary to execute a water leakage determination process. Alternatively, regardless of the determination result of step S4, it may be determined that it is necessary to execute a water leakage determination process when a predetermined time has passed after step S4.

[0135] Here, if it is determined that execution is necessary (YES in step S3'), the water leakage determination unit 112 executes the water leakage determination process and stores the result in the storage unit 12 as the water leakage determination result 122 (step S2). Note that if the water leakage determination unit 112 determines that execution of the water leakage determination process is unnecessary (NO in step S3'), the process in step S2 is skipped.

[0136] Next, the output unit 114 executes a determination result output process and controls the communication unit 14 to transmit the water leakage determination result 122, the minimum vibration strength for each frequency 123, and the detectability determination result 124 stored in the memory unit 12 to the management server 20 via the network N (step S5). Note that if the water leakage determination process has not been executed, the minimum vibration strength for each frequency 123 and the detectability determination result 124 are transmitted to the management server 20 via the network N.

[0137] Meanwhile, in the management server 201 , the communication unit 23 receives the water leakage determination result 122 , the minimum vibration strength for each frequency 123 , and the detectability determination result 124 transmitted from the water leakage detection device 102 and stores them in the storage unit 22 .

[0138] Next, the UI control unit 211 of the management server 201 displays the water leakage management screen 10001 (FIG. 21) and the like based on the water leakage judgment result 122 and the detectability judgment result 224 stored in the memory unit 22 (step S6). This concludes the description of the first modified example of the water leakage detection process by the water leakage detection system 1.

[0139] According to the first modified example, when the ease of detecting a water leak is low, such as when the processing load of the water leak determination process is higher than that of the detectability determination process, the water leak determination process can be prevented from being executed. This reduces the number of times that the water leak determination process is executed unnecessarily, and enables the water leak detection device 101 to be operated for a long period of time while suppressing consumption of the battery 107 and communication costs with the management server 201.

[0140] <Second modified example of water leakage detection process by water leakage detection system 1> Fig. 35 is a flowchart for explaining a second modified example of the water leakage detection process by the water leakage detection system 1. Each step of the second modified example is assigned the same reference numeral as each step of the water leakage detection process (Fig. 11) by the water leakage detection system 1 that executes the same process, and the description thereof will be omitted as appropriate.

[0141] The second modified example omits the determination of whether or not a detectability determination process is required (step S3) in the water leak detection process (Figure 11) by the water leak detection system 1, and executes the detectability determination process in step S4 regardless of the result of the water leak determination process in step S2.

[0142] In the case of the second modified example, the detectability determination process is executed regardless of the result of the water leakage determination process, so that even if there is an erroneous determination in either the water leakage determination process or the detectability determination process, the user can be notified that there is a suspected water leakage. This can improve the detection accuracy. Note that the execution order of the water leakage determination process (step S2) and the detectability determination process (step S4) may be reversed, or they may be executed simultaneously in parallel.

[0143] <Modification of Minimum Vibration Strength Acquisition Process in Discoverability Determination Process> FIG. 36 is a flowchart illustrating a modification of the minimum vibration strength acquisition process (FIG. 16) in step S41 of the discoverability determination process described above.

[0144] This modified example has steps S411 to S413 in common with the above-mentioned minimum vibration strength acquisition process (FIG. 16), but differs in the subsequent steps S414' to S419'. A description of steps S411 to S413 will be omitted.

[0145] After performing a fast Fourier transform (FFT) on the Y-th measured waveform data 121 in step S413, the discoverability determination unit 113 then extracts the vibration intensity for each frequency from the Y-th FFT result (step S414').

[0146] Next, the discoverability determination unit 113 determines whether the parameter Y is 1 or not (step S415'), and if it determines that the parameter Y is 1 (YES in step S415'), then it stores the vibration intensity for each frequency corresponding to the Y (=1)th FFT result extracted in step S414' in the memory unit 12 as the minimum vibration intensity for each frequency 123 (step S416').

[0147] Next, the discoverability determination unit 113 determines whether the parameter Y has reached the number N of measured waveform data 121 (step S417'), and if it determines that the parameter Y has not reached the number N of measured waveform data 121 (NO in step S417'), it increments the parameter Y by 1 (step S418'), returns the processing to step S412, and repeats steps S412 and after.

[0148] Then, in step S415', if it is determined that parameter Y is not 1 (NO in step S415'), discoverability determination unit 113 compares the vibration intensity for each frequency corresponding to the Yth FFT result extracted in step S414' with minimum vibration intensity 123 for each frequency up to Y-1th stored in storage unit 12. Then, if the vibration intensity for each frequency corresponding to the Yth FFT result is smaller, minimum vibration intensity 123 for each frequency stored in storage unit 12 is updated with that value (step S419').

[0149] Then, in step S417′, when the discoverability determination unit 113 determines that the parameter Y has reached the number N of measured waveform data 121 (YES in step S417′), the minimum vibration strength acquisition process ends. This concludes the description of the modified example of the minimum vibration strength acquisition process.

[0150] According to this modification, since there is no need to store N FFT results as in the above-described minimum vibration intensity acquisition process (FIG. 16), the amount of data stored in the storage unit 12 can be reduced.

[0151] <First Modification of Discoverability Determination Process> FIG. 37 is a flowchart illustrating a first modified example of the above-mentioned discoverability determination process (FIG. 15).

[0152] In the first modified example, step S42 in the above-mentioned detectability determination process (FIG. 15) is replaced with step S42', and steps S41, S43, and S44 are common, so their explanation will be omitted. In step S42 in the above-mentioned detectability determination process (FIG. 15), the minimum vibration intensity for each frequency in a predetermined frequency band is integrated as the detectability characteristic. In contrast, in step S42' of this modified example, the number of peak points (maximum points) of the minimum vibration intensity for each frequency in a predetermined frequency band is calculated as the detectability characteristic.

[0153] FIG. 38 shows the relationship between frequency and minimum vibration intensity when there is no leakage (solid line), when a small leakage occurs (dotted line), and when a large leakage occurs (dashed line), with the horizontal axis being frequency and the vertical axis being normalized minimum vibration intensity. As is clear from the figure, it can be confirmed that the number of peak points of the minimum vibration intensity for each frequency increases with an increase in leakage flow rate. Therefore, it can be seen that by calculating the number of peak points within a specified frequency band as a detectability feature and comparing it with a threshold value, it is possible to determine the detectability that reflects the magnitude of the leakage flow rate.

[0154] <Third Modification of Discoverability Determination Process> FIG. 39 is a flowchart illustrating a second modified example of the above-mentioned discoverability determination process (FIG. 15).

[0155] The second modified example is obtained by adding step S42' in FIG. 37 between steps S42 and S43 of the discoverability determination process (FIG. 15). That is, in the second modified example, in step S42, an integral value of the minimum vibration strength for each frequency in a predetermined frequency band is calculated as one type of discoverability feature, and in step S42', the number of peak points of the minimum vibration strength for each frequency in a predetermined frequency band is calculated as a second type of discoverability feature. Then, in step S43, the discoverability is determined by comparing the two types of discoverability feature with their corresponding thresholds, and the logical product (which may be a logical sum, an exclusive logical sum, or the like) of the two determination results is output as the final discoverability determination result. Note that even if the number of peak points of the minimum vibration strength for each frequency is small, the integral value of the minimum vibration strength for each frequency may be large, and so by determining the discoverability using two types of discoverability feature, the estimation accuracy can be improved. The process of integrating over a predetermined frequency band and the process of calculating the number of peak points within the predetermined frequency band do not have to be a single value, and may have multiple output values. For example, a predetermined frequency band may be divided into certain bands, and integration processes and peak (maximum) point calculation processes may be performed for the divided bands, and judgment may be performed based on the results of multiple feature quantities and their corresponding threshold judgment processes. All thresholds do not have to be fixed. Since there are many feature quantities to be handled, judgment may be performed after applying a supervised learning method such as NN (neural network) to weight important feature quantities.

[0156] <Third Modification of Discoverability Determination Process> The detectability determination process (FIG. 15), its first modified example (FIG. 37), and its second modified example (FIG. 39) described above use N pieces of measured waveform data as input. The third modified example uses N autocorrelation coefficients calculated in step S21 of the water leakage determination process (FIG. 13) executed prior to the detectability determination process as input. Therefore, as a premise of the third modified example, it is assumed that the water leakage determination process (FIG. 13) has already been executed by the water leakage determination unit 112, and that the water leakage determination unit 112 has output the N autocorrelation coefficients calculated in step S21 to the detectability determination unit 113 that executes the third modified example.

[0157] The third modified example is similar to steps S41 to S44 of the discoverability determination process (FIG. 15) described above, but since the input is different, the content of the minimum vibration strength acquisition process in step S41 is different.

[0158] 40 is a flowchart illustrating an example of the minimum vibration strength acquisition process in step S41 in the third modified example of the discoverability determination process. First, the discoverability determination unit 113 initializes a parameter Y for designating one of the N autocorrelation coefficients to 1 (step S411").

[0159] Next, the discoverability determination unit 113 acquires the Y-th autocorrelation coefficient from the N autocorrelation coefficients (step S412"). Next, the discoverability determination unit 113 determines whether or not the parameter Y is 1 (step S413"), and if it determines that the parameter Y is 1 (YES in step S413"), then it stores the Y (=1)-th autocorrelation coefficient for each delay time extracted in step S412" in the memory unit 12 as the minimum autocorrelation coefficient for each delay time (step S414").

[0160] Next, the discoverability determination unit 113 determines whether the parameter Y has reached the number N of autocorrelation coefficients (step S415"), and if it determines that the parameter Y has not reached the number N of autocorrelation coefficients (NO in step S415"), it increments the parameter Y by 1 (step S416"), returns the process to step S412", and repeats step S412" and subsequent steps.

[0161] Then, in step S413'', if it is determined that the parameter Y is not 1 (NO in step S413'', the detectability determination unit 113 compares the amplitude of the autocorrelation coefficient for each Y-th delay time extracted in step S412'' with the amplitude of the smallest autocorrelation coefficient for each delay time up to the Y-1th delay time stored in the memory unit 12. Then, if the amplitude of the autocorrelation coefficient for each Y-th delay time is smaller, the autocorrelation coefficient for each delay time stored in the memory unit 12 is updated with the autocorrelation coefficient for each Y-th delay time (step S417'').

[0162] FIG. 41 is a diagram for explaining the process of updating the autocorrelation coefficient for each lag time in step S417'', where the horizontal axis is the lag time and the vertical axis is the autocorrelation coefficient, and shows the relationship between the minimum autocorrelation coefficient for each lag time up to Y-1 (solid line) and the minimum autocorrelation coefficient for each Y-th lag time (dashed line). For example, at a lag time of 25 pt, the amplitude of the Y-th autocorrelation coefficient is small, so the Y-th autocorrelation coefficient is adopted and the minimum autocorrelation coefficient is updated. Also, for example, at a lag time of 50 pt, the amplitude of the minimum autocorrelation coefficient up to the Y-1th is small, so the minimum autocorrelation coefficient up to the Y-1th is adopted as it is, and the minimum autocorrelation coefficient is not updated.

[0163] Returning to FIG. 40, thereafter, in step S415'', if the discoverability determination unit 113 determines that the parameter Y has reached the number N of autocorrelation coefficients (YES in step S415'', then the discoverability determination unit 113 performs a fast Fourier transform (FFT) on the autocorrelation coefficients for each delay time stored in the memory unit 12, and stores the minimum vibration strength for each frequency obtained as a result in the memory unit 12 (step S418''). This concludes the description of the minimum vibration strength acquisition process in step S41 in the third modified example of the discoverability determination process.

[0164] According to this minimum vibration intensity acquisition process, since it is not necessary to store N FFT results as in the above-mentioned minimum vibration intensity acquisition process (FIG. 16), the amount of data stored in the storage unit 12 can be reduced.

[0165] <Fourth Modification of Discoverability Determination Process> A fourth modified example of the discoverability determination process (not shown) inputs N pieces of measured waveform data, similar to the above-described discoverability determination process (FIG. 15), etc. The fourth modified example is similar to steps S41 to S44 of the above-described discoverability determination process (FIG. 15), but since the input is different, the content of the minimum vibration intensity acquisition process in step S41 is different.

[0166] Fig. 42 is a flowchart for explaining an example of the minimum vibration strength acquisition process of step S41 in the fourth modified example of the discoverability determination process. The minimum vibration strength acquisition process is executed in the order of steps S411, S412, S421, and S413" to S418", with steps S411 and S412 being common to the minimum vibration strength acquisition process of Fig. 16 described above, and steps S413" to S418" being common to the minimum vibration strength acquisition process of Fig. 40 described above, and the same reference numerals are used.

[0167] First, the discoverability determination unit 113 initializes a parameter Y for designating one of the N pieces of measured waveform data 121 to 1 (step S411), and acquires the Yth measured waveform data 121 from the memory unit 12 (step S412). Next, the discoverability determination unit 113 calculates the Nth autocorrelation coefficient from the Yth measured waveform data 121 (step S421). Steps from this step S413'' onwards are the same as those in the minimum vibration strength acquisition process in Figure 40 described above, and the same reference numerals are used, so their explanation will be omitted.

[0168] According to the fourth variant of the discoverability determination process, as with the third variant of the discoverability determination process, there is no need to store N FFT results as in the minimum vibration intensity acquisition process (Figure 16) described above, so the amount of data stored in the memory unit 12 can be reduced.

[0169] The present invention is not limited to the above-described embodiments and modifications, and various modifications are possible. For example, the above-described embodiments have been described in detail to clearly explain the present invention, and the present invention is not necessarily limited to those having all of the configurations described. In addition, it is possible to replace a part of the configuration of a certain embodiment or modification with a configuration of another embodiment or modification, or to add to the configuration of another modification.

[0170] In addition, each of the above configurations, functions, processing units, processing means, etc. may be realized in hardware, for example, by designing a part or all of them in an integrated circuit. In addition, each of the above configurations, functions, etc. may be realized in software by a processor interpreting and executing a program that realizes each function. Information such as a program, table, file, etc. that realizes each function can be placed in a memory, a recording device such as a hard disk or SSD, or a recording medium such as an IC card, an SD card, or a DVD. In addition, the control lines and information lines are shown as those that are considered necessary for explanation, and not all control lines and information lines are necessarily shown in the product. In reality, it may be considered that almost all configurations are connected to each other. [Explanation of symbols]

[0171] 1, 12 to 14...water leakage detection system, 2...pipe network, 10, 101 to 104...water leakage detection device, 11...processing unit, 111...data acquisition unit, 112...water leakage determination unit, 113...detectability determination unit, 1132...minimum vibration strength acquisition unit, 114...output unit, 12...storage unit, 121...measured waveform data, 122...water leakage determination result, 123...minimum vibration strength, 124...detectability determination result, 13...measurement unit, 14...communication unit, 20, 201 to 204...management server, 21...processing unit, 211...UI control unit, 212, 213...detectability determination unit, 214...water leakage determination unit , 22....Memory unit, 222....Leakage judgment result, 223....Minimum vibration strength, 224....Detectability judgment result, 23....Communication unit, 101....Microcontroller, 102....Program, 103....Storage, 104....Input device, 105....Output device, 106....Communication module, 107....Battery, 108....Vibration sensor, 200....Computer, 201....Processor, 202....Memory, 2021....Program, 203....Storage, 204....Input device, 205....Output device, 206....Communication module, 10001~10004....Leakage management screen

Claims

1. a data acquisition unit that acquires a plurality of measurement waveform data measured at different time periods by a vibration sensor installed in a fluid pipeline network; a water leakage determination unit that executes a water leakage determination process that calculates a plurality of time series autocorrelation coefficients from the plurality of measured waveform data, calculates a water leakage score that indicates a relationship between the autocorrelation coefficients of the plurality of time series, and determines whether or not a water leakage has occurred based on the water leakage score; a detectability determination unit that executes a detectability determination process to obtain vibration intensities of less than a predetermined value for each frequency from the plurality of measured waveform data, calculate a feature value of the vibration intensities of less than the predetermined value for each frequency, and determine the detectability of a water leak based on the feature value; an output unit that outputs at least one of a result of the water leakage determination process or a result of the detectability determination process; A computing device comprising:

2. 2. The computing device according to claim 1, One of the water leakage determination unit and the detectability determination unit determines whether or not to execute a determination process by the one unit based on a result of a determination process by the other unit. Computing device.

3. 2. The computing device according to claim 1, One of the water leakage determination unit and the detectability determination unit executes a determination process by the one unit prior to a determination process by the other unit. Computing device.

4. 2. The computing device according to claim 1, The water leakage determination unit and the detectability determination unit perform their respective determination processes simultaneously in parallel. Computing device.

5. 2. The computing device according to claim 1, The water leakage determination unit calculates a degree of agreement or a degree of similarity between peak positions of the autocorrelation coefficients of the plurality of time series as the water leakage score. Computing device.

6. 2. The computing device according to claim 1, A UI control unit that displays on a UI screen a result of the water leakage determination process or a result of the detectability determination process. Computing device.

7. 7. The computing device according to claim 6, The UI control unit displays, on the UI screen, at least one of an arrangement of the arithmetic device in the pipeline network, a change in the leakage score, a vibration intensity equal to or less than a predetermined value for each frequency, the characteristic amount of the vibration intensity equal to or less than a predetermined value for each frequency, a change in the vibration intensity equal to or less than a predetermined value for each frequency, or a change in the characteristic amount of the vibration intensity equal to or less than a predetermined value for each frequency. Computing device.

8. 2. The computing device according to claim 1, The detectability determination unit integrates vibration intensity in a predetermined frequency band that is equal to or smaller than the predetermined value as the feature amount. Computing device.

9. 2. The computing device according to claim 1, The discoverability determination unit calculates, as the feature amount, the number of peak points of vibration intensity in a predetermined frequency band that is equal to or less than the predetermined value. Computing device.

10. 2. The computing device according to claim 1, The vibration intensity of each frequency equal to or less than a predetermined value is a vibration intensity of each frequency equal to or less than a predetermined value. Computing device.

11. A water leakage detection method using a computing device, comprising: A data acquisition step of acquiring a plurality of measurement waveform data measured at different time periods by a vibration sensor installed in a fluid pipeline network; a water leakage determination step of calculating a plurality of time series autocorrelation coefficients from the plurality of measured waveform data, calculating a water leakage score representing a relationship between the plurality of time series autocorrelation coefficients, and executing a water leakage determination process for determining whether or not a water leakage has occurred based on the water leakage score; a detectability determination step of acquiring vibration intensities of less than a predetermined value for each frequency from the plurality of measured waveform data, calculating feature values ​​of the vibration intensities of less than the predetermined value for each frequency, and executing a detectability determination process for determining the detectability of a water leak based on the feature values; an output step of outputting at least one of the plurality of measurement waveform data, a result of the water leakage determination process, or a result of the detectability determination process; A water leak detection method comprising:

12. A water leakage detection system having a server and a computing device, a data acquisition unit that acquires a plurality of measurement waveform data measured at different time periods by a vibration sensor installed in a fluid pipeline network; a water leakage determination unit that executes a water leakage determination process that calculates a plurality of time series autocorrelation coefficients from the plurality of measured waveform data, calculates a water leakage score that indicates a relationship between the autocorrelation coefficients of the plurality of time series, and determines whether or not a water leakage has occurred based on the water leakage score; a detectability determination unit that executes a detectability determination process to obtain vibration intensities of less than a predetermined value for each frequency from the plurality of measured waveform data, calculate a feature value of the vibration intensities of less than the predetermined value for each frequency, and determine the detectability of a water leak based on the feature value; an output unit that outputs at least one of the plurality of measurement waveform data, a result of the water leakage determination process, or a result of the detectability determination process; A water leak detection system comprising:

13. The water leak detection system according to claim 12, The computing device includes: The data acquisition unit, the water leakage determination unit, the detectability determination unit, and the output unit, The output unit outputs at least one of a result of the water leakage determination process and a result of the detectability determination process to the server. Water leak detection system.

14. The water leak detection system according to claim 12, The computing device includes: The data acquisition unit, the water leakage determination unit, and the output unit, The output unit outputs, to the server, at least one of the calculated vibration intensity equal to or less than the predetermined value or the characteristic amount of the vibration intensity equal to or less than the predetermined value for each frequency as a result of the water leakage determination process. Water leak detection system.

15. The water leak detection system according to claim 12, The computing device includes: The data acquisition unit and the output unit are provided, the output unit outputs the plurality of pieces of measured waveform data to the server; The server, The water leakage determination unit and the detection ease determination unit are provided. Water leak detection system.

Images