JPWO2017199455A1 - Water leakage determination device and water leakage determination method - Google Patents

Abstract

The problem to be solved by the present invention is to provide a water leakage determination device and a water leakage determination method for more efficiently and accurately detecting water leakage.
The water leakage determination device of the embodiment includes a reception unit that receives sound wave data, an extraction unit that extracts data of a steady section with less noise from the sound wave data, a designation unit that specifies a threshold value, and water leakage from the data of the steady section. A determination unit that obtains a ratio including a signal indicating characteristics and compares the ratio with the threshold value to determine the presence or absence of water leakage.

Description

  Embodiments described herein relate generally to a water leakage determination device and a water leakage determination method.

  In the water leakage investigation procedure using the current water leakage detector, first, a water meter meter inspector or the like obtains data for water pipe leakage investigation using the water leakage detector at the time of meter reading. For example, a time integration rate (a ratio of a signal exceeding a certain level in a certain time) and a vibration sound (leakage sound) are recorded as a sound wave file. Each sound file is associated with a recording point (position of a water pipe).

  From the acquired data, first, as a primary determination, those having a time integration rate of a certain level or more are extracted as a sound wave file with a possibility of water leakage.

  As a secondary determination, a file with a higher possibility of water leakage is extracted from the extracted sound wave file, and the number of cases is narrowed down. This secondary determination operation is determined by an experienced engineer (by reproducing a sound wave file) and listening with an ear. Conduct a field survey of the recording locations of the finally selected sound wave file. A specialized investigator will check for leaks with a sounding stick, dig up the ground after hitting it.

  The secondary judgment is a hearing judgment by the research engineer and depends on the experience and skills of the engineer. Even when the number of sound wave files obtained by the primary determination is enormous, it is necessary to listen to all sound sources, which requires a lot of labor.

JP2015-43001A

  The problem to be solved by the present invention is to provide a water leakage determination device and a water leakage determination method for more efficiently and accurately detecting water leakage.

  The water leakage determination device of the embodiment includes a reception unit that receives sound wave data, an extraction unit that extracts data of a steady section with less noise from the sound wave data, a designation unit that specifies a threshold value, and water leakage from the data of the steady section. A determination unit that obtains a ratio including a signal indicating characteristics and compares the ratio with the threshold value to determine the presence or absence of water leakage.

  In addition, the water leakage determination method of the embodiment is a water leakage determination method in a water leakage determination device that determines the presence or absence of water leakage from sound wave data, and extracts data of a steady section with less noise from the sound wave data, and determines the presence or absence of water leakage A threshold value is designated, and a ratio including a signal indicating the characteristic of water leakage is obtained from the data of the steady section, and the presence or absence of water leakage is determined by comparing the ratio with the threshold value.

It is a block diagram which shows the structure of the water leak determination apparatus which concerns on 1st Embodiment. It is a figure which shows the time-sequential waveform which caught the water leak sound. It is a figure which shows the time-sequential waveform which caught the traffic noise. An example of a time-series waveform and a waveform obtained by spectrally entropy-converting it is shown. It is a figure which shows an example which performs spectrum entropy conversion from a time series waveform, and extracts a stationary area. It is a block diagram which shows the detail of the determination part of the water leak determination apparatus which concerns on 1st Embodiment. It is a figure which shows an example at the time of setting the arbitrary frequency ranges containing the frequency component resulting from a water leak from the waveform which carried out FFT. It is the figure which overwrote the frequency characteristic at the time of applying 1/3, 1/6, and 1/12 octave band. It is a comparison figure with the case where it smooths by moving average, and the case where it smooths by a 1/12 octave band. It is a figure which shows an example which calculated | required the time integration rate from the time series waveform of the sound wave signal data after HPF application. It is a figure which shows the frequency characteristic of a septic tank sound and a motor sound. It is a figure which shows the result of having performed water leak determination of a water pipe using the 1st determination means and the 2nd determination means. It is a figure which shows an example of the determination threshold value of a 1st determination means, the determination threshold value of a 2nd determination means, and a determination amplitude value (voltage). It is a block diagram which shows the detail of the determination part of the water leak determination apparatus which concerns on 2nd Embodiment. It is a comparison figure of the time series waveform and frequency characteristic of each of a water leak sound and the water water sound (sound when using water supply). It is a figure which shows the combination of the 1st thru | or 3rd determination means. It is a block diagram which shows the detail of the determination part of the water leak determination apparatus which concerns on 3rd Embodiment. It is a detailed block diagram of a 4th determination means. It is a figure which shows the specific example of the determination procedure at the time of using a test signal. It is a figure which shows an example of the determination procedure in case a fluctuating sound is included. It is a figure which shows an example of the time-sequential waveform in case the signal of a some frequency component is included. It is a figure which shows the autocorrelation function of each time series waveform of FIG. 21, each envelope, and an approximate line. It is a figure which shows the result of having calculated | required the actually measured sound wave signal data and its autocorrelation function. It is a figure which shows an example of a determination process by setting a predetermined line segment and a threshold value. It is a figure which shows the result of having compared the magnitude of the area which an envelope and each predetermined line segment make. It is a figure which shows the result at the time of water leak determination based on either the time integration rate from the autocorrelation function, the area which an envelope forms, or the inclination of an envelope. It is a figure which shows the combination of the 1st, 2nd or 4th determination means. It is a figure which shows the combination of the 2nd, 3rd or 4th determination means. It is a figure which shows the combination of the 1st, 3rd, or 4th determination means. It is a figure which shows the combination of the 1st-4th determination means.

  Hereinafter, a water leakage determination device and a water leakage determination method according to an embodiment will be described with reference to the drawings. The same reference numerals denote the same items. Note that the drawings are schematic or conceptual, and the relationship between the thickness and width of each part, the ratio coefficient of the size between the parts, and the like are not necessarily the same as actual ones. Further, even when the same part is represented, the dimensions and ratio coefficient may be represented differently depending on the drawing.

(First embodiment)
FIG. 1 is a block diagram illustrating a configuration of a water leakage determination device 1 according to the first embodiment.

  The water leakage determination apparatus 1 includes a reception unit 2 that receives sound wave signal data, an extraction unit 3 that extracts a steady section with less noise from the input sound wave signal data, and a sound wave signal extracted by the extraction unit 3 It has the determination part 4 which determines whether the characteristic of water leakage is contained in data using two determination means, and the output part 5 which outputs a determination result. Furthermore, the designation | designated part 6 which can designate the upper limit and lower limit frequency of a frequency range, the threshold value for a user determining water leak, etc. is provided. The designation unit 6 gives a threshold value to the determination unit 4.

  For example, the reception unit 2 is a place where sound wave signal data such as flowing water flowing through a water pipe measured by a meter reader or a surveyor of a water meter is input. The sound wave signal data may be data represented by the WAV format that can be handled by a general personal computer / electronic device. Also, any sound wave signal data in another format may be used as long as it can be converted into the WAV format. For example, compressed data such as ADPCM, MP3, and WMA may be used. The accepting unit 2 may accept a file directly by USB or the like, or may accept data via an external medium such as an SD card. In addition, data may be received via wireless communication such as Wi-Fi or Bluetooth.

  In addition to the vibration sound to be detected, the sound wave signal data includes many noises such as traffic noise from cars and trains, outdoor noise from air conditioners, and human voices due to the influence of the surrounding measurement environment. It is. The sound wave signal data is mainly given as a time series waveform.

  In general, a water leaking sound from a water pipe is a steady sound including a frequency component of up to 3 kHz and a frequency component of 1 kHz to 2 kHz being dominant. Sound waves that are likely to be misjudged as leaked sounds include the sound of water flowing out of a faucet when using water supplies, and the rotating sound of water meters. In addition, sound waves caused by a motor such as an air conditioner can be used. The frequency characteristics in the state where these noises are mixed are greatly deviated from the original frequency characteristics of the leaked sound.

  The extraction unit 3 is a part that extracts a waveform of a component with less noise from the sound wave signal data input from the reception unit 2. That is, out of the time-series waveform of the sound wave signal data, a sudden vibration component having a large amplitude or a waveform in a steady section that is not a waveform portion having a large amplitude that is periodically superimposed on the waveform is extracted.

  Fig.2 (a) is a figure which shows the time-sequential waveform at the time of catching a water leak sound. The horizontal axis is time (seconds), and the vertical axis is the signal level that is amplitude. FIG. 2B shows frequency characteristics when a time series waveform of 10 seconds, which is the entire time, is subjected to fast Fourier transform (FFT). It can be seen that no clear feature has been confirmed in the range of 1 kHz to 2 kHz, which is the frequency component of the water leakage sound. On the other hand, the frequency characteristics obtained by performing the FFT using a waveform having a low noise, for example, a steady section of 2 seconds, avoiding a waveform having a large noise of about 1.6 sec in the time series waveform of FIG. ). A clear feature is confirmed in the range of 1 kHz to 2 kHz. By extracting the waveform of the steady section and performing FFT, the characteristic of water leakage can be clearly obtained.

  FIG. 3A is a diagram showing a time-series waveform when traffic noise is captured. Here, it is assumed that the water leakage sound is not superimposed. FIG. 3B shows the frequency characteristics when the time series waveform of 10 seconds, which is the entire time, is FFTed.

  Also in the waveform of FIG. 3B, clear features are confirmed in the range of 1 kHz to 2 kHz. This is an influence of external noise characterized by the same band as the water leakage sound. As a cause of noise, a high-order component of motor sound of a car or a train can be considered. In general, the traveling sound and motor sound of automobiles and trains measured in the external environment are not steady waveforms, but the time-series waveforms suddenly change depending on the road condition and the accelerator condition.

  FIG. 3C shows the frequency characteristics when FFT is performed using a waveform at a designated portion that is a stationary section of the time series waveform of FIG. It can be seen that no clear feature has been confirmed between 1 and 2 kHz compared to the waveform of FIG.

  By extracting a stationary section with little sudden noise from the time-series waveform of the sound wave signal data in the extraction unit 3, it is possible to obtain frequency characteristics from which noise components other than the water leakage sound are removed when FFT is performed thereafter. Moreover, it is possible to prevent accidental noise having a frequency component close to the water leakage sound from being erroneously detected.

  Next, a method for extracting a stationary section in the extraction unit 3 will be described.

  For example, a spectral entropy method can be used as a method for extracting a stationary section. The spectrum entropy method is a feature quantity representing the whiteness of a signal, which is obtained by calculating a signal spectrum as a probability distribution and assuming information entropy. When the spectrum such as white noise is uniform, the value is high, and when the spectrum is non-uniform such as a voice signal or traffic noise, the value is low.

The spectral entropy method is generally represented by the following formula (1).

S _f is the amplitude spectrum of the frequency component f obtained by FFT of the input signal. P _f is the existence probability of the frequency component f. H indicates spectral entropy. H is a high value for a white signal with a uniform spectrum, and a low value for a colored signal with a non-uniform spectrum such as an audio signal or traffic noise.

  FIG. 4 shows a time-series waveform and a waveform obtained by converting the time-series waveform by the spectral entropy method. The steady section of the graph shown by the spectral entropy method is flat at a high value, and the part of the external fluctuation noise has a low value. It is possible to clearly distinguish the stationary section and the external fluctuation noise part.

  As a result, only the components regarded as the steady section are extracted while avoiding local fluctuation noise points. The extraction of the steady section is performed using a threshold value. That is, a section that exceeds the set threshold and is regarded as a steady section is extracted. The threshold for drawing the steady section can be arbitrarily set. Moreover, the time width to extract can also be set arbitrarily.

  For example, depending on the sound wave signal data, there may be a case where a continuous steady section cannot be obtained. In that case, you may extract the dispersed part so that the sum total of a stationary area may become the time width set arbitrarily. However, when calculating the frequency characteristic, it is preferable that the sound wave signal data is continuous. This is because if the continuity of the time-series waveform of the sound wave signal data is lost, a different spectrum is obtained when FFT is performed.

  For example, in the case where the total of the regular intervals, which are the times to be extracted, is 1 second, when extraction is not possible in a continuous time range, it may be extracted in pieces to make a total of 1 second. When performing FFT with an arbitrary window length, it is performed for each piece of fragment data. This is because the continuity of the time-series waveform is lost when performing FFT across two pieces of fragment data.

  If it is desired to maintain the continuity of the time series waveform to be extracted, the threshold value to be set may be lowered. As a result, the section determined to be equal to or greater than the threshold becomes long, and it is easy to extract a continuous signal that is regarded as a steady section.

  FIG. 5 is a diagram illustrating an example of extracting a stationary section from a target time-series waveform using a spectrum entropy method.

  The first row in the figure is the target time series waveform. From this, a stationary section with a specified time width is extracted. The second row in the figure is a waveform converted by the spectral entropy method. A broken line is an arbitrarily determined threshold value. The third row in the figure shows the determination result when the section above the threshold is 1 and the section below the threshold is 0. A portion of “1” that is a section equal to or greater than the threshold is a place extracted as a steady section. From this, a section having an arbitrarily set time width is extracted. If there is no section longer than an arbitrary time width and a continuous steady section is required, the threshold may be set low.

  The threshold value for extracting the stationary interval may be the total average value of the spectral entropy of the extraction target interval, the frequency distribution may be calculated and the median value may be used, or any numerical value determined by the user May be given directly.

  The extraction in the extraction unit 3 is mainly performed by a CPU (Central Processing Unit) of a computer.

  The determination unit 4 determines whether or not a feature due to water leakage is included in the steady section of the sound wave signal data extracted by the extraction unit 3.

  FIG. 6 is a block diagram illustrating details of the determination unit of the water leakage determination device according to the present embodiment.

  In the determination unit of the present embodiment, the presence or absence of water leakage is determined by the first determination unit 7 and the second determination unit 8 different from the first determination unit, using the time series waveform of the steady section. By combining these determination results, it is possible to easily narrow down the secondary determination of the sound wave signal data.

  First, the first determination means 7 will be described.

  The first determination means performs FFT on the sound wave signal data in the stationary section extracted by the extraction unit 3, and calculates the ratio of the frequency component due to water leakage in an arbitrarily defined frequency range. Furthermore, the presence or absence of water leakage is determined by setting a threshold value for this ratio.

  FIG. 7 shows an example when an arbitrary frequency range including a frequency component caused by water leakage is set from the FFTed waveform. Since the frequency component resulting from water leakage is characterized by a range of approximately 1 kHz to 2 kHz, for example, a range of approximately 700 Hz to 3 kHz is set as the frequency range.

  In the first determination means, the Euclidean distance is calculated as the calculation of the ratio of frequency components due to water leakage.

Since the characteristics of the microphone and the amplifier circuit are superimposed on the frequency characteristics of the sound wave signal data when there is no sound, the frequency characteristics are not always flat, and some signal is often mixed. The Euclidean distance D of the frequency characteristic of the sound wave signal data in the steady section extracted by the extraction unit is obtained with respect to the frequency characteristic when the sound wave input level is minimum, that is, the lower limit data of the dynamic range. The Euclidean distance D is obtained by the following equation (2).

X _i is the frequency characteristic data of the steady section extracted by the extraction unit. _Pi is frequency characteristic data at the lower limit of the dynamic range. i is an array of the 1st to d-th frequencies. The frequency characteristic data of the lower limit (minimum value) of the dynamic range is interpreted as so-called background noise frequency characteristic data.

  When the ratio of the Euclidean distance in the frequency range (for example, 700 Hz or more and 3 kHz or less) including the frequency component due to water leakage exceeds the arbitrarily set threshold value, the water leakage is determined. If the amplitude value is only the sound wave signal data of the stationary section extracted by the extraction unit, the frequency component that shows a large amplitude as an absolute value is large even in the lower limit data of the dynamic range, and may not actually be a large input. It is preferable to take a difference between the frequency characteristic of the stationary section and the lower limit data of the dynamic range.

  The method of determining the lower limit data (minimum value) of the dynamic range may use a sound wave signal recorded in a place where background noise is low, or extract the lowest value of each frequency of a plurality of sound wave signal data to be input, The lower limit data may be combined by combining them.

  When the minimum value of the dynamic range is determined from a plurality of input sound wave signal data, all the files are read once before entering the block of the determination unit. FFT is performed each time a file is read, and the dynamic range information already stored for each frequency is compared with the FFT value. If the value is small, the dynamic range information is overwritten. This is performed on the entire sound wave signal data file to determine the minimum value of the dynamic range. The determination unit stores the obtained frequency characteristic of the lower limit of the dynamic range in a storage unit such as a memory, and calculates the Euclidean distance according to Equation (2) using the stored lower limit data.

  In addition to obtaining the Euclidean distance, an integral value in an arbitrary frequency range with respect to a frequency characteristic obtained by FFTing a stationary section of sound wave signal data, and an integrated value in an arbitrary frequency range with respect to a frequency characteristic having a minimum dynamic range. You may ask for the difference. Determination may be made by obtaining a ratio (integration rate) between this and the difference between the integral values in the entire frequency range of both frequency characteristics and comparing it with an arbitrarily determined threshold value. The area of the difference between the frequency characteristic obtained by performing FFT on the steady section and the frequency characteristic having the minimum dynamic range is the ratio between the case where the entire frequency range is used and the case where the frequency range is an arbitrary frequency range.

  The determination of the threshold value can be arbitrarily set by the user based on past water leakage determination data and empirical rules.

  The first determination means performs a smoothing process as an approximation method of the frequency characteristics in order to reduce the data processing amount before performing the threshold determination based on the Euclidean distance. This is because the amount of data processing becomes enormous when performing FFT simply.

  Although depending on the number of smoothing points, when steep peak noise is mixed, the graph shape is greatly increased. Therefore, it is simplified by 1 / N octave band processing, the number of data points is reduced, and the processing speed is increased. In the octave conversion, 1/1 octave and 1/3 octave are generally used for noise evaluation, but it becomes more detailed by increasing the N parameter with 1/6 octave and 1/12 octave bands. . FIG. 8 is a diagram in which the frequency characteristics in the case of 1/3, 1/6, and 1/12 octave are overwritten. The 1/12 octave band is the most detailed graph with the most data points. The value of N is preferably determined by a trade-off with the number of data points.

  FIG. 9 is a comparison diagram between the case of smoothing by moving average and the case of smoothing by 1/12 octave band. In the case of smoothing by moving average, the peak portion becomes dull due to the averaging process of a plurality of points, but smoothing in the 1/12 octave band can clearly reproduce the peak shape. By using 1 / N octave-processed data instead of simple frequency conversion data at the time of determination based on the Euclidean distance, high-speed computation can be performed with a small number of data points while leaving appropriate frequency information.

  The designation unit 6 in the first determination unit inputs an upper limit frequency and a lower limit frequency of an arbitrary frequency range. When the leakage sound is determined as described above, the frequency component due to water leakage is 1 kHz or more and 2 kHz or less, and therefore the frequency range is set in the range of 700 Hz or more and 3 kHz or less, for example. When making a determination for a sound other than a leaking sound, it is preferable to set the frequency according to the characteristics of the sound type to be extracted. The values of the upper limit frequency and the lower limit frequency can also be determined from a plurality of sound wave signal data that is surely a water leakage sound. For example, a frequency with a large contribution may be extracted from an average value of frequency-converted ones, or a frequency can be obtained by calculating a frequency distribution. Further, the designation unit 6 designates a threshold value (%) for water leakage determination with respect to the Euclidean distance D (%). An arbitrary value can be designated as the threshold value, and the threshold value can be obtained from the relationship between the frequency range and the Euclidean distance D from a plurality of sound wave signal data that is clearly a water leakage sound. From the average value of the values of D when the frequency range is changed, a threshold that can be determined as water leakage can be inferred.

  The designation of parameters by the designation unit 6 may be performed using an external terminal such as a PC or a mobile phone, or may be directly input by attaching a monitor, a touch panel, or the like. When specifying with an external terminal, data is transferred using the Internet, Wi-Fi, Bluetooth or the like. Moreover, you may specify using the display etc. of the output part 5 mentioned later.

  With 1 / N octave processing and Euclidean distance determination, water leakage determination with a small number of data points becomes possible.

  Next, the 2nd determination means 8 of the determination part 4 is demonstrated. The second determination means is means for determining water leakage mainly in a time series region.

  More specifically, a high-pass filter (HPF) is applied to the sound wave signal data in the stationary section extracted by the extraction unit 3, and the ratio (time integration rate) of the total time of signals having a determination amplitude E or higher that is arbitrarily set. Make a leak check. The time interval of the sound wave signal data for performing water leakage determination can be arbitrarily selected.

  The time integration rate (%) is expressed by the following equation (3).

F (time integration rate%) = number of times exceeding amplitude E / total number of sampling times × 100 (3)
FIG. 10 is a time-series waveform of the sound wave signal data after the HPF is applied. An example is shown in which the total time exceeding arbitrarily determined amplitude ± E is calculated as a time integration rate (%).

  By determining a threshold value for the time integration rate, it is determined that there is a possibility of water leakage when the threshold value is exceeded. In general, the frequency characteristics of the septic tank sound and motor sound that are likely to be erroneously detected by water leakage sound mainly consist of peaks in the drive power supply frequency and its multiple frequencies, and greatly affect low frequency components. FIG. 11 is a diagram showing frequency characteristics of septic tank sound and motor sound. Both frequency characteristics have a peak at a low frequency. On the other hand, the frequency characteristics of the water leakage sound are different because they have characteristics in a relatively high frequency range of 1 kHz to 2 kHz.

  Therefore, by applying the HPF, the low frequency power source driving frequency that is likely to be erroneously detected and frequency components that are multiples thereof are reduced, and the septic tank sound and the motor sound are not easily detected with the time integration rate. As a result, it is possible to narrow down the number of suspected water leaks. Note that it is possible to arbitrarily determine which frequency of the power supply driving frequency is reduced.

  The specifying unit 6 of the second determination means specifies the value of the determination amplitude E described above. In addition, a threshold value (%) for determining whether there is water leakage is specified for the time integration rate (%). Also, the power supply frequency is input. Since there are two power supply frequencies in Japan, the 50 Hz region and the 60 Hz region, the power frequency is selected depending on the measurement location. By HPF, it is possible to arbitrarily input up to what order component of the power supply frequency the peak sound is reduced.

  In the present embodiment, two types of the first determination unit and the second determination unit are described as the water leakage determination unit of the determination unit 4, but these determination units may be applied individually or in series or in parallel. It may be applied. In the case of determining in series, for example, after the presence or absence of water leakage is determined by the first determination means, the presence or absence of water leakage is determined again by the second determination means for the sound wave signal data determined to have water leakage. Which determination means is performed first can be arbitrarily set. When applied in parallel, the determination results of the first determination unit and the second determination unit may be expressed by either logical sum or logical product. As the determination result, the logical product is a stricter determination result.

  As described above, each of the first determination unit and the second determination unit may be determined as a single unit, or may be combined and determined in series or in parallel. The determination result in the determination unit is output to the output unit.

  The execution of the determination algorithm in the determination unit is mainly performed by a CPU of a computer or the like.

  FIG. 12 shows the result when the water pipe leakage determination is performed using the first determination means and the second determination means.

  A determination by the algorithm of the first determination means and the second determination means was performed on 103 sound wave signal data for which the investigator made the primary determination with the detector. The leaked water data for answering was 24 cases that were judged as leaking by hearing from 103 cases.

  FIG. 13 shows the determination threshold value of the first determination unit, the determination threshold value of the second determination unit, and the determination amplitude value (voltage).

  The determination threshold value of the first determination unit was set to 20%, and more than that was determined to be water leakage. The determination threshold value of the second determination means was set to 40%, and more than that was determined to be water leakage. For the threshold setting, the one with the highest determination accuracy was selected from past water leakage determination data and empirical rules. The determination amplitude value was determined by fitting from the detector data. The determination threshold value and the determination amplitude value can be arbitrarily selected according to the measurement object and the measurement environment.

  From FIG. 12, in the case of the single determination of the first determination means, 49 out of 103 cases were determined to have water leakage. Furthermore, 20 out of 24 cases agreed with the result of audibility determination. In the case of the single determination of the second determination means, 48 out of 103 cases were determined to have water leakage. Furthermore, 20 out of 24 cases agreed with the result of audibility determination. In the case of the combined determination of the first determination unit and the second determination unit (logical product), 40 cases out of 103 cases were determined to have water leakage. Furthermore, 20 out of 24 cases agreed with the result of audibility determination. In the case of the combined determination of the first determination means and the second determination means (logical sum), 57 cases out of 103 cases were determined to have water leakage. Furthermore, 22 out of 24 cases agreed with the result of the auditory sense determination.

  The data suspected of leaking was narrowed down to less than half by the above judgment algorithm. Moreover, it was possible to determine with high accuracy of 80% or more for data that was previously determined to be leaked by hearing.

  In the case of the combined determination of the first determination means and the second determination means (logical product), the data with the possibility of water leakage could be most effectively narrowed down.

  The output unit 5 is a part that outputs the determination result of the determination unit 4. The output unit 5 may be a display for displaying a figure or a table. In addition, a display of a portable terminal such as a personal computer, a notebook computer, or a mobile phone, a tablet terminal, or the like may be used. When displaying on a portable terminal or a tablet terminal, determination result data may be received and displayed using the Internet, Wi-Fi, Bluetooth, or the like.

  The display of the output unit 5 is displayed as tabular data as shown in FIG. For example, each determination means may be displayed in the column direction, and the number of water leakage determinations or comparison data with the audibility determination may be displayed in the row direction. Moreover, you may display with a pie chart, a bar graph, etc. instead of table | surface data. Further, the threshold value of the specifying unit 6 may be specified on the display of the output unit 5 or the like.

  By using the determination algorithm of this embodiment, in the auditory sensation determination, it is possible to efficiently and accurately perform a water leakage determination work that requires extremely labor.

(Second Embodiment)
FIG. 14 is a block diagram illustrating a detailed configuration of the determination unit of the water leakage determination device 1 according to the second embodiment.

  The water leakage determination apparatus according to the second embodiment includes a third determination unit in the determination unit. The other configuration is the same as that of the water leakage determination device of the first embodiment.

  The third determination means detects the presence or absence of a repetitive sound having a constant period with respect to the sound wave signal data in the stationary section extracted by the extraction unit. This is effective for discriminating sound waves that are likely to be erroneously determined as leaking sounds.

  FIG. 15 compares the time-series waveforms and frequency characteristics of the water leakage sound and the water sound used (sound when using water supply).

  FIG. 15A shows a time-series waveform of water leakage sound and its frequency characteristic. FIG. 15B shows a time-series waveform of the used water sound and its frequency characteristics.

  The frequency characteristics of both the water leak sound and the used water sound include the frequency component up to 3 kHz, and the contribution of the component of 1 kHz to 2 kHz is large, so that it is difficult to distinguish the water sound from the frequency characteristics.

  On the other hand, the time-series waveform is characterized in that the water leakage sound is a time-series waveform such as white noise (random noise), while the water noise used is a repetitive sound with a fixed period. The water used has such characteristics because the water meter, which is the recording location, rotates when the water supply is used, so that such a sound is easily superimposed.

  As the extraction of repeated sounds of a certain period, a method of detecting the time series waveform of meter rotation sound stored in advance in a database by comparing it with the time series waveform of the input sound wave signal data, or for the input sound wave signal data For example, a method of extracting by examining the similarity of waveforms by dividing each window length. In this case, the overlap amount of the window length can be arbitrarily set. As a result, sound types that cannot be distinguished from each other in the frequency characteristics can be determined from the time-series waveform. Alternatively, it may be determined from the frequency at which repeated sounds appear from the sound wave signal data at regular time intervals. For example, the use water sound may be a case where a repeated sound appears five times or more from the sound wave signal data for 5 seconds.

  The third determination means may be applied not to the sound wave signal data of the stationary section extracted by the extraction unit but to the sound wave signal data before being extracted by the extraction unit. This is because it is conceivable that repeated signals are removed through the extraction unit.

  The third determination means of the determination unit may be used alone. Further, it may be used in combination with the first determination unit or the second determination unit according to the first embodiment. The third determining means is preferably applied to the sound wave signal data that could not be determined as water leakage by the first and second determining means. For example, when used in a combined determination with the first and second determination means, it is preferably used in the first or last flow of the serial determination.

  As a combination of the first to third determination means, the pattern of FIG. 16 can be considered.

  As shown in FIG. 16, in the case of serial determination, there are 12 combinations (in the case of a combination of two determination means + a combination of three determination means).

  In the case of parallel determination, there are four combinations (in the case of a combination of two determination means + a combination of three determination means). In addition, there are 11 ways when the judgment by logical sum and logical product is taken into consideration.

  There are 12 patterns in the combination of serial determination and parallel determination.

  Thus, in the determination using the first to third determination means, a total of 38 combinations can be considered including the single determination. It is good to select the combination of the determination means according to the situation which performs water leak determination. For example, when the number of data to be determined is large and it is desired to narrow down to as few as possible, the first to third determination means may be applied in parallel to output the logical product of the determination results. In addition, in the case of an area where tap water is frequently used in advance, the third determining means is applied first, and then the first and second determining means are applied in parallel to output the logical product of the results. May be.

  Although it has been described that the threshold value used by the first determination unit and the second determination unit is determined by the user in advance, it may be automatically set in the apparatus. In that case, it is good to set using the database which stored multiple sound wave signal data at the time of past water leakage. For example, the algorithm (first and second determination means) according to the present embodiment is applied to each of the past sound wave signal data to reversely calculate the threshold value of each determination means. The back-calculated threshold value, frequency characteristics, and time series waveform after HPF are stored in a database in a state linked to past sound wave signal data. When there is a waveform similar to the data stored in the database for the sound wave signal data input from the reception unit, a threshold value associated with the similar waveform is applied. If there is no similar waveform, the average value of the threshold values in the database is applied. Thereby, a threshold value can be determined for each sound wave signal data.

  For determining the similarity of waveforms, a correlation coefficient may be calculated, or general machine learning may be used. Machine learning is a logic constructed using an algorithm that solves a classification problem. Examples of these algorithms include decision trees, random forests, SVM (Support Vector Machine), and neural networks. An algorithm combining these algorithms may be used. The database is stored in a hard disk, USB memory, ROM or the like. Further, the sound wave signal data at the time of past water leakage may be acquired by having a database in an external server or the like and accessing it via the Internet or the like.

(Third embodiment)
FIG. 17 is a block diagram illustrating a detailed configuration of the determination unit 4 of the water leakage determination device 1 according to the third embodiment.

  The water leakage determination device according to the third embodiment includes a fourth determination unit 10 in the determination unit 4. The other configuration is the same as that of the water leakage determination device of the first embodiment.

  The fourth determination means 10 calculates an autocorrelation function for the sound wave signal data (also referred to as a time-series waveform) in the stationary section extracted by the extraction unit 3 and compares it with the threshold value specified by the specification unit 6. Determine the presence or absence of water leakage. Specifically, an envelope of the autocorrelation function is obtained, and a predetermined predetermined line segment is compared with the envelope. A ratio at which the envelope becomes larger than a predetermined line segment is obtained and compared with a threshold value designated by the designation unit 6. For example, the case where the ratio becomes larger than a threshold value is determined as sound wave signal data with water leakage. The predetermined line segment and the threshold value are arbitrarily determined based on empirical rules, past water leakage data, and the like. The predetermined line segment is not necessarily limited to a straight line, and includes a curve and the like. Further, the comparison with the threshold value is not limited to a ratio, and may be an area formed by an envelope or an inclination of the envelope. The determination unit in FIG. 17 may include third determination means.

  The autocorrelation function is for evaluating the degree of coincidence between the signal data of two sections cut out from the same sound wave signal data. The presence or absence of water leakage is determined by evaluating the degree of coincidence of the periodic components included in the sound wave signal data in the steady section.

  An envelope is a line segment that shares a tangent with a plurality of curves, and takes a straight line or a curved shape depending on the type of the curve in contact. For example, an envelope of a plurality of curves having vertices includes a line segment that connects the vertices.

The following formula (4) is a formula showing an autocorrelation function. x (n) is an input signal, r (m) is an autocorrelation function, and N is an autocorrelation data length.

  The determination procedure of the fourth determination means 10 will be described in detail with reference to FIG.

  FIG. 18 shows an example of a detailed block diagram of the fourth determination means 10.

  As shown in FIG. 18, first, the autocorrelation function of the sound wave signal data in the steady section is obtained. Next, an absolute value is obtained for the obtained autocorrelation function, and the calculation range is limited to the positive time direction. Next, an envelope for the autocorrelation function is derived. In general, the Hilbert transform is used to calculate the envelope. Next, linear approximation is performed on the envelope. When this approximate line is regarded as a linear function, it is preferable to obtain it by the least square method. Water leakage is determined based on the obtained approximate straight line.

  FIG. 19 shows an example of a determination procedure when a test signal is used.

  Here, a 50 Hz sine wave was used as the signal of the sound wave signal data in the stationary section. FIG. 19A shows a time-series waveform of a 50 Hz Sin wave. FIG. 19B is a graph of the autocorrelation function derived based on Expression (4). FIG. 19C is a graph showing the absolute value of the autocorrelation function. Furthermore, it is limited to a graph of time in the positive direction. As shown in FIG. 19D, the time graph in the positive direction has a downward slope and tends to converge to 0 as the time increases. An envelope is derived for this graph. Further, an approximate straight line of this envelope is taken. FIG. 19E is a graph showing an approximate straight line between the waveform of the autocorrelation function and the envelope. Since the graph shape is a target in the positive and negative time directions, a graph in the negative time direction may be used as the calculation range. In that case, since the start point changes from 0 on the time axis in the negative direction, the slope of the graph is downward. In the case of a single frequency time-series waveform as shown in FIG. 19A, the shape of the obtained envelope and the approximate straight line are almost the same. Since there are signals of a plurality of frequency components, the envelope and the approximate straight line are generally different in shape.

  FIG. 20 shows an example of a determination procedure in the case of a time-series waveform including a fluctuating sound. As shown in FIG. 20A, the time-series waveform including the fluctuating sound is a time-series waveform whose amplitude is locally increased at a predetermined time. FIGS. 20B and 20C are signals obtained by obtaining an autocorrelation function of the time series waveform and taking an absolute value. FIG. 20 (d) shows the result of deriving the envelope of the waveform of FIG. 20 (c). As shown in FIG. 20 (d), the envelope in this case has a curved shape, and thus has a shape different from the approximate straight line of the envelope shown in FIG. 20 (e).

  FIG. 21 shows an example of a time-series waveform when a signal having a plurality of frequency components is included.

  FIG. 21A shows a 50 Hz Sin wave, and FIG. 21B shows a time-series waveform of a 1 kHz Sin wave. FIG. 21C shows a time series waveform in which a 50 Hz sine wave (amplitude ratio 50%) and a 1 kHz sine wave (amplitude ratio 20%) are superimposed.

  FIG. 21 (d) shows a time-series waveform of a random sound that is white noise. FIG. 21E shows a waveform in which white noise and a 50 Hz Sin wave (amplitude ratio of 50%) are superimposed. FIG. 21F shows a waveform in which white noise and a 50 Hz Sin wave (amplitude ratio of 20%) are superimposed. It is a waveform.

  22A to 22F are derived from the autocorrelation functions of the time-series waveforms of FIGS. 21A to 21F, the respective envelopes, and the approximate straight line. As shown in FIGS. 22 (a) and 22 (b), the time series waveforms in FIGS. 21 (a) and 21 (b) show a sharp drop in the autocorrelation function, while the white waveform in FIG. In the time series waveform of noise, the value of the autocorrelation function is remarkably small, and the slope of the envelope is almost zero. When two Sin waves having different frequencies are superimposed as shown in FIG. In the case where the Sin wave and white noise in FIGS. 21E and 21F are superimposed, the magnitude of the slope of the graph changes depending on the mixing ratio of the amplitude.

  As described above, the water leakage sound has the characteristics of white noise (random sound). In addition, periodic components such as sine waves are dominant in the septic tank sound and motor sounds of vending machines and outdoor units.

  Thereby, it is possible to easily determine whether or not a peak sound unrelated to the water leakage sound is included in the sound wave signal data in the steady section actually extracted by the extraction unit 3 by obtaining the autocorrelation function. Further, it is possible to visually distinguish the peak sound from the graph.

  Next, the result of calculating the autocorrelation function by the fourth determination means 10 for the actually measured sound wave signal data will be described.

  FIGS. 23A to 23D show the actually measured sound wave signal data and the result of obtaining the autocorrelation function thereof.

  As shown in FIG. 23A, the autocorrelation function of the sound wave signal data indicating a single peak sound has an envelope curve or an approximate straight line with a downward slope. In addition, the autocorrelation function of the sound wave signal data in which a plurality of peak sounds in FIG. 23B is superimposed results in convergence to zero while the envelope changes. In addition, the autocorrelation function of the sound wave signal data indicating the water leakage sound in FIG. 23C has a result that the slope of the envelope is nearly zero. In addition, in the autocorrelation function of the sound wave signal data indicating the use of the motor sound and water supply in FIG. These results are substantially the same as the test signal results.

  To summarize the above results, in the case of single-peak sound wave signal data, the slope of the envelope of the autocorrelation function (or an approximate straight line of the envelope) is relatively large, and the sound signal of white noise that indicates water leakage sound In the case of data, the slope of the autocorrelation function envelope is small. In the case of sound wave signal data in which a peak sound and a random sound are superimposed, the magnitude of the envelope slope varies depending on the amplitude ratio of the two signals. In the case of sound wave signal data in which a leak sound and a peak sound are superimposed, an arbitrary threshold value may be set to perform the leak determination process.

  Next, a method for determining and processing a predetermined line segment and threshold value to be compared with the envelope of the autocorrelation function (or an approximate straight line of the envelope) will be described in detail.

  FIG. 24 is a diagram illustrating an example of a determination process in which a predetermined line segment and a threshold value are set. In FIG. 24, a predetermined line segment is represented by black (solid line), and an envelope is represented by gray (solid line). Determination is performed at a rate that the envelope becomes larger than a predetermined line segment.

  Since the horizontal axis of the graph of FIG. 24 indicates a time of 1 second as a whole, if the slope of a predetermined line segment is X (X <0), the intercept becomes −X when 0 is set after 1 second. In FIG. 24, the threshold is set to 20%, and the determination condition is set so that there is a possibility of water leakage instead of the peak sound if the ratio of the envelope larger than the predetermined line segment (time integration rate) is 20% or less. . The ratio in which the envelope is larger than the predetermined line segment is a time integration rate, and is expressed by, for example, the following formula (5).

Time integration rate% = time when the envelope exceeds a predetermined line segment / total time (time until convergence to 0) × 100 (5)
In the case of FIGS. 24A and 24B, the time integration rate is 94.5% and 69.6%, and the result exceeds the threshold value 20% specified by the specifying unit 6. Determined as data. In the case of FIGS. 24C and 24D, the time integration rate is 1.285%, which is 0.6%, which is lower than the threshold value 20%.

  The determination of water leakage in comparison with the threshold is not limited to the time integration rate, but may be performed by time integration of the envelope of the autocorrelation function and a predetermined line segment and comparing the magnitudes thereof. This means that the area created by each of the envelope and the predetermined line segment is compared.

  FIG. 25 shows the result of comparing the size of the area created by each of the envelope and the predetermined line segment.

  When the area formed by the envelope is larger than the area formed by the predetermined line segment, it is determined as sound wave signal data of peak sound instead of leaking sound. When the area formed by the envelope is smaller than the area formed by the predetermined line segment, it is determined that there is a suspicion of leaking sound. In this case, the area created by the predetermined line segment is designated as the threshold value.

  In addition, the determination of water leakage in comparison with a threshold value may be made by comparing the slope of the envelope (or the approximate straight line of the envelope) with the slope of the predetermined line segment. In this case, the slope of the predetermined line segment is designated as the threshold value.

  The above-mentioned time integration rate derived based on the envelope of the autocorrelation function, the area formed by the envelope, and the slope of the envelope are also referred to as determination values.

  FIG. 26 shows the result when water leakage is determined from the autocorrelation function based on any of the time integration rate, the area created by the envelope, or the slope of the envelope. For the 103 sound wave signal data for which the investigator made the primary determination with the detector, the determination was performed based on either the time integration rate, the area created by the envelope, or the slope of the envelope. The leaked water data for answering was 24 cases that were judged as leaking by hearing from 103 cases. As a result, the number of refinements using the time integration rate was 45, the number of refinements using the area created by the envelope was 43, and the number of refinements using the slope of the envelope was 44. . Of the narrowed-down sound wave signal data, the number of correct answers included was 21 (out of 24), and in all cases, a high correct answer rate was shown. In the case of determining water leakage using the algorithm of the fourth determining means, there was almost no difference even if water leakage determination was made based on any of the time integration rate, the area created by the envelope, or the slope of the envelope. What is necessary is just to select suitably according to the situation which leaks, the data acquired in the past, etc.

  By using the fourth determination means, it is possible to narrow down data having a possibility of water leakage sound from a large number of sound wave signal data with high probability.

  Further, by combining with the first to third determining means according to the first or second embodiment, data having a possibility of water leakage sound can be narrowed down with a higher probability from a large number of sound wave signal data.

  The combination of the first, second, or fourth determination means may be the pattern shown in FIG.

  As shown in FIG. 27, in the case of serial determination, there are 12 combinations (in the case of a combination of two determination means + a combination of three determination means).

  In the case of parallel determination, there are four combinations (in the case of a combination of two determination means + a combination of three determination means). In addition, there are 11 ways when the judgment by logical sum and logical product is taken into consideration.

  There are 12 patterns in the combination of serial determination and parallel determination.

  As described above, in the determination using the first, second, or fourth determination means, a total of 38 combinations are conceivable including the single determination.

  The combination of the second, third, or fourth determination means may be the pattern shown in FIG.

  The combination of the second, third, and fourth determination means is the same pattern combination as the combination of the first, second, and fourth determination means.

  As a combination of the first, third, and fourth determination means, the pattern of FIG. 29 can be considered.

  Moreover, you may combine the 1st-4th determination means. When combining four determination means, the pattern of FIG. 30 can be considered.

  As shown in FIG. 30, there are 24 combinations for series determination. In the case of parallel determination, there are 13 combinations (excluding combinations that take a logical product of logical products). There are 112 combinations of serial determination and parallel determination.

  The pattern of these combinations can be selected as appropriate according to the situation where the water leakage determination is performed. For example, when it is desired to narrow down data having a possibility of water leakage from a large amount of sound wave signal data, the sound wave signal data may be narrowed down by connecting the first to fourth determination units in series. Further, the logical product of the determination results of the first to fourth determination means may be taken. Further, the logical product of the determination results of the two logical products excluding the above-described combinations may be taken.

  In addition, it has been described that the threshold value used by the fourth determination unit is determined by the user in advance, but may be automatically set in the apparatus. In that case, a method similar to the method described in the first and second determination means can be used.

  The embodiment described above can be used as a system without being limited by the water leakage determination device. For example, a server that includes a plurality of sound wave signal data measured by a detector for detecting sound waves (vibration sound) by a water leak inspection investigator such as a water pipe, including the water leak determination algorithm (extraction unit, determination unit) of the present embodiment To the Internet. The server performs water leakage determination using the transferred sound wave signal data. The server forwards the water leak judgment result to the investigator's detector. Thereby, it becomes possible for the investigator to determine water leakage only with a detector equipped with communication means such as the Internet without carrying a high-performance and large-scale device.

  Although several embodiments of the present invention have been described, these embodiments are presented by way of example and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the scope of the invention. These embodiments and modifications thereof are included in the scope and gist of the invention, and are included in the invention described in the claims and the equivalents thereof.

DESCRIPTION OF SYMBOLS 1 Leakage determination apparatus 2 Reception part 3 Extraction part 4 Determination part 5 Output part 6 Specification part 7 1st determination means 8 2nd determination means 9 3rd determination means 10 4th determination means

Claims (11)

A reception unit for receiving sound wave data;
An extraction unit for extracting data of a stationary section with less noise from the sound wave data;
A specification unit for specifying a threshold;
A water leakage determination apparatus comprising: a determination unit that obtains a ratio including a signal indicating characteristics of water leakage from the data of the steady section and compares the ratio with the threshold value to determine the presence or absence of water leakage.   The determination unit obtains an integration rate between the entire frequency range and an arbitrary frequency range with respect to a difference between the frequency characteristic of the data in the stationary section and the frequency characteristic of background noise, and compares the integration rate with the threshold value. The water leakage determination apparatus according to claim 1, further comprising first determination means for determining the presence or absence of water leakage.   The determination unit includes a filter that reduces a low frequency component of the data in the steady section, obtains a time integration rate of a predetermined amplitude or more for the data in the steady section to which the filter is applied, and the time integration ratio The water leak determination apparatus according to claim 1 or 2, further comprising: a second determination unit that determines whether or not water leaks by comparing the threshold with the threshold.   The said determination part is equipped with the 3rd determination means which detects the frequency of the repetition signal of a fixed period with respect to the data of the said regular area, and compares the said frequency with the said threshold value, and determines the presence or absence of water leakage. The water leak determination apparatus according to any one of the above.   The determination unit obtains an autocorrelation function of the data in the stationary section and compares the determination value derived based on an envelope connecting the curves of the autocorrelation function with the threshold value to determine the presence or absence of water leakage. The water leak determination apparatus according to any one of claims 1 to 4, further comprising: a determination means.   The water leakage determination apparatus according to claim 1, further comprising an output unit that outputs a determination result of the determination unit.   The water leakage determination device according to claim 6, wherein the output unit outputs a logical sum or a logical product of determination results of the first determination unit and the second determination unit.   The water leakage determination device according to claim 3, wherein the determination unit further determines the presence or absence of water leakage by the second determination unit with respect to the sound wave data determined by the first determination unit as having water leakage.   The water leakage determination device according to claim 3, wherein the determination unit further determines the presence or absence of water leakage by the first determination unit with respect to the sound wave data determined by the second determination unit as having water leakage.   The determination unit is based on a first determination unit that determines based on a difference between a frequency characteristic of data in the stationary section and a frequency characteristic of background noise, and a time integration rate that is equal to or greater than a predetermined amplitude of the data in the stationary section. The water leakage determination apparatus according to claim 1, further comprising: a second determination unit that determines the above. A water leakage determination method in a water leakage determination device for determining the presence or absence of water leakage from sound wave data,
Extract data from the sound wave data in a steady section with less noise,
Specify the threshold value for judging the presence or absence of water leakage,
Obtain the ratio of the signal indicating the characteristics of water leakage from the data of the steady section,
A water leakage determination method for determining the presence or absence of water leakage by comparing the ratio with the threshold value.

Images