JP2020101419A - Tube state detection system, method thereof and sensor terminal - Google Patents

Abstract

To provide a tube state detection system that is capable of automatically setting an optimal operation according to an installation environment of each sensor terminal.SOLUTION: There is provided a tube state detection system in which a plurality of sensor terminals 10 which are attached to a pipeline and send a monitoring signal, and a center-side device for receiving the monitoring signal are communicatively connected. The sensor terminal 10 comprises: a sensor 1 for outputting detection data including information related to an anomaly of a pipeline; a sensor signal processing unit 2 for analyzing deterioration level from the detection data and outputting the same; an installation environment evaluation processing unit 3 for processing the detection data and outputting a feature amount which is used for evaluating a terminal installation environment in which the sensor 1 is installed; a learning unit 7 for learning an environment evaluated by the feature amount; and a communicating unit 9 capable of communicating an output of the sensor signal processing unit 2 and control information to the center-side device. The learning unit 7 sets a measurement schedule 5 and an operation parameter 6 adapted for the environment individually for each sensor terminal 10 on the basis of a learning result.SELECTED DRAWING: Figure 1

Description

The present invention relates to a pipe state detection system, a method thereof, and a sensor terminal, and more particularly, to a pipe state detection system, a method thereof, and a sensor terminal for detecting whether or not there is deterioration by a difference in vibration or sound detected by a sensor.

Regarding various types of water leak detectors that detect abnormalities such as the state of pipes such as water pipes buried in the ground that are difficult to see and the occurrence of leaks, and the detection method using them, refer to Non-Patent Document 1 It is described in "Maintenance Guidelines" and "Prevention of Water Leakage in Tokyo" in Non-Patent Document 2.

In addition, for the same purpose, in the patrol inspection in which the person in charge makes a patrol in the service area to inspect, a method using a sound stick or an electronic water leak detector is used. Further, Patent Document 1 describes an inspection method using a constantly installed water leakage detector.

As is well known, 60 years have passed since the establishment of the high growth period for water supply services such as the Waterworks Bureau, and the deterioration of water distribution facilities is progressing. On the other hand, although we are conducting renewal projects that include earthquake resistance, there is a current situation that water leakage accidents frequently occur at any of the entities. In addition, the water supply business has business problems such as a decrease in revenue due to a decrease in the amount of water used as the population declines and a decrease in the number of business staff. In particular, there is a need for an efficient solution for leak control to improve the amount of water that can be earned. The amount of water collected is the amount of water collected for the collection of water charges.

Up to now, regarding water leakage, the staff in charge went to the site and used a mobile water leak detector to individually search for water leakage points. Was there. It is not efficient in terms of maintenance cost to conduct a water leak inspection by visiting a wide service area. A remote monitoring system has been demanded as an efficient method for water leakage prevention in the future. According to the remote monitoring system, inexpensive sensing terminals (hereinafter, also referred to as "sensor terminals" or simply "terminals") are constantly arranged in a wide range of multi-point water pipes, and the occurrence of water leakage is detected by remote monitoring. , The leak point position can be estimated with high accuracy.

JP, 2005-163903, A

Ministry of Health, Labor and Welfare "Water Supply Management Guidelines" (2006 version), 9.5.8 Prevention of water leakage Water leak prevention in Tokyo, published by Tokyo Metropolitan Waterworks Bureau (2016 version), 3 Leakage investigation method

When the above-mentioned terminals are distributed over a wide range, the environment is different for each installation location, and therefore measurement under the same conditions is not suitable in many cases. In addition, when the installation location is a place with a large amount of traffic or near a facility that causes a lot of disturbance in the surroundings, a large disturbance is mixed into the sensor signal of the terminal, which may cause deterioration of the quality of the measurement result. These disturbances change depending on the place and time of measurement. The above situation is not limited to water pipes, but is common to gas pipes as infrastructure with a wide network of pipes and pipes for large-scale facilities.

In particular, with respect to the buried pipe of water supply, the influence of the disturbance on the vibration signal to be acquired is large, and the intensity of the disturbance signal reaches several times to several tens of times or more that of the signal. In that environment, if the settings are such that monitoring is performed once a day on a regular basis, and if the timing of the disturbance coincides with the sampling measurement for a short time, it is difficult to remove the disturbance. is there. Further, even if leveling is performed by repeated measurement, the reliability of the measurement data cannot be maintained if high-level disturbance noise is mixed. When the measurement data whose quality is deteriorated is discarded, it is necessary to re-measure at another timing, which increases the power consumption of the battery-operated terminal, which makes it impossible to continue the use for a long period of time. The present invention has been made to solve the above problems, and an object of the present invention is to detect a pipe state capable of automatically setting an optimal operation without waste according to the installation environment of each sensor terminal. To provide a system.

The present invention for solving the above-mentioned problems is configured by communicably connecting a plurality of sensor terminals attached to a pipe to be monitored and transmitting a monitoring signal, and a center-side device that receives the monitoring signal and is used for monitoring. In the pipe state detection system described above, the sensor terminal outputs a sensor that outputs detection data that detects an abnormality caused by a deterioration state of the pipe, and a result of analyzing the deterioration state by processing the detection data. A sensor signal processing unit that outputs as a target signal, a disturbance signal is extracted from the detection data and input, and an installation environment evaluation processing unit that outputs a characteristic amount used for evaluation of a terminal installation environment in which the sensor is installed; A learning unit that learns the terminal installation environment evaluated based on a feature amount, and a communication unit that can communicate the target signal and control information output from the sensor signal processing unit to the center-side device. The learning unit individually sets the measurement schedule and the operation parameter of the sensor signal processing unit for each sensor terminal based on the learning result according to the learned terminal installation environment.

According to the present invention, it is possible to provide a pipe state detection system capable of automatically setting an optimal operation without waste according to the installation environment of each sensor terminal.

It is a block diagram which shows the structure of the water leak detection terminal (henceforth "a sensor terminal" or "this terminal") which concerns on Example 1 of this invention. It is a block diagram which shows the structure of the pipe state detection system (henceforth "this system") comprised including this terminal of FIG. It is sectional drawing which shows the utilization form which attached this terminal of FIG. 1 to the sluice valve of a water supply pipe. 4 is a flowchart showing an operation procedure of the present terminal shown in FIGS. 1 to 3 (hereinafter, also referred to as “present method”). 5 is a table showing an example of a data structure forming a measurement schedule of the terminal shown in FIGS. 1 to 4. 5 is a table showing an example of a data set forming the measurement schedule of the terminal shown in FIGS. 1 to 4. 5 is a table showing an example of a data structure forming the adjustment schedule of the terminal shown in FIGS. 1 to 4. It is a graph which shows the time change of PSD (PowerSpectrum Density) average value signal by the disturbance assumed to this terminal shown in FIGS. 1-4, FIG. 8 (a) is no disturbance, FIG. Opening and closing, etc., and FIG. 8C shows changes in flow rate, etc., respectively. FIG. 3 is a block diagram showing a configuration of a sensor signal processing unit shown in FIG. 1. FIG. 3 is a block diagram showing a configuration of an installation environment evaluation processing section shown in FIG. 1. It is a block diagram which shows the structure of the learning part shown in FIG. It is a block diagram which shows the modification of the learning part shown in FIG. It is a graph for explaining the modeling of the amount of activity, and FIG. 13(a) shows the amount of daily activity, FIG. 13(b) shows the amount of weekly activity, and FIG. 13(c) shows the amount of monthly activity. There is. 7 is a flowchart showing a process in the sensor signal processing unit shown in FIG. 1 in which the control unit in FIG. 1 partially discards the measurement data when the disturbance during measurement is large. 5 is a flowchart showing a process of judging installation failure of the terminal shown in FIGS. 1 to 4 from an evaluation result of an installation environment evaluation processing unit of FIG. 1. 6 is a flowchart showing a process in which the control unit of FIG. 1 inspects a trigger state. 6 is a flowchart showing a process of uploading a measurement schedule obtained from the evaluation result acquired by the installation environment evaluation processing unit of FIG. 1. 3 is a flowchart showing a process of uploading the evaluation result acquired by the installation environment evaluation processing unit of FIG. 1 as a learning result to the center side device 20 of FIG. 2. 18 is a flowchart showing a process of resetting the measurement schedule stored and managed by the center-side device 20 after downloading to the terminal shown in FIGS. 1 to 4 by the process of FIG. 17. It is a block diagram which shows the structure of the pipe state detection system (This is also called "this terminal") which concerns on Example 2 of this invention. 21A and 21B are graphs for explaining the processing of the sensor signal processing unit of FIG. 20, where FIG. 21A is the disturbance evaluation amount output by the moving body determination unit of FIG. 20, FIG. 21B is a delay signal, and FIG. c) shows a measurement schedule signal, respectively.

An embodiment of the present invention will be described with reference to the drawings. The component names in each figure are abbreviated names that can also be used as function names, signal names, or process names. doing. Further, functions, signals, and processes having the same effect are denoted by the same reference symbols throughout the drawings to avoid duplication of description. Hereinafter, the first embodiment will be described with reference to FIGS. 1 to 19 and then the second embodiment will be described with reference to FIGS.

FIG. 1 is a block diagram showing the configuration of a water leakage detection terminal (main terminal) according to the first embodiment of the present invention. FIG. 2 is a block diagram showing a configuration of a pipe state detection system (present system) including the present terminal of FIG. As will be described later, the terminal of FIG. 1 corresponds to the range of the sensor 1, the terminal side processing unit 12 and the communication unit 9 of FIG. Note that, in the block diagram of FIG. 1, in particular, the configuration of the terminal side processing unit 12 in the present system of FIG. 2 is enlarged and shown in detail.

As shown in FIG. 1, the terminal 10 includes a sensor 1, a sensor signal processing unit 2, an installation environment evaluation processing unit 3, a control unit 4, a learning unit 7, and a communication unit 9. Further, the measurement schedule 5, the operation parameter, and the evaluation schedule 8 are set numerical values specified by their respective names, and also mean a storage area (storage unit) in which these set numerical values are stored in a reproducible manner. ..

The sensor 1 is attached to a pipe, detects vibration of the pipe, and converts it into vibration data. The detected vibration data is processed by the sensor signal processing unit 2, and the characteristic amount (that is, the pipe state) that reflects the state of the fluid moving in the pipe is output. This feature amount is made up of one or a plurality of numerical value groups, and is an amount that changes with time. The sensor signal processing unit 2 operates at each time designated by the measurement schedule 5, and sends the feature amount at that time to the communication unit 9.

The communication unit 9 communicates with the system of the center side device 20 corresponding to this terminal, and transmits the characteristic amount indicating the state of the fluid in the pipe to the center side device 20. Further, the communication unit 9 operates to receive the received data from the center-side device 20 and transmit it to the control unit 4. The control unit 4 is a component that controls the operation of each unit of the terminal. That is, the control unit 4 performs data communication with the system of the external center side device 20 via the communication unit 9, transmits the detection data of the pipe state detection system, or receives the request of the center side device 20. Then, the operation of the entire detection device is controlled.

The vibration data output by the sensor 1 is also input to the installation environment evaluation processing unit 3. The installation environment evaluation processing unit 3 processes at each time designated by the evaluation schedule 8, calculates evaluation data for evaluating the installation environment of the device, and inputs the evaluation data to the learning unit 7. The measurement schedule 5 and the evaluation schedule 8 are independent schedules that do not overlap.

The learning unit 7 processes the evaluation data output by the installation environment evaluation processing unit and learns the amount of the evaluation data and the change over time. The evaluation data is a characteristic amount for evaluating the installation environment of the detection device, and is an amount indicating the characteristics of each installation location. The operation parameter 6 and the measurement schedule 5 obtained based on the processing result of the learning unit 7 are stored as data for system control in dedicated storage areas. Note that, as described above, the evaluation schedule 8, the measurement schedule 5, and the operation parameter 6 are illustrated so as to also be used as names that mean the respective data storage areas (storage units).

The present system of FIG. 2 is a suitable system that is adopted to detect a water leakage abnormality in a water pipe. Water leakage is a typical condition of deterioration of water pipes detected by this system, and another example is abnormal sound or vibration from a water supply device. Specific causes thereof include a water hammer effect and wear of water supply tool parts.

The system of FIG. 2 is composed of the terminal 10 and the center-side device 20, and a communication network 11 that connects the two to each other for information. The terminal 10 includes a sensor 1, a terminal-side processing unit 12, a communication unit 9, and a battery unit 13 having various batteries for driving them. The center-side device 20 includes a transmission/reception unit 21, a center-side signal processing unit 22, a time synchronization unit 23, a display device 24, and a pipeline network database 25.

A plurality of the terminals 10 are distributed and arranged in each of the buried pipes in the water distribution area within the water supply service providing area. The sensor 1 detects vibration of the water pipe and converts it into vibration data. The vibration data is converted by the sensor signal processing unit 2 on the terminal side into feature amount data (frequency data) by a frequency analysis method such as fast Fourier transform (FFT). The communication unit 9 transfers the frequency data to the center-side device 20 via the communication network 11. The battery unit 13 is a power supply unit of the terminal 10 and supplies power to each unit of the terminal 10. Next, a usage pattern of the terminal 10 is illustrated in FIG.

FIG. 3 is a cross-sectional view showing a usage pattern in which the water leakage detection terminal (main terminal) 10 according to the first embodiment of the present invention is attached to a sluice valve of a water supply buried pipe. As shown in FIG. 3, a water distribution pipe 28 is buried in the ground 29 to form a buried water distribution pipe network, and a manhole is provided at an appropriate position of the water distribution pipe 28, and a sluice valve 27 is installed in the manhole. The gate valve 27 can be operated by opening and closing the manhole cover 26.

The terminal 10 is attached to a valve cap portion (an operation unit for opening and closing the sluice valve) of a sluice valve 27 that can be operated by opening and closing the manhole cover 26. In this way, a large number of main terminals 10 are arranged over the entire area of the buried water distribution network in a form similar to that of FIG. These main terminals 10 detect the vibration propagating through the water pipe 28.

The water pipe in such an installed state is buried at a depth of about 1 m in the ground directly under the public road. Since this water pipe is not so deep from the surface of the earth, vibration generated from a moving body such as an automobile passing through the surface of the water propagates in the ground. Therefore, each main terminal 10 is likely to receive them as a disturbance. Therefore, unless some noise countermeasures are taken, the accuracy of water leak detection of the terminal 10 is extremely low. The operation procedure of the terminal 10 installed under such conditions will be described.

FIG. 4 is a flowchart showing an operation procedure (present method) of the terminal 10 shown in FIGS. The processing flow of FIG. 4 illustrates a procedure in which the control unit 4 of FIG. 1 controls the sensor signal processing unit 2 and the installation environment evaluation processing unit 3 to execute this method. As shown in FIG. 4, the present method starts from step S1, goes through each procedure described later, and returns to step S2 after the end of step S13 to make a cycle where the next adjustment time is waited, and repeat these steps. ing.

Steps S2 and S3 are timer operation processing. According to the adjustment schedule input from step S4, step S2 (timer operation) waits until a specified time (adjustment time) and starts the operation. Similarly, according to the measurement schedule input in step S5, step S3 (timer operation) waits until a specified time (measurement time) and starts the operation. The process flow after step S2 is the process of the adjustment operation (environment evaluation mode) executed at the time of adjustment, and the process flow after step S3 is the process of the measurement operation (measurement mode) executed at the measurement time.

Step S8 is processing of the installation environment processing unit 3 of FIG. 1, and performs adjustment signal processing. Step S9 is a data storage process for holding the data history of the environmental evaluation value calculated inside the installation environment processing unit 3 for a certain period. Step S10 is a step of learning the feature of each installation point from the data history of the environmental evaluation value. The learning is a process of assuming a certain model and determining a predetermined number of model parameters. The learning result in step S10, that is, the model parameter is held inside the learning unit 7.

Step S11 is a process of determining whether or not the learning amount has sufficiently reached. It is determined whether or not the newly learned amount is sufficiently accumulated after it is determined that the learned amount is sufficient at the previous measurement. If the learning amount is insufficient (NO in S11), the process returns to step S2 to wait for the next adjustment time. If the learning amount is sufficient (YES in S11), a measurement schedule is generated based on the learning result in step S12. The measurement schedule 5 is updated with the measurement schedule generated here.

Step S13 is a calculation process for generating an operation parameter based on the learning result. The operation parameter 6 is updated by the operation parameter generated here. After the end of step S13, the process returns to step S2 and waits for the next adjustment time. In step S6, the sensor signal processing unit 2 of FIG. 1 performs the regular measurement. In step S7, data communication is performed to the center side device 20 regarding the measurement result of step S6. After the end of the data communication, the process returns to step S3 and waits until the next measurement time.

FIG. 5 is a table showing an example of a data structure constituting the measurement schedule of the terminal 10 shown in FIGS. That is, FIG. 5 illustrates the stored data of the measurement schedule 5 used by the sensor signal processing unit 2. As shown in FIG. 5, each data includes a number 31, a start date/time 32, a designation of the measurement item 33, and a repeat flag 34 in the first row in order from the left column. In this example, the designated contents of date and time and measurement conditions are stored in a predetermined storage area 5 for each planned measurement.

As the start date and time 32, information of the date and time at which the measurement is started is specified from the year of the Christian era, and the precision including the time zone is specified in minute units. The designation of the measurement item 33 is a code that identifies the type of measurement, and corresponds to a plurality of types of measurement. In this table, only the designation "A" of one type of measurement item is described. The repeat flag 34 has two kinds of values of 0 and 1, and 0 indicates that the corresponding measurement has been executed or does not need to be executed. Under the control of the control unit 4, the values in this table are changed from 1 to 0 when the measurement is performed.

If the storage capacity of the terminal 10 is sufficient, the table of FIG. 5 stores the schedule of the entire usage period of the terminal 10. When the storage capacity of the terminal 10 is insufficient, a schedule for a fixed period is stored, and with the passage of time, processing for updating the old schedule with the new schedule is performed.

FIG. 6 is a table showing an example of a data set constituting the measurement schedule of the terminal 10 shown in FIGS. That is, FIG. 6 is a data set in which the measurement schedule or the evaluation schedule is grouped according to the purpose and the situation. Is the set number 35, is the data 36, and is the remark 37. The set number 35 is an identification number assigned to the data set, the data 36 describes the name of the data set, and the remark 37 describes the purpose of use of the data set and information on the corresponding situation.

Data sets corresponding to the measurement schedule and the evaluation schedule are prepared respectively, and the control unit 4 reads the data sets and transfers the data to the measurement schedule 5 and the evaluation schedule 8. When there is a data change in the measurement schedule 5 and the evaluation schedule 8, the control unit 4 transfers the data to reflect the change in the data set. In FIG. 6, data sets corresponding to four situations of set numbers 1 to 4 are shown.

The set number 1 has a data set name of “schedule data set A” and is a measurement schedule when the terminal 10 was initially installed. A data storage area 5 for the measurement schedule shown in FIG. 5 is provided for each data set, data is stored, and rewriting is also performed.

An example of a method of storing the schedule data of each data set is a method of embedding it in the data structure of FIG. In that case, the data 36 stores the schedule data following the data set name. It suffices to use a data storage format in which the data delimiter corresponding to the variable length of each data set can be understood. Another example of a method of storing schedule data in each data set is to prepare a correspondence table in which the correspondence between the data set name and the storage position of schedule data is described.

“Schedule data set B” of set number 2 is schedule data in which a daily schedule is described. The data content is every day (24 hours). It is used when the same measurement is performed every day after the measurement in the schedule of set number 1 is completed.

The “schedule data set C” of set number 3 is schedule data that is executed weekly. This data set corresponds to the execution of an additional measurement corresponding to the day of the week, in addition to the schedule of the set number 2 which is executed on a daily basis. The “schedule data set D” of set number 4 is schedule data corresponding to the lifetime period of the terminal 10 such as 5 years. In this way, the schedule data corresponding to various situations is held, and the control unit 4 operates the sensor signal processing unit 2 and the installation environment evaluation processing unit 3 based on the schedule data.

FIG. 7 is a table showing an example of a data structure forming the adjustment schedule of the terminal 10 shown in FIGS. That is, FIG. 7 illustrates the data of the evaluation schedule 8 used by the installation environment evaluation processing unit 3. As shown in FIG. 7, each data is a number 41, a start and end date and time 42, an evaluation item 43, and a repetition flag 44, as shown in order from the left column of the first row. The number 41 identifies the individual evaluation schedule registration. The start and end date/time 42 indicates the execution period of the evaluation schedule, and indicates that the evaluation content of the evaluation item 43 is executed when the current time is within this execution period.

The repetition flag 44 is data that specifies the frequency of repetition. The repeat flag 44 is composed of three elements. The first code is 0 or 1, which indicates whether the registered content is valid or invalid. The following symbols indicate repetition periods, and H, D, and W correspond to 1 hour, 1 day, and 1 week, respectively. The numbers that follow indicate the number of divisions for that period. H/1 is once every hour, D/4 is four times a day, and W/1 is once a week.

The control unit 4 reads the data of the evaluation schedule 8 shown in FIG. 7, and operates the installation environment evaluation processing unit 3 at the designated time. The instruction to read or change the evaluation schedule is delivered from the center-side device 20 to the control unit 4 via the communication unit 9. In response to this, the control unit 4 reads the received data content of the evaluation schedule 8 and delivers the data to the sensor signal processing unit 2 if it is a read command. Alternatively, if it is a change command, the data of the evaluation schedule 8 is updated by the data received by the control unit 4.

FIG. 8 is a graph showing the temporal change of the PSD average value signal due to the disturbance assumed in the terminal 10 shown in FIGS. 1 to 4, FIG. 8( a) showing no disturbance, and FIG. 8( b) showing FIG. 8C shows valve opening/closing, etc., and flow rate changes, etc., respectively. That is, FIG. 8 exemplifies a schematic display of an example of the temporal change of the disturbance by the PSD average value signal of the sensor signal. This PSD average value signal is a value obtained by integrating a short-time PSD spectrum with a frequency and converting it per unit frequency, and corresponds to acoustic intensity.

FIG. 8A shows a change in the PSD signal when no disturbance has occurred. FIG. 8B shows an example of a disturbance called a water hammer phenomenon caused by opening and closing a valve connected to a water pipe, or a disturbance caused by human footsteps. Further, FIG. 8C shows a large change in the flow rate or a change in the PSD average value signal when there is a disturbance due to the moving body. The change in the signal due to these disturbances is extremely large as compared with the target signal due to water leakage, which is the monitoring target. If signal processing is performed without removing such a disturbance, the reliability of the target signal will be significantly degraded. Therefore, it is necessary to remove the disturbance.

Returning to FIG. 2, the description of the terminal 10 will be continued. In the actual operation, the terminals 10 dispersedly installed in the above-mentioned installation places are required to be able to continue regular observation for about 5 years by supplying power from the battery unit 13. That is, the terminal 10 needs to operate with only the battery for a long period of about 5 years. Therefore, it is necessary for the communication unit (communication unit 9 and communication network 11) to employ a system of low power consumption and a system capable of transmitting data in a water distribution area covering several kilometers. As a communication network having such a reach distance, there is a low power wireless communication network (LPWA; Low Power, Wide Area). As one of the LPWA communication services, the LoRaWAN standard is listed as a promising future service candidate.

In order to enable continuous use for a long period of time, the terminal 10 saves power in the battery unit 13 by saving power. That is, the terminal 10 has a plurality of operation modes, i.e., a sleep mode and one or more normal operation modes, as a power saving operation, and operates by switching those operation modes. This control is executed by the terminal side signal processing unit 12.

The normal operation mode is an operation mode for detecting water leakage or evaluating an installation environment, and is a mode in which a relatively large amount of power is consumed. On the contrary, the sleep mode is an operation mode that consumes almost no power by lowering the clock frequency of digital processing. Most of the time zones other than the time designated by the operation schedule are set to the sleep mode, which enables continuous use for a long time.

The center-side device 20 monitors the piping state of the water distribution area while communicating with a plurality of main terminals 10 via the communication network 11. The transmission/reception unit 21 transmits data such as setting parameters of the terminal 10 as transmission data, and receives the vibration data transmitted by the terminal 10. Although the transmission data of the terminal 10 includes time information, the processing unit for improving the accuracy of time synchronization is the time synchronization unit 23.

The processing result of the center-side signal processing unit 22 is displayed on the display device 24 so as to be superimposed on the pipeline diagram of the water pipe read from the pipeline network database 25. The display device 24 is a color image display device, and when a water leak is detected on a pipe, the occurrence of the water leak is displayed at a position on the corresponding pipe by a prominent color such as red, blinking, or a pattern. Next, a configuration example of the sensor signal processing unit 2 included in the terminal side processing unit 12 will be described with reference to FIG.

FIG. 9 is a block diagram showing the configuration of the sensor signal processing unit 2 shown in FIG. As shown in FIG. 9, the sensor signal processing unit 2 includes a data input unit 51, a spectrum analysis unit (PSD) 52, a learning unit 53, a logarithmic likelihood calculation unit 54, a setting parameter input unit 55, a threshold value comparison unit 56, and It is composed of a leakage determination output unit 57.

The vibration data acquired by the sensor 1 is input from the data input unit 51, and the PSD 52 performs frequency analysis. Power Spectrum Density (PSD) is one method of frequency analysis and analyzes the signal strength distribution for each frequency. Further, the PSD 52 performs a time smoothing process and outputs a plurality of numerical values for each constant frequency band as a feature amount. The power spectrum output from the PSD 52 is input to the learning unit 53.

The learning unit 53 executes the above power spectrum in model-based learning or machine learning. The power spectrum data in the normal state is learned by a learning model such as a GMM model (Gaussian Mixture Model). If the learning at the time of water leakage can be performed, the model parameter at the time of the abnormality may be learned and used. The learning result is converted into data as a model parameter (feature amount) and held in the learning unit 53.

If necessary, the model parameters described above may be transmitted to the center-side device 20, added to the information in the pipeline network database of the center-side device 20, and managed. If it is difficult to perform learning from the beginning for each installation location, it is conceivable to initially set the learning result (model parameter) acquired in an experimental facility in the learning unit 53.

The log-likelihood calculation unit 54 calculates a composite log-likelihood between power spectra between the power spectra sequentially input and the learned power spectra of the normal model. Based on this log-likelihood, the similarity (or distance) between the spectra is evaluated, and compared with a threshold value described later to determine whether the spectrum is normal or abnormal.

The threshold comparison unit 56 sequentially compares the calculation result of the log-likelihood calculation unit 54 and the threshold value input from the setting parameter input unit 55, and a determination signal indicating an estimation result of whether or not water leakage has occurred, that is, Output the result of water leakage judgment. The signal (comparison result) is output from the leakage determination output unit 57. Next, a configuration example of the installation environment evaluation processing unit 3 is shown in FIG.

FIG. 10 is a block diagram showing the configuration of the installation environment evaluation processing unit 3 shown in FIG. As shown in FIG. 10, the installation environment evaluation processing unit 3 includes a data input unit 61, a PSD 62, feature amount calculation units 63, 64, 65, and an output unit 66. The vibration data acquired by the sensor 1 is input from the data input unit 61 and frequency-analyzed by the PSD 62.

The PSD 62 uses operating parameters (frequency range, section length) corresponding to the installation environment evaluation. As an example, the operation parameter is set such that the time resolution is made finer, instead of making the frequency resolution coarser. The spectrum data output by the PSD 62 is input to the feature amount calculation units 63, 64, 65, and the respective feature amount data is output from the output units 66, 67, 68.

In the example of FIG. 10, the feature amount calculation unit is configured with three pieces, but the number may be added as long as it is the feature amount for evaluating the installation environment. As an example of the feature amount calculated here, the following feature amount can be adopted. The feature amount calculation unit 63 outputs the amount obtained by temporally smoothing the frequency average value of the power spectrum as a feature amount. The feature amount calculation unit 64 outputs the temporal variation width of the integrated value of the power spectrum as a feature amount. The feature amount calculation unit 65 outputs the temporal increase gradient of the integrated value of the power spectrum as a feature amount. Next, FIG. 11 shows a configuration example of the learning unit 7.

FIG. 11 is a block diagram showing the configuration of the learning unit 7 shown in FIG. As shown in FIG. 11, the learning unit 7 includes an input unit 71, a daily activity amount calculation unit 72, a weekly activity amount calculation unit 73, a monthly activity amount calculation unit 74, a model parameter calculation unit 75, a schedule generation unit 76, The operation parameter calculation unit 77, the output units 78 and 79, the learning result storage unit 38, and the input/output unit 39 are included. As shown in FIG. 1, the learning unit 7 inputs the evaluation amount calculated by the installation environment evaluation processing unit 3 from the input unit 71, and outputs the schedule and the operation parameter from the output units 78 and 79.

The daily activity amount calculation unit 72 calculates “intraday activity amount” which is the feature amount of the learning model used by the learning unit 7 from the input evaluation amount, and holds data for a certain period. As an example of the daily activity amount, in addition to the average value and the variance value of the input evaluation value in the period set for one day, the difference amount between the maximum value and the minimum value with respect to the evaluation value is listed.

The weekly activity amount calculation unit 73 calculates the “weekly activity amount” and holds data for a certain period. An example of the weekly activity amount is the average value of the input evaluation values for the period of one week, the variance value, and the difference amount between the maximum value and the minimum value. The monthly activity amount calculation unit 74 calculates the “monthly activity amount” and holds data for a certain period. An example of the monthly activity amount is the average value of the input evaluation values for the period of one month, the variance value, and the difference amount between the maximum value and the minimum value.

In FIG. 11, the learning result storage unit 38 stores the above model parameters and outputs them from the input/output unit 39. The input/output unit 39 transfers data to the center side device 20 via the communication unit 9. The learning result is transferred to the center side device 20 in response to a request from the center side device 20. It is also possible to request the center side device 20 to rewrite the learning result. That is, the model parameter to be rewritten as the learning result is data-transferred from the input/output unit 39 via the communication unit 9.

In that case, the model parameter calculation unit 75 reads the stored data from the learning result storage unit 38 and corrects the model parameters held inside. As described above, the case where the existing model parameters are forcibly applied to the model parameter calculation unit 75 can be considered as the above-described case where the learning result from the center side device 20 is rewritten. By doing so, the effect of converging and stabilizing the learning result early can be expected. Next, FIG. 12 shows another configuration example of the learning unit 7.

FIG. 12 is a block diagram showing a modification of the learning unit 7 shown in FIG. Note that, in the learning unit 7a in FIG. 12, the same components as those in the learning unit 7 illustrated in FIG. That is, the daily activity amount calculation unit 72, the weekly activity amount calculation unit 73, and the monthly activity amount calculation unit 74 in the learning unit 7a in FIG. 12 are common to the learning unit 7 in FIG. Calculate daily activity, weekly activity, and monthly activity. The learning unit 7a in FIG. 12 includes an input unit 81, a model parameter calculation unit 82, learning result storage units 83, 84 and 85, a switching unit 86, output units 87 and 88, and an input/output unit 89. The learning unit 7 a inputs the evaluation amount calculated by the installation environment evaluation processing unit 3 from the input unit 81.

The daily activity amount calculation unit 72 holds the data of the daily activity amount, which will be described later with reference to FIG. 13A, for a certain period of time and outputs it in response to a request from the processing unit of the next stage. Similarly, the weekly activity amount calculation unit 73 and the monthly activity amount calculation unit 74 also hold the corresponding activity amount data for a certain period of time and output it in response to a request from the processing unit in the next stage. The model parameter calculation unit 82 receives the above-mentioned daily activity amount data, weekly activity amount data, and monthly activity amount data, and calculates a model parameter to be applied to the reference model. Similarly, model parameters are calculated for each of the daily activity data, the weekly activity data, and the monthly activity data.

One of the criteria for selecting model parameters is a parameter that minimizes the difference between the activity values predicted from the model parameters for the input of each activity amount for a certain period. The schedule generation unit 76 and the operation parameter calculation unit 77 generate schedule data and operation parameters using the model parameters as input.

The learning result storage units 83, 84, 85 store different learning results, and the model parameter calculation unit 82 controls the switching unit 86 to select one from the three learning result storage units and store the stored learning results. The result is read and used for calculation of model parameters. In this configuration example of the learning unit, different learning results are stored in advance in the learning result storage units 83, 84, 85, and any one of them can be selected to accelerate the convergence of the learning result data. Even if the learning process is not accumulated from the beginning over a long period of time, the learning process is speeded up by selecting and giving a candidate expected to be suitable for the terminal 10 at that point, from among several candidates for the learning result. be able to.

The above-mentioned learning result can be selected in the initial setting of the operation start, or any learning result can be selected by a command from the center side device 20. In the case of a command from the center side device 20, the command from the center side device 20 and the above selection information are input from the input/output unit 89, and the model parameter calculation unit 82 reads out the learning result based on the contents. To do.

The contents of the data stored in the learning result storage units 83, 84, 85 are written in the initial settings, and if necessary, the contents are rewritten based on a command from the center side device 20. In this case, the input/output unit 89 inputs the command from the center-side device 20, the selection information, and the data content to be rewritten, and the model parameter calculation unit 82 writes the learning result based on the content. ..

An example of the simplest setting method for the daily measurement schedule is to set the time when the daily activity amount is the minimum. In the example of FIG. 13A, a schedule candidate is around 3:00. By estimating the minimum time from the model parameters, it is possible to specify the time when no sample is acquired in the evaluation stage (estimated by complementing the data). The same setting method can be applied to the weekly measurement schedule and the monthly measurement schedule.

The data related to the schedule generated by the schedule generation unit 76 is output from the output unit 87, becomes the measurement schedule (data) 5 shown in FIG. 1, and is input to the sensor signal processing unit 2. The measurement schedule (storage unit) 5 in FIG. 1 is a buffer unit for schedule data. The operation parameter calculation unit 77 receives the model parameters described above as input, generates operation parameters, outputs them from the output unit 88, and inputs them to the sensor signal processing unit 2 described above. The sensor signal processing unit 2 operates by changing the operation parameter of signal processing according to the input operation parameter. The operation parameter (storage unit) 6 in FIG. 1 is a buffer unit for the operation parameter.

The operation parameter calculates a plurality of combinations according to the time of the schedule, and holds them in the measurement schedule (storage unit) 5. Corresponding data is held for the parameter corresponding to the time at which the measurement is performed on the schedule not only at the time when the disturbance is small but also at the time when the disturbance is large.

FIG. 13 is a graph for explaining the modeling of the activity amount. FIG. 13(a) shows the daily activity amount, FIG. 13(b) shows the weekly activity amount, and FIG. 13(c) shows the monthly activity amount. Shown respectively. These activity amounts are as described above, and each graph in FIG. 13 shows a schematic change for one data type (for example, average value). Next, another example of the processing contents of the sensor signal processing unit 2 shown in FIG. 1 will be described with reference to FIG.

FIG. 14 is a flowchart showing a process in the sensor signal processing unit 2 shown in FIG. 1 in which the control unit in FIG. 1 partially discards the measurement data when the disturbance during measurement is large. The processing flow of FIG. 14 is the processing content that the control unit 4 controls and executes each unit, and first, the processing is started in step S21. Next, in step S22, the sensor signal processing unit 2 executes measurement signal processing.

Next, in step S23, the installation environment evaluation processing unit 3 outputs the evaluation value. The installation environment evaluation processing unit 3 and the sensor signal processing unit 2 have different sampling rates and time intervals for data output. The installation environment evaluation processing unit 3 is set to have a short data output time interval in order to set a relatively high time resolution. When this time interval is called a frame, one frame of the sensor signal processing unit 2 corresponds to a plurality of frames of the installation environment evaluation processing unit 3. Each processing unit outputs data for each frame.

At this time, the timing determined by the data output (evaluation value) of the installation environment evaluation processing unit 3 and being largely affected by the disturbance is processed by the threshold value shown in the example of the processing content of the sensor signal processing unit 2 described above. It can be carried out in the same manner as.

Next, in the frame division step S24, the data output frame of the installation environment evaluation processing unit 3 and the data output frame of the sensor signal processing unit 2 are associated with each other. One frame of data output of the sensor signal processing unit 2 is associated with a plurality of frames of data output of the installation environment evaluation processing unit 3 to generate a combination of data.

Next, in a determination step S25, for the combination of the data output of the sensor signal processing unit 2 and the data output of the installation environment evaluation processing unit 3 described above, the evaluation value of the data output of the installation environment evaluation processing unit 3 is subjected to the threshold value determination, and the disturbance. Determine the effect of. If even one of the plurality of evaluation values exceeds the threshold value for one combination data, it is determined that the combination data is data that is greatly affected by the disturbance, and the condition is “NO in S25”. When all the plurality of evaluation values of one combination data do not exceed the threshold value, the condition is “YES in S25”.

For the combination data having the condition “YES in S25”, it is determined that there is no influence of disturbance, and the process proceeds to step S26. In step S26, one frame of the output data of the corresponding sensor signal processing is stored in the data buffer in the communication unit 9. Next, in step S28, the communication unit 9 transfers the stored data for each frame.

Regarding the combination data which is the condition “NO in S25”, the influence of the disturbance is large, and the process proceeds to step S27. In step S27, one frame of the output data of the corresponding sensor signal processing is discarded. At this time, the communication unit 9 can detect that one frame of data has been discarded by measuring the amount of data in the data buffer, and indicates that the frame data has been discarded as an alternative to the discarded data. You may make it transmit data.

Next, step S29 is an end determination process for determining whether the process has been completed for one measurement schedule. If the measurement is ongoing, the condition is "NO in S29", and if the measurement is complete, the condition is "YES in S29". In the case of the condition “NO in S29”, the process flow transits to steps S22 and S23. In the case of the condition “YES in S29”, the process proceeds to step S30, and the series of processes ends. Next, FIG. 15 exemplifies a processing flow relating to installation failure of the terminal 10.

FIG. 15 is a flow chart showing a process of judging installation failure of the terminal 10 shown in FIGS. 1 to 4 from the evaluation result of the installation environment evaluation processing unit 3 of FIG. According to this process, the installation failure of the terminal 10 can be detected. In addition, in this process, the system operation of the terminal 10 is normal, but the installation environment evaluation processing unit 3 determines whether the installation state of the sensor is in the initial stage of installation, in the middle of operation, or at which time the defect occurs. It can be judged from the evaluation result.

As shown in FIG. 15, first, the process starts from step S41. Next, in step S42, the statistical amount of the output data of the installation environment evaluation processing unit 3 is calculated. The statistic used here is the average value, minimum value, maximum value, median value, variance value, sample value of autocorrelation function, covariance between evaluation values, and sample value of cross-correlation function for multiple evaluation values. To be That is, a method of setting an expected value range or an effective value range for each statistic and monitoring deviation from the range is used.

Next, in step S43, the above-mentioned expected value of the statistic and the actual statistic are compared, that is, the difference is calculated. Next, in step S44, the magnitude of the above-mentioned difference value is evaluated to determine the presence or absence of installation failure. Here, when it is determined that the installation is defective, the condition is “YES in S44”. If it is determined that the installation is not defective, the condition is “NO in S44”. Next, if the conditional branch in step S44 is "YES in S44", a warning signal is transmitted from the communication unit 9 to the center side device 20 in step S45, and a series of processes is completed in step S46. Further, another processing flow of the terminal 10 is illustrated in FIG.

FIG. 16 is a flowchart showing a process in which the control unit of FIG. 1 inspects the trigger state. The process flow of FIG. 16 corresponds to the process of detecting the input of the external trigger and executing the measurement. As an input to the control unit 4 in FIG. 1, it is assumed that an external trigger (not shown) is input.

First, the process is started in step S51, and the sensor signal processing unit 2 is transited to the measurement mode standby state in the next step S52. Next, in step S53, the control unit executes a process of checking the trigger state. In step S54, the presence/absence of a trigger input is determined. If it is determined that there is an input, the condition is "YES in S54", and if it is not input, the condition is "NO in S54". In the case of the condition “YES in S54”, the process proceeds to step S55, and the sensor signal processing unit 2 executes the measurement. After the completion of this measurement process, a series of processes is ended in step S56. Further, another processing flow of the terminal 10 is illustrated in FIG.

FIG. 17 is a flowchart showing a process of uploading the measurement schedule obtained from the evaluation result acquired by the installation environment evaluation processing unit 3 of FIG. According to the processing procedure of FIG. 17, the center side device 20 collects the uploaded schedule data and stores and manages the measurement schedule of the terminal 10.

In the process flow of FIG. 17, first, the process starts from step S61, and in the next step S62, the sensor signal processing unit transits to the measurement mode standby state. Next, in step S63, the inspection of the measurement schedule is executed. The inspection here is confirmation of changes to the previous measurement schedule. If the measurement schedule is the default setting, or if the center-side device 20 has already been notified, no change is made.

In step S64, a determination process is performed on the change from the measurement schedule, and if there is a change, the condition is "YES". If it is determined in the above determination process that there is no change, the condition is "NO in S64". A step S65 performs a process of transmitting the measurement schedule when the condition "YES in S64". The schedule data stored in the measurement schedule (storage unit) 5 is transferred from the communication unit 9 to the center side device 20 under the control of the control unit 4. When the condition is "NO in S64", there is no change in the measurement schedule, so the schedule data is not transmitted.

After the data transmission is completed in step S65, or when the schedule data is not transmitted, the process proceeds to step S66 to complete the series of processes. Further, another processing flow of the terminal 10 is illustrated in FIG.

FIG. 18 is a flowchart showing a process of uploading the evaluation result acquired by the installation environment evaluation processing unit of FIG. 1 to the center side device 20 of FIG. 2 as a learning result. As shown in FIG. 18, the center-side device 20 collects the uploaded learning result data, and stores and manages the learning result of the terminal 10. Some of the learning results stored here are used as preset data for learning data of the terminal 10 at the same installation location or another installation location. In this processing flow, the processing is started from step S71, and the installation environment evaluation processing unit 3 is transited to the standby state of the environment adjustment mode in step S72.

Next, in step S73, the learning result is inspected. The inspection here is confirmation of a change in the previous learning result. If the learning result is preset data, or if the data has already been transmitted to the center side device 20, there is no change. Next, in step S74, a determination process is performed on the change in the learning result, and if there is a change, the condition "YES in S74" is set. If it is determined in the above determination process that there is no change, the condition is "NO in S74".

A step S75 carries out a process of transmitting data relating to the learning result when the condition “YES in S74”. The data of the learning result stored in the learning unit 7 is transferred from the communication unit 9 to the center side device 20 under the control of the control unit 4. When the condition is “NO in S74”, there is no change in the learning result, so the learning result data is not transmitted. After the data transmission is completed in step S75, or when the learning result data is not transmitted, the process proceeds to step S76 to complete the series of processes. Furthermore, another processing flow of the terminal 10 is illustrated in FIG.

FIG. 19 is a flowchart showing a process of resetting the measurement schedule stored and managed by the center-side device 20 after downloading to the terminal 10 shown in FIGS. 1 to 4 by the process of FIG. When adjusting the measurement schedule between the terminals 10, the center-side device 20 downloads the measurement schedule to each terminal 10 to instruct the change. In this processing flow, the processing is started from step S81 first, and the sensor signal processing unit 2 is transited to the measurement mode standby state in the next step S82.

Next, in step S83, with respect to the data received by the communication unit 9, the request content from the center side device 20 is inspected. In step S84, if the received data is a request from the center-side device 20 and a measurement schedule download request or a measurement schedule reset, the condition "YES in S84" is set, and the process proceeds to step S85. In step S85, a processing request from the center side device 20 is executed. If the request content of S83 is a measurement schedule download request, the control unit 4 controls the communication unit 9 to receive the measurement schedule data and write the schedule data to the measurement schedule 5 in Step S85. Execute.

When the request content in S83 is reset of the measurement schedule, the control unit 4 causes the measurement schedule 5 to be reset in step S85. By this reset, the schedule data is rewritten to initial data or preset values.

According to the first embodiment, by automatically sensing the installation environment according to the installation position of the terminal 10, it is possible to operate using the optimum values of the measurement schedule and operation parameters of the terminal 10. As an effect, it is possible to automatically cope with a wide range of situations from a disturbed installation environment to a quiet installation environment. At this time, it is not necessary to manually change the individual settings of the terminal 10 according to the installation environment. Also, if a measurement schedule with less disturbance is set according to the installation environment, long-term continuous use becomes possible. Furthermore, the arrangement of the terminal 10 can be corrected by the function of detecting and notifying an inappropriate installation environment.

As described above, in the present system, each installed terminal that remotely installs a large number of sensor terminals in a wide range of pipes, based on the information acquired by the environment evaluation unit, sets an operation schedule and operation parameters. It automatically adapts to various installation environments and enables efficient observation even in environments where there are many disturbances. Therefore, the plurality of main terminals 10 configuring the present system can reduce power consumption required for observation to a necessary minimum. As a result, the terminal 10 can be continuously used for a long period of time. That is, this system is convenient for the user.

FIG. 20 is a block diagram showing the configuration of a terminal (this is called “main terminal 19”) used in the pipe state detection system (also called “main system”) according to the second embodiment of the present invention. The same components as those in the first embodiment are designated by the same reference numerals. The constituent elements unique to the second embodiment are the sensor signal processing unit 91 and the moving body determination unit 92.

The sensor output data is processed by the sensor signal processing unit 2 and the installation environment evaluation processing unit 3 in the same manner as in the first embodiment. It is a flow of processing in which the processing result of the installation environment evaluation processing unit 3 is processed by the learning unit 7 and the measurement schedule and operation parameters of the sensor signal processing unit 91 are calculated.

The moving body determination unit 92 added in the first embodiment processes the data output by the installation environment evaluation processing unit 3 in real time. With this, the disturbance evaluation amount is calculated. The disturbance evaluation amount is an evaluation index for determining whether or not the influence of vibration propagation from a moving body such as an automobile is included in the sensor signal. More details are as follows.

First, the moving body determination unit 92 outputs the evaluation index and sends it to the sensor signal processing unit 91. The sensor signal processing unit 91 thereby changes the processing content. An example of the content of the change in the process in the sensor signal processing unit 91 is a process of delaying the measurement based on the passing time zone of the moving body. Details of this processing will be described with reference to FIG.

21 is a graph for explaining the processing of the sensor signal processing unit of FIG. 20, FIG. 21(a) is the disturbance evaluation amount output by the moving body determination unit of FIG. 20, and FIG. 21(c) shows the measurement schedule signal, respectively. As shown in FIG. 21A, it is assumed that the disturbance evaluation amount output from the moving body determination unit 92 changes in a mountain shape due to the passage of the moving body, that is, the approach and separation thereof.

A constant threshold value Y1 is set for this disturbance evaluation amount, the threshold value Y1 is compared with the disturbance evaluation amount, and there are time zones X2 to X4 that are equal to or greater than the threshold value Y1. A timing signal that rises at timing X1 and falls at timing X5 is generated before and after the time zones X2 to X4 to obtain a rectangular wave signal (delay signal) as shown in X1 to X5 of FIG. .. These timings X1 to X5 can be adjusted in the front-rear direction depending on the setting of the threshold value Y1.

On the other hand, based on the measurement schedule, a measurement schedule signal indicating the start timing of the measurement schedule as shown in FIG. 21C is generated. This measurement schedule signal can be delayed using the delay signal of FIG. 21(b) to obtain a measurement start control signal as shown at timing X5 in FIG. 21(d). If the measurement processing of the sensor signal processing unit 91 is performed using the measurement start control signal obtained in this way and the data is transferred from the communication unit 9 using the processing result, the disturbance due to the moving body is mixed. The detection result excluding the timing can be obtained.

According to the second embodiment, as in the first embodiment, the installation environment is automatically sensed according to the installation position of the terminal 19, and the optimum values of the measurement schedule and operation parameters of the terminal 19 are determined. It can be used and operated, and it can detect a disturbance in real time and exclude it. As a result, long-term continuous use is possible, and it is possible to prevent deterioration of signal quality due to disturbance.

The main points of the present invention will be described below with reference to the claims.
[1] The present system (FIG. 2) includes a plurality of sensor terminals 10 attached to a pipe 28 (FIG. 3) to be monitored and transmitting a monitoring signal, a center side device 20 that receives the monitoring signal and is used for monitoring. Is a pipe state detection system configured by communicatively connecting to each other. The sensor terminal 10 used in the present system includes a sensor 1, a sensor signal processing unit 2, an installation environment evaluation processing unit 3, a learning unit 7, and a communication unit 9.

The sensor 1 outputs detection data including information regarding an abnormality caused by the deterioration state of the pipe 28. The sensor signal processing unit 2 processes the detection data and analyzes the deterioration state, and outputs the result as a target signal. The installation environment evaluation processing unit 3 processes the detection data and outputs a characteristic amount for evaluating the disturbance applied to the pipe. The learning unit 7 learns the terminal installation environment evaluated based on the feature amount. The communication unit 9 can communicate the target signal and the control information output from the sensor signal processing unit 2 with the center side device 20. Further, the learning unit 7 individually and optimally sets the measurement schedule 5 and the operation parameter 6 of the sensor signal processing unit 2 for each sensor terminal 10 based on the learning result according to the terminal installation environment.

According to the present system, the learning unit 7 optimally sets the measurement schedule 5 and the operation parameter 6 of the sensor signal processing unit 2 individually for each sensor terminal 10 based on the learning result that differs for each terminal installation environment. As a result, it is possible to automatically set an optimal operation without waste according to the installation environment of each sensor terminal 10.

[2] This system (FIG. 2) is preferably configured as follows. The sensor terminal 10 includes a battery unit 9 and is driven by a battery. The pipe 28 is a buried pipe 28 buried in the ground. The sensor 1 detects at least vibration or sound, converts it into an electric signal, and outputs detection data. The sensor signal processing unit 2 processes the detection data and generates a target signal indicating the degree of deterioration of the buried pipe 28. The installation environment evaluation processing unit 3 processes the detected data and generates a characteristic amount for evaluating a disturbance applied to the buried pipe as vibration or sound. The communication unit 9 can wirelessly communicate with the center-side device 20. The learning unit 7 sets the measurement schedule 5 and the operation parameter 6 to the necessary minimum operation to save power.

The sensor 28, which is equipped with a battery unit 9 and is driven by a battery, has a pipe 28 arranged in a buried pipe 28 buried in the ground. The sensor 1 detects at least vibration or sound from the buried pipe 28 that is buried and generates a target signal. The installation environment evaluation processing unit 3 generates a feature amount by using a disturbance signal that differs for each environment of the place where the buried pipe 28 is buried. The learning unit 7 learns with the feature amount generated according to the terminal installation environment. Based on the learning result, the measurement schedule 5 and the operation parameter 6 of the sensor signal processing unit 2 are optimally set individually for each sensor terminal 10 so as to avoid mixing of disturbance noise. Therefore, it is possible to maintain the reliability of the efficiently measured measurement data without discarding the measurement data whose quality has deteriorated or re-measurement at another timing instead of discarding it. As a result, the power consumption of the battery-operated sensor terminal 10 can be suppressed, so that it can be continuously used for a long period of time. Furthermore, since the communication unit 9 wirelessly communicates with the center-side device 20, it is easy to use.

[3] In this system, the pipe is the water pipe 28 (FIG. 3), and the deterioration state is water leakage (FIG. 8). According to this, inexpensive sensor terminals are always arranged in a wide range of multi-point water pipes, the occurrence of water leakage is detected by remote monitoring, and the leak point position can be estimated with high accuracy.
[4] In the present system, the sensor signal processing unit 2 excludes the data of the measurement period in which the disturbance signal is generated and outputs the target signal (FIGS. 8 and 21). According to this, the target signal can be obtained by excluding the data of the measurement period in which the high-level disturbance noise is mixed. Therefore, the reliability of the measurement data can be efficiently maintained.
[5] In the present system, the sensor signal processing unit 2 uses the measurement schedule signal X3 and the measurement start control signal based on the delay signals (X1 to X5 in FIG. 21B) generated based on the result of evaluating the disturbance signal. The timing of data acquisition is delayed (X5 in FIG. 21D), and the measurement period is delayed in the time zones X1 to X5 in which the disturbance is occurring (FIG. 21). According to this, the target signal can be obtained while avoiding the time zones X1 to X5 in which the disturbance is occurring. Therefore, the reliability of the measurement data can be efficiently maintained.
[6] The terminal 10 is used in any one of the above [1] to [5] for the tube state detection system. The technical characteristics of this terminal 10 are clear even if it is a single item.

[7] This method is a pipe state detection method used by the center side device 20 to receive the monitoring signals transmitted from the plurality of sensor terminals 10 attached to the pipe 28 to be monitored and used for monitoring. The sensor terminal 10 (FIGS. 1 and 2) is configured to include the sensor 1, the sensor signal processing unit 2, the installation environment evaluation processing unit 3, the learning unit 7, and the communication unit 9, and includes the control information. Work based.

The method has the following steps (Fig. 4). The step in which the sensor 1 outputs the detection data in which the abnormality caused by the deterioration state of the pipe 28 is detected, and the step in which the sensor signal processing unit 2 processes the detection data and analyzes the deterioration state as a target signal. And a step in which the installation environment evaluation processing unit 3 extracts and inputs the disturbance signal from the detection data and outputs a feature amount used for evaluation of the terminal installation environment in which the sensor 1 is installed, and the learning unit 7 causes the feature amount. Step S10 of learning the terminal installation environment evaluated based on the above, and the learning unit 7 generates the measurement schedule 5 and the operation parameter 6 of the sensor signal processing unit 2 in accordance with the learned terminal installation environment, and each sensor terminal 10 Steps S12 and S13 for individually setting the control signal to the center side device 20 in addition to the target signal output from the sensor signal processing unit 2 by the communication unit 9. According to this, the same operational effect as the above [1] can be obtained.

[8] The method is preferably carried out by the following procedure. That is, for a certain period (timer operation S3) from the time when the sensor terminal 10 is installed, the sensor environment 10 is operated according to a preset measurement schedule (S5), the installation environment evaluation processing unit 3 is operated (timer S2), and the learning unit 7 operates. After the corresponding learning result is obtained (learning amount determination S11), the measurement schedule 5 is executed, that is, the regular processing (S6) is performed. As a result, after the operation is started promptly, the optimum operation can be performed by using the appropriate learning result.

[9] In this method, a plurality of learning results 83, 84, 85 (FIG. 12) are held in the sensor terminal 10 in advance, and one of them is read during the initial operation when the sensor terminal 10 is installed. It is preferable that the learning unit 7 starts the learning (S10).
[10] In this method, the sensor signal processing unit 2 may receive a trigger signal from the outside (S53 of FIG. 16) and start the measurement (S55).
[11] In this method, the installation environment evaluation processing unit 3 may detect a defect in the installation state of the sensor terminal 10 (S44 in FIG. 15) and notify the center-side device 20.
[12] In this method, the operation parameter 6 corresponding to each measurement schedule 5 may be held, the operation parameter 6 corresponding to each measurement schedule 5 may be changed, and the measurement by the sensor signal processing unit 2 may be executed ( (S12, S13 in FIG. 4).

[13] In this method, the measurement schedule 5 may be uploaded to the center-side device 20 (S75 in FIG. 18).
[14] In this method, as the learning content of the learning unit 7, the evaluation data of the terminal installation environment may be uploaded to the center side device 20 (S75 in FIG. 18).
[15] In this method, the measurement schedule 5 may be downloaded from the center side device 20 or reset according to an instruction from the center side device 20 (S83 to S85 in FIG. 19). According to the above [8] to [15], it is possible to realize the tube state detection with good usability.

1 sensor, 2, 91 sensor signal processing unit, 3 installation environment evaluation processing unit, 4 control unit, 5 measurement schedule (storage unit), 6 operation parameters (storage unit), 7, 7a learning unit, 8 evaluation schedule, 9 ( (Wireless) communication unit, 10, 19 water leakage detection terminal (sensor terminal, main terminal), 11 communication network, 12 terminal side signal processing unit (terminal side processing unit), 13 battery unit, 20 center side device, 21 transmission/reception unit, 22 Center side signal processing unit, 23 time synchronizing unit, 24 display device, 25 pipeline network database, 26 manhole cover, 27 sluice valve, 28 water supply buried pipe (water distribution pipe, water distribution pipe, pipe), 29 ground, 31, 41 Number, 32 start date and time, 33 measurement item, 34,44 repetition flag, 35 set number, 36 data, 37 remark, 38 learning result storage section, 39 input/output section, 42 start and end date and time, 43 evaluation item, 51, 61 Data input unit, 52, 62 Spectrum analysis unit (PSD), 53 Learning unit, 54 Log likelihood calculation unit, 55 Setting parameter input unit, 56 Threshold value comparison unit, 57 Water leakage determination output unit, 63, 64, 65 Feature amount calculation Section, 66, 67, 68 output section, 71, 81, 89 input section, 72 daily activity amount calculation section, 73 weekly activity amount calculation section, 74 month activity amount calculation section, 75 model parameter calculation section, 76 schedule generation Section, 77 operation parameter calculation section, 78, 79 output section, 82 model parameter calculation section, 83, 84, 85 learning result storage section, 86 switching section, 87, 88 output section, 92 moving body determination section

Claims (15)

A pipe state detection system configured by communicatively connecting a plurality of sensor terminals attached to a pipe to be monitored and transmitting a monitor signal, and a center side device that receives the monitor signal and is used for monitoring. ,
The sensor terminal is
A sensor that outputs detection data including information about an abnormality caused by the deterioration state of the pipe,
A sensor signal processing unit that processes the detection data and outputs the result of analyzing the deterioration state as a target signal,
An installation environment evaluation processing unit that inputs the detection data and outputs a feature amount used for evaluation of a terminal installation environment in which the sensor is installed,
A learning unit that learns the terminal installation environment evaluated based on the feature amount,
A communication unit capable of communicating the target signal and control information output from the sensor signal processing unit with the center-side device;
Equipped with
The learning unit individually sets the measurement schedule and the operation parameter of the sensor signal processing unit for each sensor terminal based on the learning result according to the learned terminal installation environment.
Pipe condition detection system. The sensor terminal includes a battery section and is driven by a battery.
The pipe is a buried pipe buried in the ground,
The sensor detects at least vibration or sound and converts it into an electric signal to output the detection data,
The sensor signal processing unit processes the detection data to generate the target signal indicating the degree of deterioration of the buried pipe,
The installation environment evaluation processing unit processes the detection data to generate the characteristic amount for evaluating a disturbance applied to the buried pipe as vibration or sound,
The communication unit is capable of wireless communication with the center-side device,
The learning unit saves power by setting the measurement schedule and the operation parameter to a necessary minimum operation,
The pipe state detection system according to claim 1. The pipe is a water pipe,
The pipe state detection system according to claim 1, wherein the deterioration state is water leakage. The sensor signal processing unit outputs the target signal by excluding data of a measurement period in which disturbance has occurred, based on a feature amount used for evaluation of the terminal installation environment.
The pipe state detection system according to claim 1. The sensor signal processing unit delays the data acquisition timing by the measurement schedule signal and the measurement start control signal by the delay signal generated based on the feature amount used for the evaluation of the terminal installation environment, and the disturbance has occurred. Delay the measurement period in the time zone,
The pipe state detection system according to claim 1. The said sensor terminal used for the pipe state detection system in any one of Claims 1-5. A method for detecting a pipe condition, which is used for monitoring by receiving a monitoring signal transmitted from a plurality of sensor terminals attached to a pipe to be monitored by a center side device,
The sensor terminal includes a sensor, a sensor signal processing unit, an installation environment evaluation processing unit, a learning unit, and a communication unit, and operates based on control information.
A step in which the sensor outputs detection data including information regarding an abnormality caused by a deterioration state of the pipe;
A step in which the sensor signal processing unit processes the detection data and outputs a result of analyzing the deterioration state as a target signal;
The installation environment evaluation processing unit extracts and inputs a disturbance signal from the detection data, and outputs a feature amount used for evaluation of a terminal installation environment in which the sensor is installed,
A step in which the learning unit learns the terminal installation environment evaluated based on the characteristic amount;
A step in which the learning unit generates a measurement schedule and operation parameters of the sensor signal processing unit according to the learned terminal installation environment, and individually sets for each sensor terminal;
A step in which the communication unit communicates the control information in addition to the target signal output from the sensor signal processing unit to the center side device;
A method for detecting a tube state. After the sensor terminal is installed for a certain period of time, the measurement operation is performed according to the preset measurement schedule, the installation environment evaluation processing unit is operated, and the learning unit obtains a corresponding learning result, and then the measurement is performed. Run the schedule,
The pipe state detection method according to claim 7. A plurality of learning results are held in advance in the sensor terminal, one of them is read at the time of initial operation when the sensor terminal is installed, and the learning unit starts learning.
The pipe state detection method according to claim 7. The sensor signal processing unit receives a trigger signal from the outside and starts measurement,
The pipe state detection method according to claim 7. The installation environment evaluation processing unit detects a defect in the installation state of the sensor terminal and notifies the center side device,
The pipe state detection method according to claim 7. Holding the operation parameter corresponding to each measurement schedule, changing the operation parameter corresponding to each measurement schedule, and performing the measurement by the sensor signal processing unit,
The pipe state detection method according to claim 7. Upload the measurement schedule to the center side device,
The pipe state detection method according to claim 7. Uploading the evaluation data of the terminal installation environment to the center side device as the learning content of the learning unit,
The pipe state detection method according to claim 7. The measurement schedule is downloaded from the center side device or reset by an instruction from the center side device,
The pipe state detection method according to claim 7.

Images