JP7067895B2 - End pressure control support device, end pressure control support method and computer program - Google Patents

Description

Embodiments of the present invention relate to a terminal pressure control support device, a terminal pressure control support method, and a computer program.

As a control method of a water distribution system that supplies water to consumers, terminal pressure control that is effective for reducing extra power consumption of a water distribution pump, reducing the amount of water leakage, and the like is known. However, in order to control the end pressure, it is necessary to install a terminal pressure measuring device in the distribution pipe network, and to construct a simulation model (hereinafter referred to as "pipe network model") for performing pipe network analysis. Needs and costs a lot. Therefore, there is a demand for a technique that makes it possible to control the end pressure of a water distribution system at a lower cost.

Japanese Unexamined Patent Publication No. 2001-188614 Japanese Patent No. 3851783 Japanese Patent No. 501504

An object to be solved by the present invention is to provide an end pressure control support device, an end pressure control support method, and a computer program that enable end pressure control of a water distribution system to be realized at a lower cost.

The terminal pressure control support device of the embodiment has a terminal pressure learning unit and an terminal pressure estimation unit. The terminal pressure learning unit learns the relationship between the terminal pressure of the distribution pipe network and various quantities related to water distribution through the distribution pipe network by using a machine learning method. The terminal pressure estimation unit estimates the terminal pressure of the water distribution pipe network based on the relationship learned by the terminal pressure learning unit and the information indicating the various quantities.

The figure which shows the specific example of the system configuration of the water distribution system 100 in 1st Embodiment. The block diagram which shows the specific example of the functional structure of the terminal pressure control support device 1 of 1st Embodiment. The flowchart which shows the operation example of the terminal pressure control support apparatus 1 of 1st Embodiment. The figure which shows the specific example of the system configuration of the water distribution system 100a in 2nd Embodiment. The block diagram which shows the specific example of the functional structure of the terminal pressure control support apparatus 1a of 2nd Embodiment. The flowchart which shows the operation example of the terminal pressure control support apparatus 1a of 2nd Embodiment. The block diagram which shows the specific example of the functional structure of the terminal pressure control support device 1b of 3rd Embodiment. The flowchart which shows the operation example of the terminal pressure control support apparatus 1b of 3rd Embodiment. The figure which shows the specific example of the system configuration of the water distribution system 100c in 4th Embodiment. The block diagram which shows the specific example of the functional structure of the terminal pressure control support device 1c of 4th Embodiment. The flowchart which shows the operation example of the terminal pressure control support apparatus 1c of 4th Embodiment. The block diagram which shows the specific example of the functional structure of the terminal pressure control support device 1d of 5th Embodiment. The flowchart which shows the operation example of the terminal pressure control support apparatus 1d of 5th Embodiment.

Hereinafter, the terminal pressure control support device, the terminal pressure control support method, and the computer program of the embodiment will be described with reference to the drawings.

(First Embodiment)
FIG. 1 is a diagram showing a specific example of the system configuration of the water distribution system 100 according to the first embodiment. The water distribution system 100 includes a terminal pressure control support device 1, a monitoring control system 2, one or more water distribution stations 3, and one or more terminal pressure measuring devices 4, and one or more consumers 6 water via the water distribution pipe network 5. It is a system that supplies to. FIG. 1 shows distribution stations 3-1 and 3-2 as examples of one or more distribution stations, and terminal pressure measuring devices 4-1 and 4-2 as examples of one or more terminal pressure measuring devices 4. As an example of the above consumer 6, consumers 6-1 to 6-3 are shown. The number of the distribution station 3, the terminal pressure measuring device 4, and the consumer 6 may be different from the example of FIG. Each of the terminal pressure control support device 1, the monitoring control system 2, each water distribution station 3, and each terminal pressure measuring device 4 is configured to be communicable with each other.

The terminal pressure control support device 1 provides information (hereinafter referred to as “support information”) for supporting the control or monitoring of the monitoring control system 2 that monitors or controls the water distribution station 3. Specifically, the terminal pressure control support device 1 acquires terminal pressure information indicating the measured value of the terminal pressure of the water distribution pipe network 5 from each terminal pressure measuring device 4, and distributes water via the water distribution pipe network 5. Information indicating various quantities is acquired, and support information is generated based on the acquired terminal pressure information and the information indicating the above-mentioned quantities. More specifically, the terminal pressure control support device 1 acquires water distribution station information indicating various quantities related to each distribution station (hereinafter referred to as "distribution station various quantities") from each distribution station 3, and the acquired terminal pressure information. And support information is generated based on the water distribution station information. For example, the support information includes an estimate of the end pressure at each end of the water distribution network 5. Further, the support information may include information generated based on the estimated value of the terminal pressure, a determination result based on the estimated value of the terminal pressure, and the like.

The monitoring control system 2 is a system that monitors or controls the water distribution station 3 using the support information provided by the terminal pressure control support device 1. For example, the monitoring control system 2 adjusts the number of operating distribution pumps and the output intensity at each distribution station 3, monitors the water level of the distribution reservoir which is the water supply source, and the like.

The distribution station 3 has various facilities (not shown) such as a distribution reservoir for storing water to be supplied to the consumer 6 and a distribution pump for sending the water from the distribution reservoir to the distribution pipeline network 5, and distributes the water in the distribution reservoir. It is a facility that supplies each customer 6 via a water pipe network 5. Various facilities included in the water distribution station 3 are monitored or controlled by the monitoring control system 2. Further, the water distribution station 3 transmits the water distribution field information indicating the various amounts (various amounts of the water distribution field) that can be observed in its own facility to the terminal pressure control support device 1.

Generally, it is considered that the terminal pressure of the water distribution pipe network 5 has a high correlation with the discharge flow rate or the discharge pressure of the pump in the water distribution field 3. Therefore, the water distribution station information includes at least information indicating the discharge flow rate or the discharge pressure of the pump. Further, since it is considered that the terminal pressure of the distribution pipe network 5 also correlates with the water level of the distribution reservoir in the distribution station 3, the distribution station information may include information indicating the water level of the distribution reservoir.

The terminal pressure measuring device 4 is a device that measures the terminal pressure of the water distribution pipe network 5. The end pressure measuring device 4 transmits the end pressure information indicating the measured end pressure to the end pressure control support device 1.

FIG. 2 is a block diagram showing a specific example of the functional configuration of the terminal pressure control support device 1 of the first embodiment. The terminal pressure control support device 1 includes a CPU (Central Processing Unit), a memory, an auxiliary storage device, and the like connected by a bus, and executes a program. The end pressure control support device 1 includes a water distribution field information storage unit 101, an end pressure information storage unit 102, an information acquisition unit 103, an end pressure learning unit 104, an end pressure estimation unit 105, and an output unit 106 by executing a program. Function. All or part of each function of the terminal pressure control support device 1 is realized by using hardware such as ASIC (Application Specific Integrated Circuit), PLD (Programmable Logic Device), and FPGA (Field Programmable Gate Array). May be good. The program may be recorded on a computer-readable recording medium. The computer-readable recording medium is, for example, a flexible disk, a magneto-optical disk, a portable medium such as a ROM or a CD-ROM, or a storage device such as a hard disk built in a computer system. The program may be transmitted over a telecommunication line.

The water distribution station information storage unit 101 and the terminal pressure information storage unit 102 are configured by using a storage device such as a magnetic hard disk device or a semiconductor storage device. The water distribution station information storage unit 101 stores water distribution station information, and the terminal pressure information storage unit 102 stores terminal pressure information.

The information acquisition unit 103 is configured to include a communication interface, and communicates with each water distribution station 3 and each terminal pressure measuring device 4 via the communication interface. The information acquisition unit 103 acquires water distribution station information from each water distribution station 3, and stores the acquired water distribution station information in the water distribution station information storage unit 101. Further, the information acquisition unit 103 acquires end pressure information from each end pressure measuring device 4, and stores the acquired end pressure information in the end pressure information storage unit 102. The information acquisition unit 103 repeatedly acquires the water distribution station information and the terminal pressure information at a predetermined timing, and accumulates the water distribution site information and the terminal pressure information in the water distribution station information storage unit 101 and the terminal pressure information storage unit 102. ..

The terminal pressure learning unit 104 performs machine learning processing using the water distribution field information stored in the water distribution station information storage unit 101 and the terminal pressure information stored in the terminal pressure information storage unit 102 as teacher data. A machine learning technique for generating or updating a classifier by supervised learning is applied to the terminal pressure learning unit 104. The terminal pressure learning unit 104 learns the relationship between the various quantities of the water distribution station and the terminal pressure of the distribution pipe network 5 by performing machine learning processing based on the teacher data. More specifically, the terminal pressure learning unit 104 generates or updates a discriminator showing the relationship between the water distribution field quantities and the terminal pressure of the distribution pipe network 5. The terminal pressure learning unit 104 outputs data such as parameters representing the generated or updated classifier to the terminal pressure estimation unit 105 as a learning result. Hereinafter, learning of the above relationship is referred to as "learning of terminal pressure" as necessary.

The terminal pressure estimation unit 105 estimates the terminal pressure corresponding to the given water distribution field amount based on the relationship between the water distribution field amount learned by the terminal pressure learning unit 104 and the terminal pressure of the water distribution pipe network 5. do. The terminal pressure estimation unit 105 outputs the estimated terminal pressure information indicating the terminal pressure obtained by the estimation to the output unit 106. The terminal pressure estimation unit 105 can estimate the terminal pressure at the end where the terminal pressure learning unit 104 has learned the terminal pressure.

The output unit 106 includes a communication interface and communicates with the monitoring control system 2 via the communication interface. The output unit 106 generates support information based on the estimated end pressure information output from the end pressure estimation unit 105, and transmits the generated support information to the monitoring control system 2.

FIG. 3 is a flowchart showing an operation example of the terminal pressure control support device 1 of the first embodiment. First, the information acquisition unit 103 acquires water distribution site information from each water distribution station 3 and acquires terminal pressure information from each terminal pressure measuring device 4 (step S101). The information acquisition unit 103 stores the acquired water distribution station information in the water distribution station information storage unit 101, and stores the acquired terminal pressure information in the terminal pressure information storage unit 102. By repeatedly executing the acquisition of such information, the terminal pressure control support device 1 accumulates the water distribution site information and the terminal pressure information (step S102).

Subsequently, the terminal pressure learning unit 104 determines the amount of water distribution station and the water distribution pipe based on the water distribution field information stored in the water distribution station information storage unit 101 and the terminal pressure information stored in the terminal pressure information storage unit 102. Learn the relationship with the terminal pressure of the net 5. That is, the terminal pressure learning unit 104 learns the terminal pressure of a certain end based on the past terminal pressure information of the end and the past water distribution field information (step S103). The terminal pressure learning unit 104 outputs the learning result to the terminal pressure estimation unit 105.

Subsequently, the information acquisition unit 103 acquires the current distribution station information from each distribution station 3 (step S104). The terminal pressure estimation unit 105 estimates the current terminal pressure of the water distribution pipe network 5 based on the learning result by the terminal pressure learning unit 104 and the acquired current water distribution field information (step S105). The terminal pressure learning unit 104 outputs the estimated terminal pressure information obtained by estimation to the output unit 106. The output unit 106 generates support information based on the estimated terminal pressure information, and transmits the generated support information to the monitoring control system 2 (step S106).

The terminal pressure control support device 1 of the first embodiment configured in this way is applied to, for example, a water distribution system in which a terminal pressure measuring device is not permanently installed. Specifically, in the water distribution system 100 shown in FIG. 1, the terminal pressure measuring device 4 is temporarily present. In this case, the terminal pressure control support device 1 learns the relationship between the water distribution field quantities and the terminal pressure based on the terminal pressure information and the water distribution station information acquired during the period in which the terminal pressure measuring device 4 exists. After the end pressure measuring device 4 is removed, the end pressure is estimated based on the learning result and the water distribution station information. That is, the terminal pressure control support device 1 learns the relationship between the amount of water distribution field and the terminal pressure based on the past terminal pressure information and the past water distribution station information, and obtains the learning result and the current water distribution field information. Estimate the current terminal pressure based on.

According to the terminal pressure control support device 1 as described above, the water distribution system 100 can perform terminal pressure control without requiring the permanent installation of the terminal pressure measuring device 4. For example, the terminal pressure measuring device 4 is temporarily installed only during the design stage or adjustment period of the water distribution system 100 to learn in advance the relationship between the amount of water distribution field and the terminal pressure, and the terminal pressure is used during actual operation. It is possible to estimate the terminal pressure without arranging the measuring device 4. Therefore, by applying the terminal pressure control support device 1 of the first embodiment, it becomes possible to realize the terminal pressure control of the water distribution system 100 at a lower cost.

Specifically, it is possible to estimate the terminal pressure of the distribution pipe network 5 without the need to construct a pipe network model. Further, it is possible to estimate the terminal pressure of the water distribution pipe network 5 without permanently installing the terminal pressure measuring device 4 in the water distribution system 100. Further, the terminal pressure control support device 1 can learn and estimate the terminal pressure at any end of the water distribution pipe network 5 if it is possible to acquire the past terminal pressure information. Therefore, it is possible to control the terminal pressure of the water distribution pipe network 5 more accurately. This makes it possible to reduce the excess terminal pressure in the water distribution pipe network 5. Further, by reducing the excess terminal pressure, it is possible to reduce the amount of water leakage in the water distribution pipe network 5.

Any machine learning method may be used for learning the terminal pressure in the present embodiment. For example, a method such as SVM (Support Vector Machine) or DL (Deep Learning) may be used. However, it was confirmed by experiments that machine learning using a random forest is effective (that is, the estimation accuracy is high) for estimating the terminal pressure of the distribution pipe network. Therefore, the terminal pressure control support device of this embodiment and the following embodiments assumes a case where the terminal pressure is estimated by machine learning based on a random forest.

(Second embodiment)
FIG. 4 is a diagram showing a specific example of the system configuration of the water distribution system 100a according to the second embodiment. The water distribution system 100a is different from the water distribution system 100 in the first embodiment in that the terminal pressure control support device 1a is provided in place of the terminal pressure control support device 1. Other configurations of the water distribution system 100a are the same as those of the water distribution system 100 in the first embodiment. Therefore, the description of other configurations will be omitted by adding the same reference numerals as those in FIG.

FIG. 5 is a block diagram showing a specific example of the functional configuration of the terminal pressure control support device 1a according to the second embodiment. The end pressure control support device 1a further includes a permanent end pressure measuring device 107 (an example of a measuring unit), a point including a terminal pressure learning unit 104a instead of the end pressure learning unit 104, and a point instead of the end pressure estimation unit 105. It differs from the terminal pressure control support device 1 of the first embodiment in that the terminal pressure estimation unit 105a is provided. Other configurations of the terminal pressure control support device 1a are the same as those of the terminal pressure control support device 1 of the first embodiment. Therefore, the description of other configurations will be omitted by adding the same reference numerals as those in FIG.

The permanent end pressure measuring device 107 is a terminal pressure measuring device permanently installed at a specific end (hereinafter referred to as “permanent point”) of the water distribution pipe network 5. In the first embodiment, the terminal pressure measuring device 4 is installed to acquire the terminal pressure information used for learning the relationship between the water distribution field quantities and the terminal pressure, whereas the permanent terminal pressure measuring device 107 is installed. Is installed to obtain end pressure information used for both learning and estimation of the end pressure described above. The permanent terminal pressure measuring device 107 measures the terminal pressure of the permanent point, and outputs the terminal pressure information (hereinafter referred to as “permanent terminal pressure information”) indicating the measured terminal pressure of the permanent point to the information acquisition unit 103. The permanent end pressure information is stored in the end pressure information storage unit 102 together with the end pressure information acquired by the other end pressure measuring device 4 by the information acquisition unit 103.

The terminal pressure learning unit 104a distributes water based on the past terminal pressure information acquired by the terminal pressure measuring device 4 and the permanent terminal pressure measuring device 107 and the past water distribution site information, as in the first embodiment. Learn the relationship between the field quantities and the terminal pressure of the distribution pipe network 5. More specifically, the terminal pressure learning unit 104a learns the relationship between the quantity of the distribution station and the terminal pressure at the permanent point and the terminal pressure at any terminal other than the permanent point where the past terminal pressure information can be obtained. do. In this respect, the terminal pressure learning unit 104a is different from the terminal pressure learning unit 104 in the first embodiment. It should be noted that the point that the past end pressure information of the end is used for learning the end pressure of the end other than the permanent point to be estimated is the same as that of the first embodiment.

The terminal pressure estimation unit 105a estimates the terminal pressure corresponding to the given water distribution field amount based on the relationship between the water distribution field amount learned by the terminal pressure learning unit 104a and the terminal pressure of the water distribution pipe network 5. do. Here, the terminal pressure estimation unit 105a estimates the current terminal pressure by inputting the current water distribution field information in the terminal pressure estimation unit 105 in the first embodiment, whereas the current water distribution field information and the current permanent installation unit 105a. It differs from the end pressure estimation unit 105 in the first embodiment in that the current end pressure at any end other than the permanent point is estimated by inputting the end pressure information.

FIG. 6 is a flowchart showing an operation example of the terminal pressure control support device 1a according to the second embodiment. First, the information acquisition unit 103 acquires the water distribution station information and the terminal pressure information (step S201) as in the first embodiment, and the acquired information is stored in the water distribution station information storage unit 101 and the terminal pressure information storage unit 102. Accumulates in (step S202). The end pressure information acquired here includes the end pressure information acquired by the end pressure measuring device 4 and the end pressure information (permanent end pressure information) acquired by the permanent end pressure measuring device 107.

Subsequently, the terminal pressure learning unit 104a learns the terminal pressure based on the past water distribution field information and the past terminal pressure information stored in the water distribution field information storage unit 101 and the terminal pressure information storage unit 102 (step S203). ). Specifically, the terminal pressure learning unit 104a learns the relationship between the amount of water distribution field and the terminal pressure at the permanent point and the terminal pressure at an arbitrary end of the water distribution pipe network 5. That is, by this learning, a discriminator that outputs the terminal pressure at an arbitrary end of the water distribution pipe network 5 is generated by inputting the water distribution field information and the permanent terminal pressure information. The terminal pressure learning unit 104a outputs the learning result to the terminal pressure estimation unit 105a.

Subsequently, the information acquisition unit 103 acquires the current permanent end pressure information and the current water distribution station information (step S204). The terminal pressure estimation unit 105a estimates the current terminal pressure at an arbitrary end of the distribution pipe network 5 based on the learning result by the terminal pressure learning unit 104a, the current water distribution field information, and the current permanent terminal pressure information. (Step S205). The terminal pressure learning unit 104a outputs the estimated terminal pressure information obtained by estimation to the output unit 106. The output unit 106 generates support information based on the estimated terminal pressure information, and transmits the generated support information to the monitoring control system 2 (step S206).

The terminal pressure control support device 1a of the second embodiment configured in this way uses the past permanent end pressure information and the past terminal pressure information acquired for the other ends to provide various quantities of the water distribution station. The relationship between the pressure and the end pressure is learned, and the current end pressure at any end of the distribution pipe network 5 is estimated based on the current water distribution site information and the current permanent end pressure information. In this way, learning the relationship between the amount of water distribution station and the end pressure, and estimating the current end pressure based on the learning result, are performed based on the measured value of the end pressure at a specific end (that is, the permanent point). As a result, the terminal pressure control support device 1a can estimate the terminal pressure of the water distribution pipe network 5 with higher accuracy.

(Third embodiment)
The water distribution system 100b (not shown) in the third embodiment has the same system configuration as the water distribution system 100 in the first embodiment, and replaces the terminal pressure control support device 1 with the terminal pressure control support device 1b. It differs from the water distribution system 100 in the first embodiment in that it is provided.

FIG. 7 is a block diagram showing a specific example of the functional configuration of the terminal pressure control support device 1b according to the third embodiment. The terminal pressure control support device 1b further includes a permanent candidate point determination unit 108, a point including a terminal pressure learning unit 104b instead of the terminal pressure learning unit 104, and a terminal pressure estimation unit 105b instead of the terminal pressure estimation unit 105. It is different from the terminal pressure control support device 1 of the first embodiment in that it is provided. Other configurations of the terminal pressure control support device 1a are the same as those of the terminal pressure control support device 1 of the first embodiment. Therefore, the description of other configurations will be omitted by adding the same reference numerals as those in FIG.

The permanent candidate point determination unit 108 is considered to have a high installation effect of the terminal pressure measuring device based on the learning result of the terminal pressure by the terminal pressure learning unit 104b and the estimation result of the terminal pressure by the terminal pressure estimation unit 105b. Is estimated, and the estimated end is determined as a candidate for a permanent point (hereinafter referred to as "permanent candidate point").

FIG. 8 is a flowchart showing an operation example of the terminal pressure control support device 1b according to the third embodiment. The flowchart of FIG. 8 shows a flow of processing in which the terminal pressure control support device 1b determines a permanent candidate point. First, the permanent candidate point determination unit 108 acquires the terminal pressure information and the water distribution station information stored in the water distribution station information storage unit 101 and the terminal pressure information storage unit 102 (step S301). The permanent candidate point determination unit 108 generates learning data and evaluation data based on the acquired terminal pressure information and water distribution station information (step S302). The training data is the data used for learning the terminal pressure, and the evaluation data is the data used for estimating the permanent point candidate points based on the learning results.

For example, the permanent candidate point determination unit 108 classifies the terminal pressure information into learning and evaluation, and uses a set of the terminal pressure information classified for learning and the corresponding water distribution field information as learning data. .. Similarly, the permanent candidate point determination unit 108 uses a set of terminal pressure information classified for evaluation and corresponding water distribution station information as evaluation data. The water distribution station information and the terminal pressure information may be classified at random or based on any statistical method. The training data and the evaluation data are generated based on an arbitrary calculation formula that outputs the training data or the evaluation data by inputting the water distribution station information and the terminal pressure information, regardless of the above classification. May be good. Further, from the viewpoint of the reliability of the estimated permanent candidate points, it is desirable that the training data and the evaluation data are generated so as not to include overlapping data.

On the other hand, the permanent candidate point determination unit 108 generates a plurality of end combinations (hereinafter referred to as "permanent candidate patterns") consisting of one or more ends that can be permanent candidate points among the respective ends of the water distribution pipe network 5 (step). S303). The permanent candidate pattern may be a random combination of ends or a combination of ends extracted by any standard. Further, a permanent candidate pattern corresponding to all combinations at all ends may be generated, or a permanent candidate pattern corresponding to some combinations may be generated. Since the number of permanent candidate patterns affects the time required for the process of determining the permanent candidate points, it should be adjusted according to the required reliability, the number of end pressure measuring devices that can be arranged, the allowable processing time, etc. good.

Subsequently, the terminal pressure learning unit 104b learns the terminal pressure for each permanent candidate pattern generated by the permanent candidate point determination unit 108 based on the learning data (step S304). Specifically, the terminal pressure learning unit 104b assumes that the permanent candidate point is a permanent point, and determines the relationship between the quantity of the distribution station and the terminal pressure at the permanent point and the terminal pressure at any terminal other than the permanent point. learn. This learning is similar to the learning of the terminal pressure in the second embodiment. Further, for this learning, the water distribution site information and the terminal pressure information included in the learning data are used.

Subsequently, the terminal pressure estimation unit 105b is based on the learning result in step S304, the water distribution field information included in the evaluation data, and the terminal pressure information of the permanent candidate point included in the evaluation data, and any arbitrary point other than the permanent point. The end pressure at the end is estimated (step S305). This estimation is similar to the end pressure estimation in the second embodiment.

The permanent candidate point determination unit 108 sets the permanent candidate point as a permanent point for each permanent candidate pattern based on the difference between the estimated value of the terminal pressure estimated in step S305 and the measured value of the terminal pressure included in the evaluation data. (Step S306), it is determined whether or not the criteria (hereinafter referred to as “permanent criteria”) are satisfied. For example, the permanent candidate point determination unit 108 determines that the permanent candidate point satisfies the permanent standard when the total difference between the estimated value of the terminal pressure and the measured value in a certain permanent candidate pattern is equal to or less than a predetermined threshold value. do. The method for determining the permanent standard is any method as long as it can determine whether or not the estimation accuracy of the terminal pressure is equal to or higher than the predetermined accuracy when the permanent candidate point is assumed to be the permanent point. There may be.

Subsequently, the permanent candidate point determination unit 108 determines whether or not all the permanent candidate patterns satisfy the permanent criteria (step S307). When there is an undetermined permanent candidate pattern (step S307-NO), the permanent candidate point determination unit 108 selects the next permanent candidate pattern to be determined and returns the process to step S304. On the other hand, when there is no undetermined permanent candidate pattern (step S307-YES), the permanent candidate point determination unit 108 outputs information indicating the permanent candidate pattern determined to satisfy the permanent standard to the output unit 106 as a processing result. (Step S308).

The permanent candidate point determination unit 108 does not necessarily have to make the above determination for all the permanent candidate patterns. For example, the permanent candidate point determination unit 108 may be configured to output an estimation result when at least one permanent candidate pattern satisfying the permanent standard is obtained. Further, the permanent candidate point determination unit 108 does not necessarily have to output information indicating all the permanent candidate patterns satisfying the permanent criteria. For example, the permanent candidate point determination unit 108 may be configured to select and output a permanent candidate pattern having a score equal to or higher than a predetermined value among the permanent candidate patterns determined to satisfy the permanent criteria. In this case, for example, the permanent candidate point determination unit 108 gives a higher score to the permanent candidate pattern in which the estimation accuracy of the terminal pressure in step S305 is high and the number of permanent candidate points is small, and the estimation accuracy is low. The larger the number of permanent candidate patterns, the lower the score. That is, when there are a plurality of terminal combinations (permanent candidate patterns) determined as permanent candidate points, the permanent candidate point determination unit 108 determines the terminal represented by the combination with a smaller number of terminals as the permanent candidate point. May be good.

According to the terminal pressure control support device 1b of the third embodiment as described above, in the water distribution system 100b, it is possible to select an appropriate permanent point in terms of estimation accuracy of the terminal pressure and installation cost. Therefore, by applying the terminal pressure control support device 1b of the third embodiment, it becomes possible to realize the terminal pressure control of the water distribution system 100b at a lower cost.

(Fourth Embodiment)
FIG. 9 is a diagram showing a specific example of the system configuration of the water distribution system 100c according to the fourth embodiment. The water distribution system 100c is different from the first water distribution system 100 in that the terminal pressure control support device 1c is provided in place of the terminal pressure control support device 1. Further, the terminal pressure control support device 1c uses water demand information indicating the amount of water demand of each consumer 6 in addition to the water distribution station information and the terminal pressure information in the generation of the support information provided to the monitoring control system 2. It differs from the terminal pressure control support device 1 of the first embodiment in that. In this case, the terminal pressure control support device 1c is configured to be communicable with measuring devices (not shown) such as smart meters that measure the amount of water used by each consumer 6, and each of them communicates with these measuring devices. Acquire the water demand information of the consumer 6.

FIG. 10 is a block diagram showing a specific example of the functional configuration of the terminal pressure control support device 1c according to the fourth embodiment. The terminal pressure control support device 1c of the fourth embodiment further includes a water demand information storage unit 109, a point including an information acquisition unit 103c instead of the information acquisition unit 103, and a terminal pressure instead of the terminal pressure learning unit 104. It differs from the terminal pressure control support device 1 of the first embodiment in that the learning unit 104c is provided and the terminal pressure estimation unit 105c is provided instead of the terminal pressure estimation unit 105. Other configurations of the terminal pressure control support device 1c are the same as those of the terminal pressure control support device 1 of the first embodiment. Therefore, the description of other configurations will be omitted by adding the same reference numerals as those in FIG.

The water demand information storage unit 109 is configured by using a storage device such as a magnetic hard disk device or a semiconductor storage device. The water demand information storage unit 109 stores water demand information.

The information acquisition unit 103c is different from the information acquisition unit 103 in the first embodiment in that it acquires water demand information from each consumer 6 in addition to the water distribution station information and the terminal pressure information. The information acquisition unit 103c stores the acquired water demand information in the water demand information storage unit 109. The information acquisition unit 103c accumulates water demand information in the water demand information storage unit 109 by repeatedly acquiring the water demand information at a predetermined timing.

The terminal pressure learning unit 104c has the water distribution field information stored in the water distribution station information storage unit 101, the terminal pressure information stored in the terminal pressure information storage unit 102, and the water demand information stored in the water demand information storage unit 109. Based on the above, the terminal pressure of the distribution pipe network 5 is learned. Specifically, the terminal pressure learning unit 104c learns the relationship between the water distribution field quantities and the water demand of each consumer 6 and the terminal pressure at an arbitrary end in the water distribution pipe network 5. In this respect, the terminal pressure learning unit 104c is different from the terminal pressure learning unit 104 in the first embodiment. It should be noted that the point that the past end pressure information of the end is used for learning the end pressure of any end to be estimated is the same as that of the first embodiment.

The terminal pressure estimation unit 105c estimates the terminal pressure corresponding to any water distribution field quantity and the water demand of each consumer 6 based on the relationship learned by the terminal pressure learning unit 104c. That is, the terminal pressure estimation unit 105c is different from the terminal pressure estimation unit 105 in the first embodiment in that the current terminal pressure is estimated by inputting the current water distribution site information and the current water demand information.

FIG. 11 is a flowchart showing an operation example of the terminal pressure control support device 1c according to the fourth embodiment. First, the information acquisition unit 103c acquires water distribution station information, terminal pressure information, and water demand information (step S401), and stores the acquired information in the water distribution station information storage unit 101, the terminal pressure information storage unit 102, and the water demand information storage. Accumulate in unit 109 (step S402).

Subsequently, the terminal pressure learning unit 104c has the past water distribution field information stored in the water distribution station information storage unit 101, the past terminal pressure information stored in the terminal pressure information storage unit 102, and the water demand information storage unit 109. The terminal pressure is learned based on the past water demand information accumulated in (step S403). Specifically, the terminal pressure learning unit 104c learns the relationship between the water distribution field quantities and the water demand of each consumer 6 and the terminal pressure at an arbitrary end of the water distribution pipe network 5. That is, by this learning, a discriminator that outputs the end pressure at an arbitrary end of the water distribution pipe network 5 is generated by inputting the water distribution place information and the water demand information. The terminal pressure learning unit 104c outputs the learning result to the terminal pressure estimation unit 105c.

Subsequently, the information acquisition unit 103c acquires the current water distribution site information and the current water demand information (step S404). The terminal pressure estimation unit 105c estimates the current terminal pressure at an arbitrary end of the water distribution pipe network 5 based on the learning result by the terminal pressure learning unit 104c, the current water distribution site information, and the current water demand information ( Step S405). The terminal pressure learning unit 104c outputs the estimated terminal pressure information indicating the estimated terminal pressure to the output unit 106. The output unit 106 generates support information based on the estimated terminal pressure information, and transmits the generated support information to the monitoring control system 2 (step S406).

The terminal pressure control support device 1c of the fourth embodiment configured in this way uses the past water distribution site information, the past terminal pressure information, and the past water demand information to obtain the terminal pressure of the distribution pipe network 5. Is learned, and the current end pressure at any end of the distribution pipe network 5 is estimated based on the current water distribution station information and the current water demand information. In this way, by learning and estimating the terminal pressure using the water demand information of each consumer 6 in addition to the water distribution site information and the terminal pressure information, the terminal pressure control support device 1c is in the water distribution pipe network 5. It is possible to estimate the current end pressure more accurately.

(Fifth Embodiment)
The water distribution system 100d (not shown) in the fifth embodiment has the same system configuration as the water distribution system 100a in the second embodiment, and includes a terminal pressure control support device 1d in place of the terminal pressure control support device 1a. In that respect, it differs from the water distribution system 100a in the second embodiment.

FIG. 12 is a block diagram showing a specific example of the functional configuration of the terminal pressure control support device 1d according to the fifth embodiment. The terminal pressure control support device 1d is different from the terminal pressure control support device 1a of the second embodiment in that the estimation result information storage unit 110 and the leak diagnosis unit 111 are further provided. Other configurations of the terminal pressure control support device 1d are the same as those of the terminal pressure control support device 1a of the second embodiment. Therefore, the description of other configurations will be omitted by adding the same reference numerals as those in FIG.

The estimation result information storage unit 110 is configured by using a storage device such as a magnetic hard disk device or a semiconductor storage device. The estimation result information storage unit 110 stores estimated end pressure information indicating the end pressure estimated by the end pressure estimation unit 105. As a result, past estimated terminal pressure information is accumulated in the estimation result information storage unit 110.

The water leakage diagnosis unit 111 leaks water in the water distribution pipe network 5 based on the past terminal pressure information stored in the terminal pressure information storage unit 102 and the past estimated terminal pressure information stored in the estimation result information storage unit 110. Diagnose the presence or absence of.

FIG. 13 is a flowchart showing an operation example of the terminal pressure control support device 1d according to the fifth embodiment. The flowchart of FIG. 13 shows the flow of processing in which the terminal pressure control support device 1d diagnoses the presence or absence of water leakage in the water pipe network 5. Here, the same processing as in the operation example in the second embodiment is designated by the same reference numerals as those in FIG. 6, and the description thereof will be omitted. That is, each process of steps S201 to S205 is the same as the operation example in the second embodiment, and learning and estimation of the terminal pressure are performed in these steps.

Subsequently, the terminal pressure estimation unit 105a stores the estimated terminal pressure information in the estimation result information storage unit 110. The terminal pressure estimation unit 105a repeatedly executes the estimation of the terminal pressure, and accumulates the estimated terminal pressure information in the estimation result information storage unit 110 (step S501).

The water leakage diagnosis unit 111 leaks water in the water distribution pipe network 5 based on the past terminal pressure information stored in the terminal pressure information storage unit 102 and the past estimated terminal pressure information stored in the estimation result information storage unit 110. Diagnose the presence or absence of (step S502). Specifically, the water leakage diagnosis unit 111 estimates that water leakage has occurred in the water distribution pipe network 5 when the measured value of the terminal pressure is larger than the estimated value of the terminal pressure for a predetermined time. When the water leakage diagnosis unit 111 determines that water leakage has occurred at a certain end, the water leakage diagnosis unit 111 notifies the output unit 106 to that effect (step S503). Then, the output unit 106 outputs information indicating the occurrence of water leakage (hereinafter referred to as “leakage information”) in a predetermined manner in response to the notification of the water leakage diagnosis unit 111, whereby the occurrence of water leakage in the water distribution pipe network 5 occurs. Is notified. For example, the leak information may be displayed on the display device or may be output by voice through the speaker. Further, the leak information may be included in the support information and transmitted to the monitoring control system 2.

The terminal pressure control support device 1d of the fifth embodiment configured in this way can diagnose the presence or absence of water leakage in the water distribution system 100d and notify the diagnosis result. By giving such a notification, in the water distribution system 100d, it becomes possible to perform an appropriate treatment at an appropriate timing according to the occurrence of water leakage. For example, if the diagnosis result is notified to the monitoring control system 2, the monitoring control system 2 can reduce the amount of water leakage by lowering the discharge pressure of the pump of the water distribution station 3. Therefore, according to the terminal pressure control support device 1d of the fifth embodiment, it is possible to more appropriately control the terminal pressure of the water distribution pipe network 5.

(Modification example)
In the fifth embodiment, the mode in which the water leakage diagnosis unit 111 determines the presence or absence of water leakage based on the measured value and the measured value of the terminal pressure at each terminal has been described, but the water leakage diagnosis unit 111 determines the presence or absence of water leakage at each terminal. , The presence or absence of water leakage may be determined based on the result of the water leakage diagnosis at the peripheral end thereof. For example, in this case, the pipe network information indicating the distance between the permanent points or the pipe length is stored in advance in the terminal pressure control support device 1d. When the water leakage diagnosis unit 111 determines that water leakage has occurred at the end of a certain diagnosis target, the other end located within a predetermined range from the end of the diagnosis target based on the pipe network information (hereinafter referred to as "peripheral end"). ) Is identified. Then, when the water leakage diagnosis unit 111 determines that water leakage has also occurred at the peripheral end, it may finally determine that water leakage has occurred at the end of the diagnosis target. In this way, by determining the presence or absence of water leakage at a certain end based on the diagnosis results of a plurality of ends, it is possible to more accurately diagnose the presence or absence of water leakage.

The terminal pressure control support device 1c of the fourth embodiment may include the permanent terminal pressure measuring device 107 of the second embodiment. In this case, the terminal pressure control support device 1c is an arbitrary terminal other than the permanent point based on the past water distribution station information, the past permanent terminal pressure information, the past terminal pressure information, and the past water demand information. The current end pressure at any end other than the permanent point may be estimated based on the current distribution station information, the current permanent end pressure information, and the current water demand information. ..

According to at least one embodiment described above, the terminal pressure learning unit that learns the relationship between the water distribution field quantities and the terminal pressure based on the past terminal pressure information and the past water distribution station information by machine learning. , The terminal pressure of the water distribution system by having the terminal pressure estimation unit that estimates the current terminal pressure in the distribution pipe network based on the above relationship learned by the terminal pressure learning unit and the current water distribution site information. Control can be realized at lower cost.

Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other embodiments, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and variations thereof are included in the scope of the invention described in the claims and the equivalent scope thereof, as are included in the scope and gist of the invention.

1,1a, 1b, 1c, 1d ... Terminal pressure control support device, 2 ... Monitoring control system, 3,3-1,3-2 ... Water distribution station, 4,4-1,4-2 ... Terminal pressure measuring device, 5 ... Water distribution pipe network, 6,6-1 to 6-3 ... Consumers, 100, 100a, 100b, 100c, 100d ... Water distribution system, 101 ... Water distribution station information storage unit, 102 ... Terminal pressure information storage unit, 103, 103c ... Information acquisition unit, 104, 104a, 104b, 104c ... Terminal pressure learning unit, 105, 105a, 105b, 105c ... Terminal pressure estimation unit, 106 ... Output unit, 107 ... Permanent terminal pressure measuring device, 108 ... Permanent candidate point Decision unit, 109 ... Water demand information storage unit, 110 ... Estimated result information storage unit, 111 ... Water leak diagnosis unit

Claims (10)

An information acquisition unit that acquires terminal pressure information indicating the terminal pressure of the water pipe network and water distribution station information indicating various quantities related to the water distribution station to be distributed to the water pipe network.
A terminal pressure learning unit that learns the relationship between the terminal pressure of the distribution pipe network and the various quantities based on the terminal pressure information and the water distribution field information by using a machine learning method.
A terminal pressure estimation unit that estimates the terminal pressure of the water distribution pipe network based on the relationship learned by the terminal pressure learning unit and the water distribution field information.
A determination unit that determines a specific end for measuring the end pressure in the water distribution pipe network based on the end pressure estimation result by the end pressure estimation unit.
Equipped with
Based on the distribution field information and the end pressure information given for learning, the end pressure learning unit assumes that a predetermined end of the ends indicated by the end pressure information is the specific end, and the end pressure is described. Learn the relationship between the quantities and the end pressure at the specific end and the end pressure at any end other than the specific end in the distribution network.
The terminal pressure estimation unit is the terminal pressure of the specific end among the relationship learned by the terminal pressure learning unit, the water distribution field information given for evaluation, and the terminal pressure information given for evaluation. Based on the terminal pressure information indicating, the terminal pressure at the arbitrary end of the distribution pipe network is estimated.
Whether the determination unit makes the predetermined end the specific end based on the difference between the end pressure indicated by the end pressure information given for evaluation and the end pressure estimated by the end pressure estimation unit. Judge whether or not,
End pressure control support device. Further equipped with a measuring unit for measuring the current end pressure at a specific end of the water distribution pipe network.
The end pressure estimation unit is based on the relationship learned by the end pressure learning unit, the current water distribution field information, and the current end pressure information acquired at the specific end, and the water distribution pipe network. Estimate the current end pressure at any of the above ends,
The terminal pressure control support device according to claim 1. When there are a plurality of combinations of ends determined as the specific end, the determination unit determines the end represented by the combination having a smaller number of ends as the specific end.
The terminal pressure control support device according to claim 1 or 2. Information acquisition unit that acquires terminal pressure information indicating the terminal pressure of the water distribution pipe network, water distribution station information indicating various amounts of water distributed to the distribution pipe network, and water demand information indicating the water demand of each consumer. When,
Terminal pressure learning to learn the relationship between the above quantities, terminal pressure and water demand based on past water distribution station information, past terminal pressure information, and past water demand information using a machine learning method. Department and
End pressure estimation that estimates the current end pressure at any end of the water distribution network based on the relationship learned by the end pressure learning unit, current water distribution site information, and current water demand information. Department and
A terminal pressure control support device equipped with. An information acquisition unit that acquires terminal pressure information indicating the terminal pressure of the water pipe network and water distribution station information indicating various quantities related to the water distribution station to be distributed to the water pipe network.
A measuring unit that measures the current end pressure at a specific end of the water distribution pipe network,
Based on the past end pressure information including the end pressure information acquired at the specific end and the past water distribution station information, the quantities and the end pressure at the specific end and the specific in the distribution pipe network. The terminal pressure learning unit that learns the relationship with the terminal pressure at any end other than the end using a machine learning method ,
The present at any end of the water distribution network based on the relationship learned by the end pressure learning unit, the current distribution field information, and the current end pressure information acquired at the particular end. The terminal pressure estimation unit that estimates the terminal pressure of
A leak diagnosis unit that diagnoses the presence or absence of leaks in the water distribution pipe network,
Equipped with
The leak diagnosis unit is the specific end when the measured value of the end pressure is larger than the estimated value of the end pressure for a predetermined time at a specific end and the end around the specific end. Judge that water leakage has occurred at the end,
End pressure control support device. The terminal pressure learning unit learns the relationship by a machine learning method based on a random forest.
The terminal pressure control support device according to any one of claims 1 to 5. An information acquisition step for acquiring terminal pressure information indicating the terminal pressure of the water distribution pipe network and water distribution site information indicating various quantities related to the water distribution station to be distributed to the distribution pipe network.
A terminal pressure learning step for learning the relationship between the terminal pressure of the distribution pipe network and the various quantities based on the terminal pressure information and the water distribution field information by using a machine learning method.
A terminal pressure estimation step for estimating the terminal pressure of the water distribution pipe network based on the relationship learned in the terminal pressure learning step and the distribution field information, and a terminal pressure estimation step.
Based on the end pressure estimation result in the end pressure estimation step, a determination step for determining a specific end for measuring the end pressure in the water distribution pipe network, and a determination step.
Have,
In the end pressure learning step, based on the distribution field information and the end pressure information given for learning, it is assumed that a predetermined end of the ends indicated by the end pressure information is the specific end, and the end pressure is described. Learn the relationship between the quantities and the end pressure at the specific end and the end pressure at any end other than the specific end in the distribution network.
In the end pressure estimation step, the end pressure of the specific end among the relationship learned in the end pressure learning step, the distribution field information given for evaluation, and the end pressure information given for evaluation. Based on the terminal pressure information indicating, the terminal pressure at the arbitrary end of the distribution pipe network is estimated.
Whether to make the predetermined end the specific end based on the difference between the end pressure indicated by the end pressure information given for evaluation in the determination step and the end pressure estimated in the end pressure estimation step. Judge whether or not,
End pressure control support method having. Information acquisition step to acquire terminal pressure information indicating the terminal pressure of the water distribution pipe network, water distribution station information indicating various quantities related to the water distribution station to be distributed to the distribution pipe network, and water demand information indicating the water demand of each consumer. When,
Terminal pressure learning to learn the relationship between the above quantities, terminal pressure and water demand based on past water distribution station information, past terminal pressure information, and past water demand information using a machine learning method. Steps and
End pressure estimation to estimate the current end pressure at any end of the distribution network based on the relationship learned in the end pressure learning step, current distribution site information, and current water demand information. Steps and
End pressure control support method having. An information acquisition step for acquiring terminal pressure information indicating the terminal pressure of the water distribution pipe network and water distribution station information indicating various quantities related to the water distribution station to be distributed to the distribution pipe network.
A measurement step to obtain a measurement value of the current end pressure at a specific end of the water distribution pipe network, and a measurement step.
Based on the past end pressure information including the end pressure information acquired at the specific end and the past water distribution station information, the quantity and the end pressure at the specific end and the specific in the distribution pipe network. An end pressure learning step that learns the relationship with end pressure at any end other than the end,
The current at any end of the distribution network based on the relationship learned in the end pressure learning step, the current distribution field information, and the current end pressure information acquired at the particular end. End pressure estimation step to estimate the end pressure of
A leak diagnosis step for diagnosing the presence or absence of leaks in the water distribution pipe network, and
Have,
In the leak diagnosis step, when the measured value of the end pressure is larger than the estimated value of the end pressure at a specific end and the end around the specific end for a predetermined time, the specific end is specified. Judge that water leakage has occurred at the end,
End pressure control support method. A computer program for operating a computer as the terminal pressure control support device according to any one of claims 1 to 6 .

Images