CN104636817A - Water leakage survey plan making device, system and water leakage survey plan making method - Google Patents

Abstract

The invention provides a water leakage investigation plan formulation device, system and water leakage investigation plan formulation method. With limited resources, a cost-effective water leakage investigation plan can be developed even when there is uncertainty about water leakage. Based on at least one of water leakage information, pipeline information, and investigation/repair information, generate prediction model information for predicting changes in water leakage in the area, generate area predicted water leakage information based on the prediction model information, and generate predicted water leakage information based on the predicted water leakage information. To formulate a water leakage investigation plan that determines the order of implementation of water leakage investigations in a plurality of regions. Predicted water leakage information is generated from both the expected value of the water leakage and the predicted value of the uncertainty, and a water leakage investigation plan is prepared using the calculated water leakage cost.

Description

Water Leakage Investigation Plan Formulation Device, System, and Water Leakage Investigation Plan Formulation Method

technical field

The invention relates to a water leakage investigation plan formulation device, in particular to a water leakage investigation plan formulation device for formulating a cost-effective plan.

Background technique

Claim 1 of Patent Document 1 describes "a system for extracting water leakage investigation target routes, which analyzes past water leakage repair data collected/accumulated in the process of water distribution pipeline network supplying clean water to end consumers, which It is characterized in that it includes: a main DB that stores past water leakage repair data and data on the number of buried water supply pipes; and a data extraction unit that extracts the number of repairs for each drawing number and the number of buried water supply pipes for each project number from the main DB. Data such as the repair year and the laying year; the grid evaluation unit, which calculates the number of repairs or the repair ratio of each drawing number relative to the entire water distribution pipeline network according to the data obtained from the data extraction unit, and calculates the number of repairs according to the attached drawing Numericalize or emphatically display the calculated value; the project number list extraction unit, which extracts the project number to which the drawing number with a high water leakage risk obtained through the grid evaluation unit belongs, and converts the project number, the number of repaired pieces in the drawing , the number of all repairs, the number of buried water supply pipes, and the repair ratio are tabulated; and the water leakage investigation priority evaluation unit calculates the water leakage investigation priority based on the extracted project number list and based on the parameters set by the user."

prior art literature

patent documents

Patent Document 1: Japanese Unexamined Patent Publication No. 2011-59799

Contents of the invention

Although the water leakage investigation object route extraction system of Patent Document 1 can extract areas with high water leakage risks from repair information, it cannot allocate limited resources (personnel, etc.) to determine which area to conduct the next water leakage investigation. In addition, the water leakage investigation object route extraction system of Patent Document 1 cannot cope with the uncertainty of the water leakage risk.

Therefore, an object of the present invention is to provide a water leakage investigation plan preparation device capable of creating a cost-effective water leakage investigation plan even when there is uncertainty about water leakage with limited resources.

In order to solve the above-mentioned problems, for example, the configuration described in the claims is adopted. This application includes a plurality of means for solving the above-mentioned problems. As an example, a water leakage investigation plan formulation device for formulating a water leakage investigation plan for a plurality of areas divided into water pipe networks is characterized in that the water leakage investigation plan formulation device has :

a measurement information collection unit that collects measurement information related to water flow from a measurement device including a flow meter installed on the water pipe network; a water consumption storage unit that stores water consumption information in the area; a water leakage estimation unit estimating the amount of water leakage in the area based on the measurement information and the water consumption information; a pipeline information storage unit storing pipeline information including extension information of a water pipeline network in the area; a survey/repair information storage unit storing survey/repair information including surveys of water leaks in the region and execution times of pipeline repairs; a predictive model learning unit at least one of the survey/repair information to generate prediction model information for predicting changes in the amount of water leakage in the area; a water leakage amount prediction unit that generates predicted water leakage amount information in the area based on the prediction model information; and an investigation plan formulation unit that prepares a water leakage investigation plan for determining an order of implementation of water leakage investigations in the plurality of areas based on the predicted water leakage amount information,

The water leakage amount prediction unit generates predicted values of both an expected value of the water leakage amount and an uncertainty of the expected value of the water leakage amount as the predicted water leakage amount information, and the survey plan formulation unit uses The water leakage cost calculated from the predicted value of both the expected value and the uncertainty is used to formulate the water leakage investigation plan.

According to the present invention, it is possible to provide a water leakage investigation plan making device that makes a cost-effective plan.

The problems, configurations, and effects other than those described above will be clarified more clearly through the description of the following embodiments.

Description of drawings

FIG. 1 is a block diagram of a water leakage investigation plan making device in this embodiment.

Fig. 2 is a hardware block diagram of the device for formulating a water leakage investigation plan in this embodiment.

Fig. 3 is a diagram showing that the water leakage investigation plan preparation device takes the water pipe network and the water distribution block as the objects of the water leakage investigation plan preparation.

Fig. 4 is a diagram showing table pipeline information of water distribution pipes registered in a pipeline information storage unit.

Fig. 5 is a diagram showing table pipeline information of water supply pipes registered in a pipeline information storage unit.

6 is a diagram showing meter water leakage investigation information registered in an investigation/repair history storage unit.

FIG. 7 is a diagram showing meter pipeline repair information registered in an investigation/repair history storage unit.

Fig. 8 is a diagram showing an example of actual transition of the water leakage amount of the water distribution block.

FIG. 9 is a diagram showing a predicted transition of a leaked water amount by a leaked water amount predicting unit.

FIG. 10 is a diagram showing table prediction model information registered in a prediction model storage unit.

Fig. 11 is a diagram showing meter water leakage investigation plan information registered in a water leakage plan storage unit.

FIG. 12 is a flowchart showing the processing of the predictive model learning unit.

Fig. 13 is a flowchart showing processing of a leaked water amount predicting unit.

FIG. 14 is a flowchart showing processing of a survey plan formulation unit.

Fig. 15 is a diagram showing a screen display performed by a screen display unit related to a water leakage investigation plan.

FIG. 16 is a diagram showing a screen display performed by a screen display unit related to a water leakage amount prediction result.

Symbol Description

100 Water leakage investigation planning system

101 Water leakage investigation plan making device

111 Predictive Model Learning Department

112 Water Leakage Prediction Department

113 Investigation Planning Department

121 Pipeline information storage department

122 Investigation/Repair Information Storage Department

125 Cost Information Storage Department

131 Forecast model storage department

132 Investigation plan storage department

174 screen display unit

Detailed ways

Hereinafter, an embodiment will be described using the drawings. In addition, the same reference numerals are attached to substantially the same parts, and the description thereof will not be repeated.

FIG. 1 is a block diagram of a water leakage investigation plan making device 101 in this embodiment.

The water leakage investigation plan formulation device 101 has: a water leakage amount estimation unit 110, a prediction model learning unit 111, a water leakage amount prediction unit 112, an investigation plan formulation unit 113, a pipeline information storage unit 121, an investigation/repair information storage unit 122, and a measurement information storage unit. unit 123, water consumption storage unit 124, cost information storage unit 125, forecast model storage unit 131, survey plan storage unit 132, survey terminal IF unit 171, measurement device IF unit 172, meter inspection terminal IF unit 173, and screen display unit 174.

The water leakage investigation plan formulation system 100 has a water leakage investigation plan formulation device 101 , an investigation terminal 181 , a measurement device 182 , and a meter inspection terminal 183 .

The structure in which the water leakage investigation plan preparation device 101 makes a water pipe network, a water distribution block, and the like as objects of water leakage investigation plan preparation will be described later using FIG. 3 .

The water leakage amount estimating unit 110 takes the measurement information registered in the measurement information storage unit 123 and the usage amount information registered in the water usage storage unit 124 as input, and estimates the water leakage amount in each region in a predetermined period (for example, one day), The estimated water leakage amount is sent to the predictive model learning unit 111 as water leakage amount information.

Known techniques such as estimation based on nighttime minimum flow or water budget calculation (estimation of water leakage by subtracting water usage from the cumulative value of distributed water, or other factors) can be used to estimate the amount of leaked water. Through the description of FIG. 8 , the leaked water amount information that is the output of the leaked water amount estimating unit 110 is supplemented.

The predictive model learning unit 111 combines the water leakage information in areas such as water distribution blocks received from the water leakage estimation unit 110 , the pipeline information registered in the pipeline information storage unit 121 , and the survey information registered in the investigation/repair information storage unit 122 . /Repair information is used as an input to learn a prediction model for calculating both the expected value and the uncertainty of the future water leakage in each area, and the learned prediction model is sent to the prediction model storage unit 131 as prediction model information. The details of the processing of the predictive model learning unit 111 will be described later through the description of FIG. 12 .

The water leakage prediction unit 112 takes the prediction model information registered in the prediction model storage unit 131 as an input, calculates the prediction of both the expected value and the uncertainty of the water leakage in each area, and sends the result as predicted water leakage information to The investigation plan formulation unit 113 and the screen display unit 174 . The details of the processing of the leaked water amount predicting unit 112 will be described later by referring to the description of FIG. 13 .

The investigation plan formulation unit 113 takes the water leakage amount prediction information received from the water leakage amount prediction unit 112 and the cost information registered in the cost information storage unit 125 as input, and uses both the expected value and the uncertainty of the water leakage amount The water leakage cost calculated based on the forecast is used as the evaluation index of the water leakage investigation plan, and the water leakage investigation plan formulation and calculation process is performed, and the prepared water leakage investigation plan is sent to the investigation plan storage unit 132 .

Here, the so-called water leakage investigation plan is a plan for determining the execution order of the water leakage investigation in a plurality of areas. The so-called water leakage investigation means, for example, that a worker investigates whether or not a water leakage occurs by conducting a sound inspection of a water pipe. The details of the processing of the survey plan formulation unit 113 will be described later by referring to the description of FIG. 13 .

The pipeline information storage unit 121 registers pipeline information including extension information of the water pipeline network related to the water pipeline network to be planned by the water leakage investigation plan making device 101 . Specifically, the piping information of the water distribution pipe which will be described in the description of FIG. 4 which will be described later and the piping information of the water supply pipe which will be described in the description of FIG. 5 which will be described later are registered.

The survey/repair information storage unit 122 registers survey/repair information about the water pipe network to be planned by the water leak survey planning device 101 , including the execution time of the water leak survey and pipeline repair. Specifically, water leakage investigation information to be described later in the description of FIG. 6 and piping repair information to be described in the later description of FIG. 7 are registered.

The measurement information storage unit 123 registers sensor measurement information in a water pipe network to be planned by the water leakage investigation plan making device 101 . The period transmitted from the measuring device 182 is registered in time series, for example, the sensor measurement data (measured value of pressure or flow rate) of each measuring device in a 1-minute period.

The water consumption storage unit 124 registers the water consumption information of the water users in the water pipe network to which the water leakage investigation plan preparation device 101 makes plans. Water users introduce water from the water distribution pipe of the water pipe network through the water supply pipe, and set up a water meter for fee collection at the introduction point. The water consumption measured by the water meter is regularly read by a meter inspector or an automatic meter inspection system. The water usage-amount storage unit 124 records the water usage-amount information of each water user collected as described above, that is, the water usage-amount information used by a certain water user during a certain period.

The cost information storage unit 125 registers cost information including expenses required for water leakage investigation and pipeline repair and losses per unit amount of water leakage in the water pipe network to be planned by the water leakage investigation planning device 101 .

Here, the cost of water leakage investigation and pipeline repair refers to the cost of conducting water leakage investigation for each area of the water pipe network by means of audio-audiometry and performing pipeline maintenance for the water leakage found through the investigation. In addition, the loss due to a unit amount of water leakage means, for example, an expense caused by letting a cubic meter of water leak.

The prediction model storage unit 131 registers the prediction model information output by the prediction model learning unit 111 . Specifically, it will be described later in the description of FIG. 11 .

The survey plan storage unit 132 registers the survey plan information output by the survey plan formulation unit 113 . Specifically, it will be described later in the description of FIG. 11 .

The investigation terminal IF unit 171 sends information received from the investigation terminal 181 described later to the investigation/repair information storage unit 122 to add or update the water leakage investigation information and pipeline repair information registered in the investigation/repair information storage unit 122 .

The measurement device IF unit 172 transmits information received from a measurement device 182 described later to the measurement information storage unit 123 , and adds new measurement information to the measurement information storage unit 123 .

The meter inspection terminal IF unit 173 transmits information received from the meter inspection terminal 183 described later to the water consumption storage unit 124 , and adds or updates the water consumption information registered in the water consumption storage unit 124 .

The screen display unit 174 transmits the water leakage prediction information received from the water leakage prediction unit 112 and the water leakage investigation plan information registered in the investigation plan storage unit 132 to the operator of the water leakage investigation plan formulation device 101 through an output device such as a display, for example. hint. Specifically, presentation is made using a table or a graph in the form described in FIGS. 15 and 16 .

Each measurement device 182 is connected to the water leakage investigation plan preparation device 101 via a communication network. Measuring devices such as flowmeters and pressure gauges installed in the managed water pipe network send measured sensor data to the measuring device IF unit 172 of the water leakage investigation plan making device 101 via the communication network. A specific example of the measuring device will be described later in the description of FIG. 3 .

Each investigation terminal 181 and meter inspection terminal 183 (portable information terminals such as PDA) are connected to the water leak investigation plan making device 101 via a communication network.

When conducting water leakage investigation and pipeline repair, the investigation terminal 181 takes information related to water leakage investigation and pipeline repair as input through the user's operation of the investigation terminal, and sends the information to the investigation terminal of the water leakage investigation plan formulation device 101 IF Section 171.

In addition, when the meter is used for billing, the meter inspection terminal 183 takes the read value of the water meter as input through the operation of the user of the meter inspection terminal, and sends this information to the inspection of the water leakage investigation plan making device 101. Table terminal IF section 173.

FIG. 2 is a hardware block diagram of the device 101 for making a water leakage investigation plan in this embodiment. In FIG. 2 , the water leakage investigation plan making device 101 has a CPU 201 , a memory 202 , a medium input and output unit 203 , a communication control unit 204 , an input unit 205 , a display unit 206 , a peripheral device IF unit 207 and a bus 210 .

CPU 201 executes programs on memory 202 . The memory 202 temporarily stores programs, tables, and the like. The medium input/output unit 203 is, for example, an interface with an information recording medium including an SD card.

The communication control unit 204 is connected to the network 220 and performs a communication interface with an external device. The input unit 205 is a user interface including a keyboard and a mouse.

The display unit 206 is the display described in FIG. 1 . The peripheral device IF unit 207 is an interface with nearby devices including a printer.

The bus 210 interconnects the CPU 201 , the memory 202 , the medium input/output unit 203 , the communication control unit 204 , the input unit 205 , the display unit 206 , and the peripheral device IF unit 207 .

As can be seen from a comparison between FIG. 1 and FIG. 2 , the water leakage investigation plan making device 101 in FIG. 1 operates when the CPU 201 executes a program.

FIG. 3 is a diagram showing a water pipe network and a water distribution block as targets for making a water leakage investigation plan by the water leakage investigation plan preparation device 101 . In Fig. 3 there is shown a water distribution tank 301 supplying water to the water distribution network and the water distribution network drawn in solid lines. Furthermore, flow meters 310 to 313 and pressure meters 321 to 324 are shown as measuring devices arranged in the water network.

The water distribution block refers to the area where the flow rate of all the water distribution pipes flowing into and out of the area set to divide the water pipe network is measured by a flow meter. In the example of FIG. 3 , the areas 331 and 332 are provided with a flow meter 311 and flow meters 312 and 313 in the inflow pipeline, forming water distribution blocks. In addition, the water distribution block is also called DMA (District Metered Area, independent metering area).

The water leakage investigation planning unit 113 of the water leakage investigation plan formulation device 101 targets at the water distribution block or the area in which the water distribution block is further divided, and prepares a plan for determining the order in which to conduct the water leakage investigation in a plurality of areas as the water leakage. survey plan. Hereinafter, the unit that conducts the water leakage investigation including the water distribution block is referred to as the district.

Here, the water leakage investigation refers to a business of detecting water leakage from a water pipe by a person using a device such as a sound bar, a sound device, or a correlative water leakage detector. A specific example of the water leakage investigation plan will be described later in the description of FIG. 11 .

FIG. 4 is a diagram showing table pipe line information 400 of water distribution pipes registered in the pipe line information storage unit 121 . The columns of the table pipeline information 400 are: water distribution pipe ID information 401 , location information 402 , extension information 403 , caliber information 404 , pipe type information 405 , years of laying information 406 , accessory information 407 , and area information 408 . In the table pipe line information 400 , all the information is registered within a possible range for all the water distribution pipes of the water pipe network managed by the water leakage investigation plan making device 101 , with one water distribution pipe as one line. In FIG. 4, only one water distribution pipe is shown as an example.

In the water distribution pipe ID information 401, the ID which uniquely determines a specific water distribution pipe among all the water distribution pipes is stored. In the position information 402, coordinate information specifying the position where the water distribution pipe is to be buried is stored in cooperation with GIS (Geographic Information System: Geographic Information System). Information on the extension and diameter of the water distribution pipe is stored in the extension information 403 and the diameter information 404 .

In the pipe type information 405, information such as pipe types such as DIP (Graphite Cast Iron Pipe: Ductile Iron Pipe) and CIP (Cast Iron Pipe) and pipe specifications (with or without a corrosion-resistant sleeve) are stored. The number of years of installation of the water distribution pipe is registered in the number of years of installation information 406 . Or you register the year of laying, and you can find the number of years of laying from these by calculation. The accessory information 407 stores information such as the number and position of accessories such as fire hydrants and air valves, and the number of water supply pipes taken out. Information on the area (water distribution block) to which the water distribution pipe belongs is stored in the area information 408 .

FIG. 5 is a diagram showing the table water supply pipe information 500 of the pipe information of the water supply pipes registered in the pipe information storage unit 121 . The columns of the table water supply pipe information 500 are: water supply pipe ID information 501, location information 502, connection destination water distribution pipe ID information 503, extension information 504, caliber information 505, pipe type information 506, laying years information 507, and area information 508 . In the table water supply pipe information 500 , all the information on one water supply pipe as a row is registered for all the water supply pipes in the water pipe network managed by the water leak investigation plan making device 101 as much as possible. In FIG. 5, only one water supply pipe is shown as an example.

In the water supply pipe ID information 501, the ID which uniquely determines a specific water supply pipe among all the water supply pipes is stored. In the position information 502, coordinate information specifying the position where the water supply pipe is to be buried is stored in cooperation with GIS. The water distribution pipe ID connected to the water supply pipe is stored in the connection destination water distribution pipe ID information 503 .

Information on the extension and diameter of the water supply pipe is stored in the extension information 504 and the diameter information 505 . Pipe type information 506 stores pipe type information such as PE (polyethylene pipe) and LP (lead pipe). The number of years of installation of the water supply pipe is registered in the number of years of installation information 507 . Alternatively, the number of years of burying may be registered. The area (water distribution block) information to which the water supply pipe belongs is stored in the area information 508 .

FIG. 6 is a diagram showing meter water leakage investigation information 600 of the water leakage investigation information registered in the investigation/repair information storage unit 122 . The columns of the meter water leakage investigation information 600 are investigation ID information 601 , period information 602 , and target area information 603 . In the table water leakage investigation information 600 , all the information is registered in one line for the water leakage investigation history carried out in all the areas managed by the water leakage investigation plan making device 101 for one area. In FIG. 6 , only two water leakage investigation histories are shown as an example.

In the survey ID information 601, an ID uniquely identifying a specific survey history among all survey histories is stored. The period information 602 stores information on the period during which the survey was carried out. In the target area information 603, the ID of the area where the water leakage investigation was carried out by this investigation is stored.

FIG. 7 is a diagram showing meter pipeline repair information registered in the survey/repair information storage unit 122 . The columns of table pipeline repair information 700 are: repair ID information 701, category information 702, pipe ID information 703, location information 704, cause information 705, water leakage prevention information 706, date and time information 707, and investigation ID information 708. In the table pipeline repair information 700 , all the information is registered on a pipeline repair history for water distribution pipes and water supply pipes managed by the water leakage investigation plan making device 101 as a line. In FIG. 7 , only one pipeline repair history is displayed as an example.

In the repair ID information 701, an ID that uniquely determines a specific repair history among all the repair histories is stored. In the category information 702 and the pipe ID information 703, information indicating whether the repair target is a water distribution pipe or a water supply pipe and ID information of the target pipe are stored. In the position information 704 , the position information where the repair was performed is stored in cooperation with GIS. That is, information on which position of the target pipe has been repaired is stored.

In the cause information 705, the cause information of the estimated repair water leakage is stored. For example, information on causes such as deterioration due to aging, corrosion, overweight, or unknown is stored. In the prevented water leakage amount information 706, information on the result of observing the water leakage amount (flow rate) at the repair time of the water leakage to be repaired from the repair site is stored. The date and time information on which the repair was performed is stored in the date and time information 707 . In the investigation ID information 708, the water leakage investigation ID information which found the water leakage which is the object of this repair is stored. If the target water leak is not a water leak found by a water leak investigation but, for example, a water leak found by a report of a ground water leak, ID information capable of specifying the reason for the discovery is stored.

Fig. 8 is a diagram showing an example of actual transition of the water leakage amount of the water distribution block. In the graph of FIG. 8 , the horizontal axis represents time, and the vertical axis represents the amount of water leakage in a specific area (water distribution block). Generally, as indicated by the amount of water leakage 801 , the amount of water leakage in an area monotonically increases except during the implementation period of the water leakage prevention work indicated by the prevention work period 811 and the prevention work period 812 . Here, the water leakage prevention work refers to a water leakage investigation and repair of a water leakage discovered through the water leakage investigation.

As described above, the water leakage amount estimating unit 110 estimates the past water leakage amount in each region as shown in FIG. 8 based on the information registered in each storage unit.

FIG. 9 is a diagram showing the predicted transition of the leaked water amount by the leaked water amount predicting unit 112 . With reference to FIG. 9 , prediction of both the expected value of the water leakage amount in a specific area (water distribution block) and the uncertainty thereof by the water leakage amount prediction unit 112 will be described. In the graph of FIG. 9 , the horizontal axis represents the elapsed time after the last water leakage investigation and repair in the area, and the vertical axis represents the amount of water leakage in the area.

The prediction of the transition of the leakage amount output by the leakage amount prediction unit 112 relates to the expected value 901 of the predicted leakage amount, the lower value 903 of the predicted leakage amount, and the upper value of the predicted leakage amount corresponding to the elapsed time after the last water leakage investigation and repair. 902 and other three time series. The high-order value 902 of the predicted water leakage amount and the low-order value 903 of the predicted water leakage amount represent the uncertainty of the expected value 901 of the predicted water leakage amount. For example, the high level value and the low level value can be set as the upper limit value and the lower limit value of the 95% reliable region, which are calculated from the correspondence degree of the past leakage amount change of the prediction model, for example.

Generally, the occurrence of water leakage is related to many uncertain factors, so it is difficult to deal with it as a decisive event. Therefore, the prediction error of the expected value of only the water leakage amount is large, and it cannot take into account that the uncertainty of the prediction varies from region to region.

The water leakage investigation plan making device 101 outputs high and low values as uncertainties of expected values in addition to the above-mentioned expected values, thereby enabling more useful prediction of water leakage when formulating an effective water leakage investigation plan. As a method of expressing the uncertainty of the expected value, in addition to the upper and lower values, for example, the magnitude of the deviation from the expected value can also be used.

FIG. 10 is a diagram showing table prediction model information 1000 registered in the prediction model storage unit 131 . The columns of the table prediction model information 1000 are prediction model ID information 1001 , target region information 1002 , model type information 1003 , explanatory variable information 1004 , coefficient information 1005 , and category information 1006 .

In the table prediction model information 1000 , one prediction model is registered as one row for all the prediction models output by the prediction model learning unit 111 . In FIG. 10, two prediction models are shown as an example. In addition, the table prediction model information 1000 includes at least one prediction model that can be applied to one region for all the regions where the water leakage investigation plan making device 101 is the planning target.

An ID for uniquely determining a prediction model is stored in the prediction model ID information 1001 . In the target area information 1002, area IDs to which the prediction model can be applied are stored. For a model applicable to a plurality of regions, information capable of specifying an applicable region is stored.

In the model expression information 1003, the formula number used by the prediction model for prediction is stored. In the explanatory variable information 1004, the explanatory variable information of the area used when applying the prediction model to each area is stored. The predictive model learning unit 111 and the leaked water amount predicting unit 112 acquire specific values of region-specific variables from the pipeline information storage unit 121 and the survey/repair information storage unit 122 as necessary. Explanatory variables will be described later.

The specific value of the coefficient of the prediction formula indicated by the model formula information 1003 is stored in the coefficient information 1005 . In the category information 1006, information indicating which of the general forecast model and the regional forecast model the forecast model corresponds to is stored.

The prediction model learning unit 111 outputs the prediction model information described in FIG. 10 . The prediction model output by the prediction model learning unit 111 is classified into a region-specific prediction model and a general prediction model as shown in the description of the category information 1006, wherein the region-specific prediction model can only be applied to a specific region, and the A general predictive model can be applied to multiple regions by substituting values in that region.

For example, the forecast model whose forecast model ID is E4A332 shown in FIG. 10 is a regional forecast model. As a specific example of the prediction formula of the forecast model for each area, the water leakage investigation plan preparation device 101 uses, for example, the following prediction formula. Hereinafter, formulas (1a) to (1c) are collectively referred to as formula (1).

L(t)＝L0+k×t···(1a)

Lh(t)＝L(t)+Dh0+mh×t ···(1b)

L1(t)＝L(t)-D10-m1×t ···(1c)

here,

L(t): Expected value of predicted water leakage [m ³ /h]

L0: Initial value as above (after water leak repair) [m ³ /h]

Lh(t): High value of predicted water leakage [m ³ /h]

Dh0: Initial value as above (after water leak repair) [m ³ /h]

L1(t): Low value of predicted water leakage [m ³ /h]

D10: Initial value as above (after water leakage repair) [m ³ /h]

k, mh, m1; positive coefficient

t: elapsed time [days]

For example, the prediction model whose prediction model ID is E3AGE shown in FIG. 10 is a general prediction model. As a specific example of the prediction expression of the general prediction model, the water leakage investigation plan preparation device 101 uses, for example, the following prediction expression. Hereinafter, formulas (2a) to (2c) are collectively referred to as formula (2).

L(t, x)＝L0(x)+k(x)×t···(2a)

Lh(t, x)=L(t, x)+Dh0+mh×t ···(2b)

L1(t, x)＝L(t, x)-D10-m1×t ···(2c)

【Formula 1】

L ₀ (x)＝exp(α ₀ +Σ _s α _s ×x _s )···(2d)

【Formula 2】

k(x)＝exp(β ₀ +Σ _s β _s ×x _s )···(2e)

here,

L(t, x): Expected value of predicted water leakage [m ³ /h]

L0(x): Initial value as above (after water leak repair) [m ³ /h]

Lh(t, x): High value of predicted water leakage [m ³ /h]

Dh0: Initial value as above (after water leak repair) [m ³ /h]

L1(t, x): low value of predicted water leakage [m ³ /h]

D10: Initial value as above (after water leakage repair) [m ³ /h]

α ₀ , β ₀ , α _s , β _s : Coefficients

k(x), mh, m1; positive coefficient

s: the index of the description variable (index)

x _s : explanatory variable for index s

x: all explanatory variables

t: elapsed time [days]

Regarding s, indexes of all explanatory variables are acquired.

As an explanatory variable of the general predictive model processed by the water leakage investigation plan formulation device 101, the past number of water leakage repairs in the region based on the number of past water leakage repairs stored in the pipeline information storage unit 121, the investigation/repair information storage unit 122, etc., can be used. Among the number of repaired water leaks, the number of water leaks discovered by notification instead of leak investigation (the number of reported leak repairs), the number of water supply pipes in the area, the age of the oldest pipes in the area, and the number/total number of pipes over 30 years old, for example Arbitrary index calculated from information such as extension.

Even if the above-mentioned same prediction formula (2) is used, when a different explanatory variable group is used, the water leakage investigation plan making device 101 treats these as other prediction models. In addition, the general prediction models registered in the prediction model storage unit 131 include not only the models output by the prediction model learning unit 111 but also general prediction models arbitrarily added by the user of the water leakage investigation plan making device 101 .

For example, it is also possible to store a general-purpose prediction model learned in an area not targeted by the water leakage investigation plan formulation device 101 in the prediction model storage unit 131, and the water leakage amount prediction unit 112 utilizes the general-purpose prediction model in the planning of the water leakage investigation plan. The device 101 is in the process of predicting the amount of water leakage in the planning target area. The arbitrarily added general prediction model is fixed to the model related to the expected value, and the coefficients related to the uncertainty can also be learned by the prediction model learning unit 111, that is, only Dh0, D10, mh, and m1 in the example of the prediction formula (2) are learned. .

FIG. 11 is a diagram showing meter water leakage investigation plan information 1100 registered in the investigation plan storage unit 132 . As described above, the water leakage investigation plan determines the order of implementation of the water leakage investigation in a plurality of regions. For example, in addition to the order of implementation, it is also possible to determine the period during which water leakage surveys will be carried out in each area within the planned period. However, leak investigations may not be implemented in some areas. The water leakage investigation plan information 1100 indicates the period during which the water leakage investigation is determined in each area, and indicates which period among the planned periods 1102 to 1104 the water leakage investigation is to be performed for each area indicated by the area ID information 1101 .

For example, in Fig. 11 , it shows that during the three-year planning period, three water leakage investigations of survey period 1111, survey period 1112 and survey period 1113 are planned in area 331, and two survey periods of survey period 1121 and survey period 1122 are planned in area 332. Water leak investigation. The above-mentioned investigation plan information is stored in the water leakage investigation plan information 1100 for all areas targeted for planning.

FIG. 12 is a flowchart showing the processing of the predictive model learning unit 111 . FIG. 12 shows the operation flow until the predictive model learning unit 111 extracts information of each registered region, performs learning to generate a predictive model, and sends it to the predictive model storage unit 131 . In the start step 1200, the prediction model learning unit 111 starts processing.

In the input information receiving step 1201, the predictive model learning unit 111 receives the pipeline information registered in the pipeline information storage unit 121 and the survey/repair information registered in the survey/repair information storage unit 122, and also receives the information from the leakage amount estimation unit. 110 receives past water leakage information for each region.

In the water distribution area extraction step 1202, the prediction model learning unit 111 extracts one water distribution area (area) as a learning object of the prediction model for each area. However, the predictive model learning unit 111 extracts only the region where the past water leakage amount transition is estimated by the water leakage amount estimating unit 110 .

In step 1203 of learning a forecast model for each area, the forecast model learning unit 111 learns a forecast model for each area targeting the extracted area.

For example, in order to learn an area-by-area prediction model using the prediction formula (1), the prediction model learning unit 111 calculates an initial value L0 and a coefficient k for reproducing the value from the water leakage estimation unit. 110 receives the actual data of the water leakage amount 801 between the prevention work period 811 and the prevention work period 812 in FIG. 8 . For this calculation, known techniques such as the least square method can be used, for example.

In addition, as a method of determining the initial values Dh0, D10, and the coefficients mh, m1, the predictive model learning unit 111 can, for example, use the predictive formula (1a) obtained above to determine that the actual data must be the high-order value Lh(t) and the low-order value Minimum initial values Dh0, D10, coefficients mh, m1 in the range between L1(t).

In the determination step 1204 , the prediction model learning unit 111 determines whether or not to learn the prediction model for each area for all the learnable areas. When there is an area that has not yet been studied, it returns to the extraction step 1202 of the water distribution area. When learning is completed for all regions that can be learned, it proceeds to step 1205 of extracting a general prediction model.

In step 1205 of extracting a general predictive model, the predictive model learning unit 111 extracts one general predictive model to be learned.

In step 1206 of extracting forecast models for each area, the forecast model learning unit 111 extracts all the areas where the explanatory variable group used by the general forecast model of the learning target can be calculated, and extracts the forecast model for the area from these.

In general, the pipeline information storage unit 121 and the investigation/repair information storage unit 122 do not necessarily register all the information on all the pipes in terms of the characteristics of the water pipe business that the buried pipelines have been used for decades. Therefore, information required for calculation of specific explanatory variables is not registered for each region, and specific explanatory variables may not be calculated. Therefore, in the step 1206 of extracting the predictive model by region, the predictive model learning unit 111 extracts only the region and the predictive model by region for which all explanatory variable groups used can be calculated.

In the general prediction model learning step 1207 , the prediction model learning unit 111 learns the extracted general prediction model. In the learning of determining the coefficients of the general prediction model, learning is performed based on the extracted coefficients of the prediction model for each area. Hereinafter, the case of using the formula (2) in the prediction formula of the general forecast model and the case of using the formula (1) in all the forecast formulas of the respective forecast models will be described.

Set the index (index) of the extracted region and the forecast model by region to p, set the coefficients of the prediction formula (1) of each forecast model by region to L0p, kp, Dh0p, D10p, mhp, m1p, and set each forecast The values are set to Lp(t), Lhp(t), and L1p(t). In addition, the value in the area p of the explanatory variable of the index s is described as xsp, and the explanatory variable in the area p is collectively described as xp.

At this time, the prediction model learning unit 111 calculates α0, β0, αs, and βs so that equations (2d) and (2e) always reproduce the coefficients L0p and kp of the above-mentioned regional prediction models. Known techniques such as the least square method can be used for this calculation. Furthermore, the prediction model learning unit 111 determines the minimum coefficients Dh0 , D10 , mh , and m1 so that the following two expressions are satisfied for all regions p, using the prediction expression (2a) obtained above.

Lh(t, xp)≥Lhp(t)

L1(t, xp)≤L1p(t)

In the determination step 1208 , the prediction model learning unit 111 determines whether or not all general-purpose prediction models have been learned. When there is a general prediction model that has not yet been learned, return to the extraction step 1205 of extracting a general prediction model. When the learning is completed for all the common prediction models, it proceeds to the step 1209 of transmitting output information. In the output information sending step 1209 , the prediction model learning unit 111 sends the learned prediction model information to the prediction model storage unit 131 . In end step 1210 , the prediction model learning unit 111 ends the processing.

FIG. 13 is a flowchart showing the processing of the water leakage amount prediction unit 112 . In Fig. 13, it is shown that the water leakage prediction unit 112 predicts the future water leakage according to the prediction model, and selects the predicted water leakage information of the prediction model based on the result of the difference between the high value and the low value that is the smallest, and sends it to the investigation plan. The flow of operations up to the formulation unit 113 and the screen display unit 174 . In step start 1300, the leaked water amount prediction unit 112 starts processing.

In an input information receiving step 1301 , the water leakage amount prediction unit 112 receives prediction model information created by the prediction model storage unit 131 according to the flow shown in FIG. 12 . In addition, the leaked water amount prediction unit 112 receives information necessary for calculation of explanatory variables for each area from the pipeline information storage unit 121 , the investigation/repair information storage unit 122 and the like as necessary.

In step 1302 of extracting a water distribution area, the water leakage amount prediction unit 112 extracts one water distribution area (area) to be predicted as a water leakage amount. In the prediction model extraction step 1303 , the water leakage amount prediction unit 112 extracts all prediction models applicable to the extracted region from the received prediction model information.

In the general prediction model-based prediction step 1304 , the water leakage amount prediction unit 112 predicts the water leakage amount in the extracted region using the general prediction model among the extracted prediction models. Here, the prediction of the amount of water leakage using the general prediction model based on the water leakage amount prediction unit 112 refers to calculating the value of the required explanatory variable for the extracted region, and applying the calculated value of the explanatory variable to the general The prediction model is used to calculate the expected value, high value and low value of the predicted water leakage shown in Fig. 9 .

In determination step 1305 , the leaked water amount prediction unit 112 determines whether or not an area-specific prediction model applicable to the extracted area is included in the extracted prediction models. When it is included, it proceeds to the prediction step 1306 based on the forecast model by area, and when it is not included, it proceeds to the selection step 1307 of the prediction result.

In the prediction step 1306 based on the forecast model for each area, the water leakage amount prediction unit 112 predicts the amount of water leakage for the area extracted using the prediction model for each area. Here, the prediction of the amount of water leakage refers to the process of calculating the expected value, upper value, and lower value of the predicted water leakage amount shown in FIG. 9 , as in the case of the general prediction model.

In the prediction result selection step 1307, the water leakage amount prediction unit 112 compares the prediction results of the water leakage amount based on the extracted prediction models, selects the prediction model with the smallest difference between the high-level value and the low-level value, and uses the prediction model based on the selected prediction model. The predicted water leakage amount information is assumed to be the predicted water leakage amount information for the area.

In determination step 1308 , the water leakage amount prediction unit 112 determines whether or not to perform the process of predicting the water leakage amount for all areas. When there is an area that has not been subjected to the prediction process, it returns to the water distribution area extraction step 1302 . When the prediction processing for all regions is completed, the process proceeds to step 1309 of transmitting output information.

In the output information transmission step 1309 , the water leakage amount prediction unit 112 transmits the calculated water leakage amount prediction information to the investigation plan formulation unit 113 and the screen display unit 174 . In end step 1310 , the leaked water amount prediction unit 112 ends the processing.

In the water leakage amount prediction unit 112, when there are a plurality of prediction models that can be applied to a specific area, the predicted water leakage amount based on the prediction model with the smallest difference between the high-level value and the low-level value is output in the prediction step 1306 based on the prediction model for each area. information, thereby being able to output a predicted water leakage that is smaller than the uncertainty.

In addition, when the leakage amount prediction unit 112 plans to update the pipeline during the exclusive period for preparing the water leakage investigation plan, it may perform processing taking this information into consideration. For example, when the update of the pipeline affects the calculation result of the explanatory variable of the region, the forecast based on the general prediction model using the calculation result of the explanatory variable using the updated information of the pipeline can be output for the updated period.

FIG. 14 is a flowchart showing the processing of the survey plan formulation unit 113 . FIG. 14 shows the operation flow until the investigation plan formulation unit 113 sends the investigation plan storage unit 132 to the investigation plan storage unit 132 the water leakage investigation plan information obtained in consideration of costs related to the investigation of the amount of water leakage and the damage caused by the water leakage. In the start step 1400, the survey plan formulation unit 113 starts processing.

In the input information receiving step 1401 , the investigation plan formulation unit 113 receives the water leakage forecast information for each area created by the water leakage forecast unit 112 according to the flow in FIG.

In the optimization problem formation step 1402 , the investigation plan formulation unit 113 constitutes a mathematical optimization problem for formulating a water leakage investigation plan. As constraints on the mathematical optimization problem constituted by the survey planning unit 113 , the first is to set the total number of areas where water leakage surveys are simultaneously conducted to be equal to or less than the determined number of water leak survey groups regardless of the planning target period. The second is to continuously secure the period required for the water leakage investigation in all the areas in the area during which the water leakage investigation is performed in one area. The former considers labor costs involved in water leakage investigation, and the latter considers operational efficiency.

In addition, the objective function for minimizing the mathematical optimization problem constituted by the investigation plan formulation unit 113 can be set to, for example, the sum of evaluation values that take into account the cost of the water leakage investigation and the uncertainty of the water leakage amount prediction of the water leakage cost. the objective function of . Hereinafter, a specific example of the mathematical optimization problem constituted by the survey planning unit 113 will be described. As subscripts, an index a indicating a region and an index t for each month in a planning period (for example, three years) are used.

As a specific example of determining the period during which the water leakage investigation is carried out in each region during the planned target period as the water leakage investigation plan, the main decision variable can be set to be 1 only for the month t when the water leakage investigation starts in area a, and 0 otherwise. The binary variable y_{a,t} of .

When defining a binary variable z_{a, t} that only takes a value of 1 for the month t that conducts water leakage investigation in area a, and takes 0 otherwise, the relationship between y_{a, t} and z_{a, t} can be Take the following constraints.

【Formula 3】

${\mathrm{<span\; class="notranslate">\; z</span>}}_{\mathrm{<span\; class="notranslate">\; a</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; t</span>}}<span\; class="notranslate">\; =</span>{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; no</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}^{{\mathrm{<span\; class="notranslate">\; l</span>}}_{\mathrm{<span\; class="notranslate">\; a</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; a</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; t</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; no</span>}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 1</span>}}$

in,

1_a: the number of months required for the water leakage investigation in area a (positive integer)

Through this constraint formula, it is ensured continuously that the period of implementing the water leakage investigation in one area must be the length of the period required to complete the water leakage investigation in all areas of the area.

The constraints used to limit the total number of areas where water leakage investigations are simultaneously conducted can be described by the following formula.

【Formula 4】

${\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}_{\mathrm{<span\; class="notranslate">\; a</span>}}{\mathrm{<span\; class="notranslate">\; z</span>}}_{\mathrm{<span\; class="notranslate">\; a</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; t</span>}}<span\; class="notranslate">\; \&le;</span>\mathrm{<span\; class="notranslate">\; T</span>}$

in,

T: Number of water leakage investigation groups (positive integer)

The investigation plan formulation unit 113 may set the objective function f to be minimized by the mathematical optimization problem as the sum of the water leakage cost and the investigation cost using, for example, the predicted value CS of the investigation cost and the predicted value CW of the water leakage cost as evaluation indexes. constitutes the total cost.

f=CS+CW

Here, the investigation plan formulation unit 113 uses the water leakage investigation cost C_a of the region a registered in the cost information storage unit 125 as a predicted value of the investigation cost, and calculates, for example, as follows.

【Formula 5】

CS=Σ _a C _a Σ _t y _{a, t} · · · (3)

On the other hand, the investigation plan formulation unit 113 calculates the predicted value CW of the cost of water leakage based on predictions of both the expected value of the amount of water leakage and its uncertainty.

For example, a parameter expressing uncertainty between the upper value and the lower value is set for the calculation of the predicted water leakage amount in each region, and evaluation is performed in relation to the parameter and the water leakage cost. Calculate the maximum water leakage cost when the parameter takes any value in the predetermined uncertainty set.

Specifically, it is calculated as

【Formula 6】

CW＝w max _|δ|≤1 Σ _a Σ _t [(1-δ _a )Lh _a (t;{y _a,τ } _τ )+(1+δ _a )Ll _a (t;{y _a,τ } _τ )]/2 · · · (4)

here,

w: Marginal cost per unit amount of water leakage registered in the cost information storage unit 125

Lh_a(t; {y_{a, τ}}: the high value of the predicted water leakage in the region a of month t when the decision variable y_{a, t} is determined

L1_a(t; {y_{a, τ}}: the low value of the predicted water leakage in the region a of month t when the decision variable y_{a, t} is determined

Here, δ_a is a parameter expressing the uncertainty of region a, and the uncertainty set of parameters is: using vector δ arranged with parameters δ_a for all regions as elements, and the norm of δ is 1 or less. gather.

In addition, the specific calculation method of Lh_a and L1_a is as follows: the ratio of the upper value and the lower value of the water leakage determined by the elapsed time after the water leakage investigation/repair received from the water leakage amount prediction part 112 is registered in the water leakage amount prediction part The period of the last water leakage investigation and repair before the period of the water leakage investigation plan in 112 and the implementation time of the water leakage investigation and repair of the period of the water leakage investigation plan determined by the above-mentioned decision variables are obtained.

In the optimization problem solution step 1403, the investigation plan formulation unit 113 performs the optimization problem solution process constructed in the optimization problem composition step 1402, and converts the obtained optimal solution into water leakage investigation plan information. . Known techniques such as heuristic algorithms (metaheuristics) such as genetic algorithms or branch and bound methods (branch and bound) can be applied to the solution processing.

In an output information receiving step 1404 , the investigation plan formulation unit 113 transmits the calculated water leakage investigation plan information to the investigation plan storage unit 132 . In end step 1405 , the survey plan formulation unit 113 ends the processing.

The predicted value CW of water leakage cost is supplemented. Generally, when the objective function of the mathematical optimization problem is to use a water leakage investigation plan obtained by applying only the water leakage cost obtained by applying the expected value of the predicted water leakage amount, when the actual water leakage amount is separated from the predicted water leakage amount, the cost (mathematical optimization The value of the objective function of the problem) is significantly worse than the evaluation at the planned moment.

The water leakage cost using only the expected value is, for example, an objective function obtained by using CWA determined by the following formula

【Formula 7】

CWA＝w Σ _a Σ _t L _a (t; {y _{a, τ} }τ) ···(5)

here,

L_a(t; {y_{a, τ}}: The expected value of the predicted water leakage in the area a of month t when the decision variable {y_{a, t} is determined

Since the prediction of the amount of water leakage always includes uncertainty, the cost of applying the water leakage investigation plan using the above-mentioned expected value is almost always greater than the objective function value of the optimal solution of the mathematical optimization problem. Therefore, in the above-mentioned predicted value CW, the consideration method of robust optimization is applied to calculate the cost on the basis of typical errors in the predicted water leakage amount. By using such evaluation values to formulate a water leakage investigation plan, it can be expected that the actual application of the water leakage investigation plan will reduce the cost compared to the case of using evaluation values obtained by applying only the expected value of the predicted water leakage amount.

The predicted value CW of water leakage cost is not limited to the above. For example, the cost of water leakage could also be calculated by giving greater weight to the costs in areas of greater uncertainty. In addition, the structure of the mathematical optimization problem is not limited to the above. For example, it is possible to use a predicted value of water leakage cost as an objective function to minimize by setting a constraint condition with an upper limit on survey cost. As the objective function of the mathematical optimization problem, the water leakage cost of formula (5) can also be used to calculate the water leakage cost of formula (4).

FIG. 15 is a diagram showing a screen display of the screen display unit 174 based on the water leakage investigation plan. The water leakage investigation plan display screen 1501 displayed by the screen display unit 174 on a monitor or the like includes a water distribution block display 1502 , a cost display 1503 , and a water leakage investigation plan display 1504 .

In the water distribution block display 1502 , the screen display unit 174 cooperates with GIS to display the water pipe network, water distribution block, area, etc. on a map for the area to be planned by the water leakage investigation planning device 101 . In this example, water block 331 and water block 332 are shown.

The screen display unit 174 displays the cost evaluation result of the water leakage investigation plan on the cost display 1503 . In the row of the survey cost 1541, for example, the cost of the water leak survey calculated by the formula (3) is displayed. In the row of the loss cost 1542, the sum of the water leakage costs calculated by the formula (4), for example, is displayed. In the row of the total cost 1543, the sum of the above investigation cost and the above loss cost is displayed.

In the column of robust cost (robust cost) 1532, the cost evaluation value considering the uncertainty of prediction is displayed. For example, the evaluation value based on evaluation formula (4) is displayed in the evaluation of loss cost. On the other hand, in the column of the average cost 1533, the cost evaluation result of the water leakage investigation plan when the predicted average (expected value) is used is displayed. For example, in the evaluation of the loss cost, the evaluation value based on the evaluation formula (5) is displayed instead of the evaluation value based on the evaluation formula (4).

The screen display unit 174 displays a table of the water leakage investigation plan in the water leakage investigation plan display 1504 similarly to FIG. 11 .

FIG. 16 is a diagram showing the screen display of the screen display unit 174 based on the prediction result of the leaked water amount. The water leakage prediction display screen 1601 displayed by the screen display unit 174 on a monitor or the like includes a water distribution block display 1502 , a water leakage prediction table display 1603 , and a water leakage prediction icon display 1604 .

The screen display unit 174 displays the predicted transition of the water leakage amount by the water leakage amount prediction unit 112 in a table on the water leakage prediction table display 1603 . In the column of the area information 1631, area IDs to be predicted are displayed. In the column of the average predicted value 1632, the expected value of the predicted leakage amount is displayed. In the column of the high-order predicted value 1633, the high-order value of the predicted water leakage amount is displayed. In the column of the low predicted value 1633, the low value of the predicted water leakage amount is displayed. When the user of the water leakage investigation plan making device 101 performs an operation to change the time of the display object, the screen display unit 174 changes the time of the display object to the designated current (predicted time) or future time.

The screen display unit 174 displays, in the water leakage prediction icon display 1604 , the predicted transition of the water leakage amount by the water leakage amount prediction unit 112 by icons in the same manner as in FIG. 9 . In addition, the vertical line 1650 represents the time (current) when the water leakage investigation plan was prepared, the left side of the vertical line 1650 represents the past water leakage amount, and the right side of the vertical line 1650 represents the future water leakage amount prediction result. When the user of the water leakage investigation plan making device 101 performs an operation to change the region to be displayed, the screen display unit 174 changes the display so that the predicted result of the water leakage amount in the designated region is displayed.

In addition, the areas where the water leakage investigation plan preparation device 101 predicts the amount of water leakage or prepares the investigation plan do not need to be all areas of the water pipe network of the application destination. For example, it is possible to perform forecasting only for all areas, and perform survey planning only for some areas.

As described above, the water leakage investigation plan preparation device 101 can create a cost-effective water leakage investigation plan even when there is uncertainty about water leakage with limited resources through the above-mentioned configuration.

The above-mentioned embodiment is aimed at making an investigation plan for water pipe leaks, but the present invention is also applicable to making a maintenance plan for equipment other than water pipes, for example, making an investigation plan for gas leaks.

In addition, this invention is not limited to the said Example, Various modification examples are included. For example, the above-mentioned embodiments have been described in detail for ease of understanding, but are not limited to having all the structures described.

In addition, with regard to the above-mentioned structures, functions, processing units, processing units, etc., some or all of them may also be realized by hardware such as integrated circuit design, for example. In addition, each of the configurations and functions described above can also be realized by software when a processor analyzes and executes a program for realizing each function. Information such as programs, tables, and files for realizing various functions can be stored in storage devices such as memory, hard disk, SSD (Solid State Drive, solid state drive), or storage media such as IC cards, SD cards, and DVDs.

In addition, control lines or information lines are shown where it is considered necessary for illustration, but not all control lines or information lines must be shown on the product. In fact, it is also conceivable to connect almost all the components to each other.

Claims (10)

1. A water leakage investigation plan formulation device, which formulates a water leakage investigation plan for a plurality of areas with water pipe networks, characterized in that the water leakage investigation plan formulation device has: a measurement information collection unit that collects measurement information related to water flow from a measurement device including a flow meter installed on the water pipe network; a water usage storage unit that stores water usage information in the area; a leaked water amount estimating unit that estimates a leaked water amount of water in the area based on the measurement information and the water consumption information; a pipeline information storage unit storing pipeline information including extension information of a water pipeline network in the region; a survey/repair information storage unit that stores survey/repair information including surveys of water leaks in the region and the implementation period of pipeline repairs; a predictive model learning unit that generates predictive model information for predicting changes in the amount of water leakage in the region based on at least one of the water leakage amount information, the pipeline information, and the survey/repair information; a water leakage prediction unit that generates predicted water leakage information in the area based on the prediction model information; and an investigation plan formulation unit that prepares a water leakage investigation plan for determining an order of implementation of water leakage investigations in the plurality of areas based on the predicted water leakage amount information, The water leakage amount prediction unit generates a predicted value of both an expected value of the water leakage amount and an uncertainty of the expected value of the water leakage amount as the predicted water leakage amount information, The investigation plan preparation unit prepares the water leakage investigation plan using the water leakage cost calculated from both the expected value of the amount of water leakage and the predicted value of the uncertainty. 2. The water leakage investigation plan formulation device according to claim 1, characterized in that, The leaked water amount predicting unit generates predicted values of both the high and low value of the leaked water amount as an uncertainty predicted value of the expected value of the leaked water amount, The predictive model learning unit generates, as the predictive model information, a predictive formula for predicting an upper value and a lower value of the leakage amount and coefficients of the predictive formula. 3. The device for formulating a water leakage investigation plan according to claim 2, wherein: When there are a plurality of prediction models that can be applied to one area, the water leakage prediction unit selects and generates a prediction with the smallest difference between the high level value of the water leakage volume and the low level value of the water leakage volume among the corresponding prediction models. Leakage information. 4. The water leakage investigation plan formulation device according to claim 3, characterized in that, In the predictive model learning section, Each prediction model of the generated prediction model information is one of a regional prediction model and a general prediction model, wherein the regional prediction model is a model that can be applied to a specific region, and the general prediction model is a model that can be applied to a plurality of regions by substituting explanatory variables of regions calculated from the pipe network information and the survey/repair information, The coefficients of the general prediction model are learned and determined based on the predetermined coefficients of the prediction model for each region. 5. The water leakage investigation plan formulation device according to claim 4, characterized in that, The survey plan formulation department decides the period to carry out the survey of water leaks in each area among the planned target periods as the prepared survey plan for water leaks, The investigation plan formulation department formulates a water leakage investigation plan that satisfies the first constraint condition and the second constraint condition, wherein the first constraint condition refers to that the total number of areas where the water leakage investigation is carried out at the same time in each period of the plan object period is the determined water leakage When the number of investigation groups is less than or equal to the number of investigation groups, the second constraint condition means that the period for continuously securing the water leakage investigation in one area is the period required to complete the water leakage investigation for all the areas in the area. 6. The water leakage investigation plan formulation device according to claim 5, characterized in that, The investigation plan formulation unit formulates the water leakage investigation plan such that the total cost constituted by the sum of the water leakage cost and the investigation cost is the smallest. 7. The water leakage investigation plan formulation device according to claim 6, characterized in that, When evaluating the cost of water leakage as the evaluation index, the survey planning department sets a parameter representing the uncertainty between the high value and the low value in the predicted water leakage amount of each region, and compares the parameter with the water leakage cost evaluation in the relationship. 8. The water leakage investigation plan formulation device according to claim 7, characterized in that, The predictive model learning unit uses the number of water leak repairs in the area, the number of reported water leak repairs in the area, the number of water supply pipes in the area, the age of the oldest pipe in the area, the number of aging pipes, and the total length of the aging pipes. At least one of them is used as the explanatory variable used in the learning of the general predictive model. 9. A system for formulating a water leakage investigation plan, characterized in that it has: The device for formulating a water leakage investigation plan according to claim 1; a measuring device including a flow meter that transmits measurement information to the water leakage investigation planning device; and An investigation terminal that sends investigation/repair information to the water leakage investigation planning device, wherein the investigation/repair information includes a location of a water leak found through a water leakage investigation. 10. A method for formulating a water leakage investigation plan, which is used to formulate a water leakage investigation plan for a plurality of regions with water pipe networks, characterized in that the method for formulating a water leakage investigation plan has the following steps: A collection step collects measurement information related to water flow; a storing step of storing water usage information in said region; an estimating step of estimating an amount of water leakage in the area based on the measurement information and the water consumption information; a pipeline information accumulation step of accumulating pipeline information including extension information of the water pipeline network in the region; An investigation/repair information accumulation step of accumulating investigation/repair information including the implementation period of water leakage investigation and pipeline repair in the area; A predictive model information generating step of generating predictive model information for predicting changes in the water leakage in the area based on at least one of the water leakage information, the pipeline information, and the survey/repair information; A step of generating predicted water leakage information, generating predicted water leakage information in the area according to the predicted model information; and a formulating step of formulating a water leakage investigation plan based on the predicted water leakage information, the water leakage investigation plan determining the order of implementation of the water leakage investigation in the plurality of areas, In the step of generating the predicted water leakage amount information, a predicted value of both an expected value of the water leakage amount and an uncertainty of the expected value of the water leakage amount is generated as the predicted water leakage amount information, In the formulating step, the water leakage investigation plan is formulated using the water leakage cost calculated based on both the expected value of the water leakage amount and the predicted value of the uncertainty.