Buried environment classification map creation device, buried pipe deterioration prediction device, buried environment classification map creation method, buried pipe deterioration prediction method and program

Abstract

To provide an embedded pipe deterioration prediction device which enables more accurate prediction of deterioration of an embedded pipe.SOLUTION: An embedded pipe deterioration prediction device 1 comprises an embedded pipe deterioration calculation unit 132. The embedded pipe deterioration calculation unit 132 calculates deterioration of each of embedded pipes, from burying environment of each of the embedded pipes identified by an optimization burying environment classification map 58a, and an embedded pipe deterioration prediction model. The optimization burying environment classification map 58a is created by optimizing a burying environment classification of foundations of a portion of a general burying environment classification map 56a by machine learning. Some foundations are selected on the basis of water leakage accident data 53 which are past results of water leakage accidents of each of the embedded pipes.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to a buried environment classification map creation device, a buried pipe deterioration degree prediction device, a buried environment classification map creation method, a buried pipe deterioration degree prediction method, and a program. [Background technology]

[0002] Pipes such as water pipes are buried in the soil. The pipes corrode over a long period of use. Japanese Patent Laid-Open Publication No. 2007-107882 (Patent Document 1) discloses a method for predicting corrosion of buried pipes. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2007-107882 Summary of the Invention [Problem to be solved by the invention]

[0004] The object of the present disclosure is to provide a buried environment classification map creation device, a buried pipe deterioration prediction device, a buried environment classification map creation method, a buried pipe deterioration prediction method, and a program that enable more accurate prediction of the deterioration of buried pipes. [Means for solving the problem]

[0005] The buried environment classification map creation device of the present disclosure includes a first map creation unit and a second map creation unit. The first map creation unit creates a general buried environment classification map for an area corresponding to the pipeline map from a pipeline map, which is a map of buried pipes, and a publicly available ground map. The second map creation unit includes a ground selection unit and an optimized buried environment classification map generation unit. The ground selection unit selects a portion of the ground in the general buried environment classification map based on water leakage accident data, which is the past record of water leakage accidents for each buried pipe. The optimized buried environment classification map generation unit generates a buried environment classification map optimized for the area corresponding to the pipeline map by optimizing the buried environment classification of the portion of the ground using machine learning.

[0006] The buried pipe deterioration prediction device disclosed herein includes a buried pipe deterioration calculation unit. The buried pipe deterioration calculation unit calculates the deterioration level of each buried pipe based on the buried environment of each buried pipe identified by a buried environment classification map optimized for a region corresponding to a pipeline map, which is a map of buried pipes, first information related to the buried period of each buried pipe, second information related to the pipe thickness of each buried pipe, and a buried pipe deterioration prediction model. The optimized buried environment classification map is created by optimizing the buried environment classification of a portion of the ground in a general buried environment classification map for the region corresponding to the pipeline map using machine learning. The general buried environment classification map is created from the pipeline map and a publicly available ground map. The portion of the ground is selected from the general buried environment classification map based on water leakage accident data, which is the past record of water leakage accidents for each buried pipe.

[0007] The buried environment classification map creation method of the present disclosure includes the steps of creating a general buried environment classification map for an area corresponding to the pipeline map from a pipeline map, which is a map of buried pipes, and a publicly available ground map; selecting a portion of the ground for the general buried environment classification map based on leak accident data, which is the past history of leak accidents for each buried pipe; and generating a buried environment classification map optimized for the area corresponding to the pipeline map by optimizing the buried environment classification of the portion of the ground using machine learning.

[0008] The buried pipe deterioration prediction method disclosed herein includes a step of calculating the deterioration level of each buried pipe from the buried environment of each buried pipe identified by a buried environment classification map optimized for a region corresponding to a pipeline map, which is a map of buried pipes, first information related to the buried period of each buried pipe, second information related to the pipe thickness of each buried pipe, and a buried pipe deterioration prediction model. The optimized buried environment classification map is created by optimizing the buried environment classification of a portion of the ground in the general buried environment classification map for the region using machine learning. The general buried environment classification map is created from the pipeline map and a publicly available ground map. The portion of the ground is selected from the general buried environment classification map based on water leakage accident data, which is the past history of water leakage accidents for each buried pipe.

[0009] The program of the present disclosure causes a processor to execute each step of the buried environment classification map creation method of the present disclosure.

[0010] The program of the present disclosure causes a processor to execute each step of the buried pipe deterioration prediction method of the present disclosure. [Effects of the Invention]

[0011] The buried environment classification map creation device, buried pipe deterioration prediction device, buried environment classification map creation method, buried pipe deterioration prediction method, and program disclosed herein enable more accurate prediction of the deterioration of buried pipes. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a schematic diagram illustrating a hardware configuration of a buried pipe deterioration prediction device according to an embodiment. [Figure 2] 1 is a block diagram illustrating the functional configuration of a buried pipe deterioration prediction device according to an embodiment. [Figure 3] 2 is a block diagram illustrating the functional configuration of a correspondence table creation unit of a buried pipe deterioration prediction device according to an embodiment. FIG. [Figure 4] 3 is a block diagram illustrating the functional configuration of a second map creation unit of the buried pipe deterioration prediction device according to the embodiment. FIG. [Figure 5] 2 is a block diagram illustrating the functional configuration of a fitness calculation unit of the buried pipe deterioration prediction device according to the embodiment. FIG. [Figure 6] 2 is a block diagram illustrating the functional configuration of a memory unit of a buried pipe deterioration prediction device according to an embodiment. FIG. [Figure 7] FIG. 2 is a diagram illustrating an example of the data structure of investigation pipe data. [Figure 8] FIG. 2 is a schematic diagram illustrating a ground map. [Figure 9] FIG. 10 is a diagram showing an example of the data structure of a ground information-ground ID-corrosion rate-burial environment correspondence table. [Figure 10] FIG. 1 shows a box plot depicting the relationship between burial environment and corrosion rate. [Figure 11] FIG. 10 is a diagram showing a pipeline map. [Figure 12] FIG. 10 is a diagram illustrating an example of a data structure of buried pipe attribute data. [Figure 13] FIG. 10 is a diagram illustrating an example of a data structure of water leakage accident data. [Figure 14] FIG. 10 is a diagram showing a general integration map. [Figure 15] FIG. 10 is a diagram showing an optimized integrated map. [Figure 16] FIG. 10 is a diagram illustrating an example of the data structure of nominal pipe thickness data. [Figure 17] FIG. 10 is a diagram showing an example of calculating an estimated water leakage accident rate using a water leakage accident rate prediction model. [Figure 18] 10 is a diagram showing an example of buried pipe deterioration degree prediction results (buried pipe deterioration degree prediction table). FIG. [Figure 19] FIG. 10 is a diagram showing an example of buried pipe deterioration degree prediction results (buried pipe deterioration degree prediction map). [Figure 20] FIG. 10 is a flowchart illustrating a correspondence table creation method according to an embodiment. [Figure 21] FIG. 10 is a flowchart illustrating a method for creating an optimized integrated map according to an embodiment. [Figure 22] FIG. 10 is a flowchart illustrating steps for creating an optimized integrated map according to an embodiment. [Figure 23]FIG. 10 is a flowchart showing steps for selecting a soil ID that is a candidate for optimization of buried environment classification. [Figure 24] FIG. 10 is a flowchart illustrating an example of steps for excluding ground IDs that do not require a change in buried environment classification. [Figure 25] FIG. 10 is a flowchart showing steps for calculating the estimated number of water leakage accidents. [Figure 26] FIG. 10 is a diagram illustrating an example of a data structure of first preprocessed buried pipe data. [Figure 27] FIG. 10 is a flowchart showing steps for creating first preprocessed buried pipe data. [Figure 28] FIG. 10 is a flowchart showing steps for optimizing the buried environment classification of a ground ID selected as a candidate for optimization of the buried environment classification by machine learning. [Figure 29] FIG. 10 is a diagram showing examples of genes for each of multiple buried environment map candidates. [Figure 30] FIG. 1 shows a flowchart of the steps for generating a new generation population. [Figure 31] FIG. 10 is a flowchart showing steps for calculating the fitness of each individual that constitutes the current generation population. [Figure 32] FIG. 10 is a diagram illustrating an example of the data structure of second preprocessed buried pipe data. [Figure 33] FIG. 10 is a flowchart showing steps for creating second preprocessed buried pipe data. [Figure 34] FIG. 10 is a diagram illustrating an example of a data structure of an estimated water leakage accident rate result for an individual. [Figure 35] FIG. 10 is a diagram illustrating an example of the fitness of an individual. [Figure 36] FIG. 1 is a flowchart illustrating a buried pipe deterioration degree prediction method according to an embodiment. [Figure 37] FIG. 10 is a flowchart showing steps for calculating an estimated water leakage accident rate. [Figure 38] FIG. 10 is a diagram illustrating an example of the data structure of third preprocessed buried pipe data. [Figure 39]FIG. 10 is a flowchart showing steps for creating third preprocessed buried pipe data. [Figure 40] FIG. 10 is a diagram showing an example of calculating the degree of deterioration of a buried pipe using a buried pipe deterioration degree prediction model. [Figure 41] FIG. 10 is a diagram showing a schematic configuration of a buried pipe deterioration prediction system according to a modified example of an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, embodiments of the present disclosure will be described. Note that the same reference numerals are used to designate the same components, and the description thereof will not be repeated.

[0014] A buried pipe deterioration degree prediction device 1 will be described with reference to Figures 1 to 6. The buried pipe deterioration degree prediction device 1 is a device that predicts the degree of deterioration of a buried pipe. In this embodiment, the buried pipe deterioration degree prediction device 1 also functions as a buried environment classification map creation device 2 and a correspondence table creation device 3. The buried environment classification map creation device 2 is a device that creates an optimized buried environment classification map 58a (see Figure 15). The correspondence table creation device 3 is a device that creates a ground information-ground ID-corrosion rate-buried environment correspondence table 46 (hereinafter simply referred to as "correspondence table 46"; see Figure 9).

[0015] <Hardware configuration>

[0016] 1, the hardware configuration of the buried pipe deterioration prediction device 1 will be described. The buried pipe deterioration prediction device 1 includes an input device 11, a processor 12, a memory 13, a display 14, a network controller 16, a storage medium drive 17, and a storage 19.

[0017] The input device 11 accepts various input operations and is, for example, a keyboard, a mouse, or a touch panel.

[0018] The display 14 displays information necessary for processing in the buried pipe deterioration prediction device 1. The display 14 displays, for example, an optimized integrated map 58 (see FIG. 15) and buried pipe deterioration prediction results 65 (see FIGS. 18 and 19). The display 14 is, for example, an LCD (Liquid Crystal Display) or an organic EL (Electroluminescence) display.

[0019] The processor 12 executes a program described below to perform processing required to realize the functions of the buried pipe deterioration prediction device 1. The processor 12 is configured by, for example, a CPU or a GPU.

[0020] The memory 13 provides a storage area for temporarily storing program code, work memory, etc. when the processor 12 executes a program. The memory 13 is, for example, a volatile memory device such as a DRAM (Dynamic Random Access Memory) or an SRAM (Static Random Access Memory).

[0021] The network controller 16 transmits and receives programs or data to and from an external device (not shown) via a communication network (not shown) such as the Internet or an intranet. For example, the network controller 16 transmits an optimized integrated map 58 (see FIG. 15 ) and buried pipe deterioration prediction results 65 (see FIGS. 18 and 19 ) to the external device via the communication network. The network controller 16 may also receive buried pipe data 50 (see FIGS. 11 and 12 ) from a customer (e.g., a water utility) via the communication network. The network controller 16 supports any communication method, such as Ethernet (registered trademark), wireless LAN, or Bluetooth (registered trademark).

[0022] The storage medium drive 17 is a device that reads out programs or data stored in the storage medium 18. The storage medium drive 17 may also be a device that writes programs or data to the storage medium 18. The storage medium 18 is a non-transitory storage medium that stores programs or data in a non-volatile manner. The storage medium 18 is, for example, an optical storage medium such as an optical disk (e.g., a CD-ROM or a DVD-ROM), a semiconductor storage medium such as a flash memory or a USB memory, a magnetic storage medium such as a floppy disk (FD) or a storage tape, or a magneto-optical storage medium such as an MO (Magneto-Optical) disk.

[0023] The storage 19 is a non-volatile memory device such as a hard disk or a solid-state drive (SSD). The storage 19 stores the following: inspection pipe data 40 (see FIG. 7), a ground map 42 (see FIG. 8), a correspondence table 46 (see FIG. 9), buried pipe data 50 (see FIGS. 11 and 12), a general integrated map 56 (see FIG. 14), an optimized integrated map 58 (see FIG. 15), nominal pipe thickness data 60 (see FIG. 16), a water leakage accident rate prediction model 28 (see FIGS. 6, 17, and 40), a buried pipe deterioration degree prediction result 65, and programs executed by the processor 12. The programs include a buried environment classification map creation program 31 (see FIG. 6), a buried pipe deterioration degree prediction program 32 (see FIG. 6), and a correspondence table creation program 33 (see FIG. 6).

[0024] Programs for realizing the functions of the buried pipe deterioration prediction device 1, such as the buried environment classification map creation program 31 (see FIG. 6), the buried pipe deterioration prediction program 32 (see FIG. 6), and the correspondence table creation program 33 (see FIG. 6), may be stored in a non-transitory storage medium 18 and distributed, and installed in the storage 19. Programs for realizing the functions of the buried pipe deterioration prediction device 1, such as the buried environment classification map creation program 31, the buried pipe deterioration prediction program 32, and the correspondence table creation program 33, may be downloaded to the buried pipe deterioration prediction device 1 via the Internet or an intranet.

[0025] In this embodiment, an example is shown in which a general-purpose computer (processor 12) executes a program to realize the functions of the buried pipe deterioration prediction device 1. All or part of the functions of the buried pipe deterioration prediction device 1 may be realized using an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0026] <Functional configuration>

[0027] 2 to 19, an example of the functional configuration of the buried pipe deterioration degree prediction device 1 will be described. Referring to Fig. 2, the buried pipe deterioration degree prediction device 1 includes a storage unit 20, a correspondence table creation unit 90, a buried pipe data reception unit 99, a map creation unit 100, and a buried pipe deterioration degree prediction unit 130.

[0028] <Storage section 20>

[0029] The memory unit 20 is realized by a storage 19 (see FIG. 1) or a storage medium 18 (see FIG. 1). Referring to FIG. 6, the memory unit 20 includes an investigation pipe data memory unit 21, a ground map database unit 22, a correspondence table memory unit 23, a buried pipe data memory unit 24, a map memory unit 25, a nominal pipe thickness database unit 26, a water leakage accident rate prediction model memory unit 27, a buried pipe deterioration degree prediction result memory unit 29, and a program memory unit 30.

[0030] 6 and 7, the inspection pipe data storage unit 21 stores inspection pipe data 40. The inspection pipe is, for example, a water pipe. The inspection pipe is buried in the soil. The inspection pipe data 40 is, for example, pipe inspection data obtained by test boring pipes at numerous inspection sites (for example, approximately 6,000 inspection sites) throughout Japan. The inspection pipe data 40 includes the inspection number, the address of the inspection site, the soil type and soil resistivity, the corrosion depth and installation year of the inspection pipe, and the inspection year. The address of the inspection site is the address of the site where the inspection pipe is buried. The soil type is the type of soil in which the inspection pipe is buried. The soil resistivity is the resistivity of the soil in which the inspection pipe is buried. The inspection year is the year in which the corrosion depth of the inspection pipe was inspected. The inspection pipe data 40 is provided, for example, by the storage medium 18 (see FIG. 1) or via a communication network such as the Internet or an intranet.

[0031] 6 and 8, the ground map database unit 22 stores a ground map 42. The ground map 42 includes, for example, a surface geological map 43 and a topography classification map 44. The surface geological map 43 is a map showing the geology of the earth's surface. The surface geological map 43 includes, for example, major classifications and minor classifications. The topography classification map 44 is a map showing the topography. The topography classification map 44 includes, for example, major classifications and minor classifications. The surface geological map 43 and the topography classification map 44 are provided by public institutions such as the Ministry of Land, Infrastructure, Transport and Tourism, and are publicly available.

[0032] 6 and 9, a correspondence table 46 is stored in the correspondence table storage unit 23. The correspondence table 46 is created from the investigation pipe data 40 and the ground map 42. In the correspondence table 46, ground information, ground ID, typical corrosion rate, and buried environment are associated with each other.

[0033] The ground information is, for example, a combination of the surface geology and topography at the address of the survey location (see Figure 7). A ground ID is assigned corresponding to the ground information. The representative corrosion rate for each ground ID is, for example, the average corrosion rate for each ground ID or the median corrosion rate for each ground ID. The average corrosion rate for each ground ID is the average corrosion rate of the survey pipes assigned the same ground ID. The median corrosion rate for each ground ID is the 50th percentile of the corrosion rates of the survey pipes assigned the same ground ID.

[0034] In the correspondence table 46, the investigation pipe data 40 is classified into four burial environments, AD, based on the soil type (see Figure 7) and soil resistivity (see Figure 7). Burial environment A represents soil with a soil resistivity of less than 1500 Ω·cm or soil with a corrosive property equivalent to that of the soil for buried pipes. Burial environment B represents clay soil with a soil resistivity of 1500 Ω·cm or more or soil with a corrosive property equivalent to that of the clay soil for buried pipes. Burial environment C represents silt soil with a soil resistivity of 1500 Ω·cm or more or soil with a corrosive property equivalent to that of the silt soil for buried pipes. Burial environment D represents sand soil with a soil resistivity of 1500 Ω·cm or more or soil with a corrosive property equivalent to that of the sand soil for buried pipes.

[0035] The soils in which the pipes are buried are classified into four burial environments AD for the following two reasons. The first reason is that the inventors analyzed the survey pipe data 40 and found that there is a statistically significant correlation between the burial environment AD and the corrosion rate of the pipes, as shown in Figure 10. The second reason is that the number of survey data that fall into the four burial environments AD accounts for the majority (80% or more) of the total number of survey data.

[0036] As shown in Figure 10, the median corrosion rate of soil classified as buried environment A is the highest among all medians for buried environments AD. Burial environment A is the most corrosive to buried pipes among all buried environments AD. The median corrosion rate of soil classified as buried environment B is the second highest among all medians for buried environments AD. The median corrosion rate of soil classified as buried environment B is the third lowest among all medians for buried environments AD. Buried environment B is less corrosive to buried pipes than buried environment A, and more corrosive to buried pipes than buried environments C and D. The median corrosion rate of soil classified as buried environment C is the second lowest among all medians for buried environments AD. Buried environment C is less corrosive to buried pipes than buried environments A and B, and more corrosive to buried pipes than buried environment D. The median corrosion rate of soils classified as Burial Environment D is the smallest among all the medians of Burial Environment AD. Burial Environment D is the least corrosive to buried pipes among all the Burial Environment AD.

[0037] 6 and 11 to 13, buried pipe data storage unit 24 stores buried pipe data 50 (see FIGS. 11 and 12) and water leakage accident data 53 (see FIG. 13). The purpose of the buried pipe is the same as the purpose of the investigation pipe, and the buried pipe is, for example, a water pipe. The buried pipe is buried in the soil.

[0038] The buried pipe data 50 includes, for example, a pipe map 51 (see FIG. 11) and buried pipe attribute data 52 (see FIG. 12).

[0039] 11, the pipeline map 51 is a map of buried pipes managed by a customer, and includes the pipeline IDs of the buried pipes and the addresses of the buried pipes (buried locations). In the pipeline map 51, the pipeline IDs of the buried pipes and the addresses of the buried pipes are associated with each other, and the addresses of the buried pipes are displayed on the map for each pipeline ID of the buried pipe.

[0040] Referring to FIG. 12, buried pipe attribute data 52 includes first information related to the buried period of the buried pipe and second information related to the thickness of the buried pipe. The buried pipe attribute data 52 includes, for example, the pipeline ID and pipeline length of the buried pipe, the year the buried pipe was installed as the first information, and the nominal diameter, joint type, and type of pipe thickness of the buried pipe as the second information. In the buried pipe attribute data 52, the pipeline ID, year of installation, nominal diameter, joint type, type of pipe thickness, and pipeline length are associated with each other. The year the buried pipe was installed is the year the buried pipe was installed (buried). Examples of joint types include A-type, K-type, T-type, and NS-type. Examples of pipe thickness types include type 1, type 2, and type 3. The pipeline length is the length of the buried pipe.

[0041] 13, the water leakage accident data 53 is the past record of water leakage accidents for each buried pipe. The water leakage accident data 53 includes, for example, a water leakage accident map 54 and the start and end dates of a water leakage accident data collection period 55. The water leakage accident map 54 is a map in which the locations where water leakage accidents occurred within the water leakage accident data collection period 55 are indicated on the pipeline map 51.

[0042] The map storage unit 25 stores a general integrated map 56 (see FIG. 14) of the area corresponding to the pipeline map 51, and an optimized integrated map 58 (see FIG. 15) of the area corresponding to the pipeline map 51.

[0043] 14, the general integrated map 56 is a map obtained by integrating the pipeline map 51, the general buried environment classification map 56a of the area corresponding to the pipeline map 51, and the ground ID map 56b of the area corresponding to the pipeline map 51. The general buried environment classification map 56a is a map showing the buried environment of the area corresponding to the pipeline map 51. The ground ID map 56b is a map showing the ground ID of the area corresponding to the pipeline map 51.

[0044] 15, the optimized integrated map 58 is a map obtained by integrating the pipeline map 51, the optimized buried environment classification map 58a of the area corresponding to the pipeline map 51, and the ground ID map 56b of the area corresponding to the pipeline map 51. The optimized buried environment classification map 58a is generated by optimizing the buried environment classification of the general buried environment classification map 56a using the water leakage accident data 53.

[0045] 6 and 16, the nominal pipe thickness database unit 26 stores nominal pipe thickness data 60. The nominal pipe thickness data 60 includes, for example, the year of pipe installation, nominal diameter, joint type, pipe thickness type, and nominal pipe thickness. In the nominal pipe thickness data 60, the year of pipe installation, nominal diameter, joint type, pipe thickness type, and nominal pipe thickness are associated with each other. The nominal pipe thickness of a pipe is the standard pipe thickness of the pipe.

[0046] 6, the water leakage accident rate prediction model storage unit 27 stores a plurality of water leakage accident rate prediction models 28 that differ from one another according to the buried environment and the nominal pipe thickness. The water leakage accident rate prediction models 28 include, for example, a water leakage accident rate prediction model for buried environment A, a water leakage accident rate prediction model for buried environment B, a water leakage accident rate prediction model for buried environment C, and a water leakage accident rate prediction model for buried environment D. The water leakage accident rate prediction model for buried environment A, the water leakage accident rate prediction model for buried environment B, the water leakage accident rate prediction model for buried environment C, and the water leakage accident rate prediction model for buried environment D each include a plurality of water leakage accident rate prediction models according to the nominal pipe thickness. FIG. 17 shows an example of the plurality of water leakage accident rate prediction models 28. The multiple water leakage accident rate prediction models 28 are not particularly limited, but may be, for example, the water leakage accident rate prediction model disclosed in Patent Publication No. 2021-56224, or the buried pipe water leakage accident rate estimation formula provided by the Water Technology Research Center, a public interest incorporated foundation.

[0047] The buried pipe leakage accident rate estimation formula provided by the Japan Water Research Center, a public interest incorporated foundation, is given by the following formula (1). y represents the pipe leakage accident rate (events / km / year), C1 represents a correction coefficient related to the pipe specifications, C2 represents a correction coefficient related to the pipe diameter, C3 represents a correction coefficient related to the ground conditions in which the pipe is buried, and f(T) represents the standard accident rate curve for each pipe type. f(T) is given by the following formula (2). T represents the length of time the pipe has been buried, and coefficients a and b represent coefficients for each pipe type that indicate the degree of increase in the leakage accident rate over time.

[0048] y=C1·C2·C3·f(T) (1)

[0049] f(T)=a T b (2)

[0050] 6, buried pipe deterioration degree prediction result storage unit 29 stores buried pipe deterioration degree prediction result 65. Buried pipe deterioration degree prediction result 65 may be a buried pipe deterioration degree prediction table 66 (see FIG. 18), a buried pipe deterioration degree prediction map 67 (see FIG. 19), or both.

[0051] The program storage unit 30 stores programs for realizing the functions of the buried pipe deterioration prediction device 1. The programs for realizing the functions of the buried pipe deterioration prediction device 1 include, for example, a buried environment classification map creation program 31, a buried pipe deterioration prediction program 32, and a correspondence table creation program 33.

[0052] <Correspondence table creation unit 90>

[0053] 2 and 3, a correspondence table creation unit 90 creates a correspondence table 46 (see FIG. 9) from the investigation pipe data 40 (see FIG. 7) and a publicly available ground map 42 (see FIG. 8). The correspondence table creation unit 90 includes a corrosion rate calculation unit 91, a ground information acquisition unit 92, a ground ID assignment unit 93, a representative corrosion rate calculation unit 94, a buried environment classification unit 95, a correspondence table generation unit 96, and a correspondence table output unit 97.

[0054] The corrosion rate calculation unit 91 calculates the corrosion rate of the investigation pipe for each investigation number (see FIG. 7). For example, the corrosion rate calculation unit 91 calculates the buried period of the investigation pipe as the difference between the investigation year (see FIG. 7) and the installation year of the investigation pipe (see FIG. 7). The corrosion rate calculation unit 91 calculates the corrosion rate of the investigation pipe by dividing the corrosion depth of the investigation pipe (see FIG. 7) by the buried period of the investigation pipe.

[0055] The ground information acquisition unit 92 obtains ground information at the address of the survey point (see FIG. 7) by referring to the survey pipe data 40 (see FIG. 7) and the ground map database unit 22. The ground ID assignment unit 93 assigns a ground ID corresponding to the ground information (for example, a combination of surface geology and topography).

[0056] The representative corrosion rate calculation unit 94 calculates a representative corrosion rate for each ground ID. The representative corrosion rate for each ground ID is, for example, the average corrosion rate for each ground ID or the median corrosion rate for each ground ID. When the representative corrosion rate for each ground ID is the average corrosion rate for each ground ID, the representative corrosion rate calculation unit 94 calculates the average corrosion rate of the investigation pipes assigned the same ground ID. When the representative corrosion rate for each ground ID is the median corrosion rate for each ground ID, the representative corrosion rate calculation unit 94 calculates the 50th percentile of the corrosion rate of the investigation pipes assigned the same ground ID.

[0057] The buried environment classification unit 95 classifies the investigation pipe data 40 into four buried environments, A, D, and E, based on the soil type (see FIG. 7) and soil resistivity (see FIG. 7). The correspondence table generation unit 96 creates a correspondence table 46 (see FIG. 9) by correlating the ground information, ground ID, typical corrosion rate, and buried environment. The correspondence table output unit 97 outputs the correspondence table 46 to the correspondence table storage unit 23 (see FIG. 6).

[0058] <Buried Pipe Data Reception Department 99>

[0059] Referring to FIG. 2, the buried pipe data receiving unit 99 receives buried pipe data 50 (see FIGS. 11 and 12) and water leakage incident data 53 (see FIG. 13) from a customer. The buried pipe data 50 and water leakage incident data 53 are provided by the customer, for example, via a storage medium 18 (see FIG. 1) or via a communication network such as the Internet or an intranet. The buried pipe data receiving unit 99 outputs the buried pipe data 50 and water leakage incident data 53 to the buried pipe data storage unit 24 (see FIG. 6). The buried pipe data 50 and water leakage incident data 53 may be stored in advance in the storage 19 (see FIG. 1).

[0060] <Map Creation Department 100>

[0061] Referring to FIG. 2, map creation unit 100 includes a first map creation unit 101 and a second map creation unit 102.

[0062] <First map creation unit 101>

[0063] Referring to Figure 2, the first map creation unit 101 creates a general integrated map 56 (see Figure 14) from the pipeline map 51 (see Figure 11), the ground map 42 (see Figure 8), and the correspondence table 46 (see Figure 9).

[0064] Specifically, the first map creation unit 101 reads a pipeline map 51 (see FIG. 11) from the buried pipe data storage unit 24 (see FIG. 6). The first map creation unit 101 reads a ground map 42 (e.g., a surface geological map 43 and a topography classification map 44) of the area corresponding to the pipeline map 51 from the ground map database unit 22 (see FIGS. 6 and 8). The first map creation unit 101 reads a correspondence table 46 (see FIG. 9) from the correspondence table storage unit 23. The first map creation unit 101 overlays the buried environment and ground ID of the area corresponding to the pipeline map 51 on the pipeline map 51 to create a general integrated map 56 (see FIG. 14).

[0065] The general integrated map 56 is a map obtained by integrating the pipeline map 51, the general buried environment classification map 56a of the area corresponding to the pipeline map 51, and the ground ID map 56b of the area corresponding to the pipeline map 51. The general buried environment classification map 56a is a map showing the buried environment of the area corresponding to the pipeline map 51. The ground ID map 56b is a map showing the ground ID of the area corresponding to the pipeline map 51. The first map creation unit 101 outputs the general integrated map 56 to the map storage unit 25 (see FIG. 6).

[0066] <Second map creation unit 102>

[0067] 2 and 4, the second map creation unit 102 creates an optimized integrated map 58 (see FIG. 15) of the area corresponding to the pipeline map 51 by optimizing the buried environment classification of the general integrated map 56 (general buried environment classification map 56a). The second map creation unit 102 includes a ground selection unit 103, an optimized buried environment classification map generation unit 110, an optimized integrated map generation unit 116, and an optimized integrated map output unit 118.

[0068] 4, the ground selection unit 103 selects a ground ID that is a candidate for optimization of the buried environment classification from all ground IDs included in the general integrated map 56. Referring to FIG. 4, the ground selection unit 103 includes a data preprocessing unit 104, an estimated water leakage accident number calculation unit 105, an actual water leakage accident number calculation unit 106, and a determination unit 107.

[0069] The data preprocessing unit 104 (see Figure 4) creates first preprocessed buried pipe data 70 (see Figure 26) from the general integrated map 56 (see Figure 14), buried pipe data 50 (see Figures 11 and 12), and water leakage accident data 53 (see Figure 13).

[0070] Referring to Fig. 4, the estimated water leakage accident number calculation unit 105 calculates the estimated number of water leakage accidents per unit time during the water leakage accident data collection period 55 (see Fig. 13) for each second tentative candidate for the ground ID, which will be described later. The estimated number of water leakage accidents per unit time is the estimated number of water leakage accidents that will occur in each second tentative candidate for the ground ID per unit time. For example, the unit time is one year, and the unit of the estimated number of water leakage accidents is cases / year.

[0071] 4, the water leakage accident actual number calculation unit 106 calculates the number of water leakage accidents per unit time during the water leakage accident data collection period 55 (see FIG. 13) for each second provisional candidate for the ground ID, which will be described later. For example, the unit time is one year, and the number of water leakage accidents per unit time is the annual average of the number of water leakage accidents that occurred in each second provisional candidate for the ground ID during the water leakage accident data collection period 55, and the unit of the number of water leakage accidents per unit time is cases / year.

[0072] 4, the determination unit 107 determines whether the difference between the estimated number of water leakage accidents and the actual number of water leakage accidents is equal to or less than a reference value for each second tentative candidate for ground ID, which will be described later. The determination unit 107 excludes ground IDs for which the difference is equal to or less than the reference value from the second tentative candidates for ground ID. The determination unit 107 leaves ground IDs for which the difference is greater than the reference value as second tentative candidates for ground ID.

[0073] 4, the optimized buried environment classification map generation unit 110 generates the optimized buried environment classification map 58a by optimizing, by machine learning, the buried environment classification of the ground ID selected by the ground selection unit 103. Referring to FIG. 4, the optimized buried environment classification map generation unit 110 includes an initial population generation unit 111, a fitness calculation unit 112, a determination unit 113, and a new generation population generation unit 114.

[0074] The initial population generating unit 111 generates an initial population consisting of multiple buried environment classification map candidates by randomly changing the buried environment classification of the ground ID selected by the ground selecting unit 103 from the general buried environment classification map 56a. The entire set of multiple buried environment classification map candidates is called a "population."

[0075] The fitness calculation unit 112 calculates the fitness of each individual constituting the initial population or the new generation population (hereinafter, the initial population and the new generation population are collectively referred to as the "current generation population"). An "individual" is each of the multiple buried environment map candidates constituting the current generation population. An individual is composed of multiple genes. As shown in FIG. 29, for example, each of the multiple genes is the number of change stages of the buried environment classification of the ground ID selected in step S21. Referring to FIG. 5, the fitness calculation unit 112 includes a corrected integrated map creation unit 120, a data preprocessing unit 121, an estimated water leakage accident rate calculation unit 122, an estimated water leakage accident rate result creation unit 123, a remaining water leakage accident number calculation unit 124, and a pipe renewal rate calculation unit 125.

[0076] 5, the modified integrated map creating unit 120 creates a modified integrated map corresponding to the individual (step S50). Specifically, the modified integrated map creating unit 120 changes the burial environment classification of the ground ID corresponding to the non-zero gene included in the individual among the ground IDs included in the general integrated map 56 (general burial environment classification map 56a) by the number of change stages of the burial environment classification expressed by the non-zero gene. In this way, a modified integrated map corresponding to the individual is created.

[0077] Referring to Figure 5, the data pre-processing unit 121 creates second pre-processed buried pipe data 74 (see Figure 32) from the modified integrated map, buried pipe attribute data 52 (see Figure 12), and water leakage accident data 53 (see Figure 13).

[0078] 5, the estimated water leakage accident rate calculation unit 122 calculates an estimated water leakage accident rate of a buried pipe for each pipeline ID included in the modified integrated map. Specifically, the estimated water leakage accident rate calculation unit 122 reads out the pipeline ID and the modified buried environment and nominal pipe thickness corresponding to the pipeline ID from the second preprocessed buried pipe data 74 (see FIG. 32). The estimated water leakage accident rate calculation unit 122 selects a water leakage accident rate prediction model 28 suitable for the read-out modified buried environment and nominal pipe thickness from among a plurality of water leakage accident rate prediction models 28 (see FIG. 6) stored in the water leakage accident rate prediction model storage unit 27 (see FIG. 6).

[0079] The estimated water leakage accident rate calculation unit 122 obtains the pipeline ID and the buried period T corresponding to the pipeline ID from the second preprocessed buried pipe data 74. m The estimated water leakage accident rate calculation unit 122 reads out the data for the buried period T m Enter the estimated water leakage accident rate R for each pipeline ID in the middle of the water leakage accident data collection period 55. m The estimated water leakage accident rate is the estimated number of water leakage accidents that occur per unit time and per unit distance. Estimated water leakage accident rate R m The units are, for example, cases / year / km.

[0080] 5, the estimated water leakage accident rate result creation unit 123 creates the estimated water leakage accident rate result 76 of the individual (see FIG. 34). Specifically, the estimated water leakage accident rate result creation unit 123 creates the estimated water leakage accident rate R m and the pipeline length (see FIG. 12) are associated with each other to create an estimated water leakage accident rate result 76.

[0081] Referring to FIG. 5, the remaining water leakage accident number calculation unit 124 calculates an estimated water leakage accident rate R m When some of the pipeline IDs included in the individual estimated water leakage accident rate results 76 are updated to new pipes in descending order of value, the remaining number of water leakage accidents is calculated by subtracting the number of water leakage accidents that could have been prevented from occurring.

[0082] Referring to Figure 5, the pipe renewal rate calculation unit 125 calculates the pipe renewal rate by dividing the pipeline length updated at the beginning of the water leakage accident data collection period 55 by the total pipeline length of the pipeline ID included in the individual's estimated water leakage accident rate result 76.

[0083] 4, determination unit 113 performs an end determination to end the generation of a new generation of population. Determination unit 113 determines whether an end condition is satisfied. The end condition is, for example, that the individual with the highest fitness in the population remains the same for a predetermined number of consecutive generations (for example, 50 generations).

[0084] Referring to FIG. 4, the new generation population generating unit 114 generates a new generation population when the termination condition is not satisfied.

[0085] Referring to FIG. 4, the optimized integrated map generating unit 116 integrates the pipeline map 51, the optimized buried environment classification map 58a, and the ground ID map 56b to generate the optimized integrated map 58 (see FIG. 15).

[0086] 4, the optimized integrated map output unit 118 outputs the optimized integrated map 58 to the map storage unit 25 (see FIG. 6). The optimized integrated map output unit 118 outputs the optimized integrated map 58 to at least one of the display 14 (see FIG. 1), the storage medium 18 (see FIG. 1), or the storage 19 (see FIG. 1).

[0087] 2, the buried pipe deterioration degree prediction unit 130 predicts the deterioration degree of a buried pipe (for example, an estimated water leakage accident rate). The buried pipe deterioration degree prediction unit 130 includes a data preprocessing unit 131, a buried pipe deterioration degree calculation unit 132, a buried pipe deterioration degree prediction result generation unit 133, and a buried pipe deterioration degree prediction result output unit 134.

[0088] The data pre-processing unit 131 creates third pre-processed buried pipe data 78 (see Figure 38) for the pipeline ID included in the optimized integrated map 58 from the optimized integrated map 58 (see Figure 15) and the buried pipe attribute data 52 (see Figure 12).

[0089] The buried pipe deterioration degree calculation unit 132 calculates the deterioration degree for each pipeline ID included in the optimized integrated map 58. The deterioration degree is, for example, an estimated water leakage accident rate. The estimated water leakage accident rate is the estimated number of water leakage accidents that occur per unit time and per unit distance. The unit of the estimated water leakage accident rate is, for example, cases / year / km.

[0090] The buried pipe deterioration degree prediction result generating unit 133 generates a buried pipe deterioration degree prediction result 65 (see FIGS. 18 and 19). The buried pipe deterioration degree prediction result 65 may be a buried pipe deterioration degree prediction table 66 (see FIG. 18), a buried pipe deterioration degree prediction map 67 (see FIG. 19), or both. The buried pipe deterioration degree prediction map 67 shows the degree of deterioration of buried pipes (e.g., estimated probability of water leakage accidents) on a map for each pipeline ID. The buried pipe deterioration degree prediction table 66 associates pipeline IDs with degrees of deterioration (e.g., estimated water leakage accident rates).

[0091] The buried pipe deterioration degree prediction result output unit 134 (see FIG. 2) outputs the buried pipe deterioration degree prediction result 65 (see FIGS. 18 and 19) to the buried pipe deterioration degree prediction result memory unit 29 (see FIG. 6). The buried pipe deterioration degree prediction result output unit 134 outputs the buried pipe deterioration degree prediction result 65 to at least one of the display 14, the storage medium 18, and the storage 19 shown in FIG. 1.

[0092] <How to create Correspondence Table 46>

[0093] A method for creating the correspondence table 46 will be described with reference to Fig. 20. The correspondence table 46 is created by a correspondence table creating unit 90.

[0094] The corrosion rate calculation unit 91 calculates the corrosion rate of the inspection pipe for each inspection number (step S1). Specifically, the corrosion rate calculation unit 91 reads out the inspection pipe data 40 (see FIG. 7) from the inspection pipe data storage unit 21 (FIG. 6). The corrosion rate calculation unit 91 calculates the buried period of the inspection pipe as the difference between the inspection year (see FIG. 7) and the installation year of the inspection pipe (see FIG. 7). The corrosion rate calculation unit 91 calculates the corrosion rate of the inspection pipe by dividing the corrosion depth of the inspection pipe (see FIG. 7) by the buried period of the inspection pipe.

[0095] The ground information acquisition unit 92 obtains ground information at the address of the investigation point (see Figure 7) (step S2). Specifically, the ground information acquisition unit 92 reads out the investigation pipe data 40 (see Figure 7) from the investigation pipe data storage unit 21 (see Figure 6), and reads out the ground map 42 from the ground map database unit 22 (see Figure 6). The ground information acquisition unit 92 obtains ground information at the address of the investigation point (see Figure 7) by referring to the investigation pipe data 40 (see Figure 7) and the ground map database unit 22. The ground ID assignment unit 93 assigns a ground ID to the ground information (e.g., a combination of surface geology and topography) (step S3).

[0096] The representative corrosion rate calculation unit 94 calculates a representative corrosion rate for each ground ID (step S4). The representative corrosion rate for each ground ID is, for example, the average corrosion rate for each ground ID or the median corrosion rate for each ground ID. When the representative corrosion rate for each ground ID is the average corrosion rate for each ground ID, the representative corrosion rate calculation unit 94 calculates the average corrosion rate of the investigation pipes assigned the same ground ID. When the representative corrosion rate for each ground ID is the median corrosion rate for each ground ID, the representative corrosion rate calculation unit 94 calculates the 50th percentile of the corrosion rates of the investigation pipes assigned the same ground ID.

[0097] The buried environment classification unit 95 classifies the investigation pipe data 40 into buried environments AD based on the soil type (see FIG. 7) and soil resistivity (see FIG. 7) (step S5). The correspondence table generation unit 96 generates a correspondence table 46 (see FIG. 9) by correlating the ground information, ground ID, typical corrosion rate, and buried environment (step S6). The correspondence table output unit 97 outputs the correspondence table 46 to the correspondence table storage unit 23 (see FIG. 6) (step S7). The correspondence table 46 is stored in the correspondence table storage unit 23.

[0098] <How to create the Optimized Integrated Map 58>

[0099] 21 to 35, a method for creating the optimized integrated map 58 (see FIG. 15) including the optimized buried environment classification map 58a (see FIG. 15) will be described. The method for creating the optimized integrated map 58 is performed by the buried pipe data receiving unit 99 (see FIG. 2) and the map creating unit 100 (see FIG. 2).

[0100] Referring to Figure 21, the method for creating the optimized buried environment classification map 58a in this embodiment includes a step of receiving buried pipe data 50 (see Figures 11 and 12) and water leakage accident data 53 (see Figure 13) from a customer (step S11), a step of creating a general integrated map 56 (see Figure 14) (step S12), and a step of creating an optimized integrated map 58 (see Figure 15) (step S13).

[0101] Referring to FIG. 21, the buried pipe data receiving unit 99 (see FIG. 2) receives buried pipe data 50 (see FIGS. 11 and 12) and water leakage accident data 53 (see FIG. 13) from a customer (step S11). The buried pipe data 50 includes, for example, a pipeline map 51 (see FIG. 11) and buried pipe attribute data 52 (see FIG. 12). The buried pipe data receiving unit 99 outputs the buried pipe data 50 and the water leakage accident data 53 to the buried pipe data storage unit 24 (see FIG. 6). The buried pipe data 50 and the water leakage accident data 53 are stored in the buried pipe data storage unit 24.

[0102] Referring to FIG. 21, the first map creating unit 101 (see FIG. 2) creates the general integrated map 56 (see FIG. 14) (step S12).

[0103] Specifically, the first map creation unit 101 reads a pipeline map 51 (see FIG. 11) from the buried pipe data storage unit 24 (see FIG. 6). The first map creation unit 101 reads a ground map 42 (e.g., a surface geological map 43 and a topography classification map 44) of the area corresponding to the pipeline map 51 from the ground map database unit 22 (see FIGS. 6 and 8). The first map creation unit 101 reads a correspondence table 46 (see FIG. 9) from the correspondence table storage unit 23. The first map creation unit 101 overlays the buried environment and ground ID of the area corresponding to the pipeline map 51 on the pipeline map 51 to create a general integrated map 56 (see FIG. 14).

[0104] The general integrated map 56 is a map obtained by integrating the pipeline map 51, the general buried environment classification map 56a of the area corresponding to the pipeline map 51, and the ground ID map 56b of the area corresponding to the pipeline map 51. The general buried environment classification map 56a is a map showing the buried environment of the area corresponding to the pipeline map 51. The ground ID map 56b is a map showing the ground ID of the area corresponding to the pipeline map 51. The first map creation unit 101 outputs the general integrated map 56 (see FIG. 14 ) to the map storage unit 25. The general integrated map 56 is stored in the map storage unit 25.

[0105] Referring to Figure 21, the second map creation unit 102 (see Figure 2) creates an optimized integrated map 58 (see Figure 15) by optimizing the buried environment classification of the general integrated map 56 (general buried environment classification map 56a) using the water leakage accident data 53 (step S13).

[0106] Step S13 will be described in detail with reference to Fig. 22. Step S13 includes a step of selecting a ground ID that is a candidate for optimization of the buried environment classification from all ground IDs included in the general buried environment classification map 56a (step S20), a step of optimizing the buried environment classification of the ground ID selected in step S20 by machine learning to generate an optimized buried environment classification map 58a (step S21), a step of generating an optimized integrated map 58 (step S22), and a step of outputting the optimized integrated map 58 (step S23).

[0107] Step S20 will be described in detail with reference to FIG.

[0108] The second map creation unit 102 (see FIG. 2) reads out the general integrated map 56 from the map storage unit 25 (see FIG. 6). The ground selection unit 103 (see FIG. 4) selects provisional candidates for ground IDs that require a change in buried environment classification from among all ground IDs included in the general integrated map 56 (general buried environment classification map 56a) (step S24).

[0109] For example, for a ground ID that is assigned a buried environment classification (e.g., buried environment A or buried environment B) that indicates relatively high corrosiveness in the general integrated map 56 (general buried environment classification map 56a), if no water leak accident has occurred within the water leak accident data collection period 55 (see Figure 13) in the water leak accident data 53 (see Figure 13), it is necessary to change the buried environment classification of that ground ID to a buried environment classification that is less corrosive to buried pipes (e.g., buried environment C or buried environment D). Therefore, the ground selection unit 103 (see Figure 4) refers to the general integrated map 56 (general buried environment classification map 56a) and the water leakage accident data 53, and selects, from among the ground IDs that have been assigned a buried environment classification (e.g., buried environment A or buried environment B) that indicates relatively high corrosiveness in the general integrated map 56 (general buried environment classification map 56a), a ground ID that has not experienced a water leakage accident within the water leakage accident data collection period 55 in the water leakage accident data 53, as the first provisional candidate for the ground ID whose buried environment classification needs to be changed.

[0110] A burial environment classification exhibiting a relatively high corrosivity is a burial environment classification exhibiting a higher corrosivity than a burial environment classification (e.g., burial environment D) exhibiting the least corrosiveness among a plurality of burial environment classifications (e.g., burial environment classification AD). A burial environment classification exhibiting a relatively high corrosivity includes, for example, a burial environment classification (e.g., burial environment A) exhibiting the most corrosiveness among a plurality of burial environment classifications (e.g., burial environment classification AD) and a burial environment classification (e.g., burial environment B) exhibiting the second most corrosiveness among a plurality of burial environment classifications (e.g., burial environment classification AD).

[0111] Furthermore, for a ground ID that has been assigned a buried environment classification (e.g., buried environment B, buried environment C, or buried environment D) that indicates relatively low corrosiveness in the general integrated map 56 (general buried environment classification map 56a), if a water leak accident occurs within the water leak accident data collection period 55 (see Figure 13) in the water leak accident data 53 (see Figure 13), it is necessary to change the buried environment classification of that ground ID to a buried environment classification that is more corrosive to buried pipes (e.g., buried environment A, etc.). Therefore, the ground selection unit 103 (see Figure 4) refers to the general integrated map 56 (general buried environment classification map 56a) and the water leakage accident data 53, and selects, from among the ground IDs that have been assigned a buried environment classification (e.g., buried environment B, buried environment C, or buried environment D) that indicates relatively low corrosiveness in the general integrated map 56 (general buried environment classification map 56a), a ground ID in which a water leakage accident has occurred within the water leakage accident data collection period 55 in the water leakage accident data 53, as a second provisional candidate for the ground ID whose buried environment classification needs to be changed.

[0112] A burial environment classification exhibiting relatively low corrosivity is a burial environment classification exhibiting lower corrosivity than a burial environment classification exhibiting the highest corrosivity (e.g., burial environment A) among a plurality of burial environment classifications (e.g., burial environment classification AD). Examples of burial environment classifications exhibiting relatively low corrosivity include a burial environment classification exhibiting the lowest corrosivity (e.g., burial environment D) among a plurality of burial environment classifications (e.g., burial environment classification AD), a burial environment classification exhibiting the second lowest corrosivity (e.g., burial environment C) among a plurality of burial environment classifications (e.g., burial environment classification AD), and a burial environment classification exhibiting the third lowest corrosivity (e.g., burial environment B) among a plurality of burial environment classifications (e.g., burial environment classification AD).

[0113] Referring to FIG. 23, the ground selection unit 103 (see FIG. 4) excludes ground IDs for which the buried environment classification does not need to be changed from the tentative candidates for ground IDs (step S25). For example, even if a ground ID is assigned a buried environment classification (e.g., buried environment A) indicating relatively high corrosiveness in the general integrated map 56 (general buried environment classification map 56a) but no water leak accident has occurred in the water leak accident data collection period 55 (see FIG. 13) in the water leak accident data 53 (see FIG. 13), the buried environment classification of the ground ID is not required to be changed. Therefore, the ground selection unit 103 refers to the general integrated map 56 (general buried environment classification map 56a) and the correspondence table 46 (see FIG. 9), and excludes ground IDs for which the representative corrosion rate is equal to or greater than the standard corrosion rate from the first tentative candidates for ground IDs, as ground IDs that are clearly highly corrosive to buried pipes.

[0114] Furthermore, there is no need to change the buried environment classification for a ground ID for which the difference between the estimated number of water leakage accidents per unit time in the water leakage accident data collection period 55 (see FIG. 13), calculated using the water leakage accident rate prediction model 28, and the actual number of water leakage accidents per unit time in the water leakage accident data collection period 55 obtained from the water leakage accident data 53, is equal to or less than a reference value. Therefore, the ground selection unit 103 (see FIG. 4) excludes from the second provisional candidates for the ground ID any ground ID for which the difference between the estimated number of water leakage accidents per unit time in the water leakage accident data collection period 55, calculated using the water leakage accident rate prediction model 28, and the actual number of water leakage accidents per unit time in the water leakage accident data collection period 55 obtained from the water leakage accident data 53, is equal to or less than a reference value.

[0115] Specifically, with reference to Fig. 24, the estimated water leakage accident number calculation unit 105 (see Fig. 4) uses the water leakage accident rate prediction model 28 (see Figs. 6 and 17) and the general integrated map 56 (see Fig. 14) to calculate the estimated number of water leakage accidents per unit time in the water leakage accident data collection period 55 for each second tentative candidate ground ID (step S26). Step S26 will be described in detail with reference to Fig. 25.

[0116] The data preprocessing unit 104 (see FIG. 4) creates first preprocessed buried pipe data 70 (see FIG. 26) for the pipeline ID included in the second provisional candidate for the ground ID from the second provisional candidate for the ground ID, the general integrated map 56 (see FIG. 14), the buried pipe data 50 (see FIGS. 11 and 12), and the water leakage accident data 53 (see FIG. 13) (step S31). Step S31 will be described in detail with reference to FIG. 27.

[0117] The data pre-processing unit 104 refers to the second provisional candidate for the ground ID and reads out the buried pipe attribute data 52 (see Figure 12) and water leakage accident data 53 (see Figure 13) of the pipeline ID included in the second provisional candidate for the ground ID from the buried pipe data storage unit 24 (see Figure 6) (step S35).

[0118] The data preprocessing unit 104 (see FIG. 4) calculates the buried period T of the buried pipe in the intermediate period between the start and end of the water leakage accident data collection period 55 (see FIG. 13) for each pipeline ID included in the second provisional candidate of the ground ID. m (Step S36). Specifically, the data pre-processing unit 104 calculates the intermediate period of the water leakage accident data collection period 55 by dividing the sum of the start period of the water leakage accident data collection period 55 and the end period of the water leakage accident data collection period 55 by two. For each pipeline ID included in the second provisional candidate for the ground ID, the data pre-processing unit 104 calculates the difference between the intermediate period of the water leakage accident data collection period 55 and the year of laying of the buried pipe (see FIG. 12) as the buried period T of the buried pipe in the intermediate period of the water leakage accident data collection period 55. m It is calculated as follows.

[0119] The data pre-processing unit 104 identifies the nominal pipe thickness of the buried pipe for each pipeline ID included in the second tentative candidates for the ground ID (step S37). Specifically, the data pre-processing unit 104 reads out the nominal pipe thickness data 60 (see FIG. 16) from the nominal pipe thickness database unit 26 (see FIG. 6). The data pre-processing unit 104 identifies the nominal pipe thickness of the buried pipe for each pipeline ID included in the second tentative candidates for the ground ID by referring to the nominal pipe thickness data 60 and the year of installation, nominal diameter, joint type, and type of pipe thickness (see FIG. 12) of the buried pipe attribute data 52.

[0120] The data preprocessing unit 104 refers to the second provisional candidate for the ground ID and the general integrated map 56 (see Figure 14) and identifies the buried environment of the buried pipe (hereinafter referred to as the "first buried environment") for each pipeline ID included in the second provisional candidate for the ground ID (step S38).

[0121] The data preprocessing unit 104 calculates the pipeline ID, the buried period T m , nominal pipe thickness, first buried environment and pipeline length (see Figure 12) are combined to generate first preprocessed buried pipe data 70 (see Figure 26) for the pipeline ID included in the second tentative candidate ground ID (step S39).

[0122] 25, the estimated water leakage accident number calculation unit 105 (see FIG. 4) calculates the estimated water leakage accident rate R of the buried pipe for each pipeline ID included in the second provisional candidate of the ground ID. m is calculated (step S32).

[0123] Specifically, the estimated water leakage accident number calculation unit 105 reads out the pipeline ID and the first buried environment and nominal pipe thickness corresponding to the pipeline ID from the first preprocessed buried pipe data 70. The estimated water leakage accident number calculation unit 105 selects a water leakage accident rate prediction model 28 suitable for the read-out first buried environment and nominal pipe thickness from among the multiple water leakage accident rate prediction models 28 stored in the water leakage accident rate prediction model storage unit 27. For example, if the read-out first buried environment is buried environment B and the read-out nominal pipe thickness is 7.5 mm, the curve for buried environment B in FIG. 17 is the water leakage accident rate prediction model 28 suitable for the read-out first buried environment and nominal pipe thickness.

[0124] The estimated water leakage accident number calculation unit 105 obtains the pipeline ID and the buried period T corresponding to the pipeline ID from the first preprocessed buried pipe data 70. m The estimated water leakage accident number calculation unit 105 reads out the data for the buried period T m Enter the estimated water leakage accident rate R for each pipeline ID in the middle of the water leakage accident data collection period 55. m (See Figure 17.) Estimated water leakage accident rate R m The units are, for example, cases / year / km.

[0125] Referring to Fig. 25, the estimated water leakage accident number calculation unit 105 (see Fig. 4) calculates the estimated number of water leakage accidents per unit time in the water leakage accident data collection period 55 for each second tentative candidate for the ground ID (step S33). For example, the unit time is one year, and the unit of the estimated number of water leakage accidents is cases / year. Specifically, the estimated water leakage accident number calculation unit 105 reads out the pipeline ID included in the second tentative candidate for the ground ID and the pipeline length corresponding to the pipeline ID from the first preprocessed buried pipe data 70 (see Fig. 26). The estimated water leakage accident number calculation unit 105 calculates the estimated water leakage accident rate R for each pipeline ID. mand the pipeline length of each pipeline ID. The estimated water leakage accident number calculation unit 105 calculates the sum of these products for each second tentative candidate ground ID. In this way, the estimated water leakage accident number calculation unit 105 calculates the estimated number of water leakage accidents per unit time in the water leakage accident data collection period 55 for each second tentative candidate ground ID.

[0126] 24, the water leakage accident actual number calculation unit 106 (see FIG. 4) refers to the general integrated map 56 and the water leakage accident data 53, and calculates the actual number of water leakage accidents per unit time in the water leakage accident data collection period 55 for each second provisional candidate ground ID (step S27). For example, the unit time is one year, and the actual number of water leakage accidents per unit time is the annual average of the actual number of water leakage accidents that occurred in each ground ID during the water leakage accident data collection period 55, and the unit of the actual number of water leakage accidents per unit time is cases / year.

[0127] Specifically, the actual water leakage accident number calculation unit 106 refers to the second provisional candidate for the ground ID and the water leakage accident data 53, and calculates the actual number of water leakage accidents that occurred within the water leakage accident data collection period 55 for each second provisional candidate for the ground ID. The actual water leakage accident number calculation unit 106 divides the actual number of water leakage accidents that occurred for each ground ID within the water leakage accident data collection period 55 by the water leakage accident data collection period 55. In this way, the actual water leakage accident number calculation unit 106 calculates the actual number of water leakage accidents per unit time in the water leakage accident data collection period 55 for each second provisional candidate for the ground ID.

[0128] Referring to FIG. 24, the determination unit 107 (see FIG. 4) determines whether or not the difference between the estimated number of water leakage accidents calculated in step S26 and the actual number of water leakage accidents calculated in step S27 is equal to or less than a reference value for each second tentative candidate ground ID (step S28). The determination unit 107 excludes ground IDs for which the difference is equal to or less than the reference value from the second tentative candidates ground ID (step S29). The determination unit 107 leaves ground IDs for which the difference is greater than the reference value as second tentative candidates ground ID (step S30). In this way, the ground selection unit 103 selects ground IDs that are candidates for optimization of the buried environment classification from all ground IDs included in the general integrated map 56.

[0129] With reference to Fig. 22, step S21 is performed by the optimized burial environment classification map generation unit 110. With reference to Fig. 22 and Figs. 28 to 35, step S21 will be described in detail. Examples of machine learning used in step S21 include evolutionary computing methods such as genetic algorithms, evolutionary algorithms, or swarm intelligence, greedy methods, neighborhood search methods, local search methods, and mathematical optimization methods. In this way, an optimized burial environment classification map 58a (see Fig. 15) reflecting the optimized burial environment classification is created. As an example, a method for creating the optimized burial environment classification map 58a using a genetic algorithm will be described.

[0130] Referring to Fig. 28, the initial population generation unit 111 generates an initial population (step S40) made up of a plurality of buried environment classification map candidates by randomly changing the buried environment classification of the ground ID selected in step S20 (see Fig. 22) from the general buried environment classification map 56a. Each of the plurality of buried environment map candidates is called an "individual." An individual is made up of a plurality of genes. As shown in Fig. 29, for example, each of the plurality of genes is the number of change stages of the buried environment classification of the ground ID selected in step S21.

[0131] Specifically, when the buried environment classification of a certain ground ID is changed to a buried environment classification that is one level more corrosive to buried pipes, such as when changing the buried environment classification of a certain ground ID from buried environment B to buried environment A, it is represented as a gene of 1. When the buried environment classification of a certain ground ID is changed to a buried environment classification that is one level less corrosive to buried pipes, such as when changing the buried environment classification of a certain ground ID from buried environment C to buried environment D, it is represented as a gene of -1. When the buried environment classification of a certain ground ID is changed to a buried environment classification that is two levels more corrosive to buried pipes, such as when changing the buried environment classification of a certain ground ID from buried environment C to buried environment A, it is represented as a gene of 2. When the buried environment classification of a certain ground ID is changed to a buried environment classification that is two levels less corrosive to buried pipes, such as when changing the buried environment classification of a certain ground ID from buried environment B to buried environment D, it is represented as a gene of -2.

[0132] 28, the fitness calculation unit 112 (see FIG. 4) calculates the fitness of each individual constituting the initial population generated in step S40 or the new generation population generated in step S43 (hereinafter, the initial population and the new generation population are collectively referred to as the "current generation population") (step S41). Examples of fitness will be described later.

[0133] The determination unit 113 (see FIG. 4) performs an end determination to end the generation of a new generation of population. The determination unit 113 determines whether an end condition is satisfied (step S42). The end condition is, for example, that the individual with the highest fitness in the population remains the same for a predetermined number of consecutive generations (for example, 50 generations).

[0134] If the termination condition is not satisfied in step S42, the new generation population generation unit 114 generates a new generation population (step S43). An example of step S43 will be described with reference to FIG.

[0135] In step S44, the new generation population generation unit 114 (see FIG. 4) selects a plurality of individuals to become parents of the next generation from the current generation population. For example, the new generation population generation unit 114 selects individuals with high fitness from among the individuals constituting the current generation population, and selects (deletes) individuals with low fitness from among the individuals constituting the current generation population (elite strategy).

[0136] In step S45, the new generation population generation unit 114 (see FIG. 4) selects two individuals from the individuals selected in step S44 and performs a crossover process to swap genes between the two individuals. New individuals with recombined genes are generated. The number of individuals generated in step S45 is equal to the number of individuals selected (deleted) in step S44, for example. In this way, the new generation population generation unit 114 generates a new population consisting of the individuals selected in step S44 and the new individuals generated in step S45. As the crossover process method, for example, a known method such as a single-point crossover method, a multi-point crossover method, or a uniform crossover method can be used.

[0137] In step S46, the new generation population generation unit 114 (see FIG. 4) performs a mutation process on the individuals that make up the new population generated in step S45, randomly replacing genes with a predetermined probability. A known method can be used as the mutation process method. In this way, a new generation population is generated.

[0138] Then, returning to step S41, the fitness calculation unit 112 (see FIG. 4) calculates the fitness of each individual constituting the population of the new generation. Then, steps S41 and S43 are repeatedly executed until the termination condition of step S42 is satisfied.

[0139] If the termination condition is satisfied in step S42, the optimized burial environment classification map generation unit 110 (see FIG. 4) selects the individual with the highest fitness among the individuals constituting the population of the current generation (step S47). The optimized burial environment classification map generation unit 110 changes the burial environment classification of the ground IDs included in the general burial environment classification map 56a that correspond to the non-zero genes included in the individual selected in step S47 by the number of change steps of the burial environment classification represented by the non-zero genes. In this way, an optimized burial environment classification map 58a (see FIG. 15) reflecting the optimized burial environment classification is created.

[0140] 22, the optimized integrated map generation unit 116 (see FIG. 4) integrates the pipeline map 51, the optimized buried environment classification map 58a, and the ground ID map 56b to generate the optimized integrated map 58 (see FIG. 15) (step S22). In step S23, the optimized integrated map output unit 118 (see FIG. 4) outputs the optimized integrated map 58 to the map storage unit 25 (see FIG. 6). The optimized integrated map 58 is stored in the map storage unit 25. The optimized integrated map output unit 118 outputs the optimized integrated map 58 to at least one of the display 14 (see FIG. 1), the storage medium 18 (see FIG. 1), or the storage 19 (see FIG. 1).

[0141] The step of calculating the fitness of each individual constituting the current generation population (step S41) will be described in detail with reference to FIGS.

[0142] Referring to Fig. 31, the modified integrated map creating unit 120 (see Fig. 5) creates a modified integrated map corresponding to the individual (step S50). Specifically, the modified integrated map creating unit 120 changes the burial environment classification of the ground ID corresponding to the non-zero gene included in the individual, among the ground IDs included in the general integrated map 56, by the number of change stages of the burial environment classification expressed by the non-zero gene. In this way, a modified integrated map corresponding to the individual is created.

[0143] 31, the data preprocessing unit 121 (see FIG. 5) creates second preprocessed buried pipe data 74 (see FIG. 32) for the pipeline IDs included in the modified integrated map from the modified integrated map, buried pipe attribute data 52 (see FIG. 12), and water leakage accident data 53 (see FIG. 13) (step S51). The second preprocessed buried pipe data 74 is created in the same manner as the first preprocessed buried pipe data 70 (see FIG. 26), but is created based on the modified integrated map instead of the general integrated map (see FIG. 14). Therefore, the second preprocessed buried pipe data 74 includes the modified buried environment included in the modified integrated map instead of the first buried environment of the first preprocessed buried pipe data 70 (see FIG. 26).

[0144] Specifically, referring to Figure 33, the data pre-processing unit 121 (see Figure 5) refers to the modified integrated map and reads out the buried pipe attribute data 52 and water leakage accident data 53 of the pipeline ID included in the modified integrated map from the buried pipe data storage unit 24 (see Figure 6) (step S60).

[0145] The data preprocessing unit 121 (see FIG. 5) calculates the buried period T of the buried pipe in the intermediate period between the start and end of the water leakage accident data collection period 55 for each pipeline ID included in the corrected integrated map. m (Step S61). Specifically, the data pre-processing unit 121 calculates the intermediate period of the water leakage accident data collection period 55 by dividing the sum of the start period of the water leakage accident data collection period 55 and the end period of the water leakage accident data collection period 55 by two. For each pipeline ID included in the corrected integrated map, the data pre-processing unit 121 calculates the difference between the intermediate period of the water leakage accident data collection period 55 and the year of laying of the buried pipe (see FIG. 12) as the buried period T of the buried pipe in the intermediate period of the water leakage accident data collection period 55. m It is calculated as follows.

[0146] The data pre-processing unit 121 (see FIG. 5) identifies the nominal pipe thickness of the buried pipe for each pipeline ID included in the modified integrated map (step S62). Specifically, the data pre-processing unit 121 reads out the nominal pipe thickness data 60 (see FIG. 16) from the nominal pipe thickness database unit 26 (see FIG. 6). The data pre-processing unit 121 identifies the nominal pipe thickness of the buried pipe for each pipeline ID included in the modified integrated map by referring to the year of installation, nominal diameter, joint type, and pipe thickness type (see FIG. 12) of the buried pipe attribute data 52 and the nominal pipe thickness data 60.

[0147] The data preprocessing unit 121 (see FIG. 5) refers to the corrected integrated map and identifies the corrected buried environment of the buried pipe for each pipeline ID included in the corrected integrated map (step S63).

[0148] The data preprocessing unit 121 (see FIG. 5) calculates the pipeline ID, the buried period T m The nominal pipe thickness and the modified buried environment are combined to generate second preprocessed buried pipe data 74 (see FIG. 32) for the pipeline ID included in the modified integrated map (step S64).

[0149] 31, the estimated water leakage accident rate calculation unit 122 (see FIG. 5) calculates the estimated water leakage accident rate R m (Step S52). Specifically, the estimated water leakage accident rate calculation unit 122 reads out the pipeline ID and the corrected buried environment and nominal pipe thickness corresponding to the pipeline ID from the second preprocessed buried pipe data 74 (see FIG. 32). The estimated water leakage accident rate calculation unit 122 selects a water leakage accident rate prediction model 28 that is suitable for the read-out corrected buried environment and nominal pipe thickness from among the multiple water leakage accident rate prediction models 28 (see FIG. 6) stored in the water leakage accident rate prediction model storage unit 27 (see FIG. 6).

[0150] The estimated water leakage accident rate calculation unit 122 obtains the pipeline ID and the buried period T corresponding to the pipeline ID from the second preprocessed buried pipe data 74. m The estimated water leakage accident rate calculation unit 122 reads out the data for the buried period T mEnter the estimated water leakage accident rate R for each pipeline ID in the middle of the water leakage accident data collection period 55. m Calculate the estimated water leakage accident rate R m The units are, for example, cases / year / km.

[0151] 31, the estimated water leakage accident rate result creation unit 123 refers to the corrected integrated map and reads out the pipe length (see FIG. 12) of the pipe ID included in the corrected integrated map from the buried pipe data storage unit 24 (see FIG. 6). The estimated water leakage accident rate result creation unit 123 calculates the pipe ID and the estimated water leakage accident rate R m and the pipe length (see FIG. 12) are associated with each other. In this way, the estimated water leakage accident rate result creation unit 123 creates the estimated water leakage accident rate result 76 (see FIG. 34) of the individual (step S53).

[0152] Referring to FIG. 31, the estimated water leakage accident rate result 76 (see FIG. 34) and the water leakage accident data 53 (see FIG. 13) of the individual are referred to, and at the start of the water leakage accident data collection period 55, the estimated water leakage accident rate R m The number of remaining water leakage accidents and the estimated water leakage accident rate R m The pipeline renewal rate when at least some of the pipeline IDs included in the individual estimated water leakage accident rate result 76 are renewed to new pipes is calculated in descending order of the number of water leakage accidents (step S54). An example of a method for calculating the remaining number of water leakage accidents and the pipeline renewal rate will be described.

[0153] At the beginning of the water leakage accident data collection period55 (see Figure 13), the estimated water leakage accident rate R m Assuming that some of the pipeline IDs included in the individual estimated water leakage accident rate results 76 (see Figure 34) are updated to new pipes in descending order of the value, this pipe update can prevent some of the water leakage accidents included in the water leakage accident data 53 from occurring.

[0154] Therefore, the remaining water leakage accident number calculation unit 124 (see FIG. 5) calculates an estimated water leakage accident rate R mThe remaining number of water leakage accidents is calculated by subtracting the number of water leakage accidents that could have been prevented when some of the pipeline IDs included in the individual estimated water leakage accident rate result 76 are updated with new pipes in descending order of value. The pipe replacement rate calculation unit 125 (see FIG. 5) calculates the pipe replacement rate by dividing the pipeline length updated at the start of the water leakage accident data collection period 55 by the total pipeline length of the pipeline IDs included in the individual estimated water leakage accident rate result 76.

[0155] Referring to Fig. 31, the fitness calculation unit 112 (see Fig. 4) calculates the fitness of the individual (step S55). Specifically, the fitness calculation unit 112 creates a graph (see Fig. 35) showing the relationship between the pipeline renewal rate and the number of remaining water leakage accidents. The horizontal axis of this graph is the pipeline renewal rate, and the vertical axis of this graph is the number of remaining water leakage accidents. It is considered that the smaller the area S (the shaded area in Fig. 35) surrounded by the vertical axis, the horizontal axis, and the line showing the relationship between the pipeline renewal rate and the number of remaining water leakage accidents, the better the corrected integrated map corresponding to the individual reflects the actual buried environment. Therefore, the fitness calculation unit 112 calculates the reciprocal of the area S as the fitness of the individual.

[0156] <Method for predicting the deterioration of buried pipes>

[0157] 36 to 40, a buried pipe deterioration degree prediction method according to this embodiment will be described. The buried pipe deterioration degree prediction method is performed by the buried pipe deterioration degree prediction unit 130. An example of the degree of deterioration of a buried pipe is an estimated water leakage accident rate.

[0158] Referring to Fig. 36, the buried pipe deterioration degree prediction unit 130 calculates the deterioration degree (e.g., estimated water leakage accident rate) for each pipeline ID using the optimized integrated map 58 (see Fig. 15) and a buried pipe deterioration degree prediction model (e.g., water leakage accident rate prediction model 28 (see Figs. 6 and 40)) (step S70). The deterioration degree (e.g., estimated water leakage accident rate) calculated in step S70 may be the deterioration degree for each pipeline ID in the current year (e.g., estimated water leakage accident rate), or the deterioration degree for each pipeline ID in a future year (e.g., estimated water leakage accident rate), or both. Step S70 will be described in detail.

[0159] Referring to Figure 37, the data pre-processing unit 131 (see Figure 2) creates third pre-processed buried pipe data 78 (see Figure 38) for the pipeline ID included in the optimized integrated map 58 from the optimized integrated map 58 (see Figure 15) and the buried pipe attribute data 52 (see Figure 12) (step S71).

[0160] 39, the data pre-processing unit 131 reads the optimized integrated map 58 from the map storage unit 25 (see FIG. 6). The data pre-processing unit 131 reads the buried pipe attribute data 52 of the pipeline ID included in the optimized integrated map 58 from the buried pipe data storage unit 24 (see FIG. 6) with reference to the optimized integrated map 58 (step S72).

[0161] The data preprocessing unit 131 (see FIG. 2) calculates the buried pipe installation period for each pipeline ID included in the optimized integrated map 58 (step S73). For example, when calculating an estimated water leakage accident rate for each pipeline ID in the current year, the data preprocessing unit 131 calculates, for each pipeline ID included in the optimized integrated map 58, the difference between the current year and the year the buried pipe was laid (see FIG. 12) as the buried pipe installation period T3. When calculating an estimated water leakage accident rate for each pipeline ID in a future year, the data preprocessing unit 131 calculates, for each pipeline ID included in the optimized integrated map 58, the difference between the future year and the year the buried pipe was laid (see FIG. 12) as the buried pipe installation period T4.

[0162] The data pre-processing unit 131 (see FIG. 2) identifies the nominal pipe thickness of the buried pipe for each pipeline ID included in the optimized integrated map 58 (step S74). Specifically, the data pre-processing unit 131 reads out the nominal pipe thickness data 60 (see FIG. 16) from the nominal pipe thickness database unit 26 (see FIG. 6). The data pre-processing unit 131 identifies the nominal pipe thickness of the buried pipe for each pipeline ID included in the optimized integrated map 58 by referring to the year of installation, nominal diameter, joint type, and type of pipe thickness (see FIG. 12) of the buried pipe attribute data 52 and the nominal pipe thickness data 60.

[0163] The data preprocessing unit 131 (see FIG. 2) refers to the optimized integrated map 58 and identifies the buried environment (second buried environment) of the buried pipe for each pipeline ID included in the optimized integrated map 58 (step S75).

[0164] The data preprocessing unit 131 (see Figure 2) combines the pipeline ID, buried period (e.g., buried periods T3 and T4), nominal pipe thickness, and second buried environment to generate third preprocessed buried pipe data 78 (see Figure 38) for the pipeline ID included in the optimized integrated map 58 (step S76).

[0165] Referring to FIG. 37, the buried pipe deterioration degree calculation unit 132 calculates the deterioration degree (for example, estimated water leakage accident rate) for each pipe line ID included in the optimized integrated map 58 (step S77).

[0166] Specifically, the buried pipe deterioration degree calculation unit 132 reads out the pipeline ID and the second buried environment and nominal pipe thickness corresponding to the pipeline ID from the third preprocessed buried pipe data 78 (see FIG. 38). The buried pipe deterioration degree calculation unit 132 selects a water leakage accident rate prediction model 28 suitable for the read-out second buried environment and nominal pipe thickness from among the multiple water leakage accident rate prediction models 28 (see FIGS. 6 and 40) stored in the water leakage accident rate prediction model storage unit 27. For example, if the read-out second buried environment is buried environment B and the read-out nominal pipe thickness is 7.5 mm, the curve for buried environment B in FIG. 40 is the water leakage accident rate prediction model 28 suitable for the read-out second buried environment and nominal pipe thickness.

[0167] The buried pipe deterioration degree calculation unit 132 reads out the pipeline ID and the buried period corresponding to the pipeline ID (e.g., buried periods T3 and T4) from the third preprocessed buried pipe data 78 (see FIG. 38). The buried pipe deterioration degree calculation unit 132 inputs the buried period of the buried pipe (see FIG. 38) into the selected water leakage accident rate prediction model 28, and calculates the deterioration degree (e.g., estimated water leakage accident rate) for each pipeline ID (see FIG. 40). The estimated water leakage accident rate is the estimated number of water leakage accidents that occur per unit time and per unit distance. The unit of the estimated water leakage accident rate is, for example, cases / year / km. The buried pipe deterioration degree calculation unit 132 may calculate the deterioration degree for each pipeline ID in the current year (e.g., estimated water leakage accident rate R3), or may calculate the deterioration degree for each pipeline ID in a future year (e.g., estimated water leakage accident rate R4), or may calculate both.

[0168] The buried pipe deterioration degree prediction result generating unit 133 generates (step S80) a buried pipe deterioration degree prediction result 65. The buried pipe deterioration degree prediction result 65 may be a buried pipe deterioration degree prediction table 66 (see FIG. 18), a buried pipe deterioration degree prediction map 67 (see FIG. 19), or both.

[0169] Specifically, the buried pipe deterioration degree prediction result generating unit 133 creates a buried pipe deterioration degree prediction table 66 (see FIG. 18) by associating the pipeline ID, the degree of deterioration of the buried pipe (e.g., estimated water leakage accident rate), and the time when the degree of deterioration of the buried pipe was calculated (e.g., the current year or a future year) with each other. The buried pipe deterioration degree prediction result generating unit 133 reads out the pipeline map 51 (see FIG. 11) from the buried pipe data storage unit 24 (see FIG. 6). The buried pipe deterioration degree prediction result generating unit 133 creates a buried pipe deterioration degree prediction map 67 (see FIG. 19) by reflecting the degree of deterioration of the buried pipe (e.g., estimated water leakage accident rate) for each pipeline ID and the time when the degree of deterioration of the buried pipe was calculated (e.g., the current year or a future year) in the pipeline map 51.

[0170] 36, in step S81, buried pipe deterioration degree prediction result output unit 134 (see FIG. 2) outputs buried pipe deterioration degree prediction result 65 to buried pipe deterioration degree prediction result memory unit 29. Buried pipe deterioration degree prediction result 65 is stored in buried pipe deterioration degree prediction result memory unit 29. Buried pipe deterioration degree prediction result output unit 134 (see FIG. 2) outputs buried pipe deterioration degree prediction result 65 to at least one of display 14, storage medium 18, or storage 19 shown in FIG. 1.

[0171] The buried environment classification map creating program 31 (see FIG. 6) causes the processor 12 (see FIG. 1) to execute the buried environment classification map creating method of this embodiment. The map creating unit 100 (see FIG. 2) is realized by the buried environment classification map creating program 31 being executed by the processor 12.

[0172] The buried pipe deterioration prediction program 32 (see FIG. 6) causes the processor 12 (see FIG. 1) to execute the buried pipe deterioration prediction method of this embodiment. The buried pipe deterioration prediction unit 130 (see FIG. 2) is realized by the buried pipe deterioration prediction program 32 being executed by the processor 12.

[0173] The correspondence table creation program 33 (see FIG. 6) causes the processor 12 (see FIG. 1) to execute the correspondence table creation method of this embodiment. The correspondence table creation unit 90 (see FIG. 2) is realized by the processor 12 executing the correspondence table creation program 33.

[0174] The computer-readable recording medium of this embodiment (a non-transitory computer-readable recording medium, for example, storage medium 18) may record programs such as a buried environment classification map creation program 31, a buried pipe deterioration prediction program 32, and a correspondence table creation program 33.

[0175] (Variation)

[0176] Referring to FIG. 41 , in a modification of the present embodiment, the functions of the buried pipe deterioration degree prediction device 1 of the present embodiment may be realized by a buried pipe deterioration degree prediction system 7. The buried pipe deterioration degree prediction system 7 includes a buried pipe deterioration degree prediction device 1b, a buried environment classification map creation device 2, a correspondence table creation device 3, a buried pipe data acceptance device 4, and a storage device 5. The buried pipe deterioration degree prediction device 1b, the buried environment classification map creation device 2, the correspondence table creation device 3, the buried pipe data acceptance device 4, and the storage device 5 are communicably connected to each other via a communication network 6 such as the Internet or an intranet. The hardware configurations of the buried pipe deterioration degree prediction device 1b, the buried environment classification map creation device 2, the correspondence table creation device 3, and the buried pipe data acceptance device 4 are the same as the hardware configuration shown in FIG. 1 . The storage device 5 includes, for example, a hard disk or a storage medium drive 17.

[0177] The correspondence table creation device 3 has the function of a correspondence table creation unit 90 (see FIG. 2). The correspondence table creation device 3 creates a correspondence table 46. The buried pipe data acceptance device 4 has the function of a buried pipe data acceptance unit 99. The buried pipe data acceptance device 4 accepts buried pipe data 50 from a customer. The storage device 5 has the function of a storage unit 20.

[0178] The buried environment classification map creating device 2 has the function of a map creating section 100 (see FIG. 2). The buried environment classification map creating device 2 includes a first map creating section 101 and a second map creating section .

[0179] The buried pipe deterioration degree prediction device 1b has the functions of a buried pipe deterioration degree prediction unit 130. Specifically, the buried pipe deterioration degree prediction device 1b includes a data preprocessing unit 131, a buried pipe deterioration degree calculation unit 132, a buried pipe deterioration degree prediction result generation unit 133, and a buried pipe deterioration degree prediction result output unit 134.

[0180] In this embodiment and its modified example, the number of buried environment classifications is four, namely, buried environments A and B, but the number of buried environment classifications is not limited to four.

[0181] The effects of the buried environment classification map creating device 2, buried pipe deterioration prediction device 1, buried environment classification map creating method, buried pipe deterioration prediction method, and program of this embodiment will be described.

[0182] The buried environment classification map creation device 2 of this embodiment includes a first map creation unit 101 and a second map creation unit 102. The first map creation unit 101 creates a general buried environment classification map 56a for the area corresponding to the pipeline map 51 from a pipeline map 51, which is a map of buried pipes, and a publicly available ground map 42. The second map creation unit 102 includes a ground selection unit 103 and an optimized buried environment classification map generation unit 110. The ground selection unit 103 selects a portion of the ground in the general buried environment classification map 56a based on water leakage accident data 53, which is a record of past water leakage accidents for each buried pipe. The optimized buried environment classification map generation unit 110 creates a buried environment classification map (optimized buried environment classification map 58a) optimized for the area corresponding to the pipeline map 51 by optimizing the buried environment classification of the portion of the ground through machine learning.

[0183] Therefore, it is possible to provide an optimized buried environment classification map (optimized buried environment classification map 58a) that enables more accurate prediction of the degree of deterioration of buried pipes.

[0184] In the buried environment classification map creating device 2 of this embodiment, the second map creating unit 102 includes an optimized buried environment classification map output unit (optimized integrated map output unit 118) that outputs an optimized buried environment classification map (optimized buried environment classification map 58a).

[0185] Therefore, it is possible to provide the customer with a buried installation environment classification map (optimized buried installation environment classification map 58a) that makes it easy for the customer to plan the renewal of buried pipes.

[0186] In the buried environment classification map creation device 2 of this embodiment, the portion of the ground is assigned a buried environment classification that indicates relatively high corrosiveness in the general buried environment classification map 56a, and includes the first ground in which no water leakage accident has occurred in the water leakage accident data 53.

[0187] Therefore, it is possible to provide an optimized buried environment classification map (optimized buried environment classification map 58a) that enables more accurate prediction of the degree of deterioration of buried pipes.

[0188] In the buried environment classification map creation device 2 of this embodiment, the portion of the ground is assigned a buried environment classification indicating relatively low corrosiveness in the general buried environment classification map 56a, and includes the second ground in which a water leak accident occurred in the water leak accident data 53.

[0189] Therefore, it is possible to provide an optimized buried environment classification map (optimized buried environment classification map 58a) that enables more accurate prediction of the degree of deterioration of buried pipes.

[0190] The buried pipe deterioration degree prediction device 1, 1b of this embodiment includes a buried pipe deterioration degree calculation unit 132. The buried pipe deterioration degree calculation unit 132 calculates the deterioration degree of each buried pipe (e.g., an estimated water leakage accident rate) from the buried environment of each buried pipe identified by a buried environment classification map (optimized buried environment classification map 58a) optimized for an area corresponding to a pipeline map 51, which is a map of buried pipes, first information related to the burial period of each buried pipe (e.g., the year the buried pipe was installed), second information related to the pipe thickness of each buried pipe (e.g., the nominal diameter, joint type, and type of pipe thickness of each buried pipe), and a buried pipe deterioration degree prediction model (e.g., water leakage accident rate prediction model 28). The optimized buried environment classification map is created by optimizing, through machine learning, the buried environment classification of a portion of the ground in a general buried environment classification map 56a of the area corresponding to the pipeline map 51. The general buried environment classification map 56a is created from the pipeline map 51 and the publicly available ground map 42. Some ground is selected from the general buried environment classification map 56a based on water leakage accident data 53, which is the past record of water leakage accidents for each buried pipe.

[0191] Therefore, by using a buried environment classification map (optimized buried environment classification map 58a) optimized for the area corresponding to the pipeline map 51, it becomes possible to predict the degree of deterioration of buried pipes.

[0192] The buried pipe deterioration prediction device 1, 1b of this embodiment further includes a buried pipe deterioration prediction result output unit 134 that outputs a buried pipe deterioration prediction map 67, which is a map showing the deterioration degree (e.g., estimated water leakage accident rate) of each buried pipe.

[0193] Therefore, it is possible to provide the customer with a buried installation environment classification map (optimized buried installation environment classification map 58a) that makes it easy for the customer to plan the renewal of buried pipes.

[0194] In the buried pipe deterioration prediction device 1, 1b of this embodiment, some of the ground is assigned a buried environment classification that indicates relatively high corrosiveness in the general buried environment classification map 56a, and includes a first ground in which no water leakage accident has occurred in the water leakage accident data 53.

[0195] Therefore, by using a buried environment classification map (optimized buried environment classification map 58a) optimized for the area corresponding to the pipeline map 51, it becomes possible to more accurately predict the degree of deterioration of buried pipes.

[0196] In the buried pipe deterioration prediction device 1, 1b of this embodiment, some of the ground is assigned a buried environment classification indicating relatively low corrosiveness in the general buried environment classification map 56a, and includes a second ground in which a water leak accident occurred in the water leak accident data 53.

[0197] Therefore, by using a buried environment classification map (optimized buried environment classification map 58a) optimized for the area corresponding to the pipeline map 51, it becomes possible to more accurately predict the degree of deterioration of buried pipes.

[0198] In the buried pipe deterioration degree prediction devices 1, 1b of the present embodiment, the deterioration degree of each buried pipe is the probability of a water leakage accident occurring in each buried pipe per unit time and per unit distance (estimated water leakage accident rate).

[0199] Therefore, by using a buried environment classification map (optimized buried environment classification map 58a) optimized for the area corresponding to the pipeline map 51, it becomes possible to more accurately predict the degree of deterioration of buried pipes.

[0200] The buried environment classification map creation method of this embodiment includes the steps of: creating a general buried environment classification map 56a for the area corresponding to the pipeline map 51 from the pipeline map 51, which is a map of buried pipes, and a publicly available ground map 42 (step S12); selecting a portion of the ground in the general buried environment classification map 56a based on water leakage accident data 53, which is the past record of water leakage accidents for each buried pipe; and creating a buried environment classification map (optimized buried environment classification map 58a) optimized for the area corresponding to the pipeline map 51 by optimizing the buried environment classification of the portion of the ground through machine learning (step S21).

[0201] Therefore, it is possible to provide an optimized buried environment classification map (optimized buried environment classification map 58a) that enables more accurate prediction of the degree of deterioration of buried pipes.

[0202] The buried environment classification map creating method of this embodiment further includes a step (step S23) of outputting the optimized buried environment classification map (optimized buried environment classification map 58a).

[0203] Therefore, it is possible to provide the customer with a buried installation environment classification map (optimized buried installation environment classification map 58a) that makes it easy for the customer to plan the renewal of buried pipes.

[0204] In the buried environment classification map creation method of this embodiment, some of the ground is assigned a buried environment classification that indicates relatively high corrosiveness in the general buried environment classification map 56a, and includes a first ground in which no water leakage accident has occurred in the water leakage accident data 53.

[0205] Therefore, it is possible to provide an optimized buried environment classification map (optimized buried environment classification map 58a) that enables more accurate prediction of the degree of deterioration of buried pipes.

[0206] In the buried environment classification map creation method of this embodiment, some of the ground is assigned a buried environment classification that indicates relatively low corrosiveness in the general buried environment classification map 56a, and includes a second ground in which a water leak accident occurred in the water leak accident data 53.

[0207] Therefore, it is possible to provide an optimized buried environment classification map (optimized buried environment classification map 58a) that enables more accurate prediction of the degree of deterioration of buried pipes.

[0208] The buried pipe deterioration prediction method of this embodiment includes a step (step S70) of calculating the deterioration level of each buried pipe (e.g., an estimated water leakage accident rate) from the buried environment of each buried pipe identified by a buried environment classification map (optimized buried environment classification map 58a) optimized for a region corresponding to a pipeline map 51, which is a map of buried pipes, first information regarding the burial period of each buried pipe (e.g., the year the buried pipe was installed), second information regarding the pipe thickness of each buried pipe (e.g., the nominal diameter, joint type, and pipe thickness type of each buried pipe), and a buried pipe deterioration prediction model (e.g., water leakage accident rate prediction model 28). The optimized buried environment classification map is created by optimizing the buried environment classification of a portion of the ground in a general buried environment classification map 56a for the region using machine learning. The general buried environment classification map 56a is created from the pipeline map 51 and a publicly available ground map 42. Some of the ground is selected from the general buried environment classification map 56a based on water leakage accident data 53, which is the past record of water leakage accidents for each buried pipe.

[0209] Therefore, by using a buried environment classification map (optimized buried environment classification map 58a) optimized for the area corresponding to the pipeline map 51, it becomes possible to more accurately predict the degree of deterioration of buried pipes.

[0210] The buried pipe deterioration degree prediction method of this embodiment further includes a step (step S81) of outputting a buried pipe deterioration degree prediction map 67 which is a map showing the deterioration degree (for example, estimated water leakage accident rate) of each buried pipe.

[0211] Therefore, it is possible to provide the customer with a buried installation environment classification map (optimized buried installation environment classification map 58a) that makes it easy for the customer to plan the renewal of buried pipes.

[0212] In the buried pipe deterioration prediction method of this embodiment, some of the ground is assigned a buried environment classification that indicates relatively high corrosiveness in the general buried environment classification map 56a, and includes a first ground in which no water leakage accident has occurred in the water leakage accident data 53.

[0213] Therefore, by using a buried environment classification map (optimized buried environment classification map 58a) optimized for the area corresponding to the pipeline map 51, it becomes possible to more accurately predict the degree of deterioration of buried pipes.

[0214] In the buried pipe deterioration prediction method of this embodiment, some of the ground is assigned a buried environment classification indicating relatively low corrosiveness in the general buried environment classification map 56a, and includes a second ground in which a water leak accident occurred in the water leak accident data 53.

[0215] Therefore, by using a buried environment classification map (optimized buried environment classification map 58a) optimized for the area corresponding to the pipeline map 51, it becomes possible to more accurately predict the degree of deterioration of buried pipes.

[0216] In the buried pipe deterioration degree prediction method of this embodiment, the deterioration degree of each buried pipe is the probability that a water leakage accident occurs in each buried pipe per unit time and per unit distance (estimated water leakage accident rate).

[0217] Therefore, by using a buried environment classification map (optimized buried environment classification map 58a) optimized for the area corresponding to the pipeline map 51, it becomes possible to more accurately predict the degree of deterioration of buried pipes.

[0218] The program of this embodiment (burial environment classification map creating program 31) causes the processor 12 to execute each step of the buried environment classification map creating method of this embodiment.

[0219] Therefore, it is possible to provide an optimized buried environment classification map (optimized buried environment classification map 58a) that enables more accurate prediction of the degree of deterioration of buried pipes.

[0220] The program of this embodiment (for example, buried pipe deterioration prediction program 32) causes the processor 12 to execute each step of the buried pipe deterioration prediction method of this embodiment.

[0221] Therefore, by using a buried environment classification map (optimized buried environment classification map 58a) optimized for the area corresponding to the pipeline map 51, it becomes possible to more accurately predict the degree of deterioration of buried pipes.

[0222] Various aspects of the present disclosure are summarized below as appendices.

[0223] (Appendix 1) a first map creation unit that creates a general buried pipe environment classification map for an area corresponding to a pipeline map based on a pipeline map, which is a map of buried pipes, and a publicly available ground map; a second map creating unit including a ground selecting unit and an optimized buried environment classification map creating unit; the ground selection unit selects a part of the ground from the general buried environment classification map based on water leakage accident data, which is a past record of water leakage accidents for each of the buried pipes; The optimized buried environment classification map generation unit generates a buried environment classification map optimized for the area by optimizing the buried environment classification of the portion of the ground through machine learning. (Appendix 2) 2. The buried environment classification map creating device according to claim 1, wherein the second map creating unit includes an optimized buried environment classification map output unit that outputs the optimized buried environment classification map. (Appendix 3) A buried environment classification map creation device as described in Appendix 1 or Appendix 2, wherein the part of the ground is assigned a buried environment classification that indicates relatively high corrosiveness in the general buried environment classification map, and includes a first ground in which no water leakage accident has occurred in the water leakage accident data. (Appendix 4) A buried environment classification map creation device described in any one of Appendix 1 to Appendix 3, wherein the part of the ground is assigned a buried environment classification that indicates relatively low corrosiveness in the general buried environment classification map, and includes a second ground in which a water leak accident occurred in the water leak accident data. (Appendix 5) a buried pipe deterioration degree calculation unit that calculates the deterioration degree of each of the buried pipes from the buried environment of each of the buried pipes identified by a buried environment classification map optimized for an area corresponding to a pipeline map that is a map of buried pipes, first information related to the buried period of each of the buried pipes, second information related to the pipe thickness of each of the buried pipes, and a buried pipe deterioration degree prediction model; The optimized buried storage environment classification map is created by optimizing the buried storage environment classification of a part of the ground of the general buried storage environment classification map of the region by machine learning, The general buried environment classification map is created from the pipeline map and a commonly available ground map, A buried pipe deterioration prediction device, wherein the part of the ground is selected from the general buried environment classification map based on water leakage accident data, which is the past record of water leakage accidents for each of the buried pipes. (Appendix 6) The buried pipe deterioration prediction device described in Appendix 5 further includes a buried pipe deterioration prediction result output unit that outputs a buried pipe deterioration prediction map, which is a map showing the deterioration degree of each of the buried pipes. (Appendix 7) A buried pipe deterioration prediction device as described in Appendix 5 or Appendix 6, wherein the part of the ground is assigned a buried environment classification that indicates relatively high corrosiveness in the general buried environment classification map, and includes a first ground in which no water leakage accident has occurred in the water leakage accident data. (Appendix 8) A buried pipe deterioration prediction device as described in any one of Appendix 5 to Appendix 7, wherein the part of the ground is assigned a buried environment classification that indicates relatively low corrosiveness in the general buried environment classification map, and includes a second ground in which a water leakage accident occurred in the water leakage accident data. (Appendix 9) A buried pipe deterioration prediction device described in any of Appendix 5 to Appendix 8, wherein the deterioration degree of each of the buried pipes is the probability of a water leakage accident occurring in each of the buried pipes per unit time and unit distance. (Appendix 10) A step of creating a general buried pipe environment classification map for an area corresponding to a pipeline map based on a pipeline map, which is a map of buried pipes, and a publicly available ground map; A step of selecting a part of the ground of the general buried environment classification map based on water leakage accident data which is the past record of water leakage accidents of each of the buried pipes; A buried environment classification map creation method comprising a step of generating a buried environment classification map optimized for the area by optimizing the buried environment classification of the portion of the ground using machine learning. (Appendix 11) 11. The buried environment classification map creating method according to claim 10, further comprising the step of outputting the optimized buried environment classification map. (Appendix 12) A buried environment classification map creation method as described in Appendix 10 or Appendix 11, wherein the part of the ground is assigned a buried environment classification that indicates relatively high corrosiveness in the general buried environment classification map, and includes a first ground in which no water leakage accident has occurred in the water leakage accident data. (Appendix 13) A buried environment classification map creation method described in any of Appendix 10 to Appendix 12, wherein the part of the ground is assigned a buried environment classification that indicates relatively low corrosiveness in the general buried environment classification map, and includes a second ground in which a water leak accident occurred in the water leak accident data. (Appendix 14) The method includes a step of calculating the degree of deterioration of each of the buried pipes from the buried environment of each of the buried pipes specified by a buried environment classification map optimized for an area corresponding to a pipeline map, which is a map of buried pipes, first information on the buried period of each of the buried pipes, second information on the pipe thickness of each of the buried pipes, and a buried pipe deterioration degree prediction model, The optimized buried storage environment classification map is created by optimizing the buried storage environment classification of a part of the ground of the general buried storage environment classification map of the region by machine learning, The general buried environment classification map is created from the pipeline map and a commonly available ground map, A buried pipe deterioration prediction method, wherein the part of the ground is selected from the general buried environment classification map based on water leakage accident data, which is the past record of water leakage accidents for each of the buried pipes. (Appendix 15) A buried pipe deterioration prediction method as described in Appendix 14, further comprising a step of outputting a buried pipe deterioration prediction map, which is a map showing the deterioration degree of each of the buried pipes. (Appendix 16) A buried pipe deterioration prediction method as described in Appendix 14 or Appendix 15, wherein the part of the ground is assigned a buried environment classification that indicates relatively high corrosiveness in the general buried environment classification map, and includes a first ground in which no water leakage accident has occurred in the water leakage accident data. (Appendix 17) A buried pipe deterioration prediction method as described in any one of Appendix 14 to Appendix 16, wherein the part of the ground is assigned a buried environment classification that indicates relatively low corrosiveness in the general buried environment classification map, and includes a second ground in which a water leakage accident occurred in the water leakage accident data. (Appendix 18) A buried pipe deterioration prediction method described in any of Appendix 14 to Appendix 17, wherein the deterioration degree of each of the buried pipes is the probability of a water leakage accident occurring in each of the buried pipes per unit time and unit distance. (Appendix 19) A program that causes a processor to execute each step of the buried environment classification map creation method described in any one of Supplementary Note 10 to Supplementary Note 13. (Appendix 20) A program that causes a processor to execute each step of the buried pipe deterioration prediction method described in any one of Supplementary Note 14 to Supplementary Note 18.

[0224] The embodiments disclosed herein should be considered to be illustrative in all respects and not restrictive. The scope of the present disclosure is defined by the claims, not by the above description, and is intended to include all modifications within the meaning and scope of the claims. [Explanation of symbols]

[0225] 1, 1b Buried pipe deterioration prediction device, 2 Buried environment classification map creation device, 3 Correspondence table creation device, 4 Buried pipe data reception device, 5 Storage device, 6 Communication network, 7 Buried pipe deterioration prediction system, 11 Input device, 12 Processor, 13 Memory, 14 Display, 16 Network controller, 17 Storage medium drive, 18 Storage medium, 19 Storage, 20 Memory unit, 21 Investigation pipe data memory unit, 22 Ground map database unit, 23 Correspondence table memory unit, 24 Buried pipe data memory unit, 25 Map memory unit, 26 Nominal pipe thickness database unit, 27 Water leakage accident rate prediction model memory unit, 28 Water leakage accident rate prediction model, 29 Buried pipe deterioration prediction result memory unit, 30 Program memory unit, 31 Buried environment classification map creation program, 32 Buried pipe deterioration prediction program, 33 Correspondence table creation program, 40 Investigation pipe data, 42 Ground map, 43 Surface geological map, 44 Topography classification map, 46 Ground information - Ground ID - Corrosion rate - Buried environment correspondence table, 50 Buried pipe data, 51 Pipeline map, 52 Buried pipe attribute data, 53 Water leakage accident data, 54 Water leakage accident map, 55 Water leakage accident data collection period, 56 General integrated map, 56a General buried environment classification map, 56b Ground ID map, 58 Optimized integrated map, 58a Optimized buried environment classification map, 60 Nominal pipe thickness data, 65 Buried pipe deterioration prediction result, 66 Buried pipe deterioration prediction table, 67 Buried pipe deterioration prediction map, 70 First preprocessed buried pipe data, 74 Second preprocessed buried pipe data, 76 Estimated water leakage accident rate result, 78 Third preprocessed buried pipe data, 90 Correspondence table creation unit, 91 Corrosion rate calculation unit, 92 Ground information acquisition unit, 93 Ground ID assignment unit, 94 Representative corrosion rate calculation unit, 95 Buried environment classification unit, 96 Correspondence table generation unit, 97 Correspondence table output unit, 99 Buried pipe data reception unit, 100 Map creation unit, 101 First map creation unit, 102 Second map creation unit, 103 Ground selection unit, 104, 121, 131 Data preprocessing unit, 105 Estimated water leakage accident number calculation unit, 106 Actual water leakage accident number calculation unit, 107,113 judgment unit, 110 optimized buried environment classification map generation unit, 111 initial population generation unit, 112 fitness calculation unit, 114 new generation population generation unit, 116 optimized integrated map generation unit, 118 optimized integrated map output unit, 120 modified integrated map creation unit, 122 estimated water leakage accident rate calculation unit, 123 estimated water leakage accident rate result creation unit, 124 water leakage accident number calculation unit, 125 pipe renewal rate calculation unit, 130 buried pipe deterioration degree prediction unit, 132 buried pipe deterioration degree calculation unit, 133 buried pipe deterioration degree prediction result generation unit, 134 buried pipe deterioration degree prediction result output unit.

Claims

1. a first map creation unit that creates a general buried environment classification map of an area corresponding to a pipeline map from a pipeline map, which is a map of buried pipes, and a publicly available ground map, the general buried environment classification map being a map of buried environment classification of the ground of the area, and the buried environment classification classifying the buried environment of the ground according to the corrosiveness of the ground to the buried pipes; a second map creating unit including a ground selecting unit and an optimized buried environment classification map creating unit; the ground selection unit selects a portion of the ground in the general buried environment classification map based on water leakage accident data, which is a past record of water leakage accidents for each of the buried pipes; The optimized buried environment classification map generation unit uses the water leakage accident data to optimize the buried environment classification of the part of the ground through machine learning, thereby generating an optimized buried environment classification map that is a buried environment classification map optimized for the area.

2. 2. The buried environment classification map creating device according to claim 1, wherein the second map creating section includes an optimized buried environment classification map output section that outputs the optimized buried environment classification map.

3. The buried environment classification map creation device of claim 1 or claim 2, wherein the portion of the ground is assigned a buried environment classification indicating relatively high corrosiveness in the general buried environment classification map and includes a first ground in which no water leakage accident has occurred in the water leakage accident data.

4. The buried environment classification map creation device of claim 1 or claim 2, wherein the portion of the ground is assigned a buried environment classification indicating relatively low corrosiveness in the general buried environment classification map, and includes a second ground in which a water leak accident occurred in the water leak accident data.

5. A buried pipe deterioration prediction device comprising a buried pipe deterioration degree calculation unit that calculates the deterioration degree of each of the buried pipes from the buried environment of each of the buried pipes identified by the optimized buried environment classification map created by the buried environment classification map creation device described in claim 1, first information regarding the burial period of each of the buried pipes, second information related to the pipe thickness of each of the buried pipes, and a buried pipe deterioration degree prediction model.

6. The buried pipe deterioration prediction device according to claim 5, further comprising a buried pipe deterioration prediction result output unit that outputs a buried pipe deterioration prediction map, which is a map showing the deterioration degree of each of the buried pipes.

7. The buried pipe deterioration prediction device of claim 5 or claim 6, wherein the portion of the ground is assigned a buried environment classification that indicates relatively high corrosiveness in the general buried environment classification map and includes a first ground in which no water leakage accidents have occurred in the water leakage accident data.

8. The buried pipe deterioration prediction device of claim 5 or claim 6, wherein the portion of the ground is assigned a buried environment classification indicating relatively low corrosiveness in the general buried environment classification map, and includes a second ground in which a water leak accident occurred in the water leak accident data.

9. 7. The buried pipe deterioration prediction device according to claim 5, wherein the deterioration degree of each of the buried pipes is a probability of a water leakage accident occurring in each of the buried pipes per unit time and per unit distance.

10. A buried environment classification map creation method executed by a processor, comprising: a step of creating a general buried environment classification map of an area corresponding to the pipeline map from a pipeline map, which is a map of buried pipes, and a publicly available ground map, the general buried environment classification map being a map of buried environment classification of the ground of the area, and the buried environment classification classifying the buried environment of the ground according to the corrosiveness of the ground to the buried pipes; selecting a part of the ground in the general buried environment classification map based on water leakage accident data, which is the past record of water leakage accidents of each of the buried pipes; and generating an optimized buried environment classification map, which is a buried environment classification map optimized for the area, by optimizing the buried environment classification of the portion of the ground through machine learning using the water leakage accident data.

11. The buried environment classification map creating method according to claim 10 , further comprising the step of outputting the optimized buried environment classification map.

12. The buried environment classification map creation method of claim 10, wherein the portion of the ground is assigned a buried environment classification indicating relatively high corrosiveness in the general buried environment classification map and includes a first ground in which no water leakage accidents have occurred in the water leakage accident data.

13. The buried environment classification map creation method of claim 10, wherein the portion of the ground is assigned a buried environment classification indicating relatively low corrosiveness in the general buried environment classification map, and includes a second ground in which a water leak accident occurred in the water leak accident data.

14. A buried pipe deterioration prediction method executed by a processor, comprising: A buried pipe deterioration prediction method comprising a step of calculating the deterioration degree of each of the buried pipes from the buried environment of each of the buried pipes identified by the optimized buried environment classification map created by the buried environment classification map creation method described in claim 10, first information regarding the burial period of each of the buried pipes, second information related to the pipe thickness of each of the buried pipes, and a buried pipe deterioration degree prediction model.

15. The buried pipe deterioration prediction method according to claim 14, further comprising the step of outputting a buried pipe deterioration prediction map which is a map showing the deterioration degree of each of the buried pipes.

16. The buried pipe deterioration prediction method of claim 14, wherein the portion of the ground is assigned a buried environment classification that indicates relatively high corrosiveness in the general buried environment classification map and includes a first ground in which no water leakage accidents have occurred in the water leakage accident data.

17. The buried pipe deterioration prediction method of claim 14, wherein the portion of the ground is assigned a buried environment classification indicating relatively low corrosiveness in the general buried environment classification map, and includes a second ground in which a water leak accident occurred in the water leak accident data.

18. 15. The buried pipe deterioration degree prediction method according to claim 14, wherein the deterioration degree of each of the buried pipes is a probability of a water leakage accident occurring in each of the buried pipes per unit time and per unit distance.

19. A program that causes the processor to execute each step of the buried environment classification map creation method according to any one of claims 10 to 13.

20. A program that causes the processor to execute each step of the buried pipe deterioration prediction method according to any one of claims 14 to 18.

Images