JP7343025B1 - Prediction device, prediction method and computer program - Google Patents

Abstract

[Problem] To provide a technology that can output information that is easy to use in formulating a renewal plan for buried pipes such as water pipes, and that makes it easy to explain the basis for formulating the plan. SOLUTION: An acquisition unit of a prediction device acquires attribute information representing attributes of a buried pipe to be predicted. The prediction unit uses the age prediction model and the attribute information of the buried pipe to be predicted to calculate the predicted number of years of use of the buried pipe to be predicted. The age prediction model is generated by machine learning of the relationship data between the actual usage age information representing the number of years of use from installation to breakage of a buried pipe and the attribute information of the buried pipe. It takes the input as input and outputs the predicted service life of the buried pipe. The prediction unit further uses the predicted number of years of use and installation time information indicating the installation time included in the attribute information of the buried pipe to be predicted to predict the time when the buried pipe to be predicted will be damaged. Calculated as [Selection diagram] Figure 9

Description

The present invention is a technology related to providing information regarding the timing of replacing (updating) buried pipes such as water pipes.

Water supply, which is one of the lifelines, is required to provide a continuous supply of tap water. However, since water pipes deteriorate over time, accidents such as water leakage and water pipe bursting may occur due to damage to the water pipes due to aging. Such accidents hinder the continued stable supply of tap water. Therefore, in order to prevent such accidents from occurring, work is being carried out to gradually replace (update) old water pipes with new ones.

Note that Patent Document 1 discloses that a buried period from when a buried pipe is buried to when the corrosion depth of the buried pipe is estimated to reach an allowable corrosion depth is calculated. Furthermore, Patent Document 1 discloses that the remaining period until the allowable corrosion depth is reached is calculated by subtracting the period during which the buried pipe was actually buried from the calculated period of burial. ing. Patent Document 2 discloses a technique for evaluating the risk of a water leakage accident in a pipe in a water facility based on pipe attributes. Patent Document 3 discloses a technique for estimating the amount of water leakage for each area, which is used when formulating a water leakage investigation plan for a plurality of areas into which a water pipe network is divided.

JP 2021-56224 Publication JP 2021-140332 Publication JP2015-94665A

Patent Documents 1 to 3 use the depth of corrosion of buried pipes, the risk of water leakage accidents in pipes, and the amount of water leakage in an area as information (indices) representing the deterioration status of buried water pipes. Suppose that when planning the renewal work of water pipes, the time for renewal of the water pipes is determined using information representing the state of deterioration of the water pipes. Regarding the renewal timing of water pipes determined in this way, even if the above-mentioned numerical values representing the depth of corrosion of buried pipes, the risk of water leakage accidents, and the amount of water leakage are presented as the basis for determining the renewal timing, for example, the renewal plan The problem is that it is difficult for those who are formulating a plan to understand the basis for when it should be updated.

The present invention was devised to solve the above problems. That is, the main object of the present invention is to provide a technology that can output information that is easy to use in formulating a renewal plan for buried pipes such as water pipes and that makes it easy to explain the basis for formulating the plan.

In order to achieve the above object, the prediction device according to the present invention includes, as one aspect thereof,
an acquisition unit that acquires attribute information representing attributes of the buried pipe to be predicted;
It is generated by machine learning of the relationship data between the actual usage years information representing the number of years of use from installation to breakage of the buried pipe and the attribute information of the buried pipe, and the attribute information of the buried pipe to be predicted is input. Calculating the predicted number of years of use of the buried pipe to be predicted, using a years prediction model that outputs the predicted number of years of use from installation to breakage as the predicted number of years of use, and attribute information of the buried pipe to be predicted; Furthermore, using the predicted number of years of use and the installation time information indicating the installation time included in the attribute information of the buried pipe to be predicted, the time when the buried pipe to be predicted is predicted to break is set as the predicted failure time. A prediction unit that calculates;
and an output unit that outputs predicted failure time information expressing the predicted failure time using a calendar year or a fiscal year.

Further, as one aspect of the prediction method according to the present invention,
by computer,
Obtain attribute information representing the attributes of the buried pipe to be predicted,
It is generated by machine learning of the relationship data between the actual usage years information representing the number of years of use from installation to breakage of the buried pipe and the attribute information of the buried pipe, and the attribute information of the buried pipe to be predicted is input. Calculating the predicted number of years of use of the buried pipe to be predicted, using a years prediction model that outputs the predicted number of years of use from installation to breakage as the predicted number of years of use, and attribute information of the buried pipe to be predicted; Furthermore, using the predicted number of years of use and the installation time information indicating the installation time included in the attribute information of the buried pipe to be predicted, the time when the buried pipe to be predicted is predicted to break is set as the predicted failure time. Calculate,
Predicted failure time information expressing the predicted failure time using a calendar year or fiscal year is output.

Furthermore, as one aspect of the computer program according to the present invention,
A process of acquiring attribute information representing attributes of a buried pipe to be predicted;
It is generated by machine learning of the relationship data between the actual usage years information representing the number of years of use from installation to breakage of the buried pipe and the attribute information of the buried pipe, and the attribute information of the buried pipe to be predicted is input. Calculating the predicted number of years of use of the buried pipe to be predicted, using a years prediction model that outputs the predicted number of years of use from installation to breakage as the predicted number of years of use, and attribute information of the buried pipe to be predicted; Furthermore, using the predicted number of years of use and the installation time information indicating the installation time included in the attribute information of the buried pipe to be predicted, the time when the buried pipe to be predicted is predicted to break is set as the predicted failure time. The calculation process and
The computer is caused to execute a process of outputting predicted failure time information expressing the predicted failure time using a calendar year or a fiscal year.

According to the present invention, it is possible to output information that is easy to use for formulating a renewal plan for buried pipes such as water pipes, and that is easy to explain the basis for formulating the plan.

FIG. 1 is a diagram illustrating the configuration of a prediction device according to a first embodiment of the present invention. FIG. 3 is a diagram illustrating an example of a mode in which predicted failure time information is displayed on a display device. FIG. 3 is a diagram illustrating an example of a mode in which an explanation of the basis of the calculated predicted number of years of use is displayed on a display device. FIG. 3 is a diagram illustrating an example of a mode in which information regarding the calculated predicted number of years of use is displayed on a display device. FIG. 3 is a diagram illustrating an example of a mode in which predicted failure time information is displayed on a display device by superimposing it on a map. It is a flow chart explaining an example of operation in a prediction device of a 1st embodiment. It is a figure explaining a 2nd embodiment. It is a figure explaining other embodiments. It is a block diagram showing the composition of the prediction device of other embodiments concerning the present invention. It is a flowchart explaining an example of operation of a prediction device in other embodiments.

Embodiments according to the present invention will be described below with reference to the drawings.

<First embodiment>
FIG. 1 is a diagram illustrating the configuration of a prediction device according to a first embodiment of the present invention. This prediction device 1 is a device that predicts when a buried pipe will break. A buried pipe is a pipe that is buried underground. There are multiple types of buried pipes, such as water pipes, sewer pipes, gas pipes, etc. Here, the configuration of the prediction device will be explained using a water pipe, which is a type of buried pipe, as an example. In addition, "the buried pipe (water pipe) is damaged" here refers to a state in which damage such as cracks and holes has occurred in the water pipe due to deterioration of the water pipe.

The prediction device 1 is a computer device, and is connected to an information source 3, a database 4, an input device 5, and a display device 7. Furthermore, the prediction device 1 can be connected to a printer 8 if necessary. The input device 5 is composed of a keyboard, a mouse, etc., and is a device that inputs information to the prediction device 1 according to a user's operation. The display device 7 is a device that displays information on a screen using characters and images. The printer 8 is a device that receives data such as characters, images, and graphics from a computer and prints it on paper or the like.

The information source 3 is an information source that can provide information used for processing performed by the prediction device 1. Specific examples of the information source 3 include computer equipment and databases of systems that manage water pipes. Information regarding water pipes to be predicted is provided from such an information source 3 to the prediction device 1. The database 4 is a storage device, and stores information provided to the prediction device 1 from the information source 3, information input to the prediction device 1 by the input device 5, and the like.

The prediction device 1 includes a calculation device 10 and a storage device 40. The storage device 40 includes a storage medium that stores data and a computer program (hereinafter also referred to as a program) 41. There are multiple types of storage devices such as magnetic disk drives and semiconductor memory devices, and there are also multiple types of semiconductor memory devices such as RAM (Random Access Memory) and ROM (Read Only Memory). As such, there are many types. The type of storage device 40 included in the prediction device 1 is not limited to one type. Computer devices are often equipped with multiple types of storage devices. Here, the type and number of storage devices 40 provided in the prediction device 1 are not limited, and the description thereof will be omitted. Furthermore, when the prediction device 1 is equipped with multiple types of storage devices 40, they are collectively referred to as the storage device 40.

The arithmetic device 10 includes a processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit). By reading and executing the program 41 stored in the storage device 40, the arithmetic device 10 can have various functions based on the program 41. Here, the arithmetic device 10 includes an acquisition section 11, a prediction section 12, and an output section 13 as functional sections involved in a breakage time prediction process that predicts when a water pipe will break.

The acquisition unit 11 acquires attribute information representing the attributes of the water pipe to be predicted. The water pipe attribute information obtained here is used to predict the service life of the water pipe. Here, the service life of a water pipe is the number of years from when the water pipe is buried until the water pipe breaks. The main cause of water pipe breakage is deterioration. In other words, deterioration causes damage to water pipes, such as cracks and holes. The service life of water pipes is related to the rate of deterioration in the water pipes. For this reason, the water pipe attribute information acquired by the acquisition unit 11 includes information that is assumed to be involved in the rate of progress of deterioration of the water pipe (hereinafter also referred to as deterioration-related information). In other words, the deterioration-related information is information representing elements related to the deterioration of water pipes.

For example, the attribute information of water pipes acquired by the acquisition unit 11 includes installation location information and installation time information, and furthermore, as deterioration related information, pipe size information, pipe type information, usage information, and information on buried pipes. Contains soil information. The installation location information is information including the address and pipe length indicating the location where the water pipe is buried. To give a specific example, the address information included in the installation location information is address information such as 3-1, ○○○-cho, △△-ku. The information on the pipeline extension included in the installation location information is information on the pipeline length, such as a pipeline distance of 300 meters. Note that the address of the water pipe to be predicted is an address based on a predetermined rule, such as an address corresponding to a position half the length of the water pipe to be predicted. The installation time information is information indicating the time when the water pipe was buried, and is, for example, information expressed by a calendar year (for example, Western calendar) or a fiscal year.

The pipe size information is information representing the size of the water pipe, and includes information representing the diameter and pipe thickness (wall thickness) indirectly or directly, for example. The pipe type information is type information that classifies water pipes based on the material of the water pipes. Specific examples of water pipe types include ductile cast iron pipes, stainless steel pipes, polyethylene pipes, and the like. The usage information is information representing the usage of the water pipe, and is information related to the water pressure, water volume, and water flow of the tap water flowing inside the pipe. The information on the buried soil is, for example, information such as sand, silt, and clay. Further, the soil information may include information representing soil quality such as moisture content and acidity.

Furthermore, the attribute information may include information representing the quality of tap water flowing through the water pipe (for example, the content rate of components such as chlorine) as deterioration-related information. Furthermore, the attribute information includes information on factors that may have an effect on water pipes as deterioration-related information (for example, if a water pipe is buried in a road, information on the traffic volume on the road, Information on the water pressure, water volume, and water flow of flowing tap water may also be included. Note that information representing the state of tap water, such as the quality, pressure, and volume of water flowing through water pipes, may fluctuate for some reason, so for example, if the water quality, pressure, and volume are continuously measured, Alternatively, measurement may be performed intermittently (for example, once a day) and the measurement data may be retained. Then, from the measurement data, for example, an average value for the most recent predetermined period (for example, three months) is calculated. This average value may be included in the attribute information as information representing the state of the fluid (tap water) flowing inside the water pipe during a predetermined period. That is, the attribute information of the water pipe to be predicted may include information representing the state of the tap water flowing inside the water pipe during a predetermined period.

The above-mentioned water pipe attribute information is stored, for example, in a database of a water pipe management system built in a water utility, or in a database connected to a personal computer used by a water utility's staff. The data is held electronically in the database. The prediction device 1 calculates water pipe attribute information from the database (that is, the information source 3) used by such water utilities, for example, in response to the user's operation of the input device 5 or at predetermined time intervals. It is read out and stored in the database 4. In the database 4, attribute information of water pipes is associated with pipe identification information that identifies the water pipe.

When the user operates the input device 5 to request the start of the breakage time prediction process and the pipe identification information corresponding to the water pipe to be predicted is input to the prediction device 1, the acquisition unit 11 detects the pipe identification information. Using the information, attribute information of the water pipe to be predicted is acquired from the database 4. The attribute information acquired by the acquisition unit 11 is attribute information predetermined as information to be acquired from among the plurality of types of attribute information as described above, and here, at least one deterioration-related information and installation time information. including.

For example, it is conceivable that the attribute information of water pipes held by each water utility is different. In such a case, the type of water pipe attribute information to be acquired by the acquisition unit 11 is determined for each water utility. Then, the acquisition unit 11 acquires the type of attribute information according to the water utility that manages the water pipe that is the prediction target. Note that in such a case, for example, the pipe identification information for identifying the water pipe includes information representing the managing water utility or information representing the municipality that operates the water utility. Further, when there are a plurality of water pipes to be predicted and a plurality of pipe identification information corresponding to each of the water pipes to be predicted is input, the acquisition unit 11 acquires the attribute information of the water pipes to be predicted. All data are acquired from the database 4.

The prediction unit 12 predicts when the target water pipe will break. That is, the prediction unit 12 first calculates the predicted number of years of use of the water pipe to be predicted. The predicted number of years of use is the expected number of years from when a water pipe is buried until the water pipe breaks. The prediction unit 12 uses AI (Artificial Intelligence) technology to calculate the predicted number of years of use. That is, the prediction unit 12 uses the age prediction model generated by AI technology to calculate the predicted number of years of use of the water pipe to be predicted. The age prediction model is a model that inputs the attribute information of the water pipe to be predicted and outputs the predicted service life of the water pipe to be predicted.It is generated by machine learning using the following training data. Ru. The teacher data used to generate the age prediction model is data in which the actual number of years of use of a water pipe is associated with the attribute information of the water pipe (relationship data between the number of years of actual use and the attribute information of the water pipe). The actual service life of a water pipe is the number of years from the time the water pipe was installed until the water pipe actually breaks. The attribute information associated with the actual number of years of use is attribute information of the actually damaged water pipe, and includes at least one piece of deterioration-related information. The attribute information of the water pipe to be predicted, which is input to the age prediction model, is the type of attribute information included in the attribute information of the teacher data used for machine learning of the age prediction model, and includes installation location information and installation time information. and at least one deterioration related information.

For example, the type of attribute information for water pipes held by water utilities may differ, and in this case, the types of attribute information that can be used to generate (learn) the age prediction model differ depending on the water utility. There are cases. In such a case, for example, multiple types of age prediction models are generated for each water utility (in other words, for each area). In other words, multiple types of age prediction models are prepared based on different types of water pipe attribute information used to generate age prediction models. In this way, there are cases where a plurality of age prediction models are prepared which the prediction unit 12 uses to calculate the predicted years of use. In this case, the prediction unit 12 selects an age prediction model to be used for calculating the predicted number of years of use from among the plurality of types of age prediction models according to the type of information included in the attribute information of the water pipe to be predicted. Select a model for predicting the number of years. Then, the prediction unit 12 uses the selected age prediction model and the attribute information of the water pipe to be predicted to calculate the predicted number of years of use of the water pipe to be predicted.

Note that there are multiple methods for generating the age prediction model. As mentioned above, when a number of years prediction model is prepared for each water utility, a number of years prediction model generated using the same generation method may be prepared for each water utility; Instead of preparing a prediction model for each water utility, a model for predicting the number of years generated using a generation method depending on the water utility may be prepared as follows. That is, first, a plurality of age prediction models using different generation methods are generated for each water utility, and the predicted number of years of use is actually calculated using each of the generated multiple age prediction models. In this calculation process, attribute information of water pipes for which information on the actual number of years of use has been obtained is input into the age prediction model. Then, the output result from the age prediction model is compared with the actual number of years of use, and the age prediction model generated using the generation method that is determined to be suitable for the water utility based on the comparison results is selected for the water utility. It is used as an age prediction model corresponding to the body.

By the way, one type of AI technology is explainable AI (Artificial Intelligence). Explainable AI is an AI technology that can output not only the result of calculation from a model, but also an explanation of the basis on which the result was calculated. Here, the age prediction model is an explainable model generated using the explainable AI technology. As a result, the age prediction model not only outputs the predicted number of years of use by inputting the attribute information of the water pipe to be predicted, but also outputs information explaining the basis for outputting the predicted number of years of use. Note that there are multiple types of explainable AI technology, and the type of explainable AI technology employed here is not limited, so the explanation thereof will be omitted.

Further, the prediction unit 12 uses the predicted number of years of use outputted from the age prediction model and the installation time information included in the attribute information regarding the water pipe to be predicted, to predict whether the water pipe to be predicted is damaged or not. The expected time when it will be put away (herein also referred to as the predicted breakage time) is calculated. That is, the prediction unit 12 calculates the predicted failure time by adding the predicted number of years of use to the installation time (installation year) included in the installation time information. Specifically, for example, if the installation date of the water pipe to be predicted is 1975 A.D. and the predicted number of years of use is 52 years, the predicted breakage time can be calculated by adding 52 years to 1975 A.D. The prediction unit 12 calculates that it is the year 2027. Note that if the installation time in the installation time information included in the attribute information is expressed in years rather than calendar years, the predicted breakage time calculated by the prediction unit 12 will also be expressed in years.

In this way, the prediction unit 12 calculates the predicted breakage time of the water pipe to be predicted, expressed in terms of calendar year or fiscal year. The calculated predicted failure time information is stored in the database 4 with associated pipe identification information, attribute information, predicted years of use, and explanation of the basis for calculating the predicted years of use of the corresponding water pipe. Stored.

The output unit 13 outputs predicted failure time information representing the predicted failure time calculated by the prediction unit 12. For example, the output unit 13 receives a request to display predicted breakage time information and information specifying a water pipe for which the predicted breakage time information is to be displayed (in other words, a water pipe to be displayed) in response to a user's operation of the input device 5. When input to the prediction device 1, the output unit 13 causes the display device 7 to display predicted breakage time information of the water pipe to be displayed. That is, the output unit 13 has a function of controlling the display operation of the display device 7. For example, a display template used for displaying predicted breakage time information is provided to the prediction device 1, and the output unit 13 uses the display template to display predicted breakage time information for the water pipe to be displayed on the screen of the display device 7. to be displayed. Although the aspect of the display template is not limited, an example thereof is shown in FIG. In the example of FIG. 2, the display template is in the form of a table, and in the table, predicted breakage time information for the water pipe to be displayed is displayed in association with attribute information and information on the estimated number of years of use of the water pipe. There is. In the first embodiment, as described above, the age prediction model used to calculate the predicted years of use is an explainable model. Therefore, an explanation of the basis for the calculated predicted number of years of use is output from the number of years prediction model. The explanation of this basis is stored in the database 4 in association with the information on the predicted number of years of use. When displaying information on the predicted number of years of use on the display device 7, the output unit 13 may also output an explanation of the basis to the display device 7 and display it on the display device 7. For example, the explanation of the basis may be incorporated into a table as shown in FIG. 2 and displayed, or displayed as a pop-up as shown in FIG. 3.

Note that when displaying information including predicted breakage timing information regarding a plurality of water pipes in a table as shown in FIG. It may also have a sorting function. In other words, the output unit 13 arranges information including predicted breakage time information regarding a plurality of prediction target water pipes in order of predicted breakage time, in order of oldest installation year, or in advance into categories. It is also possible to display them together by region.

Further, the output unit 13 may display an explanation of the basis of the predicted breakage time information regarding the water pipe on the display device 7 in a display mode as shown in FIG. In the example in Figure 4, for the water pipe for which an explanation was requested (in the example in Figure 4, the water pipe with pipe identification information: Ab-fmw), the information on the explanation of the basis output from the age prediction model is displayed in a table or graph. It is expressed using In other words, on the display device 7, information on the water pipe features used by the age prediction model to calculate the predicted service life of the water pipe is displayed in the form of a table, and the target water pipe (for example, pipe identification information : The degree of involvement (importance) of the feature amount that influences the predicted number of years of use of the Ab-fmw water pipe) is displayed. Furthermore, in the example of FIG. 4, the display device 7 displays written explanations of the grounds based on the items represented in the tables and graphs.

Another example of a mode in which the output unit 13 displays the predicted breakage time information on the display device 7 is a display mode in which the predicted breakage time information is superimposed on a map 30 as shown in FIG. In the example of FIG. 5, in the map 30, information of colors and patterns representing the predicted breakage time of the water pipe is superimposed on the road portion where the water pipe to be displayed is buried. In other words, if the predicted breakage time of a water pipe is within the period up to 2025 AD, the information representing the predicted breakage time is determined to be A pattern color or hatching, and the predicted breakage time of the water pipe is within the period up to 2025 AD. If it is within the period from 2030 to 2030, the color or hatching representing the predicted failure time is determined, such as the information representing the predicted failure time is determined to be the color or hatching of pattern B. In the map 30, information about the predicted breakage time of the water pipe, represented by predetermined colors and hatching, is superimposed on the road portion where the water pipe to be displayed is buried. Note that, as shown in FIG. 5, when information on the predicted breakage time of water pipes is superimposed on the map 30, the output unit 13 displays the water pipe ( Information indicating the area where the water pipe to be displayed is buried is input. Thereby, the output unit 13 can display on the display device 7 the map 30 including the area where the water pipes to be displayed are buried.

When an instruction to print predicted breakage time information is input to the prediction device 1 through the user's operation of the input device 5, the output unit 13 outputs the predicted breakage time information of the requested print target. is printed by the printer 8.

The prediction device 1 of the first embodiment is configured as described above. Next, an example of the operation of the failure time prediction process in the prediction device 1 will be described with reference to FIG. 6. FIG. 6 is a flowchart illustrating an example of the operation of the failure time prediction process in the prediction device 1.

For example, when a request to start a breakage time prediction process is input to the prediction device 1 by a user's operation on the input device 5, the acquisition unit 11 receives the request to start the process (step 101 in FIG. 6). This process start request is associated with pipe identification information corresponding to the water pipe to be predicted. The acquisition unit 11 uses the pipe identification information to acquire attribute information of the water pipe to be predicted from the database 4 (step 102).

Thereafter, the prediction unit 12 calculates the predicted number of years of use of the water pipe to be predicted (step 103). In the first embodiment, an age prediction model based on AI technology is used to calculate the predicted years of use. That is, the prediction unit 12 calculates the predicted number of years of use by inputting the attribute information of the water pipe to be predicted into the number of years prediction model, and performs a calculation operation using the number of years prediction model.

After that, the prediction unit 12 calculates the predicted breakage time expressed by calendar year or fiscal year by adding the installation time information included in the attribute information and the predicted number of years of use regarding the water pipe to be predicted. (step 104). The prediction unit 12 stores information on the predicted failure time calculated in this way in the database 4. The predicted breakage time information stored in the database 4 is associated with the corresponding water pipe's pipe identification information, attribute information, information on the predicted number of years of use, and information explaining the basis on which the predicted number of years of use was calculated. There is.

In this way, the failure time prediction process is executed. When a request to display the predicted breakage time information calculated by such processing and information specifying the water pipe to be displayed are input to the prediction device 1 by the user's operation of the input device 5, the output unit 13 causes the display device 7 to display predicted breakage timing information for the water pipe to be displayed.

As described above, the prediction device 1 of the first embodiment calculates the predicted number of years of use using the number of years prediction model based on AI technology. The age prediction model performs machine learning on relationship data between information on the actual number of years of use of a water pipe and attribute information of the water pipe (attribute information including installation location information, installation time information, and at least one deterioration-related information). Generated by That is, in the first embodiment, in order to calculate the predicted number of years of use, attention is focused on the relationship between the actual number of years of use of the water pipe and the attribute information, rather than the breakage of the water pipe itself. As a result, in the first embodiment, the age prediction model receives input of the pipe identification information and attribute information of the water pipe to be predicted, and calculates the predicted service life (the number of years from when the water pipe is buried until it is predicted to break). ) can be output.

Furthermore, the prediction unit 12 calculates the predicted breakage time represented by the calendar year or fiscal year by adding the predicted number of years of use to the installation year (calendar year) or installation year representing the installation time of the water pipe to be predicted. Calculate information on when the pipe is predicted to break. This calculated predicted failure time information is outputted by the output unit 13 as predicted failure time information. Since this predicted breakage time information is expressed in calendar years or fiscal years, it can be used as is, for example, when determining the timing of water pipe renewal work. In other words, the predicted breakage timing information is information that is easy to use in formulating a water pipe renewal plan. Furthermore, since the predicted breakage time information is information expressed in calendar years or fiscal years, by presenting the predicted breakage time information, it is possible to clearly communicate the time when the water pipes should be updated. In other words, the predicted breakage time information is information that facilitates explanation of the water pipe renewal time in the water pipe renewal plan formulated using the information.

Furthermore, in the first embodiment, since the age prediction model that calculates the predicted years of use used to calculate the predicted breakage time is an explainable model, the basis for the calculated predicted years of use is explained using the years prediction model. is output from. When a water pipe renewal plan is formulated using the predicted breakage timing information output from the prediction device 1, the explanation output from the age prediction model is used to explain the renewal plan. The plan can be more convincing.

In addition, when generating the age prediction model by machine learning, information about the causal relationship between the actual usage age information of the water pipe obtained by causal analysis technology and the attribute information of the water pipe may also be learned by machine learning. . As a result, the explanation of the basis for the predicted service life output from the age prediction model, which is an explainable model, includes an explanation of the causal relationship between the predicted service life and the attribute information of buried pipes, and this means that It is possible to further increase the credibility (reliability) of the predicted years of use and predicted breakage time.

Furthermore, the prediction device 1 may be connected to a terminal device 6 as indicated by the dotted line in FIG. The terminal device 6 is an information device having a communication function and a display function, and here, specific examples include portable information devices such as a smartphone and a tablet terminal. When the prediction device 1 is connected to the terminal device 6, the output unit 13 may have the following functions. That is, when the output unit 13 receives a request for predicted breakage time information and information specifying the requested water pipe from the terminal device 6, the output unit 13 outputs the predicted breakage time of the requested water pipe according to the request. The information is sent back (output) to the terminal device 6. In the first embodiment, the terminal device 6 (or user) permitted to receive predicted water pipe breakage timing information is registered in advance in the storage device 40 or the like. Authentication processing for the terminal device 6 (or user) is executed by the prediction device 1 using this registration information and a predetermined authentication method. The output unit 13 outputs predicted breakage time information to the terminal device 6 (or user) authenticated by the authentication process.

Furthermore, the prediction device 1 may be connected to another computer device (for example, a server) 9 as represented by the dotted line in FIG. When the prediction device 1 is connected to the computer device 9, the output unit 13 may further include the following functions. That is, when the output unit 13 receives a request for predicted breakage time information and information specifying the requested water pipe from the computer device 9, the output unit 13 outputs the predicted breakage time of the requested water pipe according to the request. The information is returned (output) to the computer device 9. For example, the computer device 9 uses the received predicted breakage timing information to generate a water pipe renewal plan that includes an estimate of the future pipeline renewal project volume and project cost. Note that the computer device 9 to which the predicted failure time information is output is, for example, a computer device that has been authenticated through authentication processing, similar to the terminal device 6.

<Second embodiment>
A second embodiment of the present invention will be described below. In the description of the second embodiment, the same reference numerals are given to the components having the same functions as those in the description of the first embodiment, and the description of the overlapping parts will be omitted.

In the second embodiment, the acquisition section 11, the prediction section 12, and the output section 13 in the prediction device 1 described in the first embodiment are incorporated into the plan formulation device 20, as shown in FIG. That is, the plan formulation device 20 is a computer device that has a function of formulating a water pipe renewal plan, and includes an arithmetic device 25 constituted by a processor and a storage device 26. The storage device 26 includes a storage medium that stores data and programs 27. By executing the program 27, the computing device 25 can have various functions based on the program 27. As part of the functions of this arithmetic device 25, the planning device 20 is provided with an acquisition section 11, a prediction section 12, and an output section 13 related to failure time prediction processing. In other words, the planning device 20 is a device that also functions as a prediction device that predicts when the buried pipe will break (predicted breakage time). The functions (configurations) of the acquisition unit 11, prediction unit 12, and output unit 13 in the second embodiment are similar to the functions (configurations) of the acquisition unit 11, prediction unit 12, and output unit 13 in the first embodiment.

The arithmetic device 25 further includes a planning section 28 as a functional section. The planning unit 28 uses the predicted breakage timing calculated by the prediction unit 12 to generate a plan for water pipe renewal work (renewal plan). An example of a method for the planning unit 28 to generate an update plan is to use AI technology. There are various types of AI technology for generating update plans, and the type of AI technology employed by the planning unit 28 is not limited, and its description will be omitted.

The planning unit 28 stores the generated water pipe renewal plan in the database 4. The water pipe renewal plan stored in the database 4 in this manner is displayed on the display device 7 by the plan formulation device 20 when the user operates the input device 5 to request display on the display device 7 . The display mode on this display device 7 is not limited, and its explanation will be omitted.

Since the planning device 20 (in other words, the prediction device) in the second embodiment has the same functions as the prediction device 1 in the first embodiment, it can achieve the same effects as in the first embodiment. Furthermore, in the plan formulation device 20, the planning unit 28 generates a water pipe renewal plan using the predicted breakage time calculated by the prediction unit 12. The predicted failure time is information expressed by calendar year or fiscal year. For this reason, for example, the planning unit 28 of the plan formulation device 20 is more efficient at updating water pipes in the process of determining when to update water pipes than when generating a plan using information on the degree of corrosion of water pipes. The burden of converting the period into a calendar year or fiscal year can be reduced.

Note that the planning unit 28 may generate a plan for water pipe renewal work, taking into account not only the breakage timing predicted by the prediction unit 12 but also information such as the degree of influence and seismic resistance regarding the water pipe. The impact level is information that represents the degree of impact when a major accident occurs, such as a large amount of water leaking from a water pipe or a water pipe bursting. This degree of influence is calculated by the planning unit 28 using, for example, usage information and flow rate information included in the attribute information of the water pipe. Furthermore, the seismic resistance is information about the seismic resistance of the water pipe, and is determined by, for example, the material of the water pipe and the type of ground in which it is buried. The seismic resistance of a water pipe is obtained, for example, from an information source 3 (for example, a computer device or database of a system that manages water pipes) as one of the attribute information of the water pipe.

<Other embodiments>
The present invention is not limited to the first and second embodiments, and can take various embodiments. For example, in the first and second embodiments, an example is shown in which a plurality of age prediction models are prepared for each water utility, as the age prediction model used by the prediction unit 12. Alternatively, for example, a common age prediction model that can be obtained from any water utility may be used to generate the age prediction model, thereby generating a common age prediction model that does not depend on the water utility. . In this case, the prediction unit 12 calculates the predicted number of years of use using the common number of years prediction model by inputting the common type of attribute information into the common number of years prediction model.

Further, in the first and second embodiments, the age prediction model used by the prediction unit 12 is a model generated using explainable AI technology, and is a model that outputs an explanation of the basis of the predicted number of years of use. . Alternatively, the age prediction model may not be an explainable model. In this case, an explanation of the basis for the calculated predicted number of years of use is not output from the number of years prediction model, but the following information may be presented as reference information. The reference information includes, for example, explanations of matters that are known in advance about the influence that the elements expressed in the attribute information of the water pipe (for example, the soil quality of the buried soil) have on the service life of the water pipe. ing.

Furthermore, in the first and second embodiments, the configuration of the prediction device is explained using a water pipe, which is a buried pipe, as an example. The same prediction device as in the first and second embodiments can be applied to the calculation of the predicted failure time.

Furthermore, the prediction device 1 of the first embodiment may include an analysis section 15 as shown in FIG. Note that the prediction device 1 shown in FIG. 8 also includes a storage device 40, and the arithmetic device 10 includes an acquisition section 11, a prediction section 12, and an output section 13, but in FIG. Omitted.

The analysis unit 15 has a function of analyzing matters related to the deterioration of a plurality of water pipes, for example, for each region, using the calculation results calculated by the prediction unit 12 and attribute information of water pipes. This analysis result is stored in the database 4 in association with the information used in the analysis. Further, the analysis result by the analysis section 15 can be displayed on the display device 7 by the function of the output section 13. An example of this display is shown in FIG. Furthermore, the analysis unit 15 may be included in the planning device 20.

FIG. 9 is a block diagram showing the configuration of a prediction device according to another embodiment of the present invention. This prediction device 50 is, for example, a computer device, and can have the following functional units by executing a computer program. That is, the prediction device 50 includes an acquisition section 51, a prediction section 52, and an output section 53.

The acquisition unit 51 acquires attribute information representing attributes of the buried pipe to be predicted. The prediction unit 52 uses the age prediction model and the attribute information of the buried pipe to be predicted to calculate the predicted number of years of use of the buried pipe to be predicted. The predicted number of years of use is the expected number of years of use from installation to failure of a buried pipe. The age prediction model is generated by machine learning of the relationship data between the actual usage age information representing the number of years of use from installation to breakage of a buried pipe and the attribute information of the buried pipe. It takes the input as input and outputs the predicted service life of the buried pipe. The prediction unit 52 further uses the predicted number of years of use and installation time information indicating the installation time included in the attribute information of the buried pipe to be predicted to predict the time when the buried pipe to be predicted will be damaged. Calculated as a period. The output unit 53 outputs predicted failure time information expressing the predicted failure time using a calendar year or a fiscal year.

Next, an example of the operation of the prediction device 50 will be described with reference to FIG. 10. FIG. 10 is a flowchart illustrating an example of the operation of the prediction device 50.

For example, when the acquisition unit 51 acquires attribute information representing the attributes of the buried pipe to be predicted (step 201), the prediction unit 52 calculates the predicted number of years of use using the attribute information and the age prediction model (step 202). ). Further, the prediction unit 52 calculates a predicted breakage time using the calculated predicted number of years of use and installation time information indicating the installation time included in the attribute information of the buried pipe to be predicted (step 203). After that, for example, when the output of the predicted breakage time is requested, the output unit 53 outputs the predicted breakage time information (step 204). The predicted failure time information is information that represents the predicted failure time using calendar years or fiscal years.

As described above, the prediction device 50 calculates the predicted number of years of use using the number of years prediction model generated by machine learning the relationship data between the actual number of years of use information and the attribute information of the buried pipe. Further, the prediction device 50 outputs a predicted breakage time using the calculated predicted years of use and installation time information, and further outputs predicted breakage time information expressing the predicted breakage time using a calendar year or a fiscal year. Since this predicted failure time information is expressed using calendar years or fiscal years, it is easy to use in formulating a renewal plan for buried pipes, and is information that is easy to understand as to the basis for formulating the plan. In other words, the prediction device 50 can output information that is easy to use in formulating a renewal plan for buried pipes and easy to explain the basis for formulating the plan.

1,50 Prediction device 11,51 Acquisition unit 12,52 Prediction unit 13,53 Output unit

Claims (8)

an acquisition unit that acquires attribute information representing attributes of the buried pipe to be predicted;
It is generated by machine learning of the relationship data between the actual usage years information representing the number of years of use from installation to breakage of the buried pipe and the attribute information of the buried pipe, and the attribute information of the buried pipe to be predicted is input. Calculating the predicted number of years of use of the buried pipe to be predicted, using a years prediction model that outputs the predicted number of years of use from installation to breakage as the predicted number of years of use, and attribute information of the buried pipe to be predicted; Furthermore, using the predicted number of years of use and the installation time information indicating the installation time included in the attribute information of the buried pipe to be predicted, the time when the buried pipe to be predicted is predicted to break is set as the predicted failure time. A prediction unit that calculates;
A prediction device comprising: an output unit that outputs predicted failure time information expressing the predicted failure time using a calendar year or a fiscal year. The age prediction model is an explainable model that also outputs an explanation of the basis for the calculated predicted number of years of use,
The prediction device according to claim 1, wherein the output unit outputs, in addition to the predicted failure time information, information including an explanation of the basis output from the age prediction model. There are multiple types of information that the acquisition unit can acquire as attribute information of the buried pipe,
Multiple types of age prediction models are available based on different types of buried pipe attribute information used to generate age prediction models.
The prediction unit selects, from among the plurality of age prediction models, an age prediction model according to the type of attribute information of the buried pipe to be predicted acquired by the acquisition unit, and selects the selected age prediction model. The prediction device according to claim 1, wherein the prediction device calculates the estimated number of years of use of the buried pipe to be predicted, using the attribute information of the buried pipe to be predicted, which is acquired by the acquisition unit. The attribute information of the predicted buried pipe acquired by the acquisition unit includes at least deterioration-related information representing elements related to deterioration of the buried pipe,
The age prediction model is generated by machine learning the relationship data between the actual usage age information of the buried pipe and the attribute information including the deterioration related information of the buried pipe,
The prediction unit according to claim 1, wherein the prediction unit calculates the predicted service life of the buried pipe to be predicted, using attribute information including deterioration-related information acquired by the acquisition unit and the age prediction model. Device. The prediction according to claim 1, wherein the attribute information of the buried pipe that is the prediction target acquired by the acquisition unit includes information representing the state of the fluid flowing inside the buried pipe in a predetermined period. Device. The age prediction model, which is an explainable model, is generated by machine learning using information about the causal relationship obtained through causal analysis technology between the actual years of use of buried pipes and the attribute information of the buried pipes. 3. The prediction device according to claim 2, wherein the explanation of the basis of the predicted number of years of use outputted from the age prediction model includes an explanation of the causal relationship between the predicted number of years of use and the attribute information of the buried pipe. by computer,
Obtain attribute information representing the attributes of the buried pipe to be predicted,
It is generated by machine learning of the relationship data between the actual usage years information representing the number of years of use from installation to breakage of the buried pipe and the attribute information of the buried pipe, and the attribute information of the buried pipe to be predicted is input. Calculating the predicted number of years of use of the buried pipe to be predicted, using a years prediction model that outputs the predicted number of years of use from installation to breakage as the predicted number of years of use, and attribute information of the buried pipe to be predicted; Furthermore, using the predicted number of years of use and the installation time information indicating the installation time included in the attribute information of the buried pipe to be predicted, the time when the buried pipe to be predicted is predicted to break is set as the predicted failure time. Calculate,
A prediction method that outputs predicted failure time information expressing the predicted failure time using a calendar year or a fiscal year. A process of acquiring attribute information representing attributes of a buried pipe to be predicted;
It is generated by machine learning of the relationship data between the actual usage years information representing the number of years of use from installation to breakage of the buried pipe and the attribute information of the buried pipe, and the attribute information of the buried pipe to be predicted is input. Calculating the predicted number of years of use of the buried pipe to be predicted, using a years prediction model that outputs the predicted number of years of use from installation to breakage as the predicted number of years of use, and attribute information of the buried pipe to be predicted; Furthermore, using the predicted number of years of use and the installation time information indicating the installation time included in the attribute information of the buried pipe to be predicted, the time when the buried pipe to be predicted is predicted to break is set as the predicted failure time. The calculation process and
A computer program for causing a computer to execute a process of outputting predicted failure time information expressing the predicted failure time using a calendar year or a fiscal year.

Images