Accident cause estimation device, and control method and program for accident cause estimation device

Abstract

To estimate an accident cause of a distribution system with high accuracy.SOLUTION: An accident cause estimation device that outputs an estimation factor of an accident caused in a power distribution system formed by being divided with a switch into a plurality of division, comprises: a learning model storage part that stores a learning model formed so as to output the examination factor of the new accident when new accident information is inputted on the basis of a type of the accident caused in the power distribution system, a date and a time when the accident is caused, an instruction value expressing a level of a ground fault when the accident is generated, the past accident information containing a division where the accident is caused, and a factor of the accident; an accident information acquisition part that acquires the new accident information; an estimation factor acquisition part that acquires the estimation factor of the accident output from the learning model by inputting the new accident information into the learning model; and an estimation factor output part that outputs the estimation factor of the accident.SELECTED DRAWING: Figure 10

Description

[Technical Field]

[0001] The present invention relates to an accident cause estimation device, a control method for an accident cause estimation device, and a program. [Background technology]

[0002] When an accident occurs in a power distribution system, the power company will use its distribution line automation system to identify and isolate the faulty section, and restore power to sound sections. At the same time, the power company will locate the location of the accident while estimating the cause of the accident based on various circumstances at the time of the accident and past experience, and begin restoration work.

[0003] As a technique for estimating the cause of such an accident in a power distribution system, for example, a technique such as that disclosed in Patent Document 1 is known. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2017-131006 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the estimation of the cause of an accident is influenced by the past experience of the person in charge, and for example, it is difficult for an inexperienced person to accurately estimate the cause of an accident. In addition, different people may have different perspectives on analyzing the situation, and the estimated cause of an accident may differ depending on the person in charge.

[0006] The present invention has been made in view of the above background, and aims to provide an accident cause estimation device, a control method for the accident cause estimation device, and a program that can accurately estimate the cause of an accident in a power distribution system. [Means for solving the problem]

[0007] One of the present inventions for achieving the above object is an accident cause estimation device that outputs a probable cause of an accident that has occurred in a power distribution system that is divided into a plurality of sections by switches, and when new accident information is input, the device outputs a probable cause of the new accident based on the type of accident that has occurred in the power distribution system, the date and time when the accident occurred, an index value that indicates the degree of a ground fault when the accident occurred, and past accident information including the section where the accident occurred, and the cause of the accident. One or more Probable cause and the probability that each of the said presumed causes is the true cause. a learning model storage unit that stores a learning model created to output the new accident information; an accident information acquisition unit that acquires the new accident information; and an accident information output unit that outputs the new accident information from the learning model by inputting the new accident information into the learning model. One or more Probable cause and the probability that each of the said presumed causes is the true cause. an estimated cause acquisition unit that acquires the cause; Depending on the selection result of whether to output the probability that each of the estimated causes is a true cause or to output only estimated causes whose probability is equal to or greater than a predetermined value, The accident One or more Probable cause and the probability that each of the estimated causes is a true cause, or the estimated causes whose probability is equal to or greater than the predetermined value. and an estimated cause output unit that outputs the estimated cause.

[0008] Other problems and solutions disclosed in the present application will be made clear in the detailed description and drawings. [Effects of the Invention]

[0009] According to the present invention, it is possible to accurately estimate the cause of an accident in a power distribution system. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram illustrating an accident cause estimation system. [Figure 2] FIG. 2 is a hardware configuration diagram of the accident cause estimation device. [Figure 3] FIG. 2 is a diagram illustrating a storage device of the accident cause estimation device. [Figure 4] FIG. 10 is a diagram showing an accident information management table. [Figure 5] FIG. 10 is a diagram showing an example of an input screen for inputting the cause of an accident. [Figure 6] FIG. 1 is a diagram illustrating a learning model. [Figure 7] FIG. 2 is a functional block diagram of the accident cause estimation device. [Figure 8] 3 is a flowchart showing a processing flow of the accident cause estimation device. [Figure 9] 3 is a flowchart showing a processing flow of the accident cause estimation device. [Figure 10] FIG. 10 is a diagram showing an example of a display screen for the estimated cause of an accident. [Figure 11] FIG. 1 is a diagram illustrating a power distribution system. DETAILED DESCRIPTION OF THE INVENTION

[0011] At least the following matters will become apparent from the description of this specification and the accompanying drawings. Hereinafter, the present invention will be described in accordance with one embodiment thereof with reference to the accompanying drawings.

[0012] ==Overall Configuration== FIG. 1 shows the overall configuration of an accident cause estimation system 1000 according to an embodiment of the present invention.

[0013] The accident cause estimation system 1000 is configured by connecting an accident cause estimation device 100 and a power distribution line automation system 200 so that they can communicate with each other via a network 500 such as the Internet, a LAN (Local Area Network), or a telephone network. The accident cause estimation device 100 is also connected to a weather information providing device 300 so that they can communicate with each other via the network 500.

[0014] The distribution line automation system 200 is a computer system that monitors and controls devices such as switches 450 and transformers 451 installed in a distribution system 400 as shown in FIG. 11 and collects measurement data such as the voltage and current of a distribution line 420, thereby detecting and recovering from accidents that occur in the distribution system 400.

[0015] The power distribution system 400 is a power system that supplies power from a power distribution substation 410 to a load 440 via a power distribution line 420 .

[0016] The distribution substation 410 includes a transformer 411, a main circuit breaker 412, and a sub circuit breaker 415, and transforms electric power supplied from a power transmission system (not shown) using the transformer 411 and supplies the transformed electric power to a distribution line 420. The distribution line automation system 200 may also be provided in the distribution substation 410.

[0017] Furthermore, a zero-phase-sequence detector 430 is installed in the distribution substation 410 and the distribution line 420. The zero-phase-sequence detector 430 includes a zero-phase-sequence current detector 431, a zero-phase-sequence voltage detector 432, and a control box 433.

[0018] The zero-phase current detector 431 is configured by, for example, a zero-phase current transformer (ZCT) or the like, and detects the combined current of three phases flowing through the power distribution line 420 as a zero-phase current I0.

[0019] The zero-phase voltage detector 432 is configured by, for example, an earthing voltage transformer (EVT) or a zero-phase potential device (ZPD), and detects the combined voltage of the three phases of the distribution line 420 as a zero-phase voltage V0.

[0020] The control box 433 performs AD conversion of the zero-phase current I0 and the zero-phase voltage V0, calculates the effective values, calculates the phase difference between the zero-phase current I0 and the zero-phase voltage V0, and transmits these values ​​to the distribution line automation system 200 via a high-speed transmission path 510 configured using an optical fiber or the like.

[0021] The power distribution system 400 is managed by dividing it into multiple sections using switches 450. The distribution line automation system 200 identifies the type of fault, such as a short circuit, a ground fault, or a disconnection, and the section in which the fault occurred, based on measurement data such as voltage and current and the open / close state of the switches 450 acquired from sensors mounted on various devices, such as the switches 450, transformers 451, and zero-phase detectors 430, installed in the power distribution system 400. The distribution line automation system 200 controls the switches 450 to isolate the section in which the fault occurred from the other sections and cut off the power, while allowing power to be supplied from the distribution substation 410 to healthy sections where no fault has occurred.

[0022] Furthermore, when the distribution line automation system 200 detects such an accident in the distribution system 400, it transmits accident information to the accident cause estimation device 100, including the date and time of the accident, the section where the accident occurred, the type of accident (short circuit, ground fault, open circuit, etc.), and the zero-phase voltage V0 at the time the accident occurred.

[0023] The accident cause estimation device 100 is a computer that estimates and outputs the cause of an accident that has occurred in the power distribution system 400, and stores a history of accident information that has been previously acquired from the power distribution line automation system 200, including the date and time of the accident, the section where the accident occurred, the type of accident, and the zero-phase voltage V0 at the time the accident occurred. The accident cause estimation device 100 analyzes past accident information and the causes of those accidents to generate a learning model (AI model) that outputs the estimated cause of a new accident when new accident information is input. By using this learning model, the accident cause estimation device 100 outputs the estimated cause of the new accident when new accident information is input.

[0024] This aspect makes it possible to accurately estimate the cause of an accident in the power distribution system 400. For example, it is possible to reduce variations in the estimated cause of an accident that arise due to differences in the experience and perspectives of situation analysis of personnel in charge of responding to an accident in the power distribution system 400. This also makes it possible to more accurately identify the location where the accident actually occurred and plan the personnel and equipment required for restoration work.

[0025] The weather information providing device 300 is a computer that provides weather information such as the weather, temperature, humidity, air pressure, and wind speed.

[0026] When a new accident occurs in the power distribution system 400, the accident cause estimation device 100 acquires predetermined types of weather information such as the weather and temperature at that time from the weather information providing device 300 and stores the information as accident information together with the time of the new accident, the section of the accident, the zero-phase voltage V0, the type of accident, and the like acquired from the power distribution line automation system 200.

[0027] Including meteorological information in the accident information improves the accuracy of the learning model, and the accident cause estimation device 100 can output a more accurate estimated cause of the accident.

[0028] Details will be provided below.

[0029] ==Accident cause estimation device== Next, the accident cause estimation device 100 will be described.

[0030] 2 shows an example of the hardware configuration of the accident cause estimation device 100. The accident cause estimation device 100 is configured to include a CPU (Central Processing Unit) 110, a memory 120, a communication device 130, a storage device 140, an input device 150, an output device 160, and a recording medium reading device 170.

[0031] The CPU 110 is responsible for overall control of the accident cause estimation device 100, and realizes various functions of the accident cause estimation device 100 by reading out an accident cause estimation device control program 700, which is composed of codes for performing various operations related to this embodiment stored in the storage device 140, and various data into the memory 120 and executing or processing them.

[0032] For example, the CPU 110 executes or processes the accident cause estimation device control program 700 and various data, and by working in cooperation with hardware devices such as the memory 120, communication device 130, and storage device 140, various functions such as the learning model memory unit 101, accident information acquisition unit 102, estimated cause acquisition unit 103, and estimated cause output unit 104, which will be described later, are realized.

[0033] The accident cause estimation device control program 700 is a general term for programs for realizing the functions of the accident cause estimation device 100, and includes, for example, application programs, an OS (Operating System), various libraries, etc. that run on the accident cause estimation device 100.

[0034] The memory 120 can be configured, for example, by a semiconductor memory device.

[0035] The storage device 140 is a device that provides a physical storage area for storing various programs, data, tables, etc., such as a hard disk drive, a solid state drive (SSD), a flash memory, etc. In this embodiment, as shown in Fig. 3, the storage device 140 stores an accident cause estimation device control program 700 as well as various data such as an accident information management table 600, learning data 610, a learning model 620, and a cause estimation result 630.

[0036] An example of the accident information management table 600 is shown in FIG.

[0037] When an accident occurs in the power distribution system 400 and the accident cause estimation device 100 receives accident information from the power distribution line automation system 200, the accident cause estimation device 100 stores the accident information in the accident information management table 600. The accident information includes the date and time of the accident, the section where the accident occurred, the type of accident (for example, at least one of a short circuit, a ground fault, and a disconnection), and the zero-phase voltage V0.

[0038] Furthermore, the accident cause estimation device 100 acquires a predetermined type of weather information at the date and time when the accident occurred from the weather information providing device 300, and stores it as accident information in the accident information management table 600. For example, the types of weather information may include information that may have some effect on an accident in the power distribution system 400, such as weather (sunny, cloudy, rain, snow, thunder, hail, etc.), temperature, humidity, wind speed, wind direction, and atmospheric pressure.

[0039] In the accident information management table 600 shown in FIG. 4, the information listed in the "Date and Time," "Type," and "Section" columns is information obtained from the power distribution line automation system 200, and the information listed in the "Weather Information" column is information obtained from a weather information providing device.

[0040] Furthermore, the information listed in the "Inspection Results" column is information regarding the inspection results of the equipment of the power distribution system 400 installed in the section where the accident occurred, and the information listed in the "Period of Use" column is information indicating the period of use of the equipment of the power distribution system 400 installed in the section where the accident occurred.

[0041] The power distribution system 400 is equipped with various pieces of equipment such as transformers 451, insulators, cross arms, and switches 450, and maintenance such as inspections and replacements is performed periodically by the electric power company and its partner companies. The electric power company records and manages information such as the inspection results of this equipment and the dates of installation and replacement in a computer (not shown). The accident cause estimation device 100 obtains this information from the computer at the time the accident occurs and records it as accident information in the "inspection results" column and "usage period" column of the accident information management table 600.

[0042] By including this information in the accident information, the accuracy of the learning model 620 is improved, and the accident cause estimation device 100 is able to output a more accurate estimated cause of the accident.

[0043] In addition, the information listed in the "Seasonal Factors" column is information indicating seasonal phenomena that occur in the area where the section where the accident occurred and that may be the cause of an accident, and the times when such phenomena are likely to occur, and the information listed in the "Regional Factors" column is information indicating geographically specific phenomena that exist in the area where the section where the accident occurred and that may be the cause of an accident.

[0044] For example, some areas are located along windier coasts than other areas, and there is a tendency for short-circuit accidents in the distribution line 420 to increase during strong winds in bad weather, while other areas are home to many wild birds, which build nests on utility poles to raise their young during a specific period each year (e.g., March to July), leading to an increase in short-circuit accidents.Furthermore, there are also areas where accidents involving snakes shorting out the distribution line 420 increase during specific periods (e.g., April to October).

[0045] Such information that may be the cause of an accident specific to a region or season is recorded in a computer (not shown), and the accident cause estimation device 100 can acquire this information from the computer and record it as accident information in the "seasonal factors" column and the "regional factors" column of the accident information management table 600.

[0046] In this way, by including this information in the accident information, the accuracy of the learning model 620 is further improved, and the accident cause estimation device 100 can output a more accurate estimated cause of the accident.

[0047] The information written in the "zero-phase-sequence voltage V0" column indicates the measurement results of the zero-phase-sequence voltage V0 measured in each section of the power distribution system 400 when the accident occurred. In the present embodiment, as an example, the information is data (waveform data) including time-series values ​​of the zero-phase-sequence voltage V0 at a predetermined cycle (e.g., every 0.1 seconds) during a predetermined period (e.g., a period from 10 seconds before to 30 seconds after) that includes the time point at which the accident occurred. The accident cause estimation device 100 acquires the zero-phase-sequence voltage V0 from the distribution line automation system 200 and records it as accident information in the "zero-phase-sequence voltage V0" column of the accident information management table 600.

[0048] By including information on the zero-phase sequence voltage V0 in the accident information, the accuracy of the learning model 620 is improved, and the accident cause estimation device 100 can output a more accurate estimated cause of the accident.

[0049] As will be explained below, the zero-phase voltage V0 changes depending on the degree of the ground fault, and can therefore be used as an index value representing the degree of the ground fault, and can be an important characteristic quantity when estimating the cause of the accident.

[0050] As described above, when a ground fault occurs in the distribution line 420 (for example, when electricity flows into the ground), the distribution line automation system 200 identifies the distribution line 420 in which the ground fault occurred based on the zero-phase-sequence voltage V0 and zero-phase-sequence current I0 at the time of the ground fault and their direction, and to ensure safety, shuts off the sub-circuit breaker 415 for that distribution line 420, causing a power outage.

[0051] At that time, the zero-phase-sequence voltage V0 changes depending on the severity of the ground fault. For example, if a ground fault occurs due to lightning or a metal object such as a wire coming into contact with the distribution line 420, the resistance of the contacting object is small, so the zero-phase-sequence voltage V0 changes relatively greatly. In contrast, if a ground fault occurs due to a bird, snake, tree, or other object with a higher resistance than metal coming into contact with the distribution line 420, the resistance of the contacting object is large, so the amount of change in the zero-phase-sequence voltage V0 is relatively small.

[0052] Therefore, the distribution line automation system 200 can determine the ground fault degree, which indicates the severity of the ground fault, according to the value of the zero-phase-sequence voltage V0. The ground fault degree is expressed, for example, as a three-level numerical value, from 1 to 3. For example, when metal objects such as the above-mentioned lightning or wire come into contact with the distribution line 420, the distribution line automation system 200 sets the ground fault degree to 3, and when an object with a higher resistance than metal, such as a bird or snake, comes into contact with the distribution line 420, the ground fault degree to 2. In this way, such ground fault degrees can also be index values ​​that indicate the severity of the ground fault, similar to the zero-phase-sequence voltage V0. The ground fault degree may also be determined by the accident cause estimation device 100 from the zero-phase-sequence voltage V0.

[0053] The fault information management table 600 according to this embodiment records the zero-phase voltage V0, but the degree of earth fault calculated from the zero-phase voltage V0 by the power distribution line automation system 200 or the fault cause estimation device 100 may also be recorded as fault information.

[0054] In this way, the degree of earth fault (for example, 1 to 3 stages) is determined according to the earth fault situation (cause), so by learning using an index value (earth fault degree) that indicates the degree of earth fault in addition to meteorological conditions such as weather, it is possible to estimate the cause of an accident on the distribution line 420 with greater accuracy.

[0055] The accident information management table 600 also has a "zero-phase current I0" column and a "phase difference" column. The information written in these columns indicates the measurement results of the zero-phase current I0 and the phase difference between the zero-phase voltage V0 and the zero-phase current I0 measured in each section of the power distribution system 400 when the accident occurred. In this embodiment, the information is data (waveform data) including time-series values ​​at a predetermined cycle (e.g., every 0.1 seconds) during a predetermined period (e.g., from 10 seconds before to 30 seconds after) that includes the time point at which the accident occurred. The accident cause estimation device 100 acquires this information from the distribution line automation system 200 and records it as accident information in the "zero-phase current I0" column and the "phase difference" column of the accident information management table 600.

[0056] Including information about the zero-phase current I0 and the phase difference in the accident information improves the accuracy of the learning model 620, enabling the accident cause estimation device 100 to output a more accurate estimated cause of the accident. Note that, because the zero-phase current I0 and the phase difference also change depending on the degree of the ground fault, these values ​​can also be included in the index value representing the degree of the ground fault.

[0057] The accident information management table 600 also has an "accident cause" column. The "accident cause" column describes the true cause of the accident that was identified through an investigation after the accident. These accident causes are recorded in the accident information management table 600, for example, when the accident cause estimation device 100 outputs a screen such as that shown in FIG. 5 to the output device 160 and a person in charge inputs the accident cause via the input device 150. In the example shown in FIG. 5, the person in charge can select the accident cause from multiple candidates, but the person in charge may also input the accident cause directly.

[0058] Returning to FIG. 3, the accident cause estimating device 100 generates learning data 610 using past accident information and accident causes recorded in the accident information management table 600.

[0059] The learning data 610 is data (teaching data) used for learning a machine learning model (learning model 620) that outputs a presumed cause of a new accident when new accident information is input.

[0060] The accident cause estimation device 100 presents accident information from a predetermined period in the past (one month, six months, one year, etc., hereinafter referred to as a "time interval") as explanatory variables (features) to the person in charge, and accepts settings of accident causes, which are objective variables (labels) for the accident information, from the person in charge. Then, the accident cause estimation device 100 generates learning data 610 by associating the accident information with the accident causes.

[0061] It should be noted that the task of associating accident information with accident causes does not need to be performed for each time interval, and it is preferable to perform the task each time an accident cause is identified. In this case, the accident cause estimation device 100 extracts data for which association with accident causes has been completed from the accident information for the time interval as learning data 610. The time interval is set empirically, for example, based on the frequency of accidents. Alternatively, learning models 620 may be generated for multiple time intervals, and these learning models 620 may be used to infer the cause of an accident in the power distribution system 400. The time interval is set, for example, based on past cases, to a length that improves the accuracy of the accident cause identification.

[0062] Alternatively, when generating the learning data 610 using the past accident information and accident causes recorded in the accident information management table 600, the accident cause estimation device 100 may use data on accidents that occurred in a specific region to generate the learning data 610. In this manner, a learning model 620 specific to that region can be generated, thereby improving the accuracy of estimating the cause of the accident.

[0063] Similarly, when generating learning data 610 using past accident information and accident causes recorded in the accident information management table 600, the accident cause estimation device 100 may use data on accidents that occurred during a specific period to generate learning data 610. This configuration makes it possible to generate a learning model 620 specific to that period, thereby improving the accuracy of estimating the cause of the accident.

[0064] Furthermore, when generating the learning data 610 using the past accident information and accident causes recorded in the accident information management table 600, the accident cause estimation device 100 may generate the learning data 610 using data on accidents that occurred in a specific region and time period. In this manner, a learning model 620 specific to the region and time period can be generated, thereby improving the accuracy of estimating the cause of the accident.

[0065] In this embodiment, the learning model 620 is a DNN (Deep Neural Network), but may be realized by other types of models such as a gradient boosting (GBDT (Gradient Boosting Decision Tree)).

[0066] FIG. 6 shows an example of a learning model 620 (neural network structure). As shown in FIG. 6, accident information is input to an input layer 621 of the learning model 620. An intermediate layer 622 includes one or more hidden layers each consisting of one or more nodes containing parameters adjusted by learning. The intermediate layer 622 calculates one or more predicted values ​​(probabilities) for the output layer 623 based on the accident information provided to the input layer 621. In the learning model 620 of this embodiment, the output layer 623 includes multiple predicted values ​​(multiple causes of accidents and their probabilities).

[0067] Returning to Fig. 3, the cause estimation result 630 includes information about the estimated cause of the accident output from the learning model 620. In this embodiment, the cause estimation result 630 includes one or more estimated causes of the accident and a calculation result of the probability that each estimated cause is the true cause. This aspect makes it possible to provide the person in charge of investigating the cause of the accident with information that is useful for securing the equipment and personnel necessary for accident restoration work, planning the work process, and so on.

[0068] Returning to FIG. 2, the storage device 140 may be built into the accident cause estimating device 100 or may be externally attached.

[0069] The recording medium reader 170 reads programs and data recorded on a recording medium 800 such as a CD-ROM or DVD, and stores them in the storage device 140 .

[0070] The communication device 130 transmits and receives data and programs to and from other computers such as the power distribution line automation system 200 and the weather information providing device 300 via a network 500 such as the Internet or a LAN (Local Area Network). For example, the above-described accident cause estimation device control program 700 can be stored in another computer (not shown), and the accident cause estimation device 100 can download and execute the accident cause estimation device control program 700 from this computer.

[0071] Alternatively, the communication device 130 may periodically receive accident information and weather information from the power distribution line automation system 200 and the weather information providing device 300. Furthermore, the accident cause estimation device 100 may not include the storage device 140, and may instead implement the functions of the accident cause estimation device 100 by using various data such as the above programs and tables stored in another computer (not shown) communicably connected via the network 500.

[0072] The input device 150 is a device used by a person in charge or the like to input data to the accident cause estimation device 100, and functions as a user interface. The input device 150 may be, for example, a keyboard, a mouse, a microphone, or the like.

[0073] The output device 160 is a device for outputting information to the outside and functions as a user interface. The output device 160 may be, for example, a display, a printer, a speaker, or the like.

[0074] <Functional configuration> 7 shows a functional block diagram of the accident cause estimation device 100 according to this embodiment. The accident cause estimation device 100 includes a learning model storage unit 101, an accident information acquisition unit 102, an estimated cause acquisition unit 103, and an estimated cause output unit 104. These functions are realized by the hardware shown in FIG. 2 executing or processing the accident cause estimation device control program 700 according to this embodiment and various data.

[0075] The learning model storage unit 101 stores a learning model 620 that is created to output an estimated cause of a new accident when new accident information is input, based on past accident information including the type of accident that occurred in the power distribution system 400, the date and time the accident occurred, an index value indicating the degree of ground fault at the time the accident occurred, and the section where the accident occurred, as well as the cause of the accident.

[0076] In this embodiment, the learning model storage unit 101 is embodied as a storage device 140 .

[0077] The accident cause estimation device 100, for example, inputs learning data 610 into a learning model 620, and then adjusts parameters defining the learning model 620 based on the difference between the result output by the learning model 620 and the input learning data 610, for example, by a method such as backpropagation, thereby training the learning model 620.

[0078] The accident information acquisition unit 102 acquires accident information of a new accident that has occurred in the power distribution system 400. The accident information includes the type of accident that has occurred in the power distribution system 400, the date and time when the accident occurred, an index value that indicates the degree of the ground fault when the accident occurred, and the section where the accident occurred, but may also include other information.

[0079] For example, the accident information may include information on the inspection results of the equipment of the power distribution system 400 installed in the section where the accident occurred. Alternatively, the accident information may include information indicating the period of use of the equipment of the power distribution system 400 installed in the section where the accident occurred.

[0080] The accident information may also include a predetermined type of weather information for the date and time when the accident occurred. The accident information may also include information indicating a geographically specific phenomenon that exists in the area to which the section where the accident occurred and that may be the cause of an accident, or information indicating a seasonally specific phenomenon that occurs in the area to which the section where the accident occurred and that may be the cause of an accident, and information indicating a time when this phenomenon is likely to occur.

[0081] By including such information in the accident information, the accuracy of the learning model 620 is further improved, and the accident cause estimation device 100 can output a more accurate estimated cause of the accident.

[0082] The estimated cause acquisition unit 103 inputs accident information of a new accident that has occurred in the power distribution system 400 into the learning model 620, thereby acquiring an estimated cause of the accident that is output from the learning model 620. The estimated causes of the accident that are output from the learning model 620 may be one or more. This configuration makes it possible to appropriately present to the person in charge possible causes of the newly occurring accident. Furthermore, the estimated causes of each accident may include a calculation result of the probability that each estimated cause is the true cause. This configuration makes it possible to present to the person in charge how likely the accident cause estimated by the accident cause estimation device 100 is to occur.

[0083] The estimated cause output unit 104 outputs the estimated cause of the accident. The accident cause estimation device 100 outputs the estimated cause of the accident by displaying, for example, a screen as shown in FIG.

[0084] The above-described aspect makes it possible to accurately estimate the cause of an accident in the power distribution system 400. In the present embodiment, the type of accident is one of a wire break, a short circuit, and a ground fault in the power distribution system 400, and the type of accident is based on the content included in the accident information acquired from the power distribution line automation system 200. Therefore, if the type of accident acquired from the power distribution line automation system 200 includes other information, the estimated cause output unit 104 may output the other information as well. Alternatively, the type of accident may be one of a ground fault and a short circuit in the power distribution system 400.

[0085] ==Processing flow== Next, with reference to Figures 8 and 9, we will explain the process in which the accident cause estimation device 100 of this embodiment uses learning data 610 to learn the learning model 620, and the process flow when using this learning model 620 to estimate the cause of an accident that occurred in the distribution system 400.

[0086] 8 is a flowchart illustrating the processing performed by the accident cause estimation device 100 when the accident cause estimation device 100 uses the learning data 610 to learn the learning model 620. The timing at which the accident cause estimation device 100 executes learning of the learning model 620 is not necessarily limited. For example, the accident cause estimation device 100 executes the learning processing of the learning model 620 when new accident information is added to the accident information management table 600, when an instruction to execute learning is received from a person in charge via a user interface, or when a predetermined timing arrives at every predetermined period (once a month, once a year, etc.).

[0087] First, the accident cause estimation device 100 generates data in which accident information and the cause of the accident are associated with each other as learning data 610 (S1000). For example, the accident cause estimation device 100 performs the association by presenting the accident information (explanatory variables) to a person in charge and accepting a setting of the cause of the accident (objective variable (label)) for the accident information from the person in charge.

[0088] Fig. 5 shows an example of a screen on which the accident cause estimation device 100 presents the above-mentioned accident information (explanatory variables) and accepts the setting of the cause of the accident (objective variable). Although not shown in Fig. 5, the above-mentioned degree of ground fault may also be displayed.

[0089] Returning to FIG. 8, the accident cause estimating device 100 performs a learning process for the learning model 620 using the learning data 610 (S1010).

[0090] The accident cause estimation device 100 may verify the prediction accuracy of the trained learning model 620. In this case, the accident cause estimation device 100 classifies the learning data 610 into learning data and verification data in advance, trains the learning model 620 using the learning data, and verifies the learning model 620 using the verification data.

[0091] FIG. 9 is a flowchart illustrating the process performed by the accident cause estimation device 100 when estimating the cause of a new accident that has occurred in the power distribution system 400.

[0092] First, the accident cause estimation device 100 acquires accident information including an index value indicating the date and time, section, type, and severity of a ground fault when the accident occurred in the power distribution system 400 (S2000). As described above, this accident information may also include other information such as weather information, equipment inspection results, period of use, seasonal factors, and regional factors.

[0093] Next, the accident cause estimation device 100 inputs the acquired accident information into the learning model 620, and acquires the output of the learning model 620 as the cause of the accident (S2010).

[0094] Then, the accident cause estimating device 100 generates a screen on which the estimated cause of the accident is described as shown in FIG. 10, and outputs the generated screen to the output device 160 (S2020).

[0095] In this manner, the cause of the accident in the power distribution system 400 can be estimated with high accuracy.

[0096] Note that the accident cause estimating device 100 displays the probability that each candidate for the estimated cause of the accident output from the learning model 620 is the true cause on the display screen for the estimated cause of the accident shown in FIG. 10 , but it may also be configured to display only estimated causes whose probability is a predetermined value or more (e.g., 30% or more) on the screen. Alternatively, the accident cause estimating device 100 may be configured to allow the person in charge to select whether to display the probability that each candidate for the estimated cause is the true cause or to display only estimated causes whose probability is a predetermined value or more (e.g., 30% or more) on the screen. Alternatively, the accident cause estimating device 100 may accept an input of a probability value and display on the screen estimated causes whose probability is equal to or higher than that value.

[0097] In this manner, possible causes of a newly occurring accident can be appropriately presented to the person in charge.

[0098] The accident cause estimation device 100, the control method and the program for the accident cause estimation device 100 according to this embodiment have been described above. According to this embodiment, it is possible to accurately estimate the cause of an accident in the power distribution system 400.

[0099] The above-described embodiment is intended to facilitate understanding of the present invention, and is not intended to limit the present invention. The present invention may be modified or improved without departing from the spirit thereof, and equivalents thereof are also included in the present invention. [Explanation of symbols]

[0100] 100 Accident cause estimation device 101 Learning model memory unit 102 Accident Information Acquisition Department 103 Probable cause acquisition unit 104 Estimated cause output section 110 CPU 120 memory 130 Communication equipment 140 Storage device 150 Input Device 160 Output Device 170 Recording medium reader 200 Power Distribution Line Automation System 300 Weather information providing device 400 Distribution system 410 Distribution Substation 411 Transformer 412 Main circuit breaker 415 Sub-circuit breaker 420 Power Distribution Line 430 Zero Phase Detector 431 Zero-phase current detector 432 Zero-phase voltage detector 433 Control Box 440 load 450 Switchgear 451 Transformer 500 Network 510 High-speed transmission line 600 Accident Information Management Table 610 training data 620 Learning Model 621 Input Layer 622 Middle Class 623 Output Layer 630 Cause estimation result 700 Accident Cause Estimation Device Control Program 800 Recording Media 1000 Accident Cause Estimation System

Claims

1. An accident cause estimation device that outputs an estimated cause of an accident that has occurred in a distribution system that is divided into a plurality of sections by switches, a learning model storage unit that stores a learning model created based on past accident information including the type of accident that occurred in the power distribution system, the date and time the accident occurred, an index value indicating the degree of the ground fault when the accident occurred, and the section where the accident occurred, and the cause of the accident, so as to output one or more presumed causes of the new accident and the probability that each of the presumed causes is the true cause when new accident information is input; an accident information acquisition unit that acquires the new accident information; an estimated cause acquisition unit that acquires one or more estimated causes of the accident output from the learning model by inputting the new accident information into the learning model and the probability that each of the estimated causes is the true cause; an estimated cause output unit that outputs one or more estimated causes of the accident and the probability that each of the estimated causes is the true cause, or outputs estimated causes whose probabilities are equal to or greater than a predetermined value, depending on a selection result of whether to output the probability that each of the estimated causes is the true cause or to output only estimated causes whose probabilities are equal to or greater than a predetermined value; An accident cause estimation device comprising:

2. 2. The accident cause estimation device according to claim 1, The accident information further includes information regarding the inspection results of the equipment of the power distribution system installed in the section where the accident occurred. Accident cause estimation device.

3. 3. The accident cause estimation device according to claim 1 or 2, The accident information further includes information indicating a period of use of the distribution system equipment installed in the section where the accident occurred. Accident cause estimation device.

4. The accident cause estimation device according to any one of claims 1 to 3, The accident information further includes a predetermined type of weather information at the date and time when the accident occurred. Accident cause estimation device.

5. The accident cause estimation device according to any one of claims 1 to 4, The accident information further includes information indicating a geographically specific phenomenon that may be a cause of the accident and exists in the area to which the section where the accident occurred belongs. Accident cause estimation device.

6. The accident cause estimation device according to any one of claims 1 to 5, The accident information further includes information indicating seasonal phenomena that occur in the area to which the section in which the accident occurred and that may be the cause of the accident, and information indicating the time periods when the phenomena are likely to occur. Accident cause estimation device.

7. The accident cause estimation device according to any one of claims 1 to 6, The type of the accident includes at least one of a break in the power distribution system, a short circuit, and a ground fault.

8. A control method for an accident cause estimation device that outputs an estimated cause of an accident that has occurred in a power distribution system that is divided into multiple sections by switches, comprising: The accident cause estimation device storing a learning model created based on past accident information including the type of accident that occurred in the power distribution system, the date and time of the accident, an index value indicating the degree of a ground fault when the accident occurred, and the section where the accident occurred, and the cause of the accident, so as to output one or more presumed causes of the new accident and the probability that each of the presumed causes is the true cause when new accident information is input; Acquire the new accident information; inputting the new accident information into the learning model to obtain one or more presumed causes of the accident output from the learning model and a probability that each of the presumed causes is a true cause; A control method for an accident cause estimation device that outputs one or more presumed causes of the accident and the probability that each of the presumed causes is the true cause, or outputs presumed causes whose probability is equal to or greater than a predetermined value, depending on the selection result of whether to output the probability that each of the presumed causes is the true cause, or to output only presumed causes whose probability is equal to or greater than a predetermined value.

9. A program for causing a computer to output a presumed cause of an accident that has occurred in a power distribution system that is divided into multiple sections by switches, a step of storing a learning model created based on past accident information including the type of accident that occurred in the power distribution system, the date and time of the accident, an index value indicating the degree of the ground fault at the time of the accident, and the section where the accident occurred, and the cause of the accident, so as to output one or more presumed causes of the new accident and the probability that each of the presumed causes is the true cause when new accident information is input; a step of acquiring the new accident information; a step of inputting the new accident information into the learning model to obtain one or more presumed causes of the accident output from the learning model and a probability that each of the presumed causes is the true cause; a step of outputting one or more presumed causes of the accident and the probability that each of the presumed causes is the true cause, or outputting only presumed causes whose probability is equal to or greater than a predetermined value, depending on the result of selection of whether to output the probability that each of the presumed causes is the true cause, or to output only presumed causes whose probability is equal to or greater than a predetermined value; A program for causing the computer to execute the above.

Images