Equipment inspection plan creation system and equipment inspection plan creation method

Abstract

Develop an effective recommended inspection plan for roadway equipment. [Solution] The equipment inspection plan creation system of one embodiment includes an equipment failure timing learning unit that uses failure timing data for equipment installed on a road and equipment failure timing relationship data, which is predetermined historical data related to the road and related to the equipment failure timing, as training data to generate an equipment failure timing prediction model through machine learning, with the equipment failure timing relationship data as input and the equipment failure timing as output; an equipment failure timing prediction unit that uses real-time equipment failure timing relationship data as input data, predicts the equipment failure timing using the equipment failure timing prediction model, and outputs the failure timing prediction result; an equipment failure risk calculation unit that calculates the equipment failure risk, which is the risk of equipment failure, based on the failure timing prediction result and past equipment inspection history; and an inspection plan creation unit that creates a recommended inspection plan, which is a plan including recommended times for inspection of equipment, based on the equipment failure risk.

Description

[Technical Field]

[0001] An embodiment of the present invention relates to an equipment inspection plan creation system and an equipment inspection plan creation method. [Background technology]

[0002] Conventionally, roads (expressways, etc.) are equipped with various types of road-related equipment, such as roadside devices that communicate with vehicles, information boards that display information to traveling vehicles, lighting devices, ventilation equipment in tunnels, etc. These road-related equipment are subject to regular inspections to prevent breakdowns, etc.

[0003] Generally, the operation of a highway facility control system involves monitoring the operating status of various facilities installed on the highway (such as information boards and tunnel ventilation equipment), contacting local maintenance staff in the event of a malfunction or failure, and taking steps to restore the system.

[0004] Furthermore, basic maintenance work such as regular inspections and regular equipment replacement is primarily carried out using "Time Based Maintenance (TBM)." However, in reality, the frequency of failures and breakdowns varies depending on the operating environment (indoor, outdoor, etc.) of each type of equipment and its age, so TBM is not necessarily the appropriate maintenance method. Ideally, "Condition Based Maintenance (CBM)," which performs maintenance according to the condition of each piece of equipment, or "Risk Based Maintenance (RBM)," which takes into account the risk of equipment failure, should be performed. However, at present, equipment condition monitoring and maintenance work are not linked.

[0005] For this reason, humans check the facility control system, which detects equipment failures in real time, and the equipment management system, which manages the operating status of various facilities.If an issue can be resolved by inspecting or repairing the equipment, it is dealt with immediately, and if not, the equipment is replaced or updated.

[0006] However, in conventional maintenance work, where real-time monitoring of equipment fault conditions is used as a trigger for maintenance work, it is difficult for the limited number of maintenance personnel to quickly address all of these issues.In addition, depending on the situation, emergency responses may need to be carried out at night or on holidays, which limits the optimization of limited resources, and this presents a challenge.

[0007] To address this issue, it is important to establish not only "reactive maintenance" triggered by the occurrence of a failure, but also "preventive maintenance" using CBM and RBM that do not rely on TBM.

[0008] For example, conventional technology predicts the risk (risk of failure) of fire detectors, which are emergency equipment for tunnels, malfunctioning (for example, detecting a fire when there is no fire), based on the number of installed equipment, operating hours, and past failure rates, and if the risk of failure exceeds a predetermined value, there is a preventive maintenance system that encourages strengthened inspections and the formulation of replacement plans. [Prior art documents] [Patent documents]

[0009] [Patent Document 1] Japanese Patent Publication No. 2020-087389 Summary of the Invention [Problem to be solved by the invention]

[0010] However, the above-mentioned conventional technology has the following problems. First, the assumption for predicting the risk of a malfunction is that multiple units of the same equipment (fire detectors) are installed in the same environment (inside the tunnel). Therefore, it cannot be applied to information boards or tunnel ventilation equipment where only one or a few units of the same equipment are installed in different environments.

[0011] Furthermore, the failure risk prediction only outputs the probability of malfunction and the number of units, but does not specify which of the multiple pieces of equipment should be inspected or replaced. In other words, the system encourages the formulation of a plan to strengthen inspections and replace all of the tunnel's emergency equipment.

[0012] Therefore, an object of this embodiment is to provide an equipment inspection plan creation system and an equipment inspection plan creation method that can create an effective recommended inspection plan for equipment installed on a road. [Means for solving the problem]

[0013] The equipment inspection plan creation system of the embodiment is an equipment failure time prediction model generated by machine learning using training data including failure time data of equipment installed on a road and equipment failure time relation data, which is predetermined historical data related to the road and is related to the equipment failure times, and includes an equipment failure time learning unit that generates an equipment failure time prediction model that outputs equipment failure times when the equipment failure time relation data is input; an equipment failure time prediction unit that predicts equipment failure times when real-time equipment failure time relation data is input using the equipment failure time prediction model and outputs failure time prediction results; and an equipment failure risk calculation unit that calculates equipment failure risk based on the failure time prediction results and the number of days since equipment inspection. The system includes a failure risk calculation unit, a failure impact calculation unit that calculates the impact of equipment failure when the equipment fails based on at least one of congestion prediction results, accident forecast results, and weather forecasts and a standard impact when the equipment fails, an inspection index value calculation unit that calculates an inspection index value that is an index value for the timing of equipment inspection based on the equipment failure risk and the impact of failure due to the occurrence of an equipment failure, and an inspection plan creation unit that creates a recommended inspection plan that is a plan in which, based on the equipment failure risk, the recommended timing of equipment inspection is added to the inspection targets for the next inspection that is earlier than the inspection timing in the standard inspection plan for equipment whose inspection index value is equal to or greater than a predetermined threshold at the inspection timing in the standard inspection plan. [Brief explanation of the drawings]

[0014] [Figure 1] FIG. 1 is a diagram showing an overall configuration of a facility control system according to a first embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of an equipment inspection history according to the first embodiment. [Figure 3]FIG. 3 is a diagram illustrating an example of data used by the failure impact calculation unit of the first embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of data used by the equipment failure risk calculation unit of the first embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of data used by the inspection index value calculation unit of the first embodiment. [Figure 6] FIG. 6 is a diagram showing an example of a recommended inspection schedule screen according to the first embodiment. [Figure 7] FIG. 7 is a diagram showing an example of the inspection recommendation basis screen according to the first embodiment. [Figure 8] FIG. 8 is a flowchart illustrating an example of processing by the facility control system of the first embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0015] The following describes an equipment inspection plan creation system and an equipment inspection plan creation method according to the present embodiment (first embodiment and second embodiment) with reference to the accompanying drawings. Note that in the present embodiment, an expressway is used as an example of the road. In the following, "forecast" may also mean just "prediction."

[0016] (First embodiment) Fig. 1 is an overall configuration diagram showing an outline of a facility control system 1 etc. according to the first embodiment. Note that in Fig. 1, arrows indicate the main flow of information, and there are cases where information is sent and received in areas without arrows.

[0017] A facility control system 1 and a traffic control system 2 are installed for the expressway R that is the object of control. Furthermore, the expressway R, which has a tunnel T, is equipped with a tunnel information board 31, a CCTV (Closed Circuit Television System) 32, a power distribution and private power generation facility 33, a tunnel lighting facility 34, a radio rebroadcasting facility 35, a fire detector 36, a water spray facility 37, a tunnel ventilation facility 38, and a remote monitoring and control facility 39. In the following, the tunnel information board 31 to the tunnel ventilation facility 38 are collectively referred to as "the facilities."

[0018] The tunnel information board 31 is installed just before the entrance to the tunnel T and is controlled by the traffic control system 2. It displays information about accidents, fires, etc. within the tunnel T, as well as information about safe driving, to vehicles about to enter the tunnel T.

[0019] The CCTV 32 is a camera installed on the roadside of the expressway R to capture images of the expressway R, and transmits the captured images to the facility control system 1 and the traffic control system 2.

[0020] The power distribution and private power generation equipment 33 is installed on the roadside of the expressway R and is equipment for power distribution and private power generation.

[0021] The tunnel lighting equipment 34 is a lighting equipment installed inside the tunnel T.

[0022] The radio rebroadcasting equipment 35 is installed inside the tunnel T and enables reception of AM (Amplitude Modulation) radio and FM (Frequency Modulation) radio in the tunnel T where normal radio broadcast signals cannot reach.

[0023] The fire detector 36 is installed inside the tunnel T, and when it detects a fire, it transmits the detection information to the facility control system 1 and the traffic control system 2.

[0024] The water spray equipment 37 is installed inside the tunnel T and extinguishes the fire by spraying water uniformly in a mist from the spray head to cover the burning area.

[0025] The tunnel ventilation equipment 38 is installed inside the tunnel T and is equipment for providing ventilation.

[0026] The remote monitoring and control equipment 39 is installed on the roadside of the expressway R and transmits, for example, equipment status data relating to the equipment (including equipment status change notifications (data) indicating changes in the equipment status) and equipment failure notifications (data) indicating failures relating to the equipment to the facility control system 1.

[0027] In addition to these facilities, vehicle detectors will also be installed. Vehicle detectors are installed on the roadside of expressways and collect information such as traffic volume [vehicles / h], average speed [km / h], vehicle density [vehicles / km], and occupancy [%], and transmit the collected information to the traffic control system 2.

[0028] The traffic control system 2 is a system that manages (monitors) and controls vehicle traffic on the expressway R. The traffic control system 2 is realized by a plurality of computer devices such as an information exchange server and a central processing unit, for example.

[0029] The traffic event 21 is information (traffic condition data) including past traffic information (traffic volume [vehicles / h], average speed [km / h], vehicle density [vehicles / km], occupancy [%], etc.) and accident information for the expressway R. The traffic event 21 is an example of equipment failure timing related data, which is predetermined historical data on the expressway R related to the timing of equipment failure.

[0030] The traffic congestion prediction model 22 is a model for predicting future traffic congestion on the expressway R by machine learning using the traffic events 21 and the like.

[0031] The accident prediction model 23 is a model for predicting future accidents on Expressway R by machine learning using traffic event 21, accident history data, and the like.

[0032] The weather information 24 is information relating to weather (weather, temperature, road temperature, wind direction, wind speed, rainfall, etc.), and is information received from a predetermined observation station or weather information center.

[0033] The traffic control system 2 outputs a congestion prediction result based on the congestion prediction model 22. The traffic control system 2 outputs an accident forecast result based on the accident forecast model .

[0034] The facility control system 1 is a system that manages (monitors) and controls road facilities (tunnel information boards 31 to tunnel ventilation facilities 38). The facility control system 1 is realized by a plurality of computer devices such as an information exchange server and a central processing unit, for example.

[0035] The facility control system 1 includes a storage unit 11, a processing unit 12, an input unit 13, and a display unit .

[0036] The storage unit 11 is a storage device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive). The storage unit 11 stores various programs and various data. The storage unit 11 stores, for example, an equipment failure time prediction model 111, an equipment inspection history 112, an equipment management ledger 113, and a standard inspection plan 114 (standard inspection plan).

[0037] The equipment failure time prediction model 111 is a learning model for estimating when and which equipment is prone to failure based on the tendency of equipment failures to occur under specific conditions (e.g., traffic conditions, equipment operating hours, etc.), and is generated by the facility central data processing unit 121 (details will be described later).

[0038] The equipment inspection history 112 is data indicating the results of past equipment inspections. 2 is a diagram showing an example of the equipment inspection history 112 according to the first embodiment. The equipment inspection history 112 includes the following items for equipment: inspection date, location, (inspection) cycle, equipment name, weather, inbound / outbound lane classification, manufacturing date, inspection device name, inspection part, inspection item, inspection result, and treatment. Note that while FIG. 2 only shows inspection history for cases where an abnormality was found, the equipment inspection history 112 also includes inspection history for cases where no abnormality was found.

[0039] Returning to FIG. 1, the facility management ledger 113 is management data of the facilities and specifications of the expressway.

[0040] The standard inspection plan 114 is a standard inspection plan on which the recommended inspection plan is based.

[0041] The processing unit 12 includes, for example, an MPU (Micro Processing Unit), a ROM (Read Only Memory), and a RAM (Random Access Memory). ROM is a storage medium for storing various programs and data, while RAM is a storage medium for temporarily storing various programs and rewriting various data. The MPU comprehensively controls the operation of the facility control system 1. The MPU executes programs stored in the ROM, the storage unit 11, etc., using the RAM as a work area.

[0042] The processing unit 12 includes a facility central data processing unit 121, a failure influence calculation unit 122, and an inspection plan creation unit 123 as functional units.

[0043] The facility central data processing unit 121 collects status data (equipment status data) of equipment installed in tunnels T of expressways R, etc. The facility central data processing unit 121 (an example of an equipment failure timing learning unit) uses equipment failure timing data (for example, equipment inspection history 112) and traffic events 21 as training data, and generates an equipment failure timing prediction model 111 by machine learning, with the traffic events 21 as input and the equipment failure timing as output.

[0044] In addition, the facility central data processing unit 121 (an example of an equipment failure time prediction unit) uses real-time traffic events 21 as input data, predicts the equipment failure time using the equipment failure time prediction model 111, and outputs the failure time prediction result (failure prediction).

[0045] The failure impact calculation unit 122 calculates the impact (failure impact) when the equipment fails. The failure impact calculation unit 122 calculates the equipment failure impact based on, for example, a standard impact when the equipment fails and one or more of a congestion prediction result based on the congestion prediction model 22, an accident forecast result based on the accident forecast model 23, and a weather forecast in the weather information 24.

[0046] 3 is a diagram showing an example of data used by the failure impact calculation unit 122 of the first embodiment. This data consists of items such as location, tunnel class, traffic congestion forecast (result), accident forecast (result), weather forecast, and failure impact table. The failure impact is expressed in five levels, from the minimum "1" to the maximum "5."

[0047] For example, in the example in the second row from the top, for "Tunnel A," the failure impact level of the tunnel information board (Tunnel Information Board 31) is "3," and the failure impact level of the CCTV (CCTV 32) is "2." Each failure impact level is set in advance by the user based on the actual impact level of equipment failures at the site.

[0048] Returning to FIG. 1, the inspection plan creation unit 123 includes an equipment failure risk calculation unit 124 , an inspection index value calculation unit 125 , and a recommended inspection plan output unit 126 .

[0049] Next, the equipment failure risk calculation unit 124 will be described with reference to FIG. 4 is a diagram showing an example of data used by the equipment failure risk calculation unit 124 of the first embodiment. The equipment failure risk calculation unit 124 calculates the equipment failure risk, which is the risk of equipment failure, based on the failure probability (failure time prediction result) and the number of days since inspection (data in the past equipment inspection history).

[0050] Here, the failure probability is classified into four levels, from lowest to highest: "slight," "low," "medium," and "high," depending on the degree. The number of days since inspection is also classified into four levels, from lowest to highest: "slight," "low," "medium," and "high," depending on the degree. Equipment failure risk is expressed on a 10-point scale, from the minimum of "0" to the maximum of "9."

[0051] For example, if the failure probability is "low" and the number of days since inspection is "medium," the equipment failure risk will be "5." Each equipment failure risk is set in advance by the user based on the actual situation of the equipment failure risk at the site.

[0052] Next, the inspection index value calculation unit 125 will be described with reference to FIG. FIG. 5 is a diagram showing an example of data used by the inspection index value calculation unit 125 of the first embodiment. The inspection index value calculation unit 125 calculates an inspection index value, which is an index value related to the timing of equipment inspection, based on the equipment failure risk calculated by the equipment failure risk calculation unit 124 and the failure impact calculated by the failure impact calculation unit 122.

[0053] Here, the failure impact is classified into four levels, from lowest to highest: "slight," "small," "medium," and "high," depending on the degree. Also, equipment failure risk is classified into four levels, from lowest to highest: "slight," "small," "medium," and "high," depending on the degree. Also, inspection index values ​​are expressed on a 10-point scale, from the minimum of "0" to the maximum of "9."

[0054] For example, if the failure impact level is "medium" and the equipment failure risk is "high," the inspection index value is "8." Each inspection index value is set in advance by the user based on the actual situation regarding the necessity of inspection.

[0055] 1, the recommended inspection plan output unit 126 creates a recommended inspection plan based on the inspection index value. For example, the recommended inspection plan output unit 126 creates a recommended inspection plan by adding, to the standard inspection plan 114, equipment whose inspection index value is equal to or greater than a predetermined threshold (for example, "6") and which is not a target for inspection at the next inspection, to the target for inspection at the next inspection.

[0056] 6 is a diagram showing an example of a recommended inspection schedule screen in the first embodiment. On the recommended inspection schedule screen, area R1 displays information indicating that it is an inspection schedule screen and the current date and time. Area R2 displays the target tunnel, target equipment, and inspection interval.

[0057] Area R3 displays the standard inspections (monthly inspections) set in the standard inspection plan 114. Area R4 displays recommended inspections, that is, inspections that would not normally be performed (2-month inspections, 3-month inspections) that were added because the inspection index value was equal to or greater than a predetermined threshold. In this example, transformers and disconnecting switches are displayed as inspection items. Pressing the "Reasons for recommended inspection" button in area R4 will take you to the screen shown in Figure 7. Note that transformers and disconnecting switches are included in the power distribution and private power generation (equipment) in the failure impact table in Figure 3.

[0058] 7 is a diagram showing an example of the inspection recommendation basis screen of the first embodiment. On the inspection recommendation basis screen, an area R11 displays a message indicating that the screen is the inspection recommendation basis screen and the current date and time information. An area R12 displays the target tunnel, the target equipment, and the inspection interval.

[0059] Area R13 displays information about equipment failure risk. Here, the graph on the left shows the relationship between the number of days since inspection and the failure probability for transformers and disconnecting switches (failure probability line; it is nonlinear as it changes depending on traffic condition data, etc.). Note that "15" in the number of days since inspection is the current day. The table on the right also shows the last inspection date, (inspection) cycle, and equipment failure risk value (current, one month from now (one month from now), and next inspection (two months from now)) for transformers and disconnecting switches. For transformers and disconnecting switches, the equipment failure risk values ​​are low at "3" and "3" at one month from now, but at the time of the next inspection they are high at "8" and "6".

[0060] Area R14 also displays information about the inspection index values. Here, the graph on the left shows the relationship between equipment failure risk and failure impact for transformers and disconnectors. The table on the right shows the last inspection date, (inspection) interval, and inspection index value (current, one month later (one month later), and next inspection (two months later)) for transformers and disconnectors. For transformers and disconnectors, the inspection index values ​​are "3" and "3" at one month's notice, which are below the threshold value of "6," but the equipment failure risk values ​​are "9" and "8" at the next inspection, which are above the threshold value of "6." In other words, since the inspection index values ​​are above the threshold value two months after the inspection timing in the standard inspection plan, it is preferable to inspect them one month prior to that.

[0061] Returning to FIG. 1, the input unit 13 is an input device that accepts user operations on the facility control system 1, and is, for example, a keyboard, a mouse, a touch panel, or the like.

[0062] The display unit 14 is a device that displays information, and is, for example, a liquid crystal display (LCD (Liquid Crystal Display)), an organic EL (Electro-Luminescence) display, or the like.

[0063] Next, with reference to FIG. 8, the processing performed by the facility control system 1 of the first embodiment will be described. FIG. 8 is a flowchart showing an example of processing by the facility control system 1 of the first embodiment.

[0064] First, in step S 1 , the facility central data processing unit 121 inputs facility status data from the remote monitoring and control facility 39 .

[0065] Next, in step S2, the facility central data processing unit 121 determines whether or not there is an equipment status change notification in the equipment status data, and if Yes, proceeds to step S3, and if No, returns to step S1.

[0066] In step S3, the facility central data processing unit 121 uses the equipment status change notification and real-time traffic events 21 as input data, predicts the equipment failure time using the equipment failure time prediction model 111, and outputs the failure time prediction result (failure probability).

[0067] Next, in step S4 , the equipment failure risk calculation unit 124 reads the data of the equipment inspection history 112 .

[0068] Next, in step S5, the equipment failure risk calculation unit 124 calculates the equipment failure risk based on the failure time prediction result (failure probability) and the number of days since inspection (data in the past equipment inspection history) (FIG. 4).

[0069] Next, in step S6, the failure impact calculation unit 122 calculates the failure impact of the equipment based on the standard impact when the equipment fails and one or more of the traffic congestion prediction results, accident forecast results, and weather forecast.

[0070] Next, in step S7, the inspection index value calculation unit 125 calculates an inspection index value based on the equipment failure risk calculated in step S5 and the failure impact degree calculated in step S6 (FIG. 5).

[0071] Next, in step S8, the recommended inspection schedule output unit 126 reads data from the standard inspection schedule 114.

[0072] Next, in step S9, the recommended inspection plan output unit 126 creates and outputs a recommended inspection plan (FIG. 6) by adding equipment whose inspection index value is equal to or greater than a predetermined threshold and that is not currently being inspected at the next inspection to the standard inspection plan 114. The recommended inspection plan output unit 126 also creates and outputs inspection recommendation grounds (visualization of equipment failure risk and inspection index value; FIG. 7) corresponding to the recommended inspection plan.

[0073] A maintenance worker M (FIG. 1) inspects the equipment based on the recommended inspection plan (FIG. 6) and the inspection recommendation grounds (FIG. 7) displayed on the display unit 14.

[0074] In this way, according to the facility control system 1 of the first embodiment, it is possible to calculate equipment failure risks and inspection index values ​​for equipment installed on roads based on failure prediction results, etc., and to create effective recommended inspection plans based on these.

[0075] Therefore, for example, preventive maintenance can reduce downtime of various highway facilities.

[0076] In addition, quantitative evidence (Figure 7) can be created and displayed when considering inspection plans for various highway facilities.

[0077] It also reduces the frequency with which maintenance personnel have to respond to unexpected incidents at night or on holidays.

[0078] (Second embodiment) Next, a second embodiment will be described. Explanations of matters similar to those in the first embodiment will be omitted as appropriate. In the first embodiment, a recommended inspection plan is created based on inspection index values, but in the second embodiment, a recommended inspection plan is created based on equipment failure risk without calculating inspection index values.

[0079] That is, the recommended inspection plan output unit 126 creates a recommended inspection plan that is a plan including recommended inspection times for the equipment, based on the equipment failure risk calculated by the equipment failure risk calculation unit 124.

[0080] In this way, according to the second embodiment, an effective recommended inspection plan can be created with simpler configuration and processing.

[0081] The programs executed by the facility control system 1 of this embodiment are provided by being pre-installed in a ROM or the like. The programs may also be provided by being recorded in an installable or executable file format on a computer-readable recording medium such as a CD-ROM, a flexible disk (FD), a CD-R, or a digital versatile disk (DVD).

[0082] Furthermore, the program may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network.The program may also be provided or distributed via a network such as the Internet.

[0083] The program has a modular configuration including the units 121 to 126 in the processing unit 12 of the facility control system 1. That is, the CPU reads out the program from the ROM and executes it, thereby loading the units 121 to 126 onto the main storage device.

[0084] Although an embodiment of the present invention has been described, this embodiment is presented as an example and is not intended to limit the scope of the invention. This novel embodiment can be embodied in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. This embodiment is included within the scope and spirit of the invention, and is also included in the invention described in the claims and their equivalents.

[0085] For example, the target roads are not limited to expressways, but the present invention can be applied to road incidental facilities installed on other roads such as ordinary roads.

[0086] Furthermore, in the facility control system 1, for example, earthquake information (seismic intensity, SI value, acceleration, etc.), carbon monoxide concentration and smoke transmittance in a tunnel (factors that affect the operation of ventilation equipment), etc. may be used to predict equipment failure.

[0087] Furthermore, as equipment failure timing related data, in addition to road traffic condition data (traffic event 21), equipment operation time data, equipment repair information data, etc. may be used. Equipment operation time data is composed of items such as equipment ID (identifier), facility name, (road) direction, equipment name, environment, completion date, manufacturer, elapsed years, maintenance deadline, etc.

[0088] <Additional Notes> (1) an equipment failure time learning unit that uses failure time data of equipment installed on a road and equipment failure time relation data, which is predetermined historical data related to the failure times of the equipment and related to the road, as training data, to generate an equipment failure time prediction model by machine learning, with the equipment failure time relation data as input and the equipment failure time as output; an equipment failure time prediction unit that uses the real-time equipment failure time relationship data as input data, predicts the equipment failure time using the equipment failure time prediction model, and outputs a failure time prediction result; an equipment failure risk calculation unit that calculates an equipment failure risk, which is a failure risk of the equipment, based on the failure time prediction result and a past equipment inspection history; and an inspection plan creation unit that creates a recommended inspection plan that includes a recommended timing for inspection of the equipment based on the equipment failure risk. (2) The equipment inspection plan creation system according to (1), wherein the equipment failure timing relationship data includes at least one of traffic condition data of the road, equipment operating time data, and equipment repair information data. (3) An inspection index value calculation unit that calculates an inspection index value that is an index value related to the timing of inspection of the equipment based on the equipment failure risk and a predetermined impact degree due to the occurrence of a failure of the equipment, The equipment inspection plan creation system according to (1), wherein the inspection plan creation unit creates the recommended inspection plan based on the inspection index value. (4) The equipment inspection plan creation system described in (3), wherein the inspection plan creation unit creates the recommended inspection plan by adding, to the standard inspection plan, the equipment whose inspection index value is equal to or greater than a predetermined threshold and which is not yet to be inspected at the next inspection, to the equipment to be inspected at the next inspection. (5) an equipment failure time learning step of generating an equipment failure time prediction model by machine learning using training data including failure time data of equipment installed on a road and equipment failure time relation data, which is predetermined historical data related to the failure times of the equipment and related to the road; and an equipment failure time prediction step of predicting the equipment failure time using the equipment failure time prediction model with the real-time equipment failure time relationship data as input data and outputting a failure time prediction result; an equipment failure risk calculation step of calculating an equipment failure risk, which is a failure risk of the equipment, based on the failure time prediction result and a past equipment inspection history; and creating a recommended inspection plan that includes a recommended timing for inspection of the equipment based on the equipment failure risk. [Explanation of symbols]

[0089] 1...facility control system, 2...traffic control system, 11...memory unit, 12...processing unit, 13...input unit, 14...display unit, 21...traffic event, 22...congestion prediction model, 23...accident forecast model, 24...weather information, 31...tunnel information board, 32...CCTV, 33...power distribution and self-generation equipment, 34...tunnel lighting equipment, 35...radio rebroadcasting equipment, 36...fire detector, 37...water spray equipment, 38...tunnel ventilation equipment, 39...remote monitoring and control equipment, 111...equipment failure time prediction model, 112...equipment inspection history, 113...equipment management ledger, 114...standard inspection plan, 121...facility central data processing unit, 122...failure impact calculation unit, 123...inspection plan creation unit, 124...equipment failure risk calculation unit, 125...inspection index value calculation unit, 126...recommended inspection plan output unit, M...maintenance staff, R...highway

Claims

1. an equipment failure time prediction model generated by machine learning using training data including failure time data of equipment installed on a road and equipment failure time relation data, which is predetermined historical data related to the failure times of the equipment and related to the road, and an equipment failure time learning unit that generates the equipment failure time prediction model that outputs the failure times of the equipment when the equipment failure time relation data is input; an equipment failure time prediction unit that predicts the equipment failure time when the equipment failure time related data in real time is input using the equipment failure time prediction model and outputs a failure time prediction result; an equipment failure risk calculation unit that calculates an equipment failure risk, which is a failure risk of the equipment, based on the failure time prediction result and the number of days since inspection of the equipment; a failure impact calculation unit that calculates a failure impact of the equipment when the equipment fails based on at least one of a congestion prediction result, an accident forecast result, and a weather forecast, and a standard impact when the equipment fails; an inspection index value calculation unit that calculates an inspection index value, which is an index value related to the timing of inspection of the equipment, based on the equipment failure risk and the failure impact degree due to the occurrence of a failure of the equipment; an inspection plan creation unit that creates a recommended inspection plan based on the equipment failure risk, which is a plan that adds, to the inspection targets for the next inspection that is earlier than the inspection timing in the standard inspection plan, the equipment whose inspection index value will be equal to or greater than a predetermined threshold at the inspection timing in the standard inspection plan; An equipment inspection plan creation system that includes:

2. The equipment failure time relationship data includes at least one of traffic condition data of the road, equipment operation time data, and equipment repair information data. The facility inspection plan creation system according to claim 1 .

3. When the equipment installed on the road is equipment installed in a tunnel, the failure impact calculation unit calculates the failure impact based on a failure impact table in which the failure impact is determined by the tunnel class, congestion forecast, accident forecast, weather forecast, and the installed equipment. The facility inspection plan creation system according to claim 1 .

4. The inspection plan creation unit creates the recommended inspection plan by adding, to the standard inspection plan, the equipment whose inspection index value is equal to or greater than a predetermined threshold and which is not a target for inspection at the next inspection, to the equipment to be inspected at the next inspection. The facility inspection plan creation system according to claim 1 .

5. The inspection plan creation unit creates the recommended inspection plan by adding, to the inspection targets for the next inspection, the equipment whose inspection index value will be below a predetermined threshold at the time of the next inspection and whose inspection index value will be equal to or greater than the predetermined threshold at the inspection timing in the standard inspection plan. The facility inspection plan creation system according to claim 1 .

6. The inspection plan creation unit creates an inspection recommendation basis corresponding to the recommended inspection plan indicating the equipment failure risk and the inspection index value. The facility inspection plan creation system according to claim 1 .

7. The inspection plan creation unit outputs a recommended inspection plan screen corresponding to the recommended inspection plan to a display unit, and when an inspection recommendation basis button in the recommended inspection plan screen is operated, an inspection recommendation basis screen corresponding to the inspection recommendation basis is output. The facility inspection plan creation system according to claim 6.

8. The computer an equipment failure time learning step for generating an equipment failure time prediction model that is generated by machine learning using training data including failure time data of equipment installed on a road and equipment failure time relation data, which is predetermined historical data related to the failure times of the equipment and related to the road, and that outputs the failure times of the equipment when the equipment failure time relation data is input; an equipment failure time prediction step of predicting the equipment failure time when the equipment failure time related data in real time is input using the equipment failure time prediction model and outputting a failure time prediction result; an equipment failure risk calculation step of calculating an equipment failure risk, which is a failure risk of the equipment, based on the failure time prediction result and the number of days since inspection of the equipment; a failure impact calculation step of calculating a failure impact of the equipment when the equipment fails based on at least one of a congestion prediction result, an accident forecast result, and a weather forecast, and a standard impact when the equipment fails; an inspection index value calculation step of calculating an inspection index value, which is an index value related to the timing of inspection of the equipment, based on the equipment failure risk and the failure impact degree due to the occurrence of a failure of the equipment; an inspection plan creation step of creating a recommended inspection plan based on the equipment failure risk, which is a plan that adds the recommended inspection timing for the equipment, for which the inspection index value will be equal to or greater than a predetermined threshold at the inspection timing in the standard inspection plan, to the inspection target for the next inspection that is earlier than the inspection timing in the standard inspection plan; A method for creating an equipment inspection plan, including:

Images