WO2023195218A1 - 鉄道保守支援システム、鉄道保守支援方法 - Google Patents
鉄道保守支援システム、鉄道保守支援方法 Download PDFInfo
- Publication number
- WO2023195218A1 WO2023195218A1 PCT/JP2023/003171 JP2023003171W WO2023195218A1 WO 2023195218 A1 WO2023195218 A1 WO 2023195218A1 JP 2023003171 W JP2023003171 W JP 2023003171W WO 2023195218 A1 WO2023195218 A1 WO 2023195218A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- maintenance
- railway
- prediction model
- equipment
- railway equipment
- Prior art date
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 443
- 238000000034 method Methods 0.000 title claims description 69
- 230000006866 deterioration Effects 0.000 claims abstract description 157
- 238000012545 processing Methods 0.000 claims abstract description 66
- 238000003860 storage Methods 0.000 claims abstract description 51
- 230000008859 change Effects 0.000 claims description 50
- 230000008569 process Effects 0.000 claims description 33
- 230000000052 comparative effect Effects 0.000 claims description 4
- 238000007689 inspection Methods 0.000 description 27
- 238000005259 measurement Methods 0.000 description 18
- 230000008439 repair process Effects 0.000 description 14
- 230000007613 environmental effect Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 238000004364 calculation method Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 8
- 238000007726 management method Methods 0.000 description 8
- 230000005856 abnormality Effects 0.000 description 7
- 230000001186 cumulative effect Effects 0.000 description 5
- 238000009826 distribution Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000002776 aggregation Effects 0.000 description 3
- 238000004220 aggregation Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 3
- 238000005315 distribution function Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000014509 gene expression Effects 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000003137 locomotive effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L23/00—Control, warning or like safety means along the route or between vehicles or trains
- B61L23/04—Control, warning or like safety means along the route or between vehicles or trains for monitoring the mechanical state of the route
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Definitions
- the present invention relates to a railway maintenance support system and a railway maintenance support method.
- Patent Document 1 sensor information of equipment is collected, deterioration status and future deterioration estimation predictions are made, and the relationship between the deterioration prediction status and occurrence of abnormal events in equipment is clarified, and future costs are estimated. It provides a means to make estimates. It is believed that the means typified by Patent Document 1 is particularly effective for devices and equipment that operate independently.
- the problem of the present invention is to provide lower-cost maintenance for railways, which is an example of a system of systems, by taking into consideration the relationship between maintenance of each facility and device, rather than the conventional maintenance method for each facility and device.
- the purpose is to derive a method.
- the railway maintenance support system includes a processor and a storage unit.
- the processor applies a deterioration prediction model used to predict the deterioration of railway equipment using maintenance accuracy as an explanatory variable, which is information regarding the accuracy of maintenance of railway equipment obtained by converting sensing data obtained from sensor devices of railway equipment, to multiple railway equipment. Estimate each time and store it in the storage unit.
- the processor estimates a second railway equipment deterioration prediction model that includes the deterioration prediction of the first railway equipment deterioration prediction model that has already been estimated and stored in the storage unit as an explanatory variable. I do.
- the processor outputs the entire maintenance cost based on the deterioration prediction of the deterioration prediction model of each railway equipment.
- the railway maintenance support system includes a processor and a storage unit.
- the processor estimates a failure prediction model for use in predicting failures of railway equipment for each of the plurality of railway equipment, and stores the model in the storage unit.
- the processor estimates a second railway equipment failure prediction model that includes failure predictions of the first railway equipment failure prediction model that have already been estimated and stored in the storage unit as explanatory variables. I do.
- the processor outputs the entire maintenance cost based on the failure prediction of the failure prediction model of each railway equipment.
- the railway maintenance support method is a method performed using a railway maintenance support system having a processor and a storage unit.
- the processor inputs maintenance accuracy that is information regarding the accuracy of maintenance of railway equipment, estimates a deterioration prediction model for each of the plurality of railway equipment to be used for predicting deterioration of railway equipment using the maintenance accuracy as an explanatory variable, and stores the model in the storage unit. Store in.
- the processor outputs the entire maintenance cost based on the deterioration prediction of the deterioration prediction model of each railway equipment.
- the processor estimates a second deterioration prediction model whose explanatory variables include the deterioration prediction of the deterioration prediction model of the first railway equipment that has already been estimated and stored in the storage unit. Performs processing to estimate a deterioration prediction model for railway equipment.
- FIG. 1 is a configuration diagram showing an example of a railway maintenance decision-making support system according to a first embodiment
- FIG. 12 is a flowchart illustrating an example of a process for estimating a deterioration prediction model and determining maintenance accuracy when maintenance cost is minimized.
- the figure which shows Numerical formula 1 The figure which shows an example of transportation information.
- FIG. 5 is a flowchart illustrating an example of a maintenance cost calculation method.
- FIG. 2 is a configuration diagram showing an example of a railway maintenance decision-making support system according to a second embodiment.
- 12 is a flowchart illustrating an example of a process for estimating a failure prediction model and determining maintenance accuracy when maintenance cost is minimized.
- FIG. 7 is a diagram showing a specific example of failure information used when calculating each coefficient.
- FIG. 7 is a diagram illustrating an example of a data structure of aggregation results according to a third embodiment.
- the figure which shows the comparative display example of maintenance cost is a configuration diagram showing an example of a railway maintenance decision-making support system according to a fourth embodiment.
- 10 is a flowchart illustrating an example of model estimation in the case of maintenance that deals with both deterioration and failure, and a process for determining the maintenance accuracy of each piece of equipment when the maintenance cost is minimized.
- 5 is a flowchart illustrating an example of model estimation for each railway facility configured based on a configuration example.
- FIG. 1 is an activity diagram illustrating an example of on-site railway maintenance up to and including maintenance execution.
- identification information When describing identification information, expressions such as “identification information”, “identifier”, “name”, “ID”, and “number” are used, but these expressions can be replaced with each other.
- equipment and equipment that have a maintenance relationship are targeted, such as rails and wheels, air brakes and electric brakes, etc., and more appropriate maintenance is performed based on the maintenance relationship between multiple equipment and equipment.
- the first embodiment estimates a model that makes it possible to predict deterioration based on sensor information sent from railway equipment and equipment, and further estimates maintenance relationships between equipment, etc., thereby improving overall maintenance.
- This invention relates to a railway maintenance decision-making support system that presents the maintenance accuracy of each facility and equipment that can reduce costs the most.
- FIG. 1 is a configuration diagram showing an example of a railway maintenance decision-making support system.
- a railway maintenance decision support system (a railway maintenance support system) includes an input interface, a storage device (main storage and auxiliary storage), a processor (e.g., CPU), a display device (e.g., a liquid crystal display), a communication unit, and these components. It consists of computer devices equipped with information processing resources such as buses that interconnect the systems.
- the input interface constitutes the input section 101.
- the maintenance manager instructs the execution of the process, and a deterioration prediction model is estimated and a search calculation is performed to find the maintenance accuracy that will minimize the overall cost.
- a main storage device e.g. memory
- an auxiliary storage device e.g. HDD
- the main storage device includes programs (deterioration prediction model estimation unit 102, deterioration prediction model estimation unit 102, deterioration prediction section 103, optimal search section 104, and result creation section 105).
- the auxiliary storage device also stores various information to be used (sensing data 106, environmental information 107, transportation information 108, deterioration information 109), a deterioration prediction model 110 that is the processing result of the program, a maintenance cost prediction 111, and a maintenance accuracy 112. Store.
- the main storage device may store a program for determining maintenance accuracy, a program for calculating maintenance cost, and the like.
- the auxiliary storage device stores programs executed by the processor.
- the processor is stored in the processing unit 113, and can perform various functions by functioning as an arithmetic execution unit that executes the processing of the program.
- the display device corresponds to the output unit 114, and allows checking of item setting status and processing results.
- the communication unit 115 is configured to include an interface used for communication.
- the processing unit 113 sends and receives sensor information sent from each railway facility or device to be managed outside the railway maintenance decision-making support system via the communication unit 115, and stores it in the auxiliary storage device.
- the bus connects the processor, input interface, storage device, display device, and interface, and contributes to the realization of functions by exchanging information.
- the above sensor information is sent to the communication unit 115 via the network.
- the results of sensing by the sensor device 117 mounted on the railway vehicle 116 are sent to the communication unit 115 via the network.
- sensing data sensed by the sensor device 119 that observes the track-related equipment 118 is sent to the communication unit 115.
- the electric circuit related equipment 120 is also sensed by the sensor device 121 and sensing data is sent to the communication unit 115.
- the number of facilities and devices to be managed is arbitrary and is not limited to the number shown in this figure. It is sufficient that there are at least two or more related facilities or devices.
- FIG. 2 is a flowchart illustrating an example of a process for estimating a deterioration prediction model and determining maintenance accuracy.
- the number of target facilities may be two or more, but additional processing in the case of three or more will be described later.
- the processing unit 113 determines the maintenance accuracy of target equipment A (railway equipment A) and target equipment B (railway equipment B) (201).
- the processing unit 113 executes a program that calculates the maintenance accuracy. There are two methods for determining this, one for each period and one for each point in time, and both can be processed in the same way.
- FIG. 3A shows an example of input data regarding a method of determining maintenance accuracy for each time point.
- equipment ID 301 is an ID indicating which equipment it is for
- measurement ID 302 is an ID that shows measurement items for that equipment.
- the maintenance date and time 303 indicates the maintenance date and time, and indicates the date and time when an inspection or repair was performed.
- a measurement value 304 indicates a value measured for the measurement ID 301.
- the inspection standard 305 indicates the inspection standard for measurement, and 160-170 in the first line of this figure means that if the measured value is between 160 and 170, it satisfies the inspection standard.
- FIG. 3B shows an example of a processing result among diagrams showing a method for determining maintenance accuracy. Note that the same components as in FIG. 3A are given the same numbers, and therefore their description will be omitted.
- the processing unit 113 estimates a deterioration prediction model for railway equipment A (202).
- this process corresponds to the deterioration prediction model estimation unit 102.
- methods for estimating the deterioration prediction model include a regression estimation method using a linear model and an estimation method using machine learning.
- regression estimation using a linear model will be taken as an example, but the estimation method of the deterioration prediction model is not limited to this.
- the objective variable y is a measured value indicating predicted deterioration.
- explanatory variable candidates other measured values of the railway equipment A and environmental information around the equipment (temperature, humidity, weather, rainfall, solar radiation, time of day, etc.) can be considered, but one of the features of the present invention is that One reason is that the maintenance accuracy of equipment A is included in the explanatory variables.
- FIG. 4 an example of a data structure in which measured values of railway equipment are registered will be explained using FIG. 4. Further, an example of environmental information will be explained using FIG. 5.
- equipment ID 401 shows the ID of the equipment
- measurement ID 402 shows the ID of the measurement item for that equipment.
- the measurement date and time 403 is the measurement date and time
- the measurement value 404 indicates the measurement value.
- FIG. 5 shows an example of environmental information, in which a date and time 501 indicates the date and time, and a temperature 502 indicates the temperature at that date and time. Similarly, humidity 503 indicates humidity, rainfall amount 504 indicates rainfall amount, and solar radiation amount 505 indicates solar radiation amount.
- this environmental information may be prepared for each section where the environmental conditions can change.
- regression estimation is performed by adding the maintenance accuracy shown in FIG. 3B.
- y A is the deterioration prediction of equipment A
- v A is the maintenance accuracy of equipment A
- w 1 , w 2 , ... w k is the explanatory variable remaining from the explanatory variable candidates (k ⁇ n)
- t is the elapsed time, and this becomes the deterioration prediction model for railway equipment A.
- the explanatory variables w 1 , w 2 , . . . w k may be explanatory variables that take transportation information into consideration.
- FIG. 7 shows an example of transportation information.
- the train number 601 indicates the train number and serves as an ID for identifying which train.
- Date and time 602 indicates the date and time.
- a running route 603 indicates a running route, and indicates which route the train is running on.
- the traveling position 604 indicates the traveling position, and is expressed, for example, as a cumulative distance from the starting station.
- Velocity 605 indicates velocity
- acceleration 606 indicates acceleration.
- Running weight 607 indicates running weight.
- Equation 3 when using the data structure shown in FIG. 7, as an example, if data exists regarding the corresponding train number, date and time, traveling route, and traveling position, it will be 1, and if not, it will be 0. Alternatively, if it is due to the number of times the train passes, it may be expressed as Equation 3 in FIG.
- num is the number of passes until the elapsed time t.
- the number of existing data regarding the corresponding train number, date and time, running route, and running position becomes the number of passes.
- w i (t) may be the value of the running weight related to the corresponding train number, date and time, running route and running position. This allows the influence of running weight to be taken into account in the deterioration.
- the explanatory variables in Equations 4, 6, 7, etc. to be described below may be explanatory variables that take transportation information into consideration.
- the processing unit 113 executes the deterioration prediction model estimation unit 102 to estimate the deterioration prediction model of the railway equipment B while adding the deterioration information of the railway equipment A (203).
- regression estimation of a linear model will be similarly explained as an example, but the estimation method is not limited to this.
- the deterioration prediction model for railway equipment B is estimated in the same way, but deterioration information on railway equipment A is also added as the first explanatory variable candidate.
- the regression equation estimated by this is Equation 4 in FIG.
- y B is the predicted deterioration of equipment B
- y A (t) is the predicted deterioration of equipment A at elapsed time t
- v B is the maintenance accuracy of equipment B
- w 1 , w 2 , ... w j are explanations
- the remaining explanatory variable (j ⁇ n) from among the variable candidates, t, is the elapsed time, and this becomes the deterioration prediction model for railway equipment B.
- a loop 204 indicates the starting point of the loop when changing the maintenance accuracy of the railway equipment A
- a loop 205 shows the starting end of the loop when changing the maintenance accuracy of the railway equipment B
- a loop 206 indicates the starting point of a loop of time change in the simulation.
- the maintenance accuracy of the railway equipment A is changed to 1, 2...k
- the maintenance accuracy of the railway equipment B is changed to 1, 2...j
- the maintenance cost is calculated at the set maintenance accuracy. .
- the processing unit 113 predicts the deterioration of the railway equipment A (207).
- the processing corresponds to the deterioration prediction unit 103.
- the deterioration prediction model of Equation 1 is used to acquire and set the values of each explanatory variable at time t from the sensing data and environmental information in the auxiliary storage device.
- the maintenance accuracy is set using the maintenance accuracy set at the start of the loop 204.
- Equation 1 uses Equation 1 to predict yA . Let this prediction result be y A (t).
- the processing unit 113 predicts deterioration of the railway equipment B (208).
- the processing corresponds to the deterioration prediction unit 103.
- the value of each explanatory variable at time t is acquired from the sensing data and environmental information of the auxiliary storage device, and in addition, yA acquired in 207 (t) to set.
- the maintenance accuracy is set using the maintenance accuracy set at the start end of the loop 204 and the start end of the loop 205.
- Equation 4 to predict yB . Let this prediction result be y B (t).
- the processing unit 113 predicts the maintenance cost of railway equipment A (209).
- the processing unit 113 executes a program that calculates maintenance costs. Calculating maintenance costs for railway equipment can be done in various ways depending on the equipment in question and the maintenance method used, but here maintenance costs are defined as inspection costs, repair costs when an abnormality is found during inspection, and repair costs when problems occur due to deterioration during transportation operations. This will be explained as three types of recovery costs.
- FIG. 11 shows an example of a method for calculating maintenance costs.
- the processing unit 113 determines whether deterioration has led to a failure between time (t-1) and time t (701). As a method of determination, for example, a method of determining whether the amount of deterioration of the target railway equipment exceeds a threshold value set in advance can be considered. If no failure has occurred, the process proceeds to 703. If a failure occurs, the processing unit 113 adds the restoration cost (702). Calculation of restoration costs includes removal fees for the target equipment, loss of usage opportunities until the target equipment is removed, etc., and is added based on a preset value.
- the processing unit 113 determines whether an inspection period is included from time (t-1) to time t (703).
- the inspection period indicates when the railway equipment is to be inspected, for example every month, and if there is an inspection period between the time (t-1) and time t, the inspection is assumed to have been carried out. If the inspection period is not included, the process advances to 708. If the inspection period is included, the processing unit 113 adds the inspection cost (704).
- the inspection cost is also a preset value, and addition is performed according to that value.
- the processing unit 113 determines whether an abnormality is found during the inspection (705). If no abnormality is found, the process advances to 708. If an abnormality is found, it is assumed that the repair has been performed, and the deterioration is changed to no deterioration (706). Regarding the treatment of no deterioration using the deterioration prediction model, for example, by resetting the elapsed time t to zero, a state of no deterioration can be achieved. Next, the processing unit 113 adds the repair cost (707). The repair cost is also a preset value, and is added according to that value. Finally, the restoration cost, inspection cost, and repair cost are summed up to form the maintenance cost (708).
- the processing unit 113 predicts the maintenance cost of railway equipment B (210).
- the processing unit 113 executes a program that calculates maintenance costs.
- the specific processing method can be determined using the maintenance cost calculation method shown in FIG. 11, for example, as in 209.
- the processing unit 113 determines the end of the time loop (211), and if the maintenance cost has not been calculated by the end time, the time is updated and the process returns to 206. If the end time has been reached, the process proceeds to 212.
- the maintenance costs of railway equipment A and railway equipment B are calculated when the maintenance accuracy of railway equipment A is k and the maintenance accuracy of railway equipment B is j (212).
- the calculation method is to add up the maintenance cost of railway equipment A and the maintenance cost of railway equipment B calculated in steps 209 and 210 at each time for each railway equipment.
- the processing unit 113 determines the end of the maintenance accuracy change loop for railway equipment B (213), and if the maintenance accuracy has not reached the end maintenance accuracy, the maintenance accuracy is updated and the process returns to 205. Otherwise, the process proceeds to 214.
- the maintenance accuracy of railway equipment A is k
- the maintenance cost of railway equipment A and the maintenance cost of railway equipment B for each maintenance accuracy (1, 2...j) of railway equipment B are output (214 ).
- the processing unit 113 determines the end of the maintenance accuracy change loop for the railway equipment A (215), and if the maintenance accuracy has not reached the end level, the maintenance accuracy is updated and the process returns to 204. Otherwise, the process proceeds to 216.
- FIG. 12 shows an example of a data structure expressing this maintenance cost.
- Maintenance accuracy 801 of railway equipment A indicates the maintenance accuracy of railway equipment A
- maintenance accuracy 802 of railway equipment B indicates the maintenance accuracy of railway equipment B.
- each maintenance accuracy is collectively expressed as an error from the reference maintenance accuracy (for example, the maintenance accuracy set at the start of a loop)
- the maintenance accuracy may be expressed using other methods.
- Inspection cost 803 of railway equipment A indicates the inspection cost of railway equipment A at the corresponding maintenance accuracy
- inspection cost 804 of railway equipment B indicates the inspection cost of railway equipment B at the corresponding maintenance accuracy.
- Repair cost 805 of railway equipment A indicates the repair cost of railway equipment A at the corresponding maintenance accuracy
- repair cost 806 of railway equipment B indicates the repair cost of railway equipment B at the corresponding maintenance accuracy.
- the restoration cost 807 of railway equipment A indicates the restoration cost of railway equipment A at the applicable maintenance accuracy
- the restoration cost 808 of railway equipment B represents the restoration cost of railway equipment B at the applicable maintenance accuracy
- Total maintenance cost 809 indicates the total maintenance cost. In this way, it is possible to grasp the total maintenance cost for each maintenance precision level of railway equipment. In addition, if multiple maintenance accuracy is included in the error range, a representative maintenance accuracy value is calculated from these maintenance accuracy, and the value of each cost (803 to 808) is calculated based on this maintenance accuracy. Good too.
- the processing unit 113 performs the search, which corresponds to the optimal search unit 104 in FIG.
- the search if the maintenance cost data structure is as shown in Figure 12, extract the record with the minimum total maintenance cost 809, and calculate the values of the maintenance accuracy 801 of railway equipment A and the maintenance accuracy 802 of railway equipment B at that time.
- a desired combination of maintenance accuracy can be specified.
- the processing unit 113 outputs the maintenance accuracy of railway equipment A and railway equipment B when the total maintenance cost is the lowest (218), and the process is completed.
- this process corresponds to the result creation unit 105.
- FIG. 13 shows an example of output when the total maintenance cost is the lowest.
- the maintenance accuracy output section 901 of railway equipment A shows the change in the maintenance accuracy of railway equipment A. In this example, when the current maintenance accuracy is 10% or less, the maintenance accuracy changes from 3% or less to error 17. % or less. Furthermore, the percentage change in maintenance accuracy relative to the current state may be expressed on a scale for easy understanding. The scale is the numerical value written from -200% to +200% in the maintenance accuracy output section 901 of railway equipment A.
- the maintenance accuracy output section 902 of the railway equipment B shows the change in the maintenance accuracy of the railway equipment B, and similarly to the maintenance accuracy output section 901 of the railway equipment A, it shows the value of the maintenance accuracy itself and the percentage change compared to the current state. It is expressed on a scale.
- a pointer 903 indicates the current maintenance accuracy of railway equipment A. Further, a pointer 904 indicates the current maintenance accuracy of the railway equipment B.
- a pointer 905 indicates the maintenance cost after the change, and in this example indicates the maintenance accuracy of the railway equipment A that minimizes the overall maintenance cost. Further, a pointer 906 indicates the maintenance cost after the change, and in this example, indicates the maintenance cost of railway equipment B where the overall maintenance cost is the minimum.
- the pointers (903 to 906) can be configured using symbols, letters, numbers, etc. as appropriate.
- Each square in the table shows the overall maintenance cost for each maintenance accuracy of railway equipment A and railway equipment B.
- the area with the lowest cost is darkened, and the area with the highest cost is shown in a heat map with a white background. It is expressed in By presenting changes in maintenance costs like this, maintenance managers can easily understand the display, and they can also judge whether combinations of other maintenance accuracy are likely to be effective, and make changes to the current maintenance management method. It becomes possible to encourage
- the maintenance accuracy change display 907 is a display example specifically showing the maintenance accuracy change that minimizes the overall maintenance cost.
- information about the current maintenance accuracy specified by pointer 903 and pointer 904 and the maintenance accuracy at the maintenance cost that minimizes the overall cost specified by pointer 905 and pointer 906 is displayed.
- the change result is output based on the scale of the percentage change from the current status of the maintenance accuracy output unit 901 of railway equipment A, the maintenance accuracy output unit 902 of railway equipment B, and the value of the maintenance cost.
- the display example of the maintenance accuracy change display 907 may also be presented in cases other than the maintenance accuracy that provides the minimum maintenance cost.
- the maintenance accuracy change display 907 may be any display that shows the overall maintenance cost change and the result of the maintenance accuracy change.
- the maintenance manager can select the minimum maintenance cost using the selection section 908 for selecting an appropriate maintenance cost. When clicking on a location that does not have a maintenance cost, information on changes in maintenance accuracy and maintenance cost from the current state to the location specified by the click may be displayed.
- the present invention is applicable not only to maintenance related to deterioration as described above, but also to maintenance related to failure.
- Deterioration is a model that predicts the progression of deterioration for a specific type of railway equipment, but since failures often occur stochastically, predictions are made by determining the failure probability distribution function for a specific type of railway equipment. .
- the configuration and differences in the case of maintenance for failure will be explained, and the same content as already explained will be omitted.
- FIG. 14 shows an example of the system configuration of a railway maintenance decision-making support system in the case of maintenance related to failures. Differences with respect to deterioration include a failure prediction model estimation section 1001, a failure prediction section 1002, failure information 1003, and a failure prediction model 1004. The differences between them will be explained using FIG. 15, which shows an example of processing contents.
- FIG. 15 is a flowchart showing an example of the process of estimating a failure prediction model in the railway maintenance decision support system, estimating the total maintenance cost, and determining the maintenance accuracy of each piece of equipment that minimizes the maintenance cost in the case of maintenance related to failures. .
- the processing unit 113 estimates a failure prediction model for railway equipment A (1101).
- the processing corresponds to the failure prediction model estimation unit 1001. In the case of a failure, it does not change sequentially as in the case of deterioration prediction, but often occurs suddenly.
- FIG. 16 shows a specific example of failure information 1003 used when calculating each coefficient of Equation 6, which will be explained later.
- the equipment type ID 1201 is an equipment type ID, and indicates, for example, the model of railway equipment A (it is assumed that there is a plurality of pieces of data for the same equipment as railway equipment A).
- the measurement period 1202 represents the measurement period, and the number of failures 1203 represents the number of failures for the equipment type ID that occurred during the measurement period. In this way, in the case of a failure, in order to treat the occurrence of an event probabilistically, model prediction is performed using data on the number of occurrences for each type of railway equipment, rather than for specific railway equipment.
- Weibull distribution estimation is often used in reliability engineering as one of the models that handles the occurrence of events stochastically. This embodiment will also be explained using failure probability estimation based on the Weibull distribution. Generally, assuming that the failure probability distribution function of a certain equipment is a Weibull distribution, it is given by Equation 5 shown in FIG.
- Equation 6 is the Weibull coefficient and ⁇ is the scale.
- z A is a failure prediction model for railway equipment A
- m is a Weibull coefficient
- ⁇ is a scale
- s A is a correction time
- THER 1 , THER 2 , . . . (7) k are explanatory variables of s A.
- explanatory variables réelle 1 , réelle 2 , ... 866 k are extracted from the sensing data 106 and the environmental information 107, as in the case of deterioration prediction. Further, by using information on passage at a position where a failure may occur, transportation information may be added as described above.
- the processing unit 113 adds the failure information of railway equipment A to estimate a failure prediction model of railway equipment B (1102).
- the processing corresponds to the failure prediction model estimation unit 1001.
- the failure prediction model for railway equipment B at this time is given by Equation 7 shown in FIG.
- z B is the failure prediction model of railway equipment B
- z A (t) is the value of z A at time t
- m is the Weibull coefficient
- ⁇ is the scale
- s B is the correction time
- zark is an explanatory variable of sB .
- estimation is performed by including the failure probability of the type of railway equipment A in the explanatory variables.
- z B and s B are estimated in the same manner as in step 1001.
- failure prediction is performed by the processing unit 113, and in FIG. 14, this is a process that corresponds to the failure prediction unit 1002.
- probabilistic equation 6 is given as the failure probability distribution function, so in this example, after once finding the failure probability z A (t) at this time t, we separately calculate the failure probability z A (t) between 0 and 1. A random number is generated, and when the random number exceeds z A (t), it is predicted that a failure has occurred.
- the processing unit 113 executes the failure prediction unit 1002 to predict failures of railway equipment B (1104).
- FIG. 20 is a diagram showing another example of the data structure of the aggregation results in 216 of FIG. This is basically an expanded version of FIG. 12, and the same numbers as in FIG. 12 are used for the same parts. Below, only the changes will be explained.
- the elapsed period 1301 indicates elapsed time, and corresponds to the time change t in the simulation described in 206 of FIG.
- the cumulative total maintenance cost 1302 indicates the cumulative total maintenance cost, and indicates the cumulative total of the total maintenance cost 709 up to the elapsed time t. In this way, data is summarized for each elapsed period 1301.
- FIG. 21 shows an example of a comparative display of maintenance costs using the aggregation results of FIG. 20.
- the current maintenance plan 1401 shows the cost change of the current maintenance plan.
- the graph on the far left is a graph of changes over time in the maintenance cost of railway equipment A, the horizontal axis of the graph indicates elapsed time, and the vertical axis of the graph indicates maintenance cost.
- the horizontal and vertical axes of the graphs shown in FIG. 21 below are all the same.
- the horizontal axis is the elapsed period 1301 in Figure 20
- the vertical axis is the sum of the codes (803, 805, 807) in the records that match the current maintenance accuracy, accumulated up to the elapsed time. This is the numerical value.
- the center graph is a graph of changes in maintenance costs for railway equipment B over time.
- the elapsed period 1301 in Figure 20 is the numerical value on the horizontal axis, and the total value of the codes (804, 806, 808) among the records that match the current maintenance accuracy is further accumulated to the elapsed time. is the numerical value on the vertical axis.
- the graph on the far right shows the total maintenance cost of railway equipment A and railway equipment B.
- the maintenance change plan 1402 shows the cost change of the maintenance change plan. Similar to current maintenance plan 1401, the graph on the far left is a graph of changes over time in the maintenance cost of railway equipment A, the center graph is a graph of changes over time in maintenance costs of railway equipment B, and the graph on the far right is a graph of changes over time in maintenance costs of railway equipment A. and the total maintenance cost of railway equipment B.
- the method of displaying a graph using the information in FIG. 20 is the same as in the case of the current maintenance plan 1401.
- a change effect 1403 shows a comparison graph of change effects.
- the total maintenance cost created in the current maintenance plan 1401 and the total maintenance cost created in the maintenance change plan 1402 are superimposed and displayed.
- the present invention is equally applicable to both deterioration and failure.
- By handling both deterioration and failure it becomes possible to deal with cases where, for example, the state of deterioration of one piece of railway equipment changes the probability of damage to another piece of railway equipment.
- the fourth embodiment below differences in configuration and processing when both deterioration and damage are handled will be explained, and explanations of the same contents as those already explained will be omitted.
- FIG. 22 shows an example of the system configuration of a railway maintenance decision-making support system that handles both deterioration and failure. Differences from FIG. 1 or FIG. 14 include a deterioration prediction model estimation section 1501 and a failure prediction model estimation section 1502. The differences between them will be explained using FIG. 23 showing the processing contents.
- Figure 23 shows the estimation of deterioration prediction or failure prediction model in the railway maintenance decision support system, estimation of total maintenance cost, and determination of maintenance accuracy for each equipment that minimizes maintenance cost in the case of maintenance that deals with both deterioration and failure. It is a flowchart which shows an example of a process. Note that in the case of the same processing, the same numbers as in FIG. 2 are assigned.
- the processing unit 113 estimates a deterioration prediction and failure prediction model for railway equipment A (1601).
- the processing corresponds to the deterioration prediction model estimation section 1501 and the failure prediction model estimation section 1502.
- the processing unit 113 adds the deterioration and failure information of the railway equipment A to estimate a deterioration prediction model and a failure prediction model of the railway equipment B (1602).
- the processing corresponds to the deterioration prediction model estimation section 1501 and the failure prediction model estimation section 1502.
- the deterioration prediction model is expressed as Equation 8 shown in FIG.
- y B is the predicted deterioration value of equipment B
- y A (t) is the predicted deterioration value of equipment A at elapsed time t
- z A (t) is the predicted failure value of equipment A at elapsed time t
- v B is the maintenance accuracy of equipment B
- w 1 , w 2 , ... w j are the explanatory variables remaining from the explanatory variable candidates (j ⁇ n)
- t is the elapsed time
- the explanatory variable is the deterioration of equipment A.
- the formula includes prediction and failure prediction values. This becomes the deterioration prediction model for railway equipment B.
- Equation 9 shown in FIG. 25 is obtained.
- z B is the failure prediction model of railway equipment B
- z A (t) is the failure prediction value of equipment A at elapsed time t
- y A (t) is the deterioration prediction value of equipment A at elapsed time t
- m is the Weibull coefficient
- ⁇ is the scale
- s B is the correction time
- (8) 1 , (7) 2 , ... (7) k are the explanatory variables of s B
- the equation includes the predicted deterioration and failure predicted values of equipment A as explanatory variables. becomes. This becomes a deterioration and failure prediction model for railway equipment B.
- the next change is the prediction of deterioration and failure of railway equipment A by the processing unit 113 (1603).
- Deterioration prediction determines whether the deterioration exceeds the standard value, and failure prediction determines whether a value exceeding the failure probability of the failure prediction model was obtained in a random trial. If it is determined that there is an abnormality, it is determined that there is an abnormality.
- the deterioration prediction and failure prediction of railway equipment B if either of them becomes abnormal, it may be determined that the equipment is abnormal (1604). Thereafter, by performing processing similar to the flow of FIG. 2, it is possible to output maintenance accuracy for reducing the overall maintenance cost when both deterioration and failure are handled.
- the present invention can also be applied to objects composed of three or more pieces of equipment or equipment.
- processing when three or more railway facilities and equipment are handled will be described. Note that descriptions of contents similar to those already explained will be omitted.
- FIG. 26 shows an example of a configuration composed of a plurality of facilities and devices.
- railway equipment A is connected to railway equipment B and railway equipment C.
- railway equipment B is connected to railway equipment D and railway equipment E.
- railway equipment D is connected to railway equipment F and railway equipment G.
- the railway equipment E is connected to the railway equipment G and the railway equipment H.
- Such a connection relationship indicates the maintenance relationship of each railway facility. In the case of such equipment, it is better to perform model estimation from the downstream equipment while referring to the configuration information.
- FIG. 27 is a flowchart illustrating an example of model estimation for each configured railway facility based on the configuration example.
- the processing unit 113 extracts the equipment group included in the equipment configuration information and sets it as a set M.
- N be the modeled equipment (1801).
- N is an empty set in the initial state.
- the configuration information is information expressing the configuration example of the railway equipment shown in FIG. 26 as data.
- the configuration information indicates the connection relationship of each railway equipment as a System of Systems
- the configuration information includes information indicating which railway equipment's maintenance accuracy will be affected by a change in the maintenance accuracy of a certain railway equipment. included.
- the configuration information is like a connection matrix in graph theory, where each piece of equipment is i and the number of railway equipment is n, it becomes an n x n two-dimensional matrix, and the elements of (i, j) are connected from railway equipment i to railway equipment.
- j indicates whether they are connected (for example, if they are connected from i to j, it is given as 1, if they are connected in the opposite direction, it is given as -1, and if they are not connected, it is given as 0).
- the processing unit 113 extracts a facility group that has no subordinate facilities from the set M and sets it as P (1802). Specifically, with reference to the above configuration information, for (i, j) for all j, i for which there is no j that is 1 becomes an element of P. Next, the processing unit 113 performs model prediction for each facility i of P (1803). This model prediction corresponds to the deterioration prediction model estimation unit 102 in FIG. 1 or the failure prediction model estimation unit 1001 in FIG. 14 (detailed processing of these has already been explained and will therefore be omitted).
- the processing unit 113 adds each element of the model-predicted P to the model-predicted set N, removes P from M, and creates a new set M (1804). Finally, the processing unit 113 determines whether M is an empty set (1805), and if it is not an empty set, the process returns to 1802. If the set is empty, the process ends. In this way, by using the connection information of railway equipment and performing model estimation from lower-level railway equipment, it is possible to perform model estimation for all railway equipment.
- the configuration information is information that indicates that equipment is more likely to deteriorate or break down as it goes downstream (that is, the lower the railway equipment is, the more likely it is to deteriorate or break down), and the processing unit 113 connects the equipment based on the configuration information.
- the process is performed using a matrix.
- prediction models for other equipment can be generated using predictions for equipment that is prone to deterioration or failure as explanatory variables, and results can be output based on equipment that is highly related to maintenance effects.
- the configuration information is input into the railway maintenance decision-making support system by an appropriate method, and can be input by a maintenance manager, for example.
- FIG. 28 shows an activity diagram at the railway maintenance site.
- sensor information is first sent from railway equipment A and railway equipment B, and is stored in the railway maintenance decision support system.
- the railway maintenance decision support system in this example is the same as the railway maintenance decision support system in FIG. 1).
- sensing information regarding the rails is input.
- Sensing information regarding wheel wear is input from railway equipment B.
- the railway maintenance decision support system outputs the maintenance accuracy that minimizes the overall cost based on the sensing information.
- the calculation process is the same as the flow in FIG. 2, and in the case of rails and wheels, the processing unit 113 first estimates a rail deterioration prediction model and a wheel deterioration prediction model. At this time, the wheel deterioration prediction model is estimated by including the rail deterioration status as an explanatory variable. Next, the processing unit 113 uses the rail and wheel deterioration prediction model to estimate the total maintenance cost when changing the rail maintenance accuracy and the wheel maintenance accuracy. Finally, the processing unit 113 outputs the combination of maintenance accuracy that provides the lowest overall cost.
- the maintenance manager can refer to this calculation result (maintenance accuracy for each piece of equipment that minimizes the overall cost) and confirm the amount of improvement maintenance cost and maintenance accuracy change proposal, thereby determining the target maintenance accuracy for each piece of equipment. Decide whether to change it. For example, in exchange for making rail distortion 1.2 times tighter than the current accuracy, the minimum cost for overall maintenance is indicated as a time when it is acceptable to allow wheel length errors up to 1.1 times the current level, and maintenance management The person will decide whether to change to the target maintenance accuracy plan. When the target maintenance accuracy is changed, the maintenance manager presents the target maintenance accuracy to the maintenance planner. The maintenance planner formulates a specific maintenance plan (inspection plan, repair plan, replacement plan) that maintains the target maintenance accuracy. This maintenance plan is presented to each maintenance person, and each maintenance person inspects, repairs, replaces, etc. the rails and wheels according to the maintenance plan.
- a specific maintenance plan inspection plan, repair plan, replacement plan
- railway maintenance decision support system railway maintenance support system
- estimating the maintenance accuracy of each facility and equipment that can reduce the overall maintenance cost
- the overall maintenance cost can be reduced.
- maintenance planners can formulate maintenance plans based on changes in maintenance management standards, and maintenance personnel can perform maintenance based on the changed maintenance plans. , overall maintenance costs can be minimized.
- the railway maintenance decision support system may be placed as a computer directly handled by a maintenance manager, or may be placed on the cloud.
- the configuration of the input section, output section, etc. of the railway maintenance decision-making support system may be omitted as appropriate, and the maintenance manager may input and output data using the communication section. It is only necessary to be able to perform appropriate processing, and the railway maintenance decision support system may be configured by, for example, one or more computers. Further, the railway maintenance decision support system may have a configuration in which the functions of the railway maintenance decision support system are realized by a plurality of devices performing processing in a distributed manner.
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Train Traffic Observation, Control, And Security (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
Description
各種情報の例として、「テーブル」、「リスト」、「キュー」等の表現にて説明することがあるが、各種情報はこれら以外のデータ構造で表現されてもよい。例えば、「XXテーブル」、「XXリスト」、「XXキュー」等の各種情報は、「XX情報」としてもよい。識別情報について説明する際に、「識別情報」、「識別子」、「名」、「ID」、「番号」等の表現を用いるが、これらについてはお互いに置換が可能である。
実施形態では、レールと車輪や、エアブレーキと電気ブレーキ等の様に、保守の関係性を有する設備や機器が対象とされ、複数の設備や機器間での保守の関係性に基づき、より適切な保守方法を提示する支援システムを説明する。
第1実施形態は、鉄道設備や機器から送られるセンサ情報をもとに、劣化予測を可能とするモデルを推定し、さらに設備等の間における保守の関係性を推定することで、全体として保守コストを最も低減できる各設備や機器の保守精度を提示する鉄道保守意思決定支援システムに関する。図1は、鉄道保守意思決定支援システムの一例を示す構成図である。
図14は故障に関する保守の場合の、鉄道保守意思決定支援システムのシステム構成の一例を表している。劣化との差分としては、故障予測モデル推定部1001、故障予測部1002、故障情報1003、故障予測モデル1004がある。それぞれの違いについては処理内容の一例を示す図15を使い説明する。
図20は、図2の216における別の集計結果のデータ構造例を示した図である。基本的に図12を拡張したものであり、同じところは図12の番号を用いている。以下、変更点についてのみ説明する。経過期間1301は経過時間を示しており、図2の206で述べたシミュレーションでの時間変化tに該当している。累積合計保守コスト1302は累積合計保守コストを示しており、経過時間tまでの合計保守コスト709の累計を示している。このように、経過期間1301ごとにデータがまとめられている。
図22は劣化と故障の両方を取り扱う場合の、鉄道保守意思決定支援システムのシステム構成の一例を表している。図1または図14との差分としては、劣化予測モデル推定部1501、故障予測モデル推定部1502がある。それぞれの違いについては、処理内容の図23を使い説明する。
図26は複数の設備や機器から構成された構成例を示している。このSystem of Sysmtemsの鉄道の例では、鉄道設備Aは鉄道設備Bと鉄道設備Cと接続していることを示しており、以下同様に鉄道設備Bは、鉄道設備Dと鉄道設備Eと接続しており、鉄道設備Dは鉄道設備Fと鉄道設備Gと接続している。また鉄道設備Eも鉄道設備Gと鉄道設備Hと接続していることを示している。このような接続関係により、各鉄道設備の保守の関係性が示される。この様な機器の場合には、構成情報を参照しながら、下流の設備からモデル推定を行うと良い。
図28は鉄道保守の現場でのアクティビティ図を示したものである。この例では、最初に鉄道設備A、鉄道設備Bからセンサ情報が送られ、鉄道保守意思決定支援システムにて格納される。(この例の鉄道保守意思決定支援システムは図1の鉄道保守意思決定支援システムと同一のものである)。例えば鉄道設備Aからは、レールに対するセンシング情報(高低、通り、水準、軌間、平面性など)が入力される。
102 劣化予測モデル推定部
105 結果作成部
Claims (15)
- プロセッサと、記憶部と、を備え、
前記プロセッサは、
鉄道設備のセンサ装置から取得するセンシングデータを変換した鉄道設備の保守の精度に関する情報である保守精度を説明変数とする鉄道設備の劣化の予測に用いる劣化予測モデルを、複数の鉄道設備ごとに推定し、前記記憶部に格納し、
前記劣化予測モデルの推定において、
既に推定して前記記憶部に格納した第1の鉄道設備の劣化予測モデルの劣化予測を説明変数に含めた第2の鉄道設備の劣化予測モデルを推定する処理を行い、
各鉄道設備の劣化予測モデルの劣化予測に基づいた保守による全体の保守コストを出力する、
ことを特徴とする鉄道保守支援システム。 - 請求項1に記載の鉄道保守支援システムであって、
前記プロセッサは、
前記記憶部に格納された各鉄道設備の劣化予測モデルを用いて保守精度を変えて劣化予測をすることで、前記の全体の保守コストを算出し、
前記の全体の保守コストを最小化する際の各鉄道設備の保守精度を特定する、
ことを特徴とする鉄道保守支援システム。 - プロセッサと、記憶部と、を備え、
前記プロセッサは、
鉄道設備の故障の予測に用いる故障予測モデルを複数の鉄道設備ごとに推定し、前記記憶部に格納し、
前記故障予測モデルの推定において、
既に推定して前記記憶部に格納した第1の鉄道設備の故障予測モデルの故障予測を説明変数に含めた第2の鉄道設備の故障予測モデルを推定する処理を行い、
各鉄道設備の故障予測モデルの故障予測に基づいた保守による全体の保守コストを出力する、
ことを特徴とする鉄道保守支援システム。 - 請求項3に記載の鉄道保守支援システムであって、
前記プロセッサは、
前記記憶部に格納された各鉄道設備の故障予測モデルを用いて、鉄道設備の保守の精度に関する情報である保守精度を変えて故障予測をすることで、前記の全体の保守コストを算出し、
前記の全体の保守コストを最小化する際の各鉄道設備の保守精度を特定する、
ことを特徴とする鉄道保守支援システム。 - 請求項2に記載の鉄道保守支援システムであって、
表示装置を備え、
前記プロセッサは、
現状の保守精度と変更案の保守精度に関して、どの程度の保守精度変更となるかについてスケールを用いて示す表示と、
前記変更案に対する全体の保守コスト変更および保守精度変更の結果を示す表示と、を前記表示装置に行う、
ことを特徴とする鉄道保守支援システム。 - 請求項4に記載の鉄道保守支援システムであって、
表示装置を備え、
前記プロセッサは、
現状の保守精度と変更案の保守精度に関して、どの程度の保守精度変更となるかについてスケールを用いて示す表示と、
前記変更案に対する全体の保守コスト変更および保守精度変更の結果を示す表示と、を前記表示装置に行う、
ことを特徴とする鉄道保守支援システム。 - 請求項2に記載の鉄道保守支援システムであって、
表示装置を備え、
前記プロセッサは、
現状の保守案である現状保守案における、鉄道設備それぞれの保守コストの時間変化および全体の保守コストの時間変化を示す表示と、
現状からの変更案である保守変更案における、鉄道設備それぞれの保守コストの時間変化および全体の保守コストの時間変化を示す表示と、
前記現状保守案と前記保守変更案の全体の保守コストの時間変化を重ね合わせた比較表示と、を前記表示装置に行う、
ことを特徴とする鉄道保守支援システム。 - 請求項4に記載の鉄道保守支援システムであって、
表示装置を備え、
前記プロセッサは、
現状の保守案である現状保守案における、鉄道設備それぞれの保守コストの時間変化および全体の保守コストの時間変化を示す表示と、
現状からの変更案である保守変更案における、鉄道設備それぞれの保守コストの時間変化および全体の保守コストの時間変化を示す表示と、
前記現状保守案と前記保守変更案の全体の保守コストの時間変化を重ね合わせた比較表示と、を前記表示装置に行う、
ことを特徴とする鉄道保守支援システム。 - 請求項1に記載の鉄道保守支援システムであって、
前記プロセッサは、
鉄道設備の故障の予測に用いる故障予測モデルを複数の鉄道設備ごとに推定し、前記記憶部に格納し、
前記劣化予測モデルの推定において、
既に推定して前記記憶部に格納した第1の鉄道設備の故障予測モデルの故障予測を説明変数に加えて第2の鉄道設備の劣化予測モデルを推定する処理を行い、
前記故障予測モデルの推定において、
既に推定して前記記憶部に格納した第1の鉄道設備の劣化予測モデルの劣化予測、および、既に推定して前記記憶部に格納した第1の鉄道設備の故障予測モデルの故障予測を説明変数に含めた第2の鉄道設備の故障予測モデルを推定する処理を行い、
前記の全体の保守コストの出力に代えて、前記記憶部に格納された各鉄道設備の劣化予測モデルの劣化予測、および、前記記憶部に格納された各鉄道設備の故障予測モデルの故障予測に基づいた保守による全体の保守コストを出力する、
ことを特徴とする鉄道保守支援システム。 - 請求項3に記載の鉄道保守支援システムであって、
前記プロセッサは、
鉄道設備のセンサ装置から取得するセンシングデータを変換した鉄道設備の保守の精度に関する情報である保守精度を説明変数とする鉄道設備の劣化の予測に用いる劣化予測モデルを、複数の鉄道設備ごとに推定し、前記記憶部に格納し、
前記故障予測モデルの推定において、
既に推定して前記記憶部に格納した第1の鉄道設備の劣化予測モデルの劣化予測を説明変数に加えて第2の鉄道設備の故障予測モデルを推定する処理を行い、
前記劣化予測モデルの推定において、
既に推定して前記記憶部に格納した第1の鉄道設備の故障予測モデルの故障予測、および、既に推定して前記記憶部に格納した第1の鉄道設備の劣化予測モデルの劣化予測を説明変数に含めた第2の鉄道設備の劣化予測モデルを推定する処理を行い、
前記の全体の保守コストの出力に代えて、前記記憶部に格納された各鉄道設備の劣化予測モデルの劣化予測、および、前記記憶部に格納された各鉄道設備の故障予測モデルの故障予測に基づいた保守による全体の保守コストを出力する、
ことを特徴とする鉄道保守支援システム。 - 請求項1に記載の鉄道保守支援システムであって、
前記プロセッサは、
前記劣化予測モデルの推定において、
3つ以上の鉄道設備が保守精度変化に関係している場合、それぞれの鉄道設備の接続関係を示す構成情報において他の鉄道設備の保守精度に影響を与えない鉄道設備から順に劣化予測モデルを推定する、
ことを特徴とする鉄道保守支援システム。 - 請求項3に記載の鉄道保守支援システムであって、
前記プロセッサは、
前記故障予測モデルの推定において、
鉄道設備の保守の精度に関する情報である保守情報に関して3つ以上の鉄道設備が保守精度変化に関係している場合、それぞれの鉄道設備の接続関係を示す構成情報において他の鉄道設備の保守精度に影響を与えない鉄道設備から順に故障予測モデルを推定する、
ことを特徴とする鉄道保守支援システム。 - 請求項1に記載の鉄道保守支援システムであって、
前記プロセッサは、
前記劣化予測モデルの推定において、
鉄道の輸送情報を用いて鉄道設備に劣化の影響がある位置での鉄道の通過の情報を説明変数に含めることで、鉄道の輸送情報を加味した説明変数に基づく劣化予測モデルを推定する、
ことを特徴とする鉄道保守支援システム。 - 請求項3に記載の鉄道保守支援システムであって、
前記プロセッサは、
前記故障予測モデルの推定において、
鉄道の輸送情報を用いて鉄道設備に故障が発生し得る位置での鉄道の通過の情報を説明変数に含めることで、鉄道の輸送情報を加味した説明変数に基づく故障予測モデルを推定する、
ことを特徴とする鉄道保守支援システム。 - プロセッサと、記憶部と、を有する鉄道保守支援システムを用いて行う鉄道保守支援方法であって、
前記プロセッサは、
鉄道設備の保守の精度に関する情報である保守精度を入力し、前記保守精度を説明変数とする鉄道設備の劣化の予測に用いる劣化予測モデルを複数の鉄道設備ごとに推定し、前記記憶部に格納し、
各鉄道設備の劣化予測モデルの劣化予測に基づいた保守による全体の保守コストを出力し、
前記の複数の鉄道設備ごとに劣化予測モデルを推定する際に、既に推定して前記記憶部に格納した第1の鉄道設備の劣化予測モデルの劣化予測を説明変数に含めた第2の鉄道設備の劣化予測モデルを推定する処理を行う、
ことを特徴とする鉄道保守支援方法。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2023251295A AU2023251295A1 (en) | 2022-04-07 | 2023-02-01 | Railroad maintenance support system, railroad maintenance support method |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2022-064180 | 2022-04-07 | ||
JP2022064180A JP2023154681A (ja) | 2022-04-07 | 2022-04-07 | 鉄道保守支援システム、鉄道保守支援方法 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023195218A1 true WO2023195218A1 (ja) | 2023-10-12 |
Family
ID=88242773
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2023/003171 WO2023195218A1 (ja) | 2022-04-07 | 2023-02-01 | 鉄道保守支援システム、鉄道保守支援方法 |
Country Status (3)
Country | Link |
---|---|
JP (1) | JP2023154681A (ja) |
AU (1) | AU2023251295A1 (ja) |
WO (1) | WO2023195218A1 (ja) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016203931A (ja) * | 2015-04-28 | 2016-12-08 | 株式会社日立製作所 | 鉄道地上設備の保守支援システム、保守支援方法、及び保守支援プログラム |
JP2017016509A (ja) | 2015-07-03 | 2017-01-19 | 横河電機株式会社 | 設備保全管理システムおよび設備保全管理方法 |
JP2019105927A (ja) * | 2017-12-11 | 2019-06-27 | 日本電信電話株式会社 | 故障確率算出装置、故障確率算出方法及びプログラム |
US20210261177A1 (en) * | 2018-06-28 | 2021-08-26 | Konux Gmbh | Planning of maintenance of railway |
-
2022
- 2022-04-07 JP JP2022064180A patent/JP2023154681A/ja active Pending
-
2023
- 2023-02-01 WO PCT/JP2023/003171 patent/WO2023195218A1/ja active Application Filing
- 2023-02-01 AU AU2023251295A patent/AU2023251295A1/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016203931A (ja) * | 2015-04-28 | 2016-12-08 | 株式会社日立製作所 | 鉄道地上設備の保守支援システム、保守支援方法、及び保守支援プログラム |
JP2017016509A (ja) | 2015-07-03 | 2017-01-19 | 横河電機株式会社 | 設備保全管理システムおよび設備保全管理方法 |
JP2019105927A (ja) * | 2017-12-11 | 2019-06-27 | 日本電信電話株式会社 | 故障確率算出装置、故障確率算出方法及びプログラム |
US20210261177A1 (en) * | 2018-06-28 | 2021-08-26 | Konux Gmbh | Planning of maintenance of railway |
Also Published As
Publication number | Publication date |
---|---|
AU2023251295A1 (en) | 2024-03-21 |
JP2023154681A (ja) | 2023-10-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Al-Douri et al. | Improvement of railway performance: a study of Swedish railway infrastructure | |
JP6000070B2 (ja) | 運転整理装置および方法 | |
AU2014100419A4 (en) | System and method for scheduling | |
WO2014110099A2 (en) | Railway track geometry defect modeling for predicting deterioration, derailment risk, and optimal repair | |
US20150302319A1 (en) | Data provisioning system and method | |
CN114072825A (zh) | 使用数字孪生监测、预测和维护铁路元素的状况 | |
JP6367757B2 (ja) | 管理方法及び管理装置 | |
CN115909729A (zh) | 一种基于数字孪生的地铁线网运营中断情况下的仿真预测方法及系统 | |
Xie et al. | A customized hybrid approach to infrastructure maintenance scheduling in railroad networks under variable productivities | |
JP2019093906A (ja) | 運行管理支援装置、及び運行制御システム | |
US10402755B2 (en) | Transportation service information providing apparatus, and transportation service information providing method | |
WO2023195218A1 (ja) | 鉄道保守支援システム、鉄道保守支援方法 | |
Carrel et al. | A framework for evaluating operations control on a metro line: integrating multiple perspectives and automatically collected train and passenger movement data | |
Shalaby et al. | Rail transit disruption management: a comprehensive review of strategies and approaches | |
JP2014091424A (ja) | 鉄道車両における運用を考慮した走行距離補正システム | |
Su et al. | Simulation-Based Method for the Calculation of Passenger Flow Distribution in an Urban Rail Transit Network Under Interruption | |
Furtado et al. | Railway bridge management system based on visual inspections with semi-Markov continuous time process | |
WO2022165195A1 (en) | Managing, monitoring, and validating train consists | |
JP6935031B1 (ja) | 劣化評価装置、検査計画立案装置、鉄道車両管理システム、劣化評価プログラムおよび劣化評価方法 | |
Yap et al. | Public transport network resilience | |
Kunimatsu et al. | The prediction of passenger flow under transport disturbance using accumulated passenger data | |
Famurewa | Maintenance analysis and modelling for enhanced railway infrastructure capacity | |
Andrade et al. | Assessing temporary speed restrictions and associated unavailability costs in railway infrastructure | |
JP7123217B1 (ja) | 保守計画作成装置、保守計画作成システム、保守計画作成方法、および保守計画作成プログラム | |
Xu et al. | Dynamic bridge maintenance management in smart cities using routine inspection data and hazard modeling |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 23784513 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2023251295 Country of ref document: AU Ref document number: AU2023251295 Country of ref document: AU |
|
ENP | Entry into the national phase |
Ref document number: 2023251295 Country of ref document: AU Date of ref document: 20230201 Kind code of ref document: A |