Information processing device

Abstract

To provide an information processing device that makes it possible to avoid vehicle failures by a method other than component replacement.SOLUTION: Stored in an information processing device 200 are a failure prediction model 140 for outputting the type of failure which is predicted to occur, and a simulation model 240 for outputting the time-series data of behavior of each vehicle part when the time-series data of driving operation is inputted. When the data of input variable at the time when a predicted type of failure is outputted from the failure prediction device 100 is acquired, the information processing device 200 calculates the simulated data of the time-series data of behavior of each vehicle part for the case where the value of control parameter of a vehicle 400 is changed by inputting the time-series data of driving operation to the simulation model 240. The information processing device 200 inputs an input variable for trial composed of the time-series data of driving operation and the simulated data to the failure prediction model 140 and searches for the value of a control parameter with which failure occurrence is no longer predicted, and presents a change to the obtained value to the user of the vehicle 400.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an information processing device. [Background technology]

[0002] Patent Document 1 discloses a failure prediction device. This failure prediction device generates a learning model for failure prediction using time-series sensor data until the monitored device fails as teacher data. The failure prediction device uses the generated learning model to predict the probability that the monitored device will fail using the time-series sensor data received from the monitored device as input. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2016-173782 A Summary of the Invention [Problem to be solved by the invention]

[0004] If a failure prediction device equipped with a failure prediction model learned through such supervised learning is applied to a vehicle and a failure of a vehicle part is predicted, the vehicle user will have no choice but to replace the part in question to prevent the failure from occurring. [Means for solving the problem]

[0005] The means for solving the above problems and their effects will be described below. An information processing device for solving the above problem includes a processing device and a storage device. In the information processing device, a failure prediction model learned by supervised learning so as to output a type of failure predicted to occur when input variables consisting of time series data of driving operations and behavior of each part of the vehicle are input is stored in the storage device. In the information processing device, a simulation model that outputs time series data of behavior of each part of the vehicle when time series data of driving operations is input is stored in the storage device. In this information processing device, the processing device obtains data of the input variables from a failure prediction device that predicts a vehicle failure using the same failure prediction model as the failure prediction model, when the failure prediction device outputs a type of failure predicted. In this information processing device, the processing device inputs time-series data of the driving operation in the acquired data of input variables into the simulation model, calculates simulation data that simulates time-series data of behavior of each part of the vehicle when values ​​of control parameters of the vehicle are changed, thereby generating trial input variables consisting of the time-series data of the driving operation in the acquired data of input variables and the simulation data, and inputs the generated trial input variables into the failure prediction model to search for values ​​of the control parameters at which the occurrence of a failure is not predicted. In this information processing device, the processing device presents the changes to the control parameters obtained by the search to values ​​at which the occurrence of a failure is not predicted to the user of the vehicle.

[0006] A second information processing device for solving the above problem is connected to a vehicle through a communication network. This information processing device includes a processing device and a storage device. In this information processing device, a failure prediction model that is trained by supervised learning so as to output a type of failure predicted to occur when input variables consisting of time series data of driving operations and behavior of each part of the vehicle are input is stored in the storage device. In this information processing device, a simulation model that outputs time series data of behavior of each part of the vehicle when time series data of driving operations is input is also stored in the storage device. In this information processing device, the processing device receives data of the input variables from the vehicle, and inputs the data to the failure prediction model to output a type of failure predicted to occur. In this information processing device, the processing device inputs time-series data of the driving operation in the input variable data when a type of failure predicted to occur is output into the simulation model, and calculates simulation data that simulates the time-series data of the behavior of each part of the vehicle when values ​​of control parameters of the vehicle are changed, thereby generating trial input variables consisting of the time-series data of the driving operation in the acquired input variable data and the simulation data, and inputs the generated trial input variables into the failure prediction model to search for values ​​of the control parameters at which the occurrence of a failure is not predicted. In this information processing device, the processing device presents the changes to the control parameters obtained by the search to values ​​at which the occurrence of a failure is not predicted to occur to a user of the vehicle. Effect of the Invention

[0007] These information processing devices allow users to avoid vehicle breakdowns in ways other than by replacing parts. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a schematic diagram showing a configuration of a failure avoidance system including an information processing device according to an embodiment. [Diagram 2]FIG. 2 is a sequence diagram showing a flow of processing by the vehicle control device, the failure prediction device, and the information processing device in the failure avoidance system of the embodiment. [Diagram 3] FIG. 3 is a flowchart showing a flow of processing executed by an information processing device in the failure avoidance system of the embodiment. [Figure 4] FIG. 4 is a flowchart showing a process flow for predicting a vehicle failure executed by the failure prediction device in the failure avoidance system of the embodiment. [Diagram 5] FIG. 5 is a flowchart showing a process flow regarding the presentation of control parameters executed by the failure prediction device in the failure avoidance system of the embodiment. [Figure 6] FIG. 6 is a schematic diagram showing the configuration of a failure avoidance system including an information processing device according to the modified example. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an embodiment of an information processing device will be described with reference to FIGS. <Configuration of failure avoidance system 10> 1, the fault avoidance system 10 includes an information processing device 200 and a vehicle 400. The information processing device 200 is connected to the vehicle 400 via a communication network 300 so as to be able to communicate with the vehicle 400.

[0010] The vehicle 400 includes the failure prediction device 100 , a vehicle control device 410 , and a display device 420 . The failure prediction device 100 includes a storage device 120 in which a program and a failure prediction model 140 are stored, and a processing device 110 that executes various processes by executing the program stored in the storage device 120. The processing device 110 includes a processor.

[0011] The failure prediction model 140 is a model that is trained by supervised learning so as to output the type of failure predicted to occur when input variables consisting of time-series data on driving operations and the behavior of each part of the vehicle are input. The time-series data on the motion operations is data indicating the amount of operation applied by the user to the vehicle 400, such as the accelerator opening, the amount of brake operation, the amount of steering operation, etc. The time-series data on the behavior of each part of the vehicle is data indicating the state of each part of the vehicle 400, such as the engine speed, vehicle speed, engine coolant temperature, supercharging pressure, intake air volume, etc.

[0012] The failure prediction device 100 includes a communication device 130. The communication device 130 is implemented as hardware such as a network adapter, various communication software, or a combination of these. The communication device 130 is configured to realize wireless communication with the information processing device 200 via a communication network 300. The failure prediction device 100 is also connected to a vehicle control device 410 and a display device 420 so as to be able to exchange information with them.

[0013] The vehicle control device 410 controls each part of the vehicle 400. Various sensors that detect the state of the vehicle 400 are connected to the vehicle control device 410. The vehicle control device 410 can acquire data of the above-mentioned input variables in the vehicle 400 from the various sensors.

[0014] The display device 420 is configured to include an input device into which the user inputs information, and a display device that displays information to the user. The display device 420 displays the information received from the failure prediction device 100 to the user of the vehicle 400. The display device 420 is, for example, a car navigation device mounted on the vehicle 400. The display device 420 may be, for example, a part of the failure prediction device 100 as a display unit.

[0015] The information processing device 200 includes a processing device 210, a storage device 220, and a communication device 230. The information processing device 200 may be configured using a plurality of computers. For example, the information processing device 200 may be configured by a plurality of server devices.

[0016] The storage device 220 stores a program, a failure prediction model 140, and a simulation model 240. The failure prediction model 140 stored in the storage device 220 is the same model as the failure prediction device 100. The simulation model 240 receives time-series data of driving operation and outputs time-series data of the behavior of each part of the vehicle.

[0017] The processing device 210 executes various processes by executing programs stored in the storage device 220. The processing device 110 includes a processor. The communication device 230 is implemented as hardware such as a network adapter, various communication software, or a combination of these. The communication device 230 is configured to realize wireless communication with the failure prediction device 100 via the communication network 300.

[0018] <Data transmission and reception in the failure avoidance system 10> Next, data transmission and reception between the failure prediction device 100, the information processing device 200, and the vehicle control device 410 will be described with reference to FIG.

[0019] 2, the vehicle control device 410 transmits data of input variables acquired from various sensors of the vehicle 400 to the failure prediction device 100. Such data transfer is performed at regular intervals set so that the failure prediction device 100 periodically performs failure prediction for the vehicle 400.

[0020] The failure prediction device 100, which has received the data of the input variables, inputs the received input variables to the failure prediction model 140 and outputs the type of failure predicted to occur in the vehicle 400. If the probability of occurrence of any type of failure is low, the failure prediction device 100 does not output the type of failure. That is, in this case, the occurrence of a failure is not predicted by the failure prediction device 100.

[0021] As shown in the upper part of Figure 2, when the failure prediction device 100 predicts the occurrence of any failure, it transmits to the information processing device 200 information on the type of failure predicted to occur and data on the input variables when the type of failure was output.

[0022] Then, the information processing device 200 uses the failure prediction model 140 to search for control parameter values ​​that will prevent the occurrence of a failure in the vehicle 400 from being predicted. As shown in the lower part of FIG. 2, when the information processing device 200 is able to acquire a control parameter value that can avoid a failure through the search, the information processing device 200 transmits the control parameter value to the failure prediction device 100.

[0023] Thereafter, the failure prediction device 100 presents to the user of the vehicle 400 a change to the value of the control parameter of the vehicle 400 received from the information processing device 200. As shown in the lower part of Fig. 2, if the user accepts the change to the presented value, the failure prediction device 100 transmits the value of the control parameter to the vehicle control device 410. The vehicle control device 410 changes the control parameter of the vehicle 400 based on the received value. In this way, the failure avoidance system 10 proposes a change to the control parameter of the vehicle 400 so that the occurrence of a failure is no longer predicted.

[0024] Hereinafter, with reference to FIGS. 3 to 5, the flow of processing executed in the information processing device 200 and the flow of processing executed in the failure prediction device 100 in order to realize the above-mentioned proposal to change the control parameters will be described in more detail.

[0025] <Processing Executed by Information Processing Device 200> 3 shows the flow of a series of processes executed in the information processing device 200. This series of processes is executed by the processing device 210 of the information processing device 200. This series of processes corresponds to the processes executed by the information processing device 200 when the information on the type of fault and the data of the input variables are received from the fault prediction device 100 as shown in the upper part of FIG.

[0026] 3, when this series of processes is started, the processing device 210 first performs an extraction process in the process of step S100. The extraction process is a process for narrowing down the types of control parameters in the vehicle 400 to be changed during a search process described later, based on the information on the type of failure received from the failure prediction device 100.

[0027] The storage device 220 stores a database that lists the types of control parameters to be changed during the search process in correspondence with the types of failures predicted by the failure prediction device 100. In the extraction process, the processing device 210 extracts the types of control parameters to be changed during the search process from the database based on the information on the type of failure. In this way, the processing device 210 narrows down the types of control parameters to be changed during the search process. The range to be searched during the search process is predetermined according to the type of control parameter to be changed. When the extraction process is completed, the process proceeds to the next step S110.

[0028] In the process of step S110, the processing device 210 starts a search process. The search process is a process for searching for a value of a control parameter that will cause the failure prediction model 140 to not output a type of failure predicted to occur in the vehicle 400. Thereafter, a series of processes from step S120 to step S160 are all performed as part of the search process. In the search process, the processing device 210 repeats the processes of step S120 to step S160, and ends the search process when the condition of step S170 is met.

[0029] In the process of step S120, the processing device 210 determines one type of control parameter to be changed in the simulation process of the next step S130 and its changed value. The type of control parameter to be changed is determined from the types narrowed down in the extraction process. The changed value of the determined control parameter is determined from within a predetermined range.

[0030] In step S130, the processing device 210 performs a simulation process. The simulation process is a process for generating trial input variables. The trial input variables are input variables to be input to the failure prediction model 140 in the failure prediction process in step S140.

[0031] In the simulation process, the processing device 210 inputs the time-series data of the driving operation among the input variables received from the failure prediction device 100 to the simulation model 240. Then, the processing device 210 calculates, using the simulation model 240, simulation data that is time-series data of the behavior of each part of the vehicle 400 when the change in the control parameters determined in step S120 is executed. After that, the processing device 210 combines the time-series data of the driving operation input to the simulation model 240 and the simulation data calculated by the simulation model 240 to generate trial input variables.

[0032] In the process of step S140, the processing device 210 performs a failure prediction process. In the failure prediction process, the processing device 210 inputs trial input variables to the failure prediction model 140. In the process of step S150, the processing device 210 determines whether or not the occurrence of a failure in the vehicle 400 is predicted as a result of the failure prediction process of step S140. Specifically, the processing device 210 determines whether or not a type of failure predicted to occur in the vehicle 400 is output as a result of inputting trial input variables to the failure prediction model 140 in the process of step S140. If the failure prediction model 140 outputs the type of failure predicted to occur, the processing device 210 determines that a failure has been predicted. On the other hand, if the failure prediction model 140 does not output the type of failure predicted to occur, the processing device 210 determines that a failure has not been predicted.

[0033] In the process of step S150, if the processor 210 determines that no failure has been predicted (step S150: NO), the process proceeds to step S160. In the next step S160, the processing device 210 stores the values ​​of the control parameters determined in step S120 and the data of the trial input variables output in the simulation process of step S130 in the storage device 220. By performing the process of step S160, the information processing device 200 can grasp the values ​​of the control parameters at which the occurrence of a failure is no longer predicted for the vehicle 400. When the process of step S160 ends, the processing device 210 returns the process to step S120 without proceeding to step S170.

[0034] If the processing device 210 determines in the process of step S150 that a failure is predicted (step S150: YES), the processing device 210 does not perform the process of step S160. At this time, the processing device 210 returns the process to step S120. In this manner, the series of processes from step S120 to step S160 is repeated regardless of whether a failure is predicted in step S150.

[0035] When the processes of steps S120 to S160 have been performed on the entire search range for all the control parameters narrowed down in step S100, the process proceeds to the next step S170. That is, the processes of steps S120 to S160 are repeated until the entire search range for all the control parameters narrowed down in the extraction process has been searched. When the process proceeds to step S170, the search process ends.

[0036] In the next step S180, the processing device 210 performs a control parameter selection process. The control parameter selection process is a process for selecting a value to be presented to the user from among multiple control parameter values ​​at which the occurrence of a failure is not predicted for the vehicle 400 stored in the storage device 220 in step S160.

[0037] The processing device 210 selects one value from among the multiple control parameter values ​​stored based on the trial input variables stored by the storage device 220 together with the control parameter values ​​in the process of step S160. The processing device 210 evaluates the influence on the dynamic performance of the vehicle 400 when the control parameter values ​​are changed based on the simulation data calculated in the simulation process of step S130 among the trial input variables. The dynamic performance of the vehicle 400 refers to performance related to the running of the vehicle 400, such as acceleration, braking, and turning in the vehicle 400. The processing device 210 selects the control parameter value evaluated to have the least adverse effect on the running performance of the vehicle 400 from among the multiple control parameter values ​​as the value to be presented to the user. If there is only one control parameter value that does not predict the occurrence of a failure stored in step S160 in the search process, that value is selected as the value to be presented to the user.

[0038] In the process of step S190, the processing device 210 determines whether or not there is a control parameter value appropriate for presenting to the user. In the process of step S190, the processing device 210 determines that there is an appropriate control parameter value if a control parameter value to be presented to the user has been selected through step S180. On the other hand, it may not be possible to obtain a control parameter value that will prevent the occurrence of a failure in the vehicle 400 from being predicted through the search process from step S110 to step S170. In this case, in the process of step S190, the processing device 210 determines that there is no appropriate control parameter value.

[0039] In the process of step S190, if the processing device 210 determines that there is an appropriate control parameter value (step S190: YES), the process proceeds to step S200. In the process of step S200, the processing device 210 transmits data indicating the control parameter value selected in step S180 to the failure prediction device 100. When the data indicating the control parameter value has been transmitted, the processing device 210 ends this series of processes.

[0040] In the process of step S190, if the processing device 210 determines that there is no appropriate control parameter value (step S190: NO), the process proceeds to step S210. In the process of step S210, the processing device 210 transmits a signal indicating that there is no appropriate control parameter value to the failure prediction device 100. If the signal has been transmitted, the processing device 210 ends this series of processes.

[0041] <Example of processing executed by information processing device 200> A specific example of the process executed by the information processing device 200 described in Fig. 3 will be presented below. In the example presented here, the control parameter for the boost pressure set in the vehicle control device 410 is rewritten to increase the boost pressure so that the user can enjoy circuit driving. Here, an example is shown in which the failure prediction device 100 outputs damage to the turbine blades of the turbocharger under such circumstances. At this time, as shown in the upper part of Fig. 2, the processing device 210 of the information processing device 200 receives from the failure prediction device 100 information indicating damage to the turbine blades of the turbocharger and data of the input variables input to the failure prediction model 140 when the damage was output.

[0042] The processing device 210 that has received the data performs the extraction process of step S100. The processing device 210 extracts the type of control parameter to be changed during the search process in response to damage to the turbine blades of the turbocharger from the database stored in the storage device 220. For example, a control parameter for the boost pressure is included, since the load on the turbine blades of the turbocharger is reduced by lowering the boost pressure. Another type of control parameter is a control parameter for the throttle opening, since the load on the turbine blades of the turbocharger is reduced by reducing the throttle opening. Another type of control parameter is a control parameter for the fuel injection amount, since the temperature in the combustion chamber is lowered by increasing the fuel injection amount, thereby reducing the load on the turbine blades of the turbocharger.

[0043] After completing the extraction process in step S100, the processor 210 performs search processes in steps S110 to S170 for the control parameters related to the boost pressure, the fuel injection amount, and the throttle opening degree within their respective predetermined ranges.

[0044] In the search process, when the values ​​of the control parameters for the boost pressure, the fuel injection amount, and the throttle opening degree at which the occurrence of a failure is not predicted are obtained, the processing device 210 performs a control parameter selection process in step S180. The processing device 210 evaluates the influence of each obtained control parameter on the dynamic performance of the vehicle 400. Then, for example, when a change in the control parameter to increase the fuel injection amount has the least adverse effect on the dynamic performance, a value that reduces the fuel injection amount is selected as the control parameter value to be presented to the user. After performing the selection process, the processing device 210 transmits data indicating the value of the control parameter selected in step S200 to the failure prediction device 100.

[0045] In this way, the information processing device 200 searches for values ​​of the control parameters that can avoid damage to the turbine blades, and presents the values ​​to the user. <Processing when the failure prediction device 100 predicts a failure of the vehicle 400> 4 shows the flow of a series of processes executed when the failure prediction device 100 predicts a failure of the vehicle 400. This series of processes is executed by the processing device 110 of the failure prediction device 100. This series of processes corresponds to the processes executed by the processing device 110 of the failure prediction device 100 when the failure prediction device 100 receives data of input variables from the vehicle control device 410, as shown in the upper part of FIG.

[0046] 4, when this series of processes is started, the processing device 110 first performs a failure prediction process in the process of step S300. In the failure prediction process, the processing device 110 receives input variable data received from the vehicle control device 410 as input, and outputs the type of failure predicted to occur using the failure prediction model 140 stored in the storage device 120.

[0047] In the process of step S310, the processing device 110 determines whether or not the occurrence of a failure in the vehicle 400 has been predicted as a result of the process of step S300. Specifically, the processing device 110 inputs the input variables received from the vehicle control device 410 in the process of step S300 to the failure prediction model 140. As a result, the processing device 110 determines whether or not a type of failure predicted to occur in the vehicle 400 has been output. If the failure prediction model 140 outputs the type of failure predicted to occur, the processing device 110 determines that the occurrence of a failure in the vehicle 400 has been predicted. On the other hand, if the failure prediction model 140 does not output the type of failure predicted to occur, the processing device 110 determines that the occurrence of a failure in the vehicle 400 has not been predicted.

[0048] In the process of step S310, if the processing device 110 determines that the occurrence of a failure in the vehicle 400 has been predicted (step S310: YES), the process proceeds to step S320. In step S320, the processing device 110 transmits information on the predicted type of failure output in step S300 and data on the input variables when the type of failure was output to the information processing device 200. After completing the process of step S320, the processing device 110 ends this series of processes.

[0049] In the process of step S310, when the processing device 110 determines that the occurrence of a failure in the vehicle 400 has not been predicted (step S310: NO), the processing device 110 ends this series of processes. That is, the processing device 110 ends this series of processes without performing the process of step S320.

[0050] <Processing Executed by the Failure Prediction Device 100 Receiving Information from the Information Processing Device 200> 5 shows the flow of a series of processes executed when the failure prediction device 100 receives information from the information processing device 200. This series of processes is executed by the processing device 110 of the failure prediction device 100. This series of processes corresponds to the processes executed when the failure prediction device 100 receives information from the information processing device 200, as shown in the lower part of FIG.

[0051] 5, when starting this series of processes, first in step S400, processing device 110 determines whether or not information indicating that there is no appropriate control parameter value has been received from information processing device 200. In the process of step S400, if processing device 110 determines that a signal has not been received (step S400: NO), the process proceeds to step S410.

[0052] In the process of step S410, the processing device 110 determines whether or not data indicating the value of the control parameter has been received from the information processing device 200. In the process of step S410, when the processing device 110 determines that data indicating the value of the control parameter has not been received (step S410: NO), the process of step S410 is repeated.

[0053] In the process of step S410, if the processing device 110 determines that data indicating the value of the control parameter has been received (step S410: YES), the process proceeds to step S420. In the process of step S420, the processing device 110 presents to the user the change to the control parameter received from the information processing device 200. For example, the processing device 110 displays on the display device 420 text information indicating the type of control parameter to be changed, the value after the change, and the effect on the vehicle 400 of the change in value.

[0054] In the next step S430, the processing device 110 determines whether the user has approved the change to the control parameter presented in step S420. That is, after presenting the change to the value of the control parameter received from the information processing device 200, the processing device 110 inquires whether the user desires to change to the presented control parameter.

[0055] For example, the processing device 110 displays a message on the display device 420 to request a response as to whether or not the change in the value of the control parameter is permitted. In response to this query, if the user performs an operation indicating an intention to permit the change, the processing device 110 determines that the user has permitted the change in the value. On the other hand, if the user performs an operation indicating an intention not to permit the change, the processing device 110 determines that the user has not permitted the change in the value.

[0056] In the process of step S430, if the processing device 110 determines that the user has accepted the change to the presented value of the control parameter (step S430: YES), the process proceeds to step S440. In the process of step S440, the processing device 110 transmits data of the presented value of the control parameter to the vehicle control device 410. The processing device 110 that transmitted the data ends this series of processes. In addition, the vehicle control device 410 that receives the data transmitted by the process of step S440 changes the value of the control parameter to the received value.

[0057] On the other hand, in the process of step S400, if the processing device 110 determines that it has received a signal from the information processing device 200 indicating that there is no appropriate control parameter value (step S400: YES), the process proceeds to step S450. Also, in step S430, if the processing device 110 determines that the user has not consented to the change in the control parameter value (step S430: NO), the process also proceeds to step S450. In the process of step S450, the processing device 110 suggests to the user to replace the part predicted to fail according to the type of failure predicted. The processing device 110 suggests to the user to replace the part predicted to fail, for example, by displaying text information on the display device 420.

[0058] <Action of this embodiment> The information processing device 200 in the fault avoidance system 10 searches for a control parameter value that will prevent the occurrence of a fault from being predicted, and presents to the user a change to the found control parameter value. That is, the information processing device 200 presents a change to the control parameter value as a countermeasure to avoid the occurrence of a fault.

[0059] <Effects of this embodiment> (1) The breakdown avoidance system 10 enables the user to avoid breakdowns of the vehicle 400 by methods other than part replacement.

[0060] (2) When the search yields multiple control parameter values ​​at which the occurrence of a failure is no longer predicted, the processing device 210 of the information processing device 200 selects, from the multiple obtained values, the value that has the least adverse effect on the dynamic performance of the vehicle 400. The processing device 210 then presents to the user a change to the selected control parameter value. Therefore, the information processing device 200 presents to the user, from the multiple found values, the one that has the least adverse effect on the dynamic performance of the vehicle 400. In this way, the information processing device 200 can suppress a decrease in dynamic performance due to a change in the value of the control parameter.

[0061] (3) The storage device 220 of the information processing device 200 stores a database that lists the types of control parameters to be changed during a search in correspondence with the types of failures predicted by the failure prediction device 100. The processing device 210 acquires information on the types of failures predicted by the failure prediction device 100. Then, the types of control parameters to be changed during a search are extracted from the database based on the information on the predicted types of failures, thereby narrowing down the types of control parameters to be changed during a search. Therefore, the information processing device 200 narrows down the types of control parameters to be changed during a search based on the information on the types of failures predicted by the failure prediction device 100. This enables the information processing device 200 to quickly find values ​​of control parameters that will prevent the occurrence of a failure from being predicted.

[0062] <Example of change> This embodiment can be modified as follows: This embodiment and the following modifications can be combined with each other to the extent that there is no technical contradiction.

[0063] The configuration of a failure avoidance system 10 including an information processing device according to a modified example will be described with reference to FIG. <Configuration of failure avoidance system 10 including information processing device of modified example> FIG. 6 shows the overall configuration of the failure avoidance system 10 in which an information processing device 200 is configured in a manner different from that described with reference to FIGS.

[0064] The fault avoidance system 10 employing the information processing device 200 shown in Fig. 6 is different from the fault avoidance system 10 described with reference to Fig. 1 in that the vehicle 400 is not equipped with the fault prediction device 100. Instead, the information processing device 200 includes a fault prediction unit 500. The fault prediction unit 500 includes a storage device 520 in which a program and a fault prediction model 140 are stored, and a processing device 510 that executes the program stored in the storage device 520 to perform various processes. The processing device 510 includes a processor.

[0065] In the fault avoidance system 10 employing the information processing device 200 shown in Fig. 6, a fault prediction unit 500 of the information processing device 200 acquires input variable data from the vehicle 400, and outputs the type of fault predicted to occur in the vehicle 400. In this way, in the fault avoidance system 10 employing the information processing device 200 shown in Fig. 6, the fault prediction unit 500 of the information processing device 200 plays the role that was played by the fault prediction device 100 in the fault avoidance system 10 described with reference to Fig. 1.

[0066] With this information processing device 200, it is possible to obtain the same effects as those of the information processing device 200 having the configuration described with reference to FIG. In the above embodiment, an example has been shown in which the processing device 110 displays text information indicating the type of control parameter to be changed, the value after the change, and the effect of the change on the vehicle 400 on the vehicle 400 on the display device 420 provided in the vehicle 400. An example has been shown in which the processing device 110 displays a message on the display device 420 to request an answer as to whether or not to permit the change in the value of the control parameter. The display device that performs such a display does not have to be the display device 420 provided in the vehicle 400. For example, a device such as a smartphone owned by the user can be used as the display device.

[0067] An example has been shown in which the information processing device 200 executes an extraction process to narrow down the types of control parameters to be changed during a search. The information processing device 200 does not necessarily have to execute an extraction process. For example, there may be cases in which the types of control parameters that can be changed are originally limited. In such cases, it is not necessary to execute an extraction process to narrow down the types of control parameters to be changed during a search.

[0068] In the above-described failure avoidance system 10, the failure prediction device 100 acquires data of input variables from the vehicle control device 410. However, the failure prediction device 100 may acquire data of input variables directly from sensors of each part of the vehicle 400.

[0069] The information processing devices 200 in the fault avoidance system 10 employing the configurations of Figures 1 and 6 are installed as multiple server devices outside the vehicle 400. In contrast, the information processing devices 200 may be mounted on the vehicle 400 and form part of the vehicle 400.

[0070] In the above-described failure avoidance system 10, the failure prediction device 100 presents in step S420 of Fig. 5 only the value of one control parameter selected by the information processing device 200 in the control parameter selection process in step S180 of Fig. 3. In contrast, the failure prediction device 100 may present multiple values ​​as the control parameter values ​​to be presented, and allow the user to select the control parameter value to which the change is to be applied.

[0071] In the above-described failure avoidance system 10, the failure prediction device 100 inquires of the user as to whether to permit the change in the value of the control parameter, and if the user permits, changes the value of the control parameter in the vehicle 400. In contrast, the failure prediction device 100 may change the value of the control parameter without requiring the user's permission. That is, in this case, the processing device 210 transmits and presents the value of the control parameter at which the occurrence of a failure is no longer predicted, and causes the vehicle 400 to change the control parameter to the presented value. In this way, the information processing device 200 can prevent a failure of the vehicle 400. [Explanation of symbols]

[0072] 10...fault avoidance system, 100...fault prediction device, 110...processing device, 120...storage device, 130...communication device, 140...fault prediction model, 200...information processing device, 210...processing device, 220...storage device, 230...communication device, 240...simulation model, 300...communication network, 400...vehicle, 410...vehicle control device, 420...display device, 500...fault prediction unit, 510...processing device, 520...storage device

Claims

1. A processing device and a storage device, A failure prediction model that is trained by supervised learning so as to output a type of failure predicted to occur when input variables consisting of time-series data on driving operations and behaviors of each part of a vehicle are input; a simulation model that outputs time-series data on the behavior of each part of a vehicle when time-series data on driving operations is input; The processing device comprises: acquiring, from a failure prediction device that predicts a vehicle failure using the same failure prediction model as the failure prediction model, data of the input variables at the time when the failure prediction device outputs a predicted type of failure; inputting time-series data of the driving operation in the acquired data of input variables into the simulation model, and calculating simulation data simulating time-series data of behaviors of each part of the vehicle when values ​​of control parameters of the vehicle are changed, thereby generating trial input variables consisting of the time-series data of the driving operation in the acquired data of input variables and the simulation data, and inputting the generated trial input variables into the failure prediction model to search for values ​​of the control parameters that will prevent the occurrence of a failure from being predicted; and presenting to a user of the vehicle the change in the control parameter obtained by the search to a value at which the occurrence of a fault is not predicted. Information processing device.

2. When a plurality of values ​​of the control parameter at which the occurrence of a failure is not predicted is obtained by the search, the processing device selects, from the plurality of values ​​obtained, the value that has the least adverse effect on the dynamic performance of the vehicle, and presents to the user a change of the control parameter to the selected value. The information processing device according to claim 1 .

3. The processing device comprises: and causing the vehicle to change the control parameter to the proposed value.

3. The information processing device according to claim 1 or 2.

4. a database summarizing types of control parameters to be changed during a search in accordance with types of failures predicted by the failure prediction device is stored in the storage device; The processing device comprises: Obtaining information on a type of failure predicted by the failure prediction device; and narrowing down the types of control parameters to be changed during a search by extracting the types of control parameters to be changed during a search from the database based on information on the type of predicted failure. The information processing device according to claim 1 .

5. an information processing device connected to a vehicle through a communication network; A processing device and a storage device, A failure prediction model that is trained by supervised learning so as to output a type of failure predicted to occur when input variables consisting of time-series data on driving operations and behaviors of each part of a vehicle are input; a simulation model that outputs time-series data on the behavior of each part of a vehicle when time-series data on driving operations is input; The processing device comprises: receiving data of the input variables from the vehicle, and inputting the data into the failure prediction model to output a type of failure predicted to occur; inputting into the simulation model time-series data of the driving operation in the input variable data when a type of failure predicted to occur is output, and calculating simulated data simulating time-series data of behavior of each part of the vehicle when values ​​of control parameters of the vehicle are changed, thereby generating trial input variables consisting of the time-series data of the driving operation in the acquired input variable data and the simulated data, and inputting the generated trial input variables into the failure prediction model to search for values ​​of the control parameters at which the occurrence of a failure is not predicted; and presenting to a user of the vehicle the change in the control parameter obtained by the search to a value at which the occurrence of a fault is not predicted. Information processing device.

Images