JP4182472B2 - Remote failure prediction system - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a remote failure prediction system that predicts a failure by connecting to a vehicle from a remote location, and a failure prediction system that predicts a failure using inter-vehicle communication.
[0002]
[Prior art]
2. Description of the Related Art Conventionally, there has been proposed a fault diagnosis system that connects to a faulty vehicle via a network and diagnoses the fault location (for example, Patent Document 1). According to this conventional technology, by connecting the fault diagnosis system and the vehicle remotely, it is possible to grasp whether or not the vehicle is out of order and the location of the fault without the customer having to go to the service factory. Met.
[0003]
However, it is even more convenient for the customer if the occurrence of a failure can be predicted before the failure, rather than the failure location after the failure. Because if the failure can be predicted, it will be possible to bring the vehicle to the service factory before the failure and replace the part in question, thereby avoiding the worst situation where the vehicle suddenly fails and gets stuck Because it can.
[0004]
Conventionally, as a remote system for predicting a failure, for example, there is an invention described in Patent Document 2. In this conventional technique, the output of a sensor mounted on each vehicle is learned, and if the learning value obtained by learning is not within the normal range, it is determined that there is an abnormality.
[0005]
[Patent Document 1]
JP 2002-228552 A
[Patent Document 2]
JP 2002-202003 A.
[0006]
[Problems to be solved by the invention]
However, in the above-described conventional technique, a learning value is acquired “for each vehicle”, and the acquired learning value is compared with a normal range. That is, a failure is diagnosed using only vehicle data obtained from the own vehicle.
[0007]
Such a determination method does not require the vehicle data of other vehicles, and therefore can be executed in the vehicle without bothering to diagnose remotely via the network. Therefore, if it is networked like the prior art, it cannot be said that it is advantageous in terms of cost. In order to use the network, added value commensurate with the cost is necessary.
[0008]
Therefore, in the present invention, by utilizing the data of other vehicles (for example, vehicle data of the same type vehicle) collected via the network, the advantage of network connection is utilized and the reliability of failure prediction is improved. For the purpose.
[0009]
As described above, in the present invention, the advantage of networking is fully utilized, but in some cases, simpler prediction may be sufficient.
[0010]
Therefore, in another invention, a failure prediction system is provided that predicts a failure by exchanging vehicle data among a plurality of identical vehicles using inter-vehicle communication.
[0011]
[Means for Solving the Problems]
In order to achieve the above object, a remote failure prediction system according to the present invention is characterized by the following configuration.
[0012]
A first invention of the present application is a remote failure prediction system that performs failure prediction on a failure prediction target vehicle remotely and transmits a failure prediction result to a customer, the failure prediction target being connected via a network Receiving means for receiving vehicle data from a vehicle and vehicle data from one or more other vehicles of the same type as the failure prediction target vehicle; vehicle data from the received failure prediction target vehicle; Storage means for storing vehicle data from the vehicle, reading means for reading out the stored vehicle data from the failure prediction target vehicle and vehicle data from the other vehicle, and a vehicle from the failure prediction target vehicle A failure prediction means for comparing the data with vehicle data from the other vehicle and predicting the occurrence of a failure based on the comparison result; And a sending means for sending to the customer of the prediction target vehicle.
[0013]
The vehicle further includes an extraction unit that extracts vehicle data of another vehicle that is in the same or similar driving condition as the failure prediction target vehicle, and the failure prediction unit includes the same or similar driving condition. There is also provided a remote failure prediction system that predicts the occurrence of a failure using vehicle data of other vehicles in the vehicle.
[0014]
Here, as the driving situation, for example, at least one of acceleration / deceleration type, road type, road curvature, road gradient, temperature, weather, day of the week, time, time zone, and traffic jam condition may be included. Good.
[0015]
The vehicle further includes an extracting unit that extracts vehicle data of a vehicle having the same or similar year model or mileage as the failure prediction target vehicle, and the failure prediction unit includes the same or similar year. A remote failure prediction system is provided that predicts the occurrence of a failure using vehicle data of another vehicle that is in a formula or mileage.
[0016]
Further, in any one of the remote failure prediction systems described above, vehicle data of other vehicles traveling in a location close to the failure prediction target vehicle based on information related to a travel position included in the vehicle data. A remote failure prediction system is provided that uses to predict the occurrence of a failure.
[0017]
Further, if the other vehicle further travels in the same travel lane as the failure prediction target vehicle or travels in the same direction, the prediction accuracy will be further improved.
[0018]
Further, based on the information on the travel position included in the vehicle data, the other vehicle that has traveled in the past in the same or in the vicinity of the failure prediction target vehicle is specified, and the other vehicle is the failure prediction target vehicle. By predicting the occurrence of a failure using the vehicle data acquired when traveling in the same or close place, other vehicle data to be compared increases, so the accuracy of prediction will be improved. In this way, since it is considered that there are many same-type vehicles that have traveled in the place going back in the past, failure prediction is possible even when there is no vehicle currently traveling in the same or close location as the failure prediction target vehicle. Can be executed.
[0019]
This object is also achieved by a remote failure prediction method corresponding to the remote failure prediction system. The object is also achieved by a program for realizing each means or each step included in the remote failure prediction system by a computer and a computer-readable storage medium storing the program code.
[0020]
In a second aspect of the present invention, a vehicle is provided for which a failure is predicted by any one of the remote failure prediction systems described above.
[0021]
That is, the vehicle of the present invention includes means for detecting information relating to the operating state of the vehicle, means for storing information relating to the detected operating state of the vehicle as vehicle data, and storing the stored vehicle data as the remote fault. It has means for transmitting to a prediction system, means for receiving a failure prediction result from the remote failure prediction system, and means for outputting the received failure prediction result.
[0022]
According to the third invention of the present application, there is provided a failure prediction system that performs failure prediction for a vehicle that accumulates vehicle data relating to an operation state.
[0023]
That is, the failure prediction system according to the present invention is a vehicle-to-vehicle communication means for communicating with another vehicle, and another vehicle that can communicate with the vehicle-to-vehicle communication means, and is a target of the occurrence prediction of the failure. A storage for storing search means for searching for another vehicle of the same type as the failure prediction target vehicle, vehicle data received from one or more other vehicles discovered by the search means, and vehicle data of the failure prediction target vehicle Means for reading out the vehicle data received from the one or more other stored vehicles and the vehicle data of the failure prediction target vehicle; received from the one or more other vehicles read out A failure prediction unit that compares vehicle data with vehicle data of the failure prediction target vehicle and predicts the occurrence of a failure based on the comparison result, and an output unit that outputs a prediction result by the failure prediction unit Characterized in that it has a.
[0024]
Moreover, in this application, the said failure prediction means is further provided with the extraction means which extracts the vehicle data of the other vehicle in the driving | running state same as or similar to the said failure prediction object vehicle among the said other vehicles, The said failure prediction means is the same or similar There is also provided a failure prediction system characterized by predicting the occurrence of a failure using the vehicle data of other vehicles in the running state.
[0025]
In addition, the traveling state may include at least one of acceleration / deceleration type, road type, road curvature, road gradient, temperature, weather, day of the week, time, time zone, and traffic jam, for example.
[0026]
Further, according to the present application, the vehicle further includes an extraction unit that extracts vehicle data of a vehicle having the same or similar year model or mileage as the failure prediction target vehicle among the other vehicles, and the failure prediction unit includes: There is also provided a failure prediction system characterized by predicting the occurrence of a failure using vehicle data of other vehicles in the same or similar year or mileage.
[0027]
According to the present application, the occurrence of a failure is predicted using the vehicle data of another vehicle that is traveling in a location close to the failure prediction target vehicle based on the information related to the travel position included in the vehicle data. A failure prediction system is also provided.
[0028]
Further, if the other vehicle further travels in the same travel lane as the failure prediction target vehicle or travels in the same direction, the prediction accuracy will be further improved.
[0029]
This object can also be achieved by a failure prediction method corresponding to the failure prediction system. The object is also achieved by a program for realizing each means or each step included in the failure prediction system by a computer and a computer-readable storage medium storing the program code.
[0030]
According to 4th invention of this application, the vehicle carrying the failure prediction system in any one of the above-mentioned is provided.
[0031]
【The invention's effect】
According to the present invention, a remote failure prediction system, a remote failure prediction method, a remote failure prediction program, and the like that can improve the reliability of failure prediction over the prior art are realized.
[0032]
That is, claim 1 4, 9, 10, 15 According to the invention described in the above, the occurrence of a failure of the failure prediction target vehicle based on the vehicle data of the failure prediction target vehicle and the vehicle data of another vehicle of the same type of the failure prediction target vehicle, taking advantage of the network connection By predicting, it is possible to improve the reliability of failure prediction. That is, if the vehicle data of the same type vehicles that are supposed to show the same tendency originally does not show the same tendency statistically, it is considered that some abnormality has occurred in the failure prediction target vehicle. This anomaly may depend on the failure itself or the failure symptom. Therefore, the failure can be predicted by detecting this abnormality.
[0033]
Claim 1, 4, 9, 10, 15 Since the vehicle data is compared between vehicles having the same or similar running conditions, the reliability of failure prediction can be further improved. If the other vehicle to be compared and the vehicle to be predicted for failure are of the same type, both vehicle data should be the same or similar. However, if one is vehicle data when traveling on a straight road and the other is vehicle data when turning a curve, it is expected that the data will differ even though they are the same type of vehicle. The In such a case, since the data of both does not match, there is a possibility that it is determined that there is a failure on one side. Therefore, the failure prediction accuracy is further improved by predicting the failure in consideration of the traveling state of the other vehicle to be compared with the vehicle to be the failure prediction target.
[0034]
Claim 3 or 11 According to the invention described above, since the failure is predicted using the vehicle data of the vehicle in the same or similar year model or mileage as the failure prediction target vehicle, the reliability of the failure prediction can be improved. That is, if both vehicles have the same or similar model year or mileage, the progress of aging is considered to be almost the same, so if both vehicle data do not match, a failure will occur on one side. There is a possibility.
[0035]
Claim 4 or 12 According to the invention described in (2), if both vehicles are traveling in a location close to each other, the traveling conditions are more approximate, so that even minor anomalies can be detected and the accuracy of failure prediction is improved. be able to.
[0036]
Claim 5 or 13 According to the invention described in the above, by using the vehicle data between the vehicles traveling in the same traveling lane or traveling in the same direction, the traveling condition is more approximated and even minor anomalies are detected. In addition, the accuracy of failure prediction can be improved. For example, even if a plurality of vehicles are traveling in close proximity, if the intersection is an intersection, the traveling direction is different, and sometimes the traveling situation is greatly different. Therefore, by imposing such additional conditions, the accuracy of failure prediction can be improved.
[0037]
Claim 6 According to the invention described in the above, by predicting the occurrence of the failure using the vehicle data of other vehicles that have traveled in the past in the same or close proximity to the failure prediction target vehicle, the other vehicle data to be compared is Increase the accuracy of the prediction.
[0038]
Claim 7 or 14 According to the invention described in (1), it is possible to report a failure prediction result to a customer such as a driver in cooperation with the remote failure prediction system described above.
[0039]
Claim 8, 16 or 17 According to the invention described in the above, since vehicle data can be exchanged with the same type vehicle by inter-vehicle communication, it is possible to easily predict the occurrence of a failure without requiring a large-scale network.
[0040]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, an embodiment of a remote failure prediction system according to the present invention will be described in detail with reference to the drawings. In the following, there may be embodiments that seem to be not described in the claims at first glance, but these are not intentionally excluded, and the invention described in the claims. It should be understood that it is not described in the claims for the sake of equality.
[0041]
[First Embodiment]
FIG. 1 is a diagram illustrating a configuration example of a system according to the present embodiment. The information center 100 is a computer group that accumulates various types of information transmitted from the customers' vehicles 110 and 111, the service factory 120, and the like and provides failure prediction results. The information center 100 is connected to the customer's vehicles 110 and 111 via the Internet 130 or a mobile communication line. The customer vehicles 110 and 111 acquire data necessary for failure prediction and transmit the data to the information center 100.
[0042]
Here, the vehicle 110 is a vehicle subject to failure prediction. The same-type vehicle 111 is a vehicle of the same type as the vehicle 110, and is a comparison target when a failure is predicted. In FIG. 1, only one vehicle 111 of the same type is shown. However, when statistical processing is performed or in order to improve the accuracy of failure prediction, a plurality or a large number of vehicles are desirable.
[0043]
The information center 100 includes a failure prediction server 101 that executes failure prediction processing, a customer information database 102 that stores information on customers (all customers or contractors of failure prediction services), and diagnosis conditions for failure prediction diagnosis. Diagnostic condition database 103 to be stored, vehicle information database 104 for accumulating vehicle data transmitted from customer vehicles 110 and 111, map database 106 for storing map data, and various programs for diagnosing or predicting a failure And a diagnostic program database 107 in which is stored. The failure prediction server 101 is a kind of computer, and includes a CPU, a memory, a hard disk drive, a communication interface, and the like. In the following description, various processes are executed by the CPU executing a program corresponding to the flowchart.
[0044]
For example, according to the failure prediction server 101 described above, vehicle data from a failure prediction target vehicle (vehicle 110) connected via a network, and one or more other vehicles (vehicle 111) of the same type as the failure prediction target vehicle. Receiving means (communication interface), vehicle data from the received failure prediction target vehicle, and vehicle data from one or more other vehicles of the same type as the failure prediction target vehicle. Storage means (hard disk drive or memory) for storing, reading means (CPU, failure prediction program) for reading out the stored vehicle data from the failure prediction target vehicle and vehicle data from the one or more other vehicles And the vehicle data from the failure prediction target vehicle and the vehicle data from the other vehicle, and the occurrence of the failure is determined based on the comparison result. A remote failure prediction system having failure prediction means (CPU, failure prediction program) for prediction and transmission means (communication interface) for transmitting a failure prediction result by the failure prediction means to a customer of the failure prediction target vehicle is configured. can do.
[0045]
FIG. 2 is a block diagram illustrating a configuration example of the vehicle according to the present embodiment. The remote vehicle client device 200 is a main controller including a CPU, a memory, and the like. The remote vehicle client device 200 acquires control data and sensor output from various control units and sensors, stores the data in the memory, and stores the stored information in a mobile terminal (mobile communication interface). ) 250 or the short-range wireless communication interface 255 to transmit to the information center 100 or receive a failure prediction result from the information center 100. The short-range wireless communication interface 225 can employ wireless standards such as wireless LAN, Bluetooth, and ETC.
[0046]
The body system 210 includes a power window unit 211, a headlight unit 212, an audio unit 213, an air conditioner unit 214, a wiper unit 215, a door lock unit 216, and the like. Output to 200.
[0047]
The control system 220 includes an ABS (anti-lock brake system) 221 that controls the brake not to lock, a DSC (dynamic stability controller) 222 that controls the behavior of the vehicle, and an EGI that controls fuel supply. (Electric Gas Injection) 223, EAT (Electric Automatic Transmission) 224 for controlling an automatic transmission, ICCW (Intelligent Cruise Control & Warning) 225 for assisting driving of a driver such as automatic driving, etc. The control result is notified to the client device 220.
[0048]
Various sensors are mounted on the vehicle. For example, a GPS sensor 231 that receives a radio wave from a GPS (Global Positioning System) satellite to calculate the current position of the vehicle, a VICS information receiver 232 that receives traffic jam information, and a vehicle speed sensor 233 that detects the speed of the vehicle. An inter-vehicle distance sensor 234 that measures the distance to other vehicles such as a vehicle ahead, a yaw rate sensor 235 that detects the yaw rate of the vehicle, an acceleration sensor that detects the acceleration of the vehicle, a steering angle sensor 237 that detects the steering angle of the vehicle, A throttle opening sensor 238 that detects the opening of the throttle, a brake pressure sensor 239 that detects the depression pressure of the brake, a winker SW sensor 240 that detects the operating state of the winker switch, an outside air temperature sensor 241 that measures the outside air temperature, and A rain sensor 24 that measures whether or not it is raining or rain Such as is mounted on the vehicle.
[0049]
The navigation controller 260 is a device that searches map information stored in a hard disk drive or the like based on the positioning data from the GPS sensor 231 and displays a map of the current position. The input / output device 270 for a driver as a customer includes a display device such as a liquid crystal display and a voice main device, and outputs map data from the navigation controller 260 and outputs a failure prediction result from the information center 100. To do.
[0050]
As described above, in the present embodiment, a vehicle whose failure is predicted by the above-described remote failure prediction system, and means for detecting information related to the operation state of the vehicle (eg, GPS sensor 231), and the detected vehicle Means for storing information on the operating state of the vehicle as vehicle data (eg, memory) and means for transmitting the stored vehicle data to the remote failure prediction system (eg, mobile communication interface 250 or short-range wireless communication interface) 255), means for receiving a failure prediction result from the remote failure prediction system (eg, mobile communication interface 250 or short-range wireless communication interface 255), and means for outputting the received failure prediction result (eg: A vehicle having an input / output device 270) is provided.
[0051]
FIG. 3 is a flowchart regarding collection of vehicle data according to the present embodiment. In step S300, the CPU mounted on the vehicle client device 200 samples outputs from various sensors and units at appropriate timings and stores them in the memory.
[0052]
In step S302, the CPU mounted on the vehicle client device 200 has a predetermined timing (for example, periodically, when the engine is started, after the engine has been started for a predetermined time, or when an explicit instruction from the driver is input). ), The vehicle data stored in the memory is read out, information for identifying the vehicle or driver is added, and the information is transmitted to the information center 100 via the mobile communication interface 250 or the short-range wireless communication interface 255.
[0053]
In step S310, the failure prediction server 101 of the information center 100 receives vehicle data transmitted from the vehicle via a mobile communication interface or the like. In step S312, the failure prediction server 101 stores the received vehicle data in the vehicle information database 104 in association with information for specifying the corresponding vehicle or driver. The vehicle data of each vehicle is stored in the vehicle database 104 by the above procedure.
[0054]
FIG. 4 is a flowchart of the remote failure prediction process according to this embodiment. In step S400, failure prediction is triggered on the vehicle side. For example, in the vehicle client device 200, the input / output device 270 is operated by a vehicle occupant to accept a failure prediction request. In step S <b> 402, the vehicle client device 200 reads vehicle data for a predetermined period stored in the memory and transmits the vehicle data to the failure prediction server 101.
[0055]
In step S <b> 404, the failure prediction server 101 receives vehicle data via the Internet 130. In step S406, the failure prediction server 101 executes failure occurrence prediction processing using the received vehicle data. In step S408, the failure prediction server 101 transmits the prediction result to the vehicle that has requested the failure prediction.
[0056]
In step S410, the vehicle client device 200 receives the failure prediction result. In step S412, the vehicle client device 200 causes the input / output device 270 to output the received failure prediction result. The failure prediction is executed according to the above flow.
[0057]
FIG. 5 is a flowchart relating to the failure prediction processing in the present embodiment. A failure prediction program corresponding to this flowchart is stored in the storage device of the failure prediction server 101. FIG. 6 is a diagram conceptually illustrating the processing of this flowchart.
[0058]
In step S500, the failure prediction server 101 reads the i-th diagnosis condition from the diagnosis condition database 103, and extracts the vehicle data of the prediction target vehicle 110 that satisfies the read i-th diagnosis condition from the vehicle information database 104 by searching. To do. Note that T is the time width of the vehicle data extracted here. If this T is too long, the prediction process takes time. Therefore, it is desirable to set the time width as short as possible, which is suitable for maintaining sufficient failure prediction accuracy.
[0059]
Alternatively, considering that the time width required for each diagnosis condition may be different, the time width T may be variable for each diagnosis condition and set to an appropriate value. In this case, the time width T required for each diagnosis condition may be determined empirically.
[0060]
As a diagnostic condition, it may be a condition that the vehicle is of the same type, or in addition, an additional condition may be that the driving situation is the same or similar. Examples of driving conditions include acceleration / deceleration type, road type, road curvature, road gradient, temperature, weather, day of the week, time of day, time zone, and traffic conditions, but of course other conditions are used. May be.
[0061]
These pieces of information are either directly included in the vehicle data or indirectly derived from the information included in the vehicle data. For example, by searching the map database 106 based on the position information acquired by the GPS sensor 231 and included in the vehicle data, whether the road on which the vehicle is traveling is a highway or a general road, Or it can be understood whether it is a straight line or a curve, and how much the gradient is. Further, by determining the time change of the vehicle speed data included in the vehicle data, it can be determined whether the vehicle is accelerating or decelerating. The temperature, weather, and the like can also be determined from vehicle data from the outside air temperature sensor 241 and the rain sensor 242 mounted on the vehicle. Further, the traffic situation can be determined from the data of the VICS information receiver 232 included in the vehicle data.
[0062]
Moreover, it is good also as an additional condition that it exists in the same or similar age model or a mileage. The data of year and mileage are also read from the ROM or the like by the vehicle client device 200 and stored in the vehicle data. Note that the failure prediction server 101 may read and acquire the year model registered in the customer database 102.
[0063]
Moreover, it is good also considering driving | running | working the place which adjoins as an additional condition. Whether or not the vehicle is located in a close place can be determined by position information acquired by the GPS sensor 231 and stored in the vehicle data. Note that “close to each other” refers to a distance relationship to the extent that both vehicle data exhibit the same or similar tendency if both the failure prediction target vehicle 110 and the same type vehicle 111 are normal.
[0064]
It may be an additional condition that the vehicle is traveling in the same traveling lane or traveling in the same direction. Whether the vehicle is traveling in the same lane or traveling in the same direction is determined by the position information acquired by the GPS sensor 231 and stored in the vehicle data, the time change of the position information, and the position information. The road information extracted from the map database 106 can be determined based on the road information. In addition, if it is a three-lane road, it will be included in the same lane of any lane, but the opposite lanes in the same road will be different lanes.
[0065]
Note that the vehicle to be compared may be only the vehicle that is currently traveling, or may be another vehicle that has previously traveled in the same location or a surrounding location. For example, the number of other vehicles that are currently traveling will not be very large, but there are many other vehicles that have traveled in the past or around the same location. Therefore, when performing failure prediction by statistical processing, failure prediction accuracy will improve as the number of parameters increases.
[0066]
The above exemplified conditions may be used alone, or an appropriate combination may be selected and used from all possible combinations.
[0067]
The diagnosis condition may correspond to a specific failure. That is, empirical conditions that can detect a specific failure are empirically specified as appropriate and registered in the database. For example, the diagnostic conditions for detecting tire wear are that the vehicle is running on a 130R curve in the rain, and a skid phenomenon is occurring.
[0068]
In the example of FIG. 6, the same type vehicle (model GF-FD3S) as the first diagnosis condition, the diagnosis condition that the weather is fine and the vehicle is traveling on the highway is extracted, and the failure prediction target vehicle that further satisfies the first diagnosis condition Are extracted.
[0069]
In step S502, the failure prediction server 101 determines whether the vehicle data of the failure prediction target vehicle 110 has been extracted that satisfies the i-th diagnosis condition. If it has been extracted, the process proceeds to step S504. If not extracted, the process proceeds to step S520, i is incremented, and the process returns to step S500.
[0070]
In step S504, the failure prediction server 101 extracts the vehicle data of the other same-type vehicle 111 that satisfies the i-th diagnosis condition from the vehicle information database 104 by searching. Here, although one piece of vehicle data may be extracted, it is desirable to have a plurality or a large number in order to improve the prediction accuracy.
[0071]
In the example of FIG. 6, as the first diagnosis condition, diagnosis conditions such as the same type vehicle (model GF-FD3S), clear weather, and traveling on the highway are extracted, and a plurality of other conditions satisfying the first diagnosis condition are extracted. Data on the same type vehicle is extracted.
[0072]
In step S506, the failure prediction server 101 performs statistical processing on the extracted vehicle data of the other same-type vehicle 111 (other vehicle group). For example, an average value and a standard deviation are obtained. In the example of FIG. 6, the average value of the air-fuel ratio data for T minutes is obtained for two other identical vehicles.
[0073]
In step S508, the failure prediction server 101 determines whether the vehicle data of the prediction target vehicle 110 and the vehicle data of the other vehicle group subjected to statistical processing are statistically the same or similar. For example, it is determined whether the vehicle data of the prediction target vehicle 110 is the same as or close to the average value of the vehicle data of other vehicle groups, or is within the error range.
[0074]
In the example of FIG. 6, the air-fuel ratio data of the failure prediction target vehicle 110 is compared with the air-fuel ratio data of other vehicle groups subjected to statistical processing, and it is determined whether they are in the same or similar tendency. If there is a statistically the same or similar tendency, the process proceeds to step S510, and if not, the process proceeds to step S512.
[0075]
In step S510, the failure prediction server 101 adds the i-th diagnosis condition to the failure list. The failure list is stored in a storage means such as a memory or a hard disk drive. Note that a failure identification code corresponding to the i-th diagnosis condition may be stored in the failure list. The correspondence relationship between the diagnosis condition and the failure identification code may be stored in the diagnosis condition database 103 or may be registered in another database.
[0076]
In step S512, the failure prediction server 101 determines whether failure prediction has been completed for all failure prediction servers. If not completed, the process proceeds to step S520, increments the value of i, returns to step S500, and performs failure prediction for the next diagnostic condition.
[0077]
In step S514, the failure prediction server 101 reads the failure list stored in the storage unit, and determines whether any diagnostic condition or failure identification code is registered. If any of the diagnostic conditions is registered, there is a possibility that some failure has occurred or some failure will occur in the future. If any failure identification code is registered, it is predicted that a failure corresponding to the failure identification code will occur in the near future. If no failure is predicted, the process proceeds to step S518. If the occurrence of a failure is predicted, the process proceeds to step S516.
[0078]
In step S516, the failure prediction server 101 creates a failure prediction result (prediction report) for reporting to the driver. For example, the failure prediction results may be created by sorting the diagnosis conditions or failure identification codes registered in the failure list for each urgency level. This failure prediction result may include, for example, all the predicted failures, or only those that cause troubles in operation or have a high degree of urgency that is directly related to safety. May be. This is because there may be a driver who is overly worried when notifying a low urgency level, so there is an advantage of notifying only a high level urgency level.
[0079]
If the urgency level of the failure is high, the urgency level may be reflected to create a failure prediction result that makes it easy for the driver to understand the urgency level.
[0080]
In step S518, the failure prediction server 101 creates a prediction result indicating no failure and stores it in the storage unit. As a prediction result, for example, “The occurrence of a failure was not predicted. Please enjoy a comfortable driving.” Or “The occurrence of a failure was not predicted at this time. Is not guaranteed. "Or" The occurrence of a failure was not predicted at this time. However, since a failure may occur unexpectedly, be sure to perform a pre-service inspection and periodic inspection. " It would be good to use a message such as
[0081]
As described above, according to the present embodiment, since the failure is predicted based on the vehicle data of the actual failed vehicle, the accuracy of the failure prediction can be increased as compared with the conventional case.
[0082]
[Second Embodiment]
A second embodiment based on the remote failure prediction system according to the first embodiment described above will be described. In the following description, the description similar to that of the first embodiment will be omitted, and the description will focus on the characteristic part of the present embodiment.
[0083]
In the second embodiment, the failure prediction process is executed even when normal vehicle data is registered in the vehicle information database 103.
[0084]
FIG. 7 is a flowchart regarding failure prediction according to the second embodiment. Steps common to FIGS. 3 and 4 are given the same reference numerals to simplify the description. In the present embodiment, step S714 and subsequent steps are added after steps S300 to S312 are executed.
[0085]
In step S714, the failure prediction server 101 determines whether a predetermined time has elapsed since the previous prediction process. The reason for providing the prediction result when the predetermined period elapses as described above is as follows. Although vehicle failures do not occur so frequently, if a failure prediction process is executed each time vehicle data arrives, the load on the system will increase unnecessarily. Therefore, it is sufficient to execute only at an appropriate timing for predicting a failure.
[0086]
More specifically, the failure prediction server 101 reads the time when the previous failure prediction process was performed from the customer database 102 for the vehicle that has transmitted the vehicle data, while acquiring the current time from the timer. The difference is taken. If this difference exceeds the predetermined time, the process proceeds to step S406, and a failure occurrence prediction process is executed.
[0087]
On the other hand, if this difference does not exceed the predetermined time, that is, if sufficient time has not passed since the previous prediction process, the process is terminated without executing the prediction process.
[0088]
If no failure is predicted as a result of the failure prediction obtained in step S406, the processing may be terminated without notifying the driver of the prediction result.
[0089]
In the present embodiment, since the failure prediction is performed at the timing when the vehicle data is transmitted, the failure prediction result can be automatically reported even when the driver has forgotten to perform the failure prediction.
[0090]
Even if the vehicle data is transmitted, if the time has not passed sufficiently since the previous prediction process, the process is terminated without executing the prediction process. Can be suppressed.
[0091]
In addition, when a failure is not predicted, the process ends without notifying the driver of the prediction result, so that it is possible to prevent unnecessary information from being transmitted to the driver. In the present embodiment, since the failure prediction is performed without being conscious of the driver, if the occurrence of the failure is not predicted, it may be preferable to keep the driver unaware as it is because it can concentrate on driving. .
[0092]
[Third Embodiment]
In the above-described embodiment, vehicle data is collected at the information center 100 using a large-scale network such as the Internet 130. This is because vehicle data of other same-type vehicles 110 that have traveled in the same place in the past are stored in the vehicle information database 104 even if there is no other same-type vehicle 110 that is running in a location close to the same date and time. If it existed, the failure could be predicted.
[0093]
Furthermore, since the data of a large number of the same type cars are accumulated in the vehicle information database 104 and statistical processing is executed, the accuracy of failure prediction is relatively high.
[0094]
However, in the above-described embodiment, although the failure prediction accuracy is high, it is necessary to install and manage the failure prediction server 101 and various databases, which is disadvantageous in terms of cost. Moreover, although the failure accuracy may be inferior, a relatively simple failure prediction may be sufficient.
[0095]
Therefore, in the third embodiment, a failure prediction system is more easily realized by applying inter-vehicle communication. That is, a large-scale network such as the Internet 130 is not indispensable, and failure prediction is possible only by forming a vehicle-to-vehicle network.
[0096]
In the third embodiment, inter-vehicle communication is used, but the communicable range of inter-vehicle communication is about several meters to 100 meters. Therefore, if the failure prediction target vehicle 110 and the other same-type vehicle 111 can communicate with each other, both vehicles are close to each other within a radius or a combination of 100 m. It can be said that there is. For example, it is true that the weather conditions are the same as long as the radius is 100 m. Therefore, in the present embodiment, there is an advantage that both pieces of vehicle data are data acquired in the same or similar running situation without extracting the vehicle data in a similar running situation.
[0097]
Further, since the vehicle data can be acquired in real time, it is not necessary to hold the vehicle data for a long time, and the vehicle data used for the failure prediction process may be discarded immediately. As a result, the memory and the hard disk drive can be used effectively.
[0098]
FIG. 8 is a diagram showing the concept of the third embodiment. In the above-described embodiment, the vehicle data acquired by the vehicle is uploaded to the vehicle information database 104, but in this embodiment, the vehicle data is acquired from the other same-type vehicle 111 by inter-vehicle communication. Then, the failure is predicted by the vehicle client mounted on the failure prediction target vehicle 110. In this sense, the vehicle client can be thought of as a failure prediction system or failure prediction device.
[0099]
FIG. 9 is a block diagram illustrating a configuration example of the vehicles 110 and 111 in the third embodiment. The same components as those in FIG. Here, the vehicle client mounted on the failure prediction target vehicle 110 functions as the failure prediction apparatus 900. On the other hand, the vehicle client or failure prediction device 900 mounted on the same-type vehicle 111 collects vehicle data and transmits the collected vehicle data to the failure prediction device 900 mounted on the failure prediction target vehicle 110. It will function as a data collection / transmission device. Of course, the vehicle client 200 may include both a function as a failure prediction device and a function as a vehicle data collection / transmission device.
[0100]
The failure prediction apparatus 900 is a device in which a failure prediction program is installed in the vehicle client 200. The CPU 201 is the core of the failure prediction apparatus 900 and executes failure prediction according to the failure prediction program 204 stored in the ROM 202. The ROM 202 stores vehicle type data 203 serving as reference information for determining whether or not the vehicle is the same type, and the failure prediction program 204 described above. The RAM 205 stores vehicle data 206 received from other same-type vehicles 111, own vehicle data 208, and a failure prediction list 209. The inter-vehicle communication unit 256 is also mounted on each vehicle.
[0101]
FIG. 10 is a flowchart of a failure occurrence prediction program according to the third embodiment. The same processes as those described in FIG. 5 are denoted by the same reference numerals, and the description thereof is omitted.
[0102]
In step S1000, failure prediction apparatus 900 searches for a vehicle of the same type in the communicable range of the failure prediction target vehicle. For example, the CPU 201 controls the inter-vehicle communication unit 256, receives a beacon transmitted by a vehicle located in the vicinity, and determines whether the vehicle is of the same type from the vehicle type data included in the beacon. When it is determined that the other surrounding vehicles are the same type, the CPU 201 controls the inter-vehicle communication unit 256 and requests more detailed vehicle data. The same-type vehicle 111 transmits vehicle data in response to this request. The CPU 201 stores the vehicle data received by the inter-vehicle communication unit 256 in the RAM 205. When there are a plurality of corresponding vehicles, vehicle data is received from as many identical vehicles as possible and stored in the RAM 205.
[0103]
In step S1002, the CPU 201 determines whether or not the vehicle data stored in the RAM 205 satisfies the i-th diagnostic condition. If there is no vehicle that satisfies the condition, the process proceeds to step S1022 to create a message indicating unpredictability and output from the input / output device 270. If there is one that satisfies the condition, the process proceeds to step S506.
[0104]
Thereafter, when the processing from S506 to S518 is finished and a prediction result is obtained, the prediction result is output in step S412.
[0105]
In the failure prediction, for example, if vehicle data for T minutes is used, after acquiring vehicle data for T minutes in advance, step S1002 and after may be executed, or t seconds shorter than T may be used. Vehicle data is received in real time from other vehicles of the same type 111, and the vehicle data is also acquired in real time in the failure target predicted vehicle 110, and these are compared. When T = n · t, every t section The comparison result may be statistically processed to perform determination for the entire T interval to predict a failure.
[0106]
Thus, in the third embodiment, the occurrence of a failure can be predicted with a simpler configuration than in the other embodiments. In addition, since other vehicle data is used, the prediction accuracy is improved as compared with the prior art.
[0107]
[Other Embodiments]
In the above-described embodiment, the occurrence of a failure is predicted by comparing vehicle data between a plurality of identical vehicles. However, if vehicle data that does not depend on the type of vehicle is used, the above-described implementation is also performed between different types of vehicles. Forms can be applied.
[0108]
Note that the statistical processing described above has determined that a failure has occurred when the vehicle data of the failure target vehicle 110 statistically deviates from the vehicle data of another vehicle of the same type 111. However, in this case, even when the vehicle data of the failure target vehicle 110 is relatively superior to the vehicle data of the other same-type vehicle 111 and does not statistically match, there is a possibility that the failure is determined. Therefore, when the vehicle deviates in such an excellent direction, the failure prediction server 101 or the failure prediction device 900 executes control that does not determine that there is a failure. For example, if it deviates in the direction in which the fuel consumption and the like are excellent, it is good for the user and is not determined as a failure. In addition, a sign means showing the same or similar tendency, and does not mean perfect coincidence.
[0109]
Moreover, although the failure prediction result may be transmitted directly from the failure prediction server 110 to the vehicle client device 200, it may be transmitted to the customer as an e-mail. For example, the failure prediction server 110 searches the customer database 102 based on the vehicle number of the failure prediction target vehicle 110 and extracts the customer's e-mail address. Then, the failure prediction server 110 transmits the prediction result to the extracted email address.
[0110]
If a plurality of e-mail addresses such as the e-mail address of the company to which the driver belongs are registered in the customer database in addition to the e-mail address of the driver, the failure prediction server 110 is not limited to the driver. Because the prediction result can be distributed to the company to which the driver belongs, the company as a whole has the advantage of being useful for safety management.
[Brief description of the drawings]
FIG. 1 is a diagram illustrating a configuration example of a system according to an embodiment.
FIG. 2 is a block diagram illustrating a configuration example of a vehicle according to the present embodiment.
FIG. 3 is a sequence related to collection of vehicle data according to the present embodiment.
FIG. 4 is a sequence of remote failure prediction processing according to the present embodiment.
FIG. 5 is a flowchart of a remote failure prediction process according to the present embodiment.
FIG. 6 is a diagram showing a concept of remote failure prediction processing according to the present embodiment.
FIG. 7 is a sequence for remote failure prediction processing according to the second embodiment;
FIG. 8 is a diagram illustrating a configuration example of a system according to a third embodiment.
FIG. 9 is a block diagram illustrating a configuration example of a vehicle according to a third embodiment.
FIG. 10 is a flowchart relating to a remote failure prediction process according to the third embodiment;
[Explanation of symbols]
100 ... Information Center
101 ... Failure prediction server
110 ... Failure prediction target vehicle
111 ... Other similar vehicles

Claims (17)

In a remote failure prediction system that performs failure prediction for a failure prediction target vehicle remotely and sends the failure prediction result to the customer,
Receiving means for receiving vehicle data from the failure prediction target vehicle and vehicle data from one or more other vehicles of the same type as the failure prediction target vehicle via a network;
Storage means for storing the received vehicle data from the failure prediction target vehicle and the vehicle data from the other vehicle;
Reading means for reading out vehicle data from the stored failure prediction target vehicle and vehicle data from the other vehicle;
Failure prediction means for comparing vehicle data from the failure prediction target vehicle with vehicle data from the other vehicle, and predicting the occurrence of a failure based on a comparison result;
Transmitting means for transmitting a failure prediction result by the failure prediction means to a customer of the failure prediction target vehicle ;
Extracting means for extracting vehicle data of other vehicles in the same or similar driving situation as the failure prediction target vehicle among the other vehicles;
With
The failure prediction means predicts the occurrence of a failure by using vehicle data of other vehicles in the same or similar running situation . The driving situation includes at least one of acceleration / deceleration type, road type, road curvature, road gradient, temperature, weather, day of the week, time, time zone, and traffic jam condition. The remote failure prediction system according to claim 1 . Among the other vehicles, the vehicle further comprises extraction means for extracting vehicle data of a vehicle having the same or similar year model or mileage as the failure prediction target vehicle,
The remote failure prediction system according to claim 1, wherein the failure prediction means predicts the occurrence of a failure using vehicle data of other vehicles in the same or similar year or mileage. Based on the information on the travel position included in the vehicle data, the other vehicle that is traveling in the vicinity of the failure prediction target vehicle is identified, and the occurrence of the failure is predicted using the vehicle data of the other vehicle. The remote failure prediction system according to any one of claims 1 to 3 , wherein: 5. The remote failure prediction system according to claim 4 , wherein the other vehicle is a vehicle that is traveling in the same traveling lane as the failure prediction target vehicle or traveling in the same direction. Based on the information on the travel position included in the vehicle data, the other vehicle that has traveled in the past in the same or in the vicinity of the failure prediction target vehicle is identified, and the occurrence of the failure using the vehicle data of the other vehicle The remote fault prediction system according to any one of claims 1 to 3 , wherein the system is predicted. A vehicle whose failure is predicted by the remote failure prediction system according to any one of claims 1 to 6 ,
Means for detecting information relating to the operating state of the vehicle;
Means for storing information relating to the detected operating state of the vehicle as vehicle data;
Means for transmitting the stored vehicle data to the remote failure prediction system;
Means for receiving a failure prediction result from the remote failure prediction system;
And a means for outputting the received failure prediction result. In a failure prediction system that predicts the occurrence of a failure in a vehicle that accumulates vehicle data related to operating conditions,
Vehicle-to-vehicle communication means for communicating with other vehicles;
Search means for searching for another vehicle that can communicate with the vehicle-to-vehicle communication means, the vehicle being the same type as the failure prediction target vehicle that is a target of the occurrence prediction of the failure;
Storage means for storing vehicle data received from one or more other vehicles discovered by the search means, and vehicle data of the failure prediction target vehicle;
Reading means for reading out vehicle data received from one or more other stored vehicles and vehicle data of the failure prediction target vehicle;
Failure prediction means for comparing vehicle data received from one or more of the read vehicles with vehicle data of the failure prediction target vehicle, and predicting the occurrence of a failure based on a comparison result;
A failure prediction system comprising: output means for outputting a failure prediction result by the failure prediction means. Among the other vehicles, the vehicle further comprises extraction means for extracting vehicle data of other vehicles in the same or similar driving situation as the failure prediction target vehicle,
The failure prediction system according to claim 8 , wherein the failure prediction unit predicts the occurrence of a failure using vehicle data of another vehicle in the same or similar traveling state. The driving situation includes at least one of acceleration / deceleration type, road type, road curvature, road gradient, temperature, weather, day of the week, time, time zone, and traffic jam condition. The failure prediction system according to claim 9 . Among the other vehicles, the vehicle further comprises extraction means for extracting vehicle data of a vehicle having the same or similar year model or mileage as the failure prediction target vehicle,
9. The failure prediction system according to claim 8, wherein the failure prediction means predicts the occurrence of a failure using vehicle data of other vehicles in the same or similar year or mileage. Based on the information on the travel position included in the vehicle data, another vehicle that is traveling in the vicinity of the failure prediction target vehicle is extracted, and the occurrence of the failure is predicted using the vehicle data of the other vehicle. failure prediction system according to any one of claims 8 to 11, characterized in that. The failure prediction system according to claim 12 , wherein the other vehicle further travels in the same travel lane as the failure prediction target vehicle or travels in the same direction. A vehicle equipped with the failure prediction system according to any one of claims 8 to 13 . In a remote failure prediction method for performing failure prediction on a failure prediction target vehicle remotely and transmitting the failure prediction result to the customer,
Receiving vehicle data from a failure prediction target vehicle via a network and vehicle data from one or more other vehicles of the same type as the failure prediction target vehicle;
Storing the received vehicle data of the failure prediction target vehicle and vehicle data from the other vehicle;
Reading vehicle data from the stored failure prediction target vehicle and vehicle data from the other vehicle;
Comparing vehicle data from the failure prediction target vehicle with vehicle data from the other vehicle, and predicting the occurrence of a failure based on a comparison result;
Transmitting the prediction result by the failure prediction means to a customer of the failure prediction target vehicle ;
Extracting vehicle data of other vehicles in the same or similar driving situation as the failure prediction target vehicle among the other vehicles;
With
The step of predicting the occurrence of a failure is a step of predicting the occurrence of a failure using vehicle data of other vehicles in the same or similar driving situation . In a failure prediction method for predicting the occurrence of a failure for a vehicle that accumulates vehicle data related to operating conditions,
Searching for another vehicle of the same type as the failure prediction target vehicle to be subject to the occurrence prediction of the failure by inter-vehicle communication;
Receiving vehicle data from one or more other vehicles discovered by the search by inter-vehicle communication;
Storing vehicle data received from one or more other vehicles discovered by the search means, and vehicle data of the failure prediction target vehicle;
Reading vehicle data received from one or more other stored vehicles and vehicle data of the failure prediction target vehicle;
Comparing the vehicle data received from the one or more other read vehicles with the vehicle data of the failure prediction target vehicle, and predicting the occurrence of a failure based on the comparison result;
A failure prediction method comprising: outputting a result of the prediction. In a failure prediction program that predicts the occurrence of a failure in a vehicle that accumulates vehicle data related to operating conditions,
Searching for another vehicle of the same type as the failure prediction target vehicle to be subject to the occurrence prediction of the failure by inter-vehicle communication;
Receiving vehicle data from one or more other vehicles discovered by the search by inter-vehicle communication;
Storing vehicle data received from one or more other vehicles discovered by the search means, and vehicle data of the failure prediction target vehicle;
Reading vehicle data received from one or more other stored vehicles and vehicle data of the failure prediction target vehicle;
Comparing the vehicle data received from the one or more other read vehicles with the vehicle data of the failure prediction target vehicle, and predicting the occurrence of a failure based on the comparison result;
A failure prediction program for causing a computer to execute the step of outputting the prediction result.

Images