FR3149102A1 - Method and device for predicting the life cycle of a vehicle computer - Google Patents

Abstract

The invention relates to a method and a device for predicting a fault in a computer of a vehicle (10). For this purpose, first operating data of the computer are collected and transmitted to a server (101). The probability that a fault in this computer will occur is predicted by feeding a computer life cycle prediction model with these first data, the prediction model having been learned during a learning phase from second computer data obtained from a set of second vehicles (11). One or more recommendations for preventive maintenance actions are transmitted according to the result of the prediction. Figure for the abstract: Figure 1

Description

Method and device for predicting the life cycle of a vehicle computer

The invention relates to methods and devices for predicting a fault or failure of one or more computers of a vehicle, in particular a motor vehicle. The invention also relates to a method and a device for predicting the life cycle of one or more computers of a vehicle. The invention also relates to a method and a device for predictive maintenance of a vehicle.

Technological background

Contemporary vehicles have a number of computers, each of which performs one or more functions, such as managing driving assistance, anti-skid, electronic brake distribution or even controlling actuators to ensure the optimal operation of a combustion engine.

These calculators are also called ECUs ("Electronic Control Units"). These calculators have embedded software that is executed to ensure the functions for which they are responsible.

These calculators, like any component or organ of a vehicle, are likely to encounter defects, breakdowns, failures or reduced performance during their life cycle. When the driver of a vehicle is faced with a defect or failure of one or more calculators, the latter must then contact a specialized center to determine whether the failure or defect observed requires corrective maintenance to correct the failure or defect after the latter has appeared. Such corrective maintenance is most often accompanied by an intervention or repair in a garage for example. Such corrective maintenance is synonymous with costs incurred by corrective maintenance and inconvenience caused by the immobilization of the vehicle for a period sometimes lasting up to several days.

To limit the risks of breakdown or defect and prevent associated problems, preventive maintenance operations of vehicles are planned. However, these maintenance operations do not guarantee that a vehicle computer will encounter a defect or suffer a breakdown after the fact.

An object of the present invention is to solve at least one of the problems of the technological background described above.

Another object of the present invention is to improve the prediction of failures or faults of a vehicle's computer(s).

According to a first aspect, the invention relates to a method for predicting a fault in a first computer of a first vehicle, the method comprising the following steps:
- reception of first data representative of the operation of the first computer;
- prediction of a fault in the first calculator by feeding a calculator life cycle prediction model with the first data,
the calculator life cycle prediction model having been learned in a so-called learning phase from second data representative of the life cycle of a set of second calculators corresponding to the first calculator and embedded in a set of second vehicles;
- transmission of third data representative of at least one recommendation based on a result of the prediction.

Such a method makes it possible to estimate more reliably and in real time the risk of breakdown or defect associated with one (or more) computers of a first vehicle based on data relating to the operation of this computer during use of the vehicle, this data being representative of the actual use made of this computer in the life conditions of the first vehicle, on the basis of a model for predicting the life cycle of the computer learned from similar data obtained from identical or similar sensors embedded in a set of second vehicles. Depending on the result of the prediction, one or more recommendations are generated automatically and transmitted, for example to a device belonging to the owner of the first vehicle, to prevent the defect or breakdown, for example by a preventive maintenance operation of the computer.

According to one variant, the at least one recommendation belongs to a set of recommendations comprising:
- a recommendation for a software update of the first calculator;
- a recommendation to replace the first calculator;
- a recommendation to modify at least one control parameter of the first calculator; and
- a recommendation to implement a diagnosis of the first computer.

According to another variant, the method further comprises a step of learning the calculator life cycle prediction model, the learning step comprising the following steps:
- receiving the second data from the set of second vehicles;
- generation of the calculator life cycle prediction model by classification of the second data.

According to an additional variant, the method further comprises a step of modifying at least one parameter of the calculator life cycle prediction model as a function of the first data and the result of the prediction.

According to yet another variant, the first data belongs to a data set comprising:
- data representative of a fault code;
- data representing changes in state of the first computer;
- data representative of instruction determined by the first computer;
- data representative of the result of the calculation carried out by the first calculator;
- representative query data generated by the first calculator.

According to an additional variant, the method further comprises a step of implementing the at least one recommendation.

According to another variant, the method further comprises a step of storing data representative of the implementation and data representative of performance levels prior to and subsequent to the implementation.

According to a second aspect, the invention relates to a device for predicting a fault in a vehicle computer, the device comprising a memory associated with a processor configured for implementing the steps of the method according to the first aspect of the invention.

According to a third aspect, the invention relates to a vehicle, for example of the automobile type, comprising a device as described above according to the second aspect of the invention.

According to a fourth aspect, the invention relates to a computer program which comprises instructions adapted for the execution of the steps of the method according to the first aspect of the invention, in particular when the computer program is executed by at least one processor.

Such a computer program may use any programming language, and may be in the form of source code, object code, or code intermediate between source code and object code, such as in a partially compiled form, or in any other desirable form.

According to a fifth aspect, the invention relates to a computer-readable recording medium on which is recorded a computer program comprising instructions for carrying out the steps of the method according to the first aspect of the invention.

On the one hand, the recording medium may be any entity or device capable of storing the program. For example, the medium may include a storage medium, such as a ROM memory, a CD-ROM or a microelectronic circuit type ROM memory, or a magnetic recording medium or a hard disk.

On the other hand, this recording medium may also be a transmissible medium such as an electrical or optical signal, such a signal being able to be conveyed via an electrical or optical cable, by conventional or terrestrial radio or by self-directed laser beam or by other means. The computer program according to the invention may in particular be downloaded from a network such as the Internet.

Alternatively, the recording medium may be an integrated circuit in which the computer program is incorporated, the integrated circuit being adapted to perform or to be used in performing the method in question.

Brief description of the figures

Other characteristics and advantages of the invention will emerge from the description of the non-limiting embodiments of the invention below, with reference to the appended figures 1 to 3, in which:

schematically illustrates a communication environment of a first vehicle, according to a particular exemplary embodiment of the present invention;

schematically illustrates a device configured for the fault prediction of one or more computers of the first vehicle of the , according to a particular exemplary embodiment of the present invention;

illustrates a flowchart of the different steps of a method for predicting a fault in one or more computers of the first vehicle of the , according to a particular exemplary embodiment of the present invention.

A method and a device for predicting a fault in one or more computers of a vehicle will now be described in the following with joint reference to FIGS. 1 to 3. The same elements are identified with the same reference signs throughout the description which follows.

The terms “first(s)”, “second(s)”, etc. are used in this document by arbitrary convention to allow the identification and potentially distinction of different elements (such as operations, means, etc.) implemented in the embodiments described below.

According to a particular and non-limiting example of embodiment of the invention, the prediction of a defect (such as a breakdown, a failure, a loss of performance, etc.) of one (or more) calculator(s) of a first vehicle, for example a calculator of an on-board system, a calculator controlling an element of the powertrain, or any other calculator, comprises the reception, for example from the first vehicle via a wireless link, of first data representative of the operation of this calculator, the first data being for example obtained from the first calculator and/or from one or more other calculators connected in communication to the first calculator. This first data is for example transmitted to a server of the “cloud” (or “cloud” in French) and/or to another calculator of the first vehicle. This first data is provided as input to a calculator life cycle prediction model to predict a potential defect of the calculator, with for example a probability that the defect will occur, for example over a horizon of a few days, a few weeks or a few months. Such a life cycle prediction model has been previously learned during a so-called learning phase of a machine learning method, also called an automatic learning method, from second data representative of the life cycles of a set of second computers corresponding to the first computer (for example computers of the same type, with the same functions, with the same references and/or the same software versions) obtained from a set of second vehicles incorporating these second computers. Third data representative of one or more recommendations are then transmitted, for example to a display device, according to the result of the prediction to prevent the occurrence of the predicted defect. The recommendation(s) correspond for example to preventive maintenance recommendations for the computer that is the subject of the prediction.

A breakdown corresponds, for example, to a failure of the computer, i.e. to a fault in operation leading to a stoppage of operation, a stoppage of one or more functions provided by the computer, a drop in performance or reliability of the results. A breakdown also corresponds to a degraded operation of the computer in question compared to normal operation, for example an operation where only part of the services provided by the computer in normal operation are provided.

The implementation of a machine learning method makes it possible to estimate more reliably and in real time the risk of associated defect in the life cycle of a vehicle computer based on the operating data obtained from this computer during its use in the vehicle, for example since the vehicle was first put into circulation, on the basis of a model predicting the future life cycle of this computer, and thus the associated risks of failure.

Predicting the risk of failure makes it possible to anticipate the problem and potentially correct it before it appears, improving the prevention of failure or failure and improving or extending the life cycle of the calculator.

There schematically illustrates a communication environment 1 of a first vehicle 10, according to a particular and non-limiting exemplary embodiment of the present invention.

The first vehicle 10 corresponds for example to a vehicle with a thermal engine, with electric motor(s) or even a hybrid vehicle with a thermal engine and one or more electric motors. The vehicle 10 thus corresponds for example to a land vehicle, for example an automobile, a truck, a coach, a motorcycle.

The first vehicle 10 also advantageously carries a communication system configured to communicate with one or more remote devices 101 via a wireless communication network infrastructure. The remote device 101 advantageously corresponds to a device configured to process data, for example data stored in the memory of the remote device 101 and/or data received from the vehicle 10. The remote device 101 corresponds for example to a server of the “cloud” 100.

The communication system of the first vehicle 10 comprises, for example, one or more communication antennas connected to a telematic control unit, called a TCU (Telematic Control Unit), itself connected to one or more computers of the on-board system of the first vehicle 10. The antenna(s), the TCU and the computer(s) form, for example, a multiplexed architecture for carrying out various services useful for the proper operation of the first vehicle 10 and for assisting the driver and/or passengers of the first vehicle 10 in controlling the first vehicle 10 and/or for establishing a diagnosis on the operation of one or more components of the first vehicle 10. The computer(s) and the TCU communicate and exchange data with each other via one or more computer buses, for example a communication bus of the CAN (Controller Area Network) or CAN FD (Controller Area Network Flexible Data-Rate) type. "Flexible Data Rate Controller Area Network"), FlexRay (according to ISO 17458) or Ethernet (according to ISO/IEC 802-3).

The mobile communication infrastructure enabling wireless data communication between the first vehicle 10 and the remote device 101 comprises, for example, one or more communication devices 110 of the relay antenna (cellular network) or roadside unit, known as UBR, type. In a communication mode using such a network architecture, the data are, for example, transmitted by the first vehicle 10 to the remote device 101 of the “cloud” 100 via a relay antenna 110 (the antenna 110 being, for example, connected to the “cloud” 100 via a wired link).

The wireless communication system allowing the exchange of data between the first vehicle 10 and the remote device 101 corresponds for example to:
- a vehicle-to-infrastructure (V2I) communication system, for example based on the 3GPP LTE-V or IEEE 802.11p ITS G5 standards; and/or
- a cellular network type communication system, for example an LTE (Long-Term Evolution) or LTE-Advanced (also called LTE 3G, 4G or 5G) type network; and/or
- a Wifi type communication system according to IEEE 802.11, for example according to IEEE 802.11n or IEEE 802.11ac.

The first vehicle 10 carries a set of computers forming the on-board system of the first vehicle 10. The computers of the first vehicle 10 are connected to each other via one or more computer buses, for example a communication bus of the CAN data bus type (from the English “Controller Area Network” or in French “Network of controllers”), CAN FD (from the English “Controller Area Network Flexible Data-Rate” or in French “Network of controllers with flexible data rate”), FlexRay (according to the ISO 17458 standard) or Ethernet (according to the ISO/IEC 802-3 standard).

A process for predicting a fault in the life cycle of one or more computers of the first vehicle 10 is advantageously implemented by a system comprising the first vehicle 10 (i.e. by one or more devices embedded in the vehicle 10, for example one or more computers) and the remote device 101 connected in communication with the first vehicle 10 via a wireless connection or link.

The prediction process advantageously includes a so-called production or prediction phase (also called inference phase) based on one or more models learned in a prior learning phase and on data feeding the learned model(s).

A life cycle prediction model is for example learned for each computer of the first vehicle 10 or for each group of computers grouped for example by type or by function(s) implemented. According to a variant, a single generic prediction model common to all the computers is learned and then implemented in the production phase, i.e. when the first vehicle 10 is put into circulation.

The learning phase and the production phase are for example implemented by the remote device 101.

The learning phase and/or the production phase are, for example, implemented by a neural network.

According to an alternative embodiment, the learning phase is implemented by the remote device 101 (or by a server outside the “cloud”, for example a server hosted in a center (for example a design office) suitable for carrying out the learning) and the production phase by the first vehicle 10, for example by a dedicated calculator of the on-board system of the first vehicle 10.

According to another embodiment variant, the learning is implemented in the learning phase as well as during the production phase during which the parameters of the prediction model(s) learned in the learning phase are refined in real time from the data received during the production phase of one or more first vehicles 10.

The process below is described with respect to a single computer for which a life cycle prediction model is learned. The invention applies identically to a plurality of computers, a prediction model being for example learned for each computer, for each group of computers of a plurality of groups of computers or a single generic prediction model being learned for all the computers embedded in a vehicle.

Learning phase

The learning advantageously corresponds to supervised learning from a set of data associated with a set or group of second vehicles 11 comprising for example a few tens, a few hundreds, thousands or tens/hundreds of thousands of second vehicles 11. According to an alternative embodiment, the learning corresponds to unsupervised learning from the set of data associated with the set of second vehicles 11.

According to a particular example, the second vehicles 11 included in the set of second vehicles all have the same configuration or a similar configuration, that is to say that they all correspond to the same type of vehicle (for example the same series of a particular model of vehicle) with second computers that are identical or similar (same version for example), in particular identical or similar to the first computer of the first vehicle 10.

In a first operation of the learning phase, the second vehicles 11 providing the second data for learning the vehicle life cycle prediction model(s) are identified, for example based on data obtained from the automobile manufacturer 102. The second vehicles 11 are for example selected based on the computers they have on board so as to have second vehicles 11 having the second computer for which a computer life cycle prediction model must be learned.

Each second vehicle 11 is for example identified by a unique identifier (for example the VIN number (from the English “Vehicle Identification Number”)) obtained with for example a set of configuration data which makes it possible to identify and group the second vehicles 11 according to the second computers which they have on board.

The second vehicles are thus selected and/or identified from data received from one or more servers 102 of a car manufacturer and/or an after-sales service, the second vehicles being for example selected in such a way that their configurations correspond.

In a second operation of the learning phase, second data representative of the operation of the second computers are collected by the server 101. These second data are for example obtained from each second vehicle since the day each second vehicle was put into circulation, for each phase of life of each second vehicle 11 (in circulation, parked in a car park or at home, being serviced in a garage, etc.).

The second data are for example received from the second vehicles by wireless connection during certain phases of life of the second vehicle 11 and/or from data processing devices such as diagnostic devices, servers, computers 102 during other phases of life (for example during maintenance of the second vehicle at a garage or a car dealership).

The second data includes for example:
- data representative of fault codes, for example received from the second computer when the latter encounters a fault returning a fault code and/or from a server 102 of a car dealership having carried out a diagnosis of the second vehicle 11 and in particular of the second computer; a fault code is also called a DTC code (from the English “Diagnostic Trouble Code” or in French “Diagnostic fault code”); and/or
- data representing changes in state of the second computer, the management of the phases of the life cycle of a computer being obtained for example by a finite automaton, the computer passing from one phase to another (or from one state to another) according to a set of parameters and/or determined rules, the number and type of state depending on the automaton and the computer considered; and/or
- data representing an instruction determined by the second computer, an instruction being for example associated with a determined state of the computer, an instruction corresponding for example to a command provided to a system or a component of the second vehicle controlled by the computer considered; and/or
- data representative of the result of the calculation carried out by the second calculator; and/or
- data representative of a request generated by the second computer, for example a request generated for another computer or a component or organ of the second vehicle.

According to an alternative embodiment, the second data further comprises data representative of requests for support for computer repairs, for example also received by the server 101. Such requests for support for repairs correspond for example to requests or requests for support for work carried out by a garage or a dealer and transmitted to the manufacturer of each second vehicle concerned, such a request also being called a “credit request”, this data being for example obtained from a server 102 of the manufacturer receiving these credit requests and/or from the servers 102 of the garage or the dealer transmitting these credit requests.

According to another embodiment, the second data further comprises data representative of maintenance of the second computer, these data being for example received from a server 102 of a car dealership where the maintenance took place. The maintenance data comprises for example data relating to a software update (version and date of the update for example), a replacement of the second computer, a reset of the second computer, etc.

Such data makes it possible, for example, to identify second computers that have experienced a breakdown or an identified fault.

The data received by the remote device 101 are for example stored in memory and associated with each second vehicle 11, each second vehicle 11 being for example identified by a unique identifier (for example the VIN number (from the English “Vehicle Identification Number”)) obtained from the configuration data.

The second data is for example transmitted at regular intervals (for example every hour, every day, every week) and/or at each event detected or encountered by the calculator (change of state, generation of a command, detection of a fault, software update, replacement, repair, etc.) during the life cycle of the calculator.

The second data is thus, for example, time-stamped on the server 101 to determine a chronology of the events experienced by the computer throughout its life cycle.

In a third operation of the learning phase, the life cycle prediction model of the calculator is generated or trained by classification of the second data obtained for the set of second vehicles 11.

The failure prediction model (also called classification model) is trained using the second data (also called training data) according to any machine learning method known to those skilled in the art, for example according to a “random forest” type learning method, by implementing a neural network or decision trees.

Such a model makes it possible to predict the life cycle of a computer and to predict the appearance of a fault or breakdown before it occurs, with for example a probability associated with each class at the output of the model.

A type of defect is for example associated with each class obtained from the classification during learning. One or more recommendations for solutions or actions to be implemented to overcome or prevent the defect associated with each class are for example also associated with each class, the recommendation(s) corresponding for example to one or more of the following recommendations, according to all possible combinations:
- a recommendation for updating the calculator software, for example according to a specific software version; and/or
- a recommendation to replace the calculator, for example with a calculator of a specific type or reference; and/or
- a recommendation to modify at least one control parameter of the calculator, for example a control parameter of the PLC associated with the calculator; and/or
- a recommendation to implement a computer diagnosis

When the prediction phase is implemented by the first vehicle 10, the parameters defining the prediction model obtained in the third operation are transmitted to the first vehicle 10 by the server 101.

For example, several prediction models are generated or learned as described above, with one prediction model being generated for each type of calculator.

Prediction phase

The prediction phase is implemented by the server 101, or, according to an alternative embodiment, by each first vehicle 10.

In a first operation of the prediction phase, the device in charge of the prediction phase (i.e. the remote device 101 or one or more computers of the on-board system of the first vehicle 10) receives or collects first data representative of the operation of a first computer of the first vehicle 10.

The first data are for example obtained from the first computer and/or other computers of the first vehicle 10 connected in communication with the first computer.

The first data is for example transmitted by the first vehicle 10 to the remote device 101 via the wireless network infrastructure over time when an event is detected or encountered by the first computer.

According to an alternative embodiment, information representative of the time instant at which each event is detected or encountered is associated with this event. In other words, the first data are time-stamped.

When the prediction phase is implemented by the remote device 101, the first vehicle 10 transmits, according to an alternative embodiment, its identification number, for example its VIN number so that the remote device 101 identifies the type of the first calculator and the associated life cycle prediction model.

Receiving or collecting the first data is similar to receiving or collecting the second data described above.

The first data belongs to a data set including:
- data representative of a fault code;
- data representing changes in state of the first computer;
- data representative of instruction determined by the first computer;
- data representative of the result of the calculation carried out by the first calculator;
- representative query data generated by the first calculator.

In a second operation of the prediction phase, the first data are provided as input to the life cycle prediction model learned for a computer corresponding to the first computer during the learning phase.

The calculator lifecycle prediction model classifies the first data and associates them with one or more of the classes generated during the learning phase, with for example a probability of belonging to each of the classes. The class with the highest probability is for example selected as corresponding to the result of the prediction.

The result of the prediction thus makes it possible to know whether the life cycle of the first computer will continue normally, i.e. as expected and without any foreseeable fault or breakdown, or on the contrary whether the life cycle of the first computer will experience a fault, failure or breakdown in the future, i.e. at a specific time horizon (for example expressed in days, weeks or months) from the day of the prediction.

When the selected class is representative of a future life cycle with a defect, an alert is for example generated and transmitted to the first vehicle 10 (or a display device of the first vehicle 10 for displaying the alert on this display device) and/or a mobile communication device 103 (for example a smartphone) belonging for example to the driver or the owner of the first vehicle 10. The generation and transmission of the alert make it possible to warn the driver or the owner of the first vehicle 10 of a risk of a future defect of the first computer. According to an alternative embodiment, the alert is also transmitted to a server 102 controlled for example by a car dealer or by the manufacturer of the first vehicle to inform of the risk of a defect so that preventive measures can be taken by the dealer or the manufacturer.

One or more recommendations are further generated to prevent the fault when the result of the prediction is representative of a future fault or failure of the first computer.

This or these recommendations correspond for example to the recommendation(s) associated with the class(es) obtained at the output of the prediction, when this or these classes include the associated recommendation(s).

When the classes associated with the prediction model do not include recommendations, the recommendation(s) are for example selected from a set of recommendations stored in memory (of the remote device 101 when the remote device 101 implements the production phase or of the first vehicle 10 when the first vehicle 10 implements the production phase) according to management rules based on the result of the prediction.

The alert and/or recommendations are, for example, generated when the probability of a fault or breakdown exceeds a specific threshold (for example 0.6 or 0.7 or 0.8).

When the prediction result is representative of a normal future life cycle, i.e. without any risk of defect or failure identified, the process ends, no alert is generated and no recommendation is made.

In a third operation of the prediction phase, third data representative of at least one recommendation are transmitted according to the result of the prediction.

Thus, when the result of the prediction indicates a risk of defect, failure or breakdown to come in the future with a determined deadline, one or more recommendations are made to the driver or owner of the first vehicle 10 to prevent this defect.

Alternatively, the third data further includes alert data.

The third data representing the recommendation(s) and/or the alert of the risk of future default are for example transmitted:
- to the first vehicle 10 and/or to the mobile communication device 103 to alert the driver of the risk of breakdown and/or inform him of the procedure to follow to prevent the breakdown; and/or
- to a server 101 associated with an after-sales service 102 responsible for contacting the first vehicle 10 (or its owner) to assist it in the measures to be taken to prevent the breakdown or defect.

When the prediction phase is implemented by the first vehicle 10, the third data representative of the recommendation(s) and/or the alert of the risk of future default are for example transmitted:
- intended for the driver or owner of the first vehicle 10 to alert him of the risk of breakdown and/or inform him of the procedure to follow to prevent the breakdown; this data is for example transmitted to a display device integrated into the first vehicle 10 and/or to a remote device such as a smartphone 103; and/or
- to a server 102 associated with an after-sales service responsible for contacting the first vehicle 10 (or its owner) to assist it in the measures to be taken to prevent the breakdown or defect.

The recommendation(s) transmitted include for example one or more of the following recommendations, depending on the type of defect predicted for example, in all possible combinations:
- a recommendation for a software update of the first calculator;
- a recommendation to replace the first calculator;
- a recommendation to modify at least one control parameter of the first calculator; and
- a recommendation to implement a diagnosis of the first computer.

The prediction phase is advantageously implemented in each first vehicle of a set or group of first vehicles comprising several first vehicles, for example tens, hundreds or thousands of first vehicles. According to this example, the first data obtained from these first vehicles are used to enrich in real time the learned prediction model(s) and refine the parameters of this or these prediction models. The data obtained during the prediction phase are thus also used in real time for continuous or real-time learning of the prediction model(s), according to this particular example. Thus, according to this example, one or more parameters of the calculator life cycle prediction model are recalculated and refined according to the first data and the result of the prediction to improve the prediction model in real time and continuously.

According to a particular embodiment, the preventive maintenance actions associated with the recommendation(s) are implemented, for example an OTA (Over The Air) type download of a software update and its installation, a replacement of the first computer in a repair center, an additional diagnosis to more precisely identify the risk of defect or breakdown, etc.

According to another particular embodiment, a history of the events associated with the first computer are recorded in a memory of the remote device 101 and/or of the first vehicle 10. For example, the prediction results are recorded with an associated prediction date, data representative of a performance level of the first computer being for example further associated with the prediction result data. When one or more preventive maintenance actions are implemented, data representative of these actions are also recorded in memory. Such an embodiment makes it possible to analyze the recorded data a posteriori to monitor the life cycle of the first computer, the evolution of the performances and the impact of the predictions and actions implemented. This allows for example the manufacturer of the first computer or of the first vehicle 10 to use this data to improve the design of the computers for the next vehicles.

There schematically illustrates a device 2 configured to predict a fault in one or more computers of a vehicle, for example the first vehicle 10, according to a particular and non-limiting exemplary embodiment of the present invention. The device 2 corresponds for example to a device embedded in the first vehicle 10, for example a computer. According to another example, the device 2 corresponds to a calculation or data processing device, for example the remote device 101.

Device 2 is for example configured to implement the operations described with regard to the and/or steps of the method described with respect to the . Examples of such a device 2 include, but are not limited to, on-board electronic equipment such as an on-board computer of a vehicle, an electronic calculator such as an ECU (“Electronic Control Unit”), a telematic control unit, called TCU (from the English “Telematic Control Unit”), a smartphone, a tablet, a laptop, a server, or a combination of several of the devices listed above. The elements of the device 2, individually or in combination, can be integrated in a single integrated circuit, in several integrated circuits, and/or in discrete components. The device 2 can be produced in the form of electronic circuits or software (or computer) modules or even a combination of electronic circuits and software modules.

The device 2 comprises one (or more) processor(s) 20 configured to execute instructions for carrying out the steps of the method and/or for executing the instructions of the software(s) embedded in the device 2. The processor 20 may include integrated memory, an input/output interface, and various circuits known to those skilled in the art. The device 2 further comprises at least one memory 21 corresponding for example to a volatile and/or non-volatile memory and/or comprises a memory storage device which may comprise volatile and/or non-volatile memory, such as EEPROM, ROM, PROM, RAM, DRAM, SRAM, flash, magnetic or optical disk.

The computer code of the embedded software(s) comprising the instructions to be loaded and executed by the processor is for example stored in the memory 21.

According to various particular embodiments, the device 2 is coupled in communication with other similar devices or systems and/or with communication devices, for example a TCU (from the English “Telematic Control Unit” or in French “Telematic Control Unit”), for example via a communication bus or through dedicated input/output ports.

According to a particular and non-limiting embodiment, the device 2 comprises a block 22 of interface elements for communicating with external devices, for example a remote server or the “cloud”, a TCU unit. The interface elements of the block 22 comprise one or more of the following interfaces:
- RF radio frequency interface, for example of the Bluetooth® or Wi-Fi® type, LTE (Long-Term Evolution), LTE-Advanced;
- USB interface (from the English “Universal Serial Bus” or “Universal Serial Bus” in French);
- HDMI interface (from the English “High Definition Multimedia Interface”);
- LIN interface (from the English “Local Interconnect Network”).

According to another particular embodiment, the device 2 comprises a communication interface 23 which makes it possible to establish communication with other devices (such as other computers of the embedded system or other servers) via a communication channel 230. The communication interface 23 corresponds for example to a transmitter configured to transmit and receive information and/or data via the communication channel 230. The communication interface 23 corresponds for example to a wired network of the CAN (Controller Area Network), CAN FD (Controller Area Network Flexible Data-Rate), FlexRay (standardized by the ISO 17458 standard) or Ethernet (standardized by the ISO/IEC 802-3 standard).

According to a further particular embodiment, the device 2 can provide output signals to one or more external devices, such as a display screen, one or more loudspeakers and/or other peripherals (projection system) via respective adapted output interfaces. According to a variant, one or the other of the external devices is integrated into the device 2.

There illustrates a flowchart of the different steps of a method for predicting a fault in one or more computers of a vehicle, for example for a first computer of the first vehicle 10, according to a particular and non-limiting exemplary embodiment of the present invention. The method is for example implemented by a device embedded in the vehicle 10 such as the device 2, by the remote device 101 or by a system comprising the first vehicle 10 and the remote device 101.

In a first step 31, first data representative of operation of the first computer are received, for example via a wireless link.

In a second step 32, a fault of the first computer is predicted by feeding a computer life cycle prediction model with the first data, the computer life cycle prediction model having been learned in a so-called learning phase from second data representative of the life cycle of a set of second computers corresponding to the first computer and embedded in a set of second vehicles.

In a third step 33, third data representative of at least one recommendation are transmitted based on a result of the prediction.

According to an alternative embodiment, the variants and examples of the operations described in relation to the apply to the process steps of the .

Of course, the invention is not limited to the embodiments described above but extends to a method of alerting of a breakdown before the breakdown occurs and the device configured for the implementation of such a method.

The invention also relates to a vehicle, for example an automobile or more generally an autonomous vehicle with a land motor, comprising the device 2 of the .

The invention also relates to a system comprising the device 2 of the (or a set of devices 2) embedded in a vehicle and a remote device, for example the remote device 101, the device(s) 2 being connected in wireless communication with the remote device 101.

Claims (10)

Method for predicting a fault in a first computer of a first vehicle (10), said method comprising the following steps:
- reception (31) of first data representative of the operation of said first computer;
- prediction (32) of a fault in said first computer by feeding a computer life cycle prediction model with said first data,
said calculator life cycle prediction model having been learned in a so-called learning phase from second data representative of the life cycle of a set of second calculators corresponding to said first calculator and embedded in a set of second vehicles (11);
- transmission (33) of third data representative of at least one recommendation based on a result of said prediction. Method according to claim 1, wherein said at least one recommendation belongs to a set of recommendations comprising:
- a recommendation for a software update of said first calculator;
- a recommendation to replace said first calculator;
- a recommendation to modify at least one control parameter of said first calculator; and
- a recommendation to implement a diagnosis of said first calculator. Method according to one of claims 1 to 2, further comprising a step of learning said calculator life cycle prediction model, said learning step comprising the following steps:
- receiving said second data from said set of second vehicles (11);
- generation of said calculator life cycle prediction model by classification of said second data. Method according to claim 3, further comprising a step of modifying at least one parameter of said calculator life cycle prediction model as a function of said first data and the result of said prediction. Method according to one of claims 1 to 4, for which said first data belong to a set of data comprising:
- data representative of a fault code;
- data representative of changes in the state of said first calculator;
- data representative of instructions determined by said first computer;
- data representative of the result of calculation carried out by said first calculator;
- data representative of the query generated by said first calculator. Method according to one of claims 1 to 5, further comprising a step of implementing said at least one recommendation. The method of claim 6, further comprising a step of storing data representative of said implementation and data representative of performance levels prior to and subsequent to said implementation. Computer program comprising instructions for implementing the method according to any one of the preceding claims, when these instructions are executed by a processor. Device (2) for predicting a fault in a first computer of a first vehicle, said device (2) comprising a memory (21) associated with at least one processor (20) configured for implementing the steps of the method according to any one of claims 1 to 5. Vehicle (10) comprising the device (2) according to claim 9.