FR3126519A1 - Method and device for identifying repaired components in a vehicle - Google Patents

Abstract

The present invention relates to a method and a device for identifying first components that have been repaired in a first vehicle (11). Identifying the first components includes receiving first data representative of diagnostic result(s) (100) from the first vehicle (11). The identification of the first components is obtained by feeding a repaired component prediction model (124) with the first data received. Such a prediction model has advantageously been learned during a prior learning phase from second data representative of the diagnostic result of each second vehicle of a set of second vehicles (12). Figure for abstract: Figure 1

Description

Method and device for identifying repaired components in a vehicle

The present invention relates to methods and devices for identifying component(s) associated with a repair in a vehicle, in particular a motor vehicle. The present invention also relates to a method and a device for determining information representative of one or more components associated with a fault detected in a diagnosis of a vehicle.

Technology background

Contemporary vehicles are made up of a large number of components or organs, each susceptible to breakdown or defect.

To check the correct operation of a vehicle, for example an automobile, it is known to carry out a diagnosis via a tool adapted for this purpose. Such a tool corresponds to a computer and is sometimes called a vehicle diagnostic kit. When plugged into the vehicle, the diagnostic tool collects data on the operation of the vehicle. By comparing this data with reference data provided by the vehicle manufacturer, it is possible to identify any faults, diagnose a fault or prevent a fault or breakage of one or more components.

The difficulty that arises, especially for people in charge of vehicle maintenance, is to be able to quickly and simply identify the component or components of the vehicle that have been repaired.

Summary of the present invention

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

An object of the present invention is to improve the identification of the components associated with a fault observed on a vehicle.

According to a first aspect, the present invention relates to a component identification method in a first vehicle, said method being implemented by at least one processor, the method comprising the following steps:

- reception of first data representative of the diagnostic result of the first vehicle;

- identification of at least a first component of the first vehicle by feeding a repaired component prediction model with the first data, each first component corresponding to a component repaired following a breakdown,

the repaired component prediction model having been learned in a so-called learning phase prior to receipt and identification from:

● second data representative of the diagnostic result of each second vehicle of a set of second vehicles;

● first information representative of at least one repair request for at least one second component in each second vehicle of the set of second vehicles; And

● second information representing the at least one second component for each second vehicle of said set of second vehicles.

According to a variant, the method further comprises a step of learning the repaired component prediction model, the learning step comprising the following steps:

- receiving the second data, the first information and the second information;

- generation of the repaired component prediction model by classifying the second data in relation to the first and second information.

According to another variant, the identification of the at least one first component comprises a classification of the first data.

According to an additional variant, the classification is implemented according to a model of multilayer perceptrons, known as MLP, implemented by a neural network.

According to yet another variant, the classification corresponds to a classification by random forests.

According to an additional variant, the identification comprises a determination of third information representative of at least one first component, the third information belonging to a set of information comprising:

- information representative of a type of component;

- information representative of a repair order for a component in a sequence of a plurality of components to be repaired;

- information representative of a time required to repair the at least one first component.

According to another variant, the first data is received from a remote device via a wired or wireless link.

According to a second aspect, the present invention relates to a device configured to identify at least a first component in a first vehicle, the device comprising a memory associated with a processor configured for the implementation of the steps of the method according to the first aspect of the present invention. invention.

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

According to a fourth aspect, the present invention relates to a system comprising a device as described above according to the second aspect of the present invention and a vehicle connected in communication to the device as described above according to the second aspect of the present invention .

According to a fifth aspect, the present 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 present invention, this in particular when the computer program is executed by at least one processor.

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

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

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

On the other hand, this recording medium can 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 hertzian radio or by self-directed laser beam or by other ways. The computer program according to the present invention can in particular be downloaded from an Internet-type network.

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

Brief description of figures

Other characteristics and advantages of the present invention will emerge from the description of the particular and non-limiting examples of embodiments of the present invention below, with reference to the appended FIGS. 1 to 5, in which:

schematically illustrates a system for learning a prediction model of repaired components and the use of such a model in a component identification process in a first vehicle, according to a particular and non-limiting embodiment of the present invention;

schematically illustrates part of a neural network configured for the implementation of part of the operations of the processes of the , according to a particular and non-limiting embodiment of the present invention;

schematically illustrates a tree structure of a method of random forests for the implementation of part of the operations of the processes of the , according to a particular and non-limiting embodiment of the present invention;

schematically illustrates a device configured to identify one or more components of the first vehicle of the having undergone a repair, according to a particular and non-limiting embodiment of the present invention;

illustrates a flowchart of the different steps of a method for identifying one or more components of the first vehicle of the having undergone a repair, according to a particular and non-limiting embodiment of the present invention.

Description of the examples of realization

A method and a component identification device (s) in a first vehicle will now be described in what will follow with reference to Figures 1 to 5. The same elements are identified with the same reference signs throughout the description that follows.

According to a particular and non-limiting embodiment of the present invention, the identification of one or more first components of a first vehicle, each first component having undergone a repair or having been associated with a repair, comprises the reception, by example by one or more processors of a computing device (for example a server, a computer or a calculator), first data representative of result(s) of one or more diagnoses of the first vehicle. One or more first components of the first vehicle that have been repaired or have been associated with a repair are identified by feeding a repaired component prediction model with the first data received. Such a prediction model has advantageously been learned during a prior learning phase from second data representative of the diagnostic result of each second vehicle of a set of second vehicles, first information representative of at least one request for repair of at least one second component in each second vehicle of the set of second vehicles and second information representative of the at least one second component for each second vehicle of said set of second vehicles. The set of second vehicles corresponds for example to a set of vehicles whose data and information were collected while these vehicles were under warranty, the volume and type of information available for these vehicles being greater than for vehicles outside guarantee.

The identification of the first component(s) is implemented by an automatic learning method, also known as machine learning.

The use of a learned model, for example from a large number of vehicles for which the information available is more complete, in particular on the components or units associated with identified failures, makes it possible to identify the components or units which have been repaired on a vehicle based on that vehicle's diagnostic data.

This makes it possible, for example, to retrieve the history of repaired parts for a vehicle, in the absence of any information on this subject, from the diagnostic data of this vehicle obtained for example from a diagnostic computer.

There schematically illustrates an environment for learning a repaired component prediction model and for identifying first component(s) in a first vehicle, according to a particular and non-limiting embodiment of the present invention.

Environment 1 of the has two parts, namely a first part 101 configured to identify one or more first components of a first vehicle 11 and a second part 102 configured to learn a predictive model of repaired components, which model is learned from data of a set of second vehicles 12.

The first component(s) correspond to components that were repaired or associated with a repair on a date prior to the date on which the identification of this or these first component(s) is implemented.

The first vehicle 11 corresponds for example to a vehicle with a combustion engine, with electric motor(s) or else a hybrid vehicle with a combustion engine and one or more electric motors. The first vehicle 11 thus corresponds for example to a land vehicle, for example an automobile, a truck, a coach.

Each second vehicle of the set 12 advantageously corresponds to a vehicle of the same type as the first vehicle 11.

A process for identifying one or more first components of the first vehicle 11 is advantageously implemented in a computing device, for example a computer or a server, for example a "cloud" server (or "cloud" in French ). According to a variant embodiment, the identification process is implemented by a computer of the first vehicle 11.

Such a process is advantageously implemented in the form of an automatic learning or machine learning method. Such an automatic learning method is for example implemented by a neural network, for example a neural network of the convolutional neural network type, also called convolutional neural network or convolutional neural network and denoted CNN or ConvNet (from English “Convolutional Neural Networks”). Such a network corresponds to a network of acyclic artificial neurons (“feed-forward”). Such a convolutional neural network comprises a convolutional part implementing one or more convolution layers and a densely connected part implementing, for example, one or more layers of densely connected (or fully connected) neurons, as illustrated by the , ensuring the classification of the diagnostic data according to a model of the MLP type (from the English “Multi Layers Perceptron” or in French “Perceptrons multicouches”) for example.

According to a variant embodiment, the classification of the diagnostic data is carried out according to the so-called random forest method, also known as decision tree forests, this method being known from the skilled in the art and is for example described in the document entitled “Random Decision Forests” by Tin Kam Ho and published in “Proceedings of the 3rd International Conference on Document Analysis and Recognition” in August 1995. Such a variant is illustrated by the .

The process of identifying the first component(s) is implemented in a so-called production, prediction or exploitation phase of the learning method, such a phase using one or more repaired component(s) prediction models learned in a so-called learning phase of this or these models. The learning phase is a preliminary phase to the production phase, the model(s) being learned or generated during this learning phase.

Each of these phases includes one or more operations described below.

The first phase and the second phase are for example implemented by the same device remote from the first vehicle 11, for example a computer or a server.

According to a variant embodiment, the learning phase is implemented by a server (for example a "cloud" server or a server hosted in a center (for example a design office of the manufacturer of the first vehicle) suitable for learning) and the production phase is implemented by a different device, for example a computer, another server or a computer of the on-board system of the first vehicle 11.

Learning stage

The learning implemented corresponds for example to unsupervised learning from a set of data associated with the set of second vehicles 12, which set comprises for example a few tens, a few hundreds, thousands or tens/ hundreds of thousands of second vehicles. According to a variant embodiment, the learning implemented in the first phase corresponds to supervised learning from the set of data associated with the set of second vehicles 12.

The set of second vehicles 12 corresponds to a set of vehicles whose monitoring is more regular and more complete than the monitoring of the first vehicle 11. Each second vehicle of the set 12 corresponds for example to a vehicle under manufacturer's warranty, such a warranty being valid for a fixed period at the start of the life of the vehicle (for example for 1 or 2 years). The set of second vehicles 12 corresponds for example to a set comprising second vehicles each having experienced a breakdown of one or more second components, this or these second components having been repaired, for example in a garage automobile or in the workshop.

In a first operation of the learning phase, data is collected for each second vehicle of set 12.

The data collected for these second vehicles 12 and used for learning the repaired component(s) prediction model(s) advantageously includes the following data or information:

- data (called second data) representative of diagnostic result(s) carried out for each of the second vehicles of the set 12. These second data are for example obtained from a diagnostic tool 100, for example by connecting this tool 100 to each second vehicle via a wired or wireless link, for example via an OBD type link (from the English “On Board Diagnostics” or in French “On-board diagnostics”). The second data measured by the diagnostic tool 100 are advantageously transmitted to a database 120 hosted in a remote device. These second data are for example associated with an identifier of the second vehicle that they concern, such an identifier corresponding for example to the VIN number (from the English “Vehicle Identification Number” or in French “Number of identification of the vehicle”). The identifier of a vehicle makes it possible, for example, to determine one or more of the following information: the type of vehicle, the model of the vehicle, the brand of the vehicle and/or the hardware and software configuration of the vehicle. The second data are for example representative of the operating state of the elements or components of the braking system, of the vehicle's safety devices, of the vehicle's intake system, of the vehicle's connection system to the ground (the tires), the vehicle's lighting system, maintenance indicators, one or more on-board ADAS systems (from English "Advanced Driver-Assistance System" or in French "Advanced Driving Assistance System"). The second data includes, for example, the actual mileage during the diagnosis, the operating status of the probes and measuring devices and the error or fault codes, also called DTC codes (from the English "Diagnostic Trouble Code" or in French "Diagnostic fault code"), related to any defect of an organ or component;

- data (called first information) representative of at least one repair request for at least one second component for one or more second vehicles of the set 12. Such a repair request corresponds for example to a credit request. A breakdown associated with a component of a second vehicle of the set 12 is for example recorded in a database 121 in the form of a request to take charge of the breakdown, called a credit request. Such a credit request is, for example, entered into the database 121 and associated with the second vehicle concerned by an operator to whom the breakdown or defect of the component is reported. The breakdown or defect is, for example, reported by the owner of the vehicle concerned or by a company providing vehicle repair (car garage or car dealership of the manufacturer, for example). The database 121 stores, for example, next to each identifier of the second vehicle of the set 12, information representing a breakdown (for example information indicating that a credit application has been made), such a credit application identifying the or the second components of the second vehicle concerned by the breakdown with optionally one or more information such as the date of occurrence or escalation of the breakdown, the identifier of the person or of the company having reported the breakdown, etc. The identifiers and the associated information are for example recorded in the database 121 in the form of a correspondence table, called LUT (from the English “Look-Up Table”) associating with each second vehicle (identified for example by its VIN number) of the set 12 of the first information representative of one or more repair requests (also called breakdown feedback or credit request); And

- data (called second information) representative of the second component(s) identified in the credit application. This second information is for example stored in a database 122, for example in the form of a LUT table matching certain information or characteristics of each second component having been the subject of a failure report (therefore repair) next to each second component (identified by a unique identifier). This second information comprises, for example, the type of the second component, the order in which this second component was repaired when the identified failure led to the repair of several components forming a determined sequence, the duration of intervention necessary for the repair of the second component, etc

In a second operation of the learning phase, the repaired component prediction model(s) 124 is/are generated or trained by classification of the second data in relation to the first and second information. Such a classification makes it possible to establish links or associations between the second data (resulting from the diagnoses carried out on the second vehicles) and the second components having been the subject of a repair. Such a classification is advantageously implemented by a classifier 123.

The classifier 123 takes for example the form of one or more layers of densely connected (or fully connected) neurons of a neural network, according to an MLP type model (from the English “Multi Layers Perceptron” or in French “ Multilayer perceptrons”).

According to another example, such a classification 123 is implemented via the so-called random forest method.

Such a learning phase thus makes it possible to determine one or more models establishing probabilities on the components of a vehicle to be repaired according to the diagnostic data of this vehicle.

production stage

In a first operation of the production phase, first data is collected from the first vehicle 11. This first data is similar to the second data collected from the second vehicles of the set 12. Thus, this first data is representative of result diagnostic(s) carried out for the first vehicle 11. These first data are for example obtained from a diagnostic tool 100, for example by connecting this tool 100 to the first vehicle 11 via a wired or wireless link, by example via an OBD type link.

The first data measured by the diagnostic tool 100 are advantageously transmitted to a database 110 hosted in a remote device. This remote device corresponds for example to a computer or to a server, different or identical to the remote device hosting at least one of the databases 120, 121, 122.

These first data are for example associated with an identifier of the first vehicle 11 which corresponds for example to the VIN number of the first vehicle 11 and which makes it possible, for example, to determine the type of the first vehicle 11, which makes it possible, for example, to determine from which set 12 this first vehicle 11 approaches for example to select the prediction model(s) learned on second vehicles similar to the first vehicle 11.

The first data of the first vehicle 11 make it possible, for example, to obtain information relating to the operating state of the on-board systems of the first vehicle 11 such as the braking system, the vehicle security system, the vehicle admission system , the vehicle's ground connection system (the tires), the vehicle's lighting system, maintenance indicators and/or one or more on-board ADAS systems (from the English "Advanced Driver-Assistance System" or in French “Advanced driver assistance system”). The first data includes, for example, the actual mileage during the diagnosis, the operating status of the sensors and measuring devices and the error or fault codes reported by the on-board system of the first vehicle 11.

When the production phase is implemented by a computer of the first vehicle 11, the first data is transmitted by the tool 100 to the first vehicle 11, for example via a wired connection or a wireless connection of the Wifi® or Bluetooth® type. .

In a second operation of the production phase, the first data is transmitted to the repaired component prediction model 124 to feed the latter. A classifier 111, for example identical to the classifier 123, implements a classification of the first data on the basis of the learned prediction model(s) 124.

The classifier 111 takes for example the form of one or more layers of densely connected (or fully connected) neurons of a neural network, according to a model of the MLP type (from the English “Multi Layers Perceptron” or in French “ Multilayer perceptrons”).

According to another example, the classifier 111 takes the form of a unit implementing the so-called random forest method.

At the output of the classification 111 are obtained one or more probabilities of belonging to one or more classes, each class identifying one or more first components of the first vehicle having been repaired according to the probability associated with the class. Third information complementary to the identification of the first component(s) identified as having been repaired is for example also obtained at the output of the classification. This third information includes, for example, one or more of the following data or information, in any possible combination:

- information representative of a type of each first component;

- information representative of a repair order for a component in a sequence of a plurality of components to be repaired;

- information representative of the time required to repair each first component.

In a third optional operation, the identifiers of the first component or components, with optional third associated information, are displayed on a display screen.

The production phase thus makes it possible to determine which components of the first vehicles have been repaired on the basis of the diagnostic data. This makes it possible to reconstruct the service or maintenance history of the vehicle in the absence of data on the components that have been repaired.

There schematically illustrates the densely connected part 2 of a neural network, according to a particular and non-limiting embodiment of the present invention.

The densely connected part 2 illustrated in comprises for example 3 layers 201, 202, 203 of neurons, the neurons of one layer being connected to the neurons of another layer. The densely connected part 2 receives as input data 21, 22, 23 coming for example from the convolutional part of the neural network (when this neural network corresponds to a CNN convolutional network), these data being received in the form of vectors For example. The data 21, 22, 23 correspond to the data resulting from the processing by the convolutional part of the network, for example of the first data (regarding the production phase) or the second data (regarding the learning phase).

This densely connected part 2 advantageously implements the classification of the first or second data according to the MLP type model (from the English “Multi Layers Perceptron” or in French “Perceptrons multicouches”).

The output of the densely connected part 2 comprises a determined number of neurons 24, 25, for example 2, 5, 10 or more, each neuron of the output corresponding to a class representative of one or more vehicle component or organ identifiers .

There schematically illustrates a tree structure 3 for the implementation of a classification according to the method of random forests, according to a particular and non-limiting embodiment of the present invention.

The tree structure 3 comprises a determined number of decision trees 31, 32, 33, for example 10, 50, 100, 500 or more trees. These decision trees 31 to 33 receive as input subsets of the first or second data 30 to be classified. A learning model is for example associated with each of these decision trees 31 to 33, the learning models resulting from the learning phase as described with regard to the .

Each decision tree 31 to 33 outputs a prediction of belonging to a class 311, 321, 331 associated with each decision tree 31, 32, 33 respectively.

The outputs 311, 321, 331 are subjected to a so-called voting operation 34 to determine the most probable class 340, which comprises the identifier(s) of the components or organs of the first vehicle 11 having the object of repair.

Such a classification method is known to those skilled in the art and was formally proposed in 2001 by Leo Breiman and Adele Cuttler, in particular in the document entitled "Random Forests" and published by Leo Breiman in January 2001.

schematically illustrates a device 4 configured to identify one or more components repaired in a vehicle from diagnostic data, according to a particular and non-limiting example embodiment of the present invention. Such a device 4 is configured for the implementation of the learning phase and the production phase of a machine learning method.

The device 4 is for example configured for the implementation of the operations described with regard to FIGS. 1, 2, and 3 and/or of the steps of the method described with regard to the . Examples of such a device 4 include, but are not limited to, a computer, a laptop computer, a server, a mobile phone, a tablet or even on-board electronic equipment such as a vehicle on-board computer or a electronic calculator such as an ECU ("Electronic Control Unit). The elements of the device 4, individually or in combination, can be integrated in a single integrated circuit, in several integrated circuits, and/or in discrete components. The device 4 can be produced in the form of electronic circuits or software (or computer) modules or else a combination of electronic circuits and software modules.

The device 4 comprises one (or more) processor(s) 40 configured to execute instructions for carrying out the steps of the method and/or for executing the instructions of the software or software embedded in the device 4. The processor 40 can include integrated memory, an input/output interface, and various circuits known to those skilled in the art. The device 4 further comprises at least one memory 41 corresponding for example to a volatile and/or non-volatile memory and/or comprises a memory storage device which can 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 on-board software or software comprising the instructions to be loaded and executed by the processor is for example stored on the memory 41.

According to a particular and non-limiting embodiment, the device 4 comprises a block 42 of interface elements for communicating with external devices, for example a remote server or the “cloud”, other nodes of the ad hoc network. Block 42 interface elements include one or more of the following interfaces:

- RF radio frequency interface, for example of the Wi-Fi® type (according to IEEE 802.11), for example in the 2.4 or 5 GHz frequency bands, or of the Bluetooth® type (according to IEEE 802.15.1), in the band frequency at 2.4 GHz, or of the Sigfox type using UBN radio technology (Ultra Narrow Band, in French ultra narrow band), or LoRa in the 868 MHz frequency band, LTE (from English " Long-Term Evolution” or in French “Evolution à long terme”), LTE-Advanced (or in French 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”, or “Interface Multimedia Haute Definition” in French);

- LIN interface (from English “Local Interconnect Network”, or in French “Réseau interconnecté local”).

According to another particular and non-limiting example of embodiment, the device 4 comprises a communication interface 43 which makes it possible to establish communication with other devices (such as other computers of the on-board system) via a communication channel 430. The communication interface 43 corresponds for example to a transmitter configured to transmit and receive information and/or data via the communication channel 430. The communication interface 43 corresponds for example to a CAN-type wired network (of the 'English "Controller Area Network" or in French "Réseau de Contrôleurs"), CAN FD (from English "Controller Area Network Flexible Data-Rate" or in French "Réseau de Contrôleurs à Flow de Data Flexible"), FlexRay ( standardized by ISO 17458) or Ethernet (standardized by ISO/IEC 802-3).

According to a particular and non-limiting example of embodiment, the device 4 can supply output signals to one or more external devices, such as a display screen, touch-sensitive or not, one or more loudspeakers and/or other devices (projection system) through respective output interfaces.

illustrates a flowchart of the different steps of a method for identifying one or more components repaired in a vehicle, according to a particular and non-limiting embodiment of the present invention. The method is for example implemented by a device of the computer or server type or by the device 4 of the .

In a first step 51, first data representative of the diagnostic result of the first vehicle are received.

In a second step 52, at least one first component of the first vehicle is identified by feeding a repaired component prediction model with the first data, each first component corresponding to a component repaired following a breakdown,

the repaired component prediction model having been learned in a so-called learning phase prior to receipt and identification from:

● second data representative of the diagnostic result of each second vehicle of a set of second vehicles;

● first information representative of at least one repair request for at least one second component in each second vehicle of the set of second vehicles; And

● second information representing the at least one second component for each second vehicle of said set of second vehicles.

According to a variant, the variants and examples of the operations described in relation to FIGS. 1, 2 and 3 apply to the steps of the method of .

Of course, the present invention is not limited to the exemplary embodiments described above but extends to a diagnostic data processing method which would include secondary steps without thereby departing from the scope of the present invention. The same would apply to a device configured for the implementation of such a method.

The present invention also relates to a system comprising the device of the connected in communication with a vehicle, for example automobile.

Claims (10)

Component identification method in a first vehicle (11), said method being implemented by at least one processor, said method comprising the following steps:
- reception (51) of first data representative of the diagnostic result of said first vehicle (11);
- identification (52) of at least a first component of said first vehicle by feeding a prediction model (124) of repaired components with said first data, each first component corresponding to a component repaired following a breakdown,
said prediction model (124) of repaired components having been learned in a so-called learning phase prior to said reception and said identification from:
● second data representative of diagnostic result of each second vehicle of a set of second vehicles (12);
● first information representative of at least one repair request for at least one second component in each second vehicle of said set of second vehicles (12); And
● second information representative of said at least one second component for each second vehicle of said set of second vehicles (12). A method according to claim 1, further comprising a step of training said predictive model (124) of repaired components, said training step comprising the steps of:
- receiving said second data, said first information and said second information;
- generation of said repaired component prediction model by classifying said second data in relation to said first and second information. A method according to claim 1 or 2, wherein said identification (52) of said at least one first component comprises a classification of said first data. Method according to claim 3, for which said classification is implemented according to a model of multilayer perceptrons, called MLP, implemented by a neural network (2). Method according to claim 3, for which said classification corresponds to a classification by random forests. Method according to one of Claims 1 to 5, for which said identification comprises a determination of third information representative of said at least one first component, said third information belonging to a set of information comprising:
- information representative of a type of component;
- information representative of a repair order for a component in a sequence of a plurality of components to be repaired;
- information representative of a time required to repair said at least one first component. Method according to one of claims 1 to 6, for which said first data is received from a remote device via a wired or wireless link. 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 (4) configured to identify at least a first component in a first vehicle, said device (4) comprising a memory (41) associated with at least one processor (40) configured for the implementation of the steps of the method according to any of claims 1 to 7. A system comprising the device (4) according to claim 9 and a vehicle (11) communicatively connected to said device (4).