Method for managing technical data emitted by a motor vehicle

Abstract

A computer-implemented method for managing technical data emitted by a motor vehicle comprises the steps of: acquiring (23) a data stream from equipment of the motor vehicle; filtering and correcting (25) the data stream by a neural network previously trained (21) by supervised learning. A system for managing technical data emitted by a motor vehicle and a motor vehicle comprising the system are also described. Figure to be published with the abstract: Fig 2

Description

Title of the invention: Method for managing technical data emitted by a motor vehicle Technical field

[0001] The present invention relates to a method for managing technical data emitted by a motor vehicle, a computer program product, a system for managing technical data emitted by a motor vehicle and a motor vehicle comprising such a system. State of the art

[0002] Data quality refers to the conformity of data to its intended uses. Thus, data is considered to be of high quality if it correctly represents the reality to which it refers.

[0003] It is therefore important for any organization to have good quality data, in order to be able to base its operational, financial or performance decisions on the underlying reality.

[0004] With connected vehicles, the automotive industry is required to handle a lot of data from this fleet of connected vehicles. It is required to use this data to improve maintenance, for example, by detecting abnormal behavior of equipment before a breakdown occurs or to optimize functionalities based on user usage. These are just two examples of the use of data received from connected vehicles among a multitude.

[0005] However, if these data are of poor quality, they will be sources of complication by generating bad interpretations, erroneous study results, etc. Data processing must then be carried out, once these data are collected, by data specialists in order to clean them and prepare them for the following processing. This has the disadvantage of consuming resources and also of often preparing the data for a particular need, requiring the same data to be prepared again when another need arises.

[0006] There is therefore a real need for a method and a system for managing technical data emitted by a motor vehicle which resolves all or part of the aforementioned drawbacks. Description of the invention

[0007] To resolve one or more of the drawbacks cited above, according to a first embodiment, a computer-implemented method for managing technical data emitted by a motor vehicle comprises the steps of: • acquisition of a data stream from a motor vehicle device; • filtering and correction of the data flow by a neural network previously trained by supervised learning.

[0008] Thus, the data from the vehicle have undergone processing to define their quality.

[0009] Particular characteristics or embodiments, usable alone or in combination, are: • the filtering and correction of the data flow comprises a first sub-step of detecting that a data item is aberrant and a second sub-step of choosing and using a function for correcting the aberrant data item; • the detection that data is aberrant is carried out by a first neural sub-network and the choice of the correction function is carried out by a second neural sub-network; • supervised neural network learning involves using a training dataset whose data is labeled as “normal” or “outlier” and the data labeled “outlier” is associated with a correction function; • after the neural network has been trained by learning with the training dataset, new data is filtered and corrected by the neural network and the result is validated to reinforce or correct the training of the neural network; • the reinforcement or correction step is carried out iteratively with new data at each iteration; and / or • the previously trained neural network is used on data from several vehicles of the same type.

[0010] In a second embodiment, a computer program product comprises program code instructions for implementing the above method when the program product is executed on a computer.

[0011] In a third embodiment, a system for managing technical data emitted by a motor vehicle comprises: • a sensor adapted to acquire a data stream from a piece of equipment of the motor vehicle; connected to • a calculator adapted to filter and correct the data flow by a neural network previously trained by supervised learning.

[0012] In a fourth embodiment, a motor vehicle comprises a system according to the third embodiment. Brief description of the figures

[0013] The invention will be better understood on reading the following description, given solely by way of example, and with reference to the appended figures in which: • [Fig.l] represents a top view of a vehicle comprising a system for managing technical data transmitted according to one embodiment; • [Fig.2] represents a flowchart of a data management process techniques issued according to an embodiment; • [Fig.3] represents a flowchart of a two-step learning process neural networks for managing technical data emitted by a vehicle according to another embodiment; and • [Fig.4] represents a flowchart of an inference process using the neural networks trained according to the method of [Fig.3]. Methods of implementation

[0014] The embodiments presented below refer to a motor vehicle, a car. However, those skilled in the art understand that these are also usable with other types of vehicle such as vans, vans, etc.

[0015] The terms “front”, “rear”, “top”, “bottom”, “transverse” are understood in relation to the vehicle.

[0016] With reference to [Fig.l], a motor vehicle 1 comprises a system 3 for managing the technical data emitted by this motor vehicle 1.

[0017] The system 3 comprises at least one sensor 5 adapted to acquire in real time a data stream originating from equipment of the motor vehicle 1. For example, the sensor 5 will acquire information originating from the operation of the engine such as the number of revolutions per minute, the energy consumption at each instant, etc. Each data item in this data stream is time-stamped so as to be able in particular to correlate it with other data received by other sensors at the same instant or in the same time range.

[0018] The system 3 comprises a computer 7 connected to the sensor 5.

[0019] The computer 7 can, for example, be integrated into the vehicle control system 1, as an advanced driver assistance system, commonly called AD AS (for “Advanced driver-assistance Systems” according to English terminology) which makes all driving decisions based on the environment and the programmed destination. The motor vehicle is then referred to as an autonomous motor vehicle. But it can also be a centralized vehicle management system including, or not, driving aids.

[0020] The transfer of data between the different elements is preferably carried out by a CAN type data bus (for “Controller Area Network” in English, or “ controller area network”) or LIN (for “Local Interconnect Network” in English, or “Local interconnected network” in French).

[0021] The computer 7 is adapted to filter and correct the data flow by a neural network previously trained by supervised learning. Thus, it uses an artificial intelligence method called deep learning.

[0022] The neural network is previously trained on a training data set in which the data is labeled (sometimes the term "labeled" is also used) between "normal" data, i.e. correctly reflecting the underlying physical reality, and "aberrant" data, i.e. the physical reality is not captured by the data. An "aberrant" data is a missing data, a data having a value outside the range possible by physics or a data stuck on a value, etc.

[0023] These aberrant data from the training set are associated with corrective functions which are, for example, of the type "replace with the last normal value", "indicate that the value is not available" or "perform a linear interpolation", etc., as well as with different types of statistical functions well known to specialists in the field.

[0024] It should be noted that this may also include data from different sensors and correlation functions between these data from different sources. For example, engine speed data associated with zero energy consumption generally indicates an anomaly unless a third stream indicates that the vehicle is traveling on a downhill lane.

[0025] The operation of system 3 is as follows, [Fig.2].

[0026] In a preliminary step 21, the neural network is trained with the training data set.

[0027] When the vehicle 1 is in operation and generates data streams, these data streams are acquired, step 23, by the sensor 5.

[0028] The computer 7 executes, step 25, the trained neural network to obtain a filtered and corrected data stream.

[0029] [Fig.l] illustrates a system according to certain embodiments. The breakdown presented has an educational purpose to highlight the different functions. However, it is understood that each block can be implemented using different means or their combinations, such as hardware components, software, one or more computers and / or electronic circuits. Each of the components can include at least one computer or a control-command unit. At least one memory can be included in each component. The memory can include computer program instructions or software code.

[0030] The calculators can be implemented by any type of device data processing, such as a central computing unit, a signal processing processor, an application-specific integrated circuit, a programmable gate array, etc. The computers can be implemented as a single controller, or a plurality of controllers or computers.

[0031] The different modules are connected to each other by data links adapted to the environment. These can be wired or wireless.

[0032] For software, the implementation may include modules or units distributed in the form of procedures, functions, etc. The memories may be any type of storage circuit. They may be part of the processor circuit, or separate from it and connected via electrical data links. These may be non-volatile type memories, hard disks, random access memories, flash memories, etc.

[0033] The program product may be downloadable from a communications network and / or recorded on a computer-readable medium. It may be directly executable by a processor or be in the form of a high-level language requiring one or more intermediate operations to be executable.

[0034] Thus the program instructions stored in the memory and processed by the computers can be any type of program code, for example, a compiled or interpreted program written in a suitable programming language.

[0035] The computer program instructions stored in the memory are such that, when executed by the computer, the latter performs one or more of the steps of the methods described above.

[0036] The invention has been illustrated and described in detail in the drawings and the preceding description. This should be considered as illustrative and given by way of example and not as limiting the invention to this description alone. Numerous alternative embodiments are possible.

[0037] The computer 7 is described above as being part of the vehicle 1. Indeed, even if it appears that currently the deep learning phase requires powerful and specialized computers which are incompatible with integration into a vehicle, specialized circuits for executing already trained neural networks appear on the market and make it possible to design systems embedded in a vehicle. A variant of this embodiment consists of transferring the raw data into a central server and carrying out the filtering and correction operations in this server.

[0038] In a second variant, the learning is completed by an iterative step in which the neural network is used on a set of unlabeled data and the result is validated by a specialist. Thus, if the neural network correctly detects that a piece of data is “normal” or “aberrant” and then the proposed correction is Once the information is adapted, the specialist validates the information, otherwise he corrects it. And this validation or correction is included in the training of the neural network. This step is repeated until the detection and correction proposed by the neural network reach a level of confidence considered adequate for subsequent uses.

[0039] We will describe, in a third variant, a detailed embodiment in relation to [Fig.3] and [Fig.4].

[0040] Firstly, the learning process is described, [Fig.3].

[0041] In step 31, the characteristics of the vehicle type are identified.

[0042] Data from different vehicles of the same type are retrieved, step 32, with associated quality criteria such as the range of signal values.

[0043] Depending on these quality criteria, a quality configuration to be applied to the vehicle data is defined, step 33. This quality configuration thus includes processing to be applied to the data such as verification, smoothing or filtering.

[0044] The quality configuration is applied, step 34, to data sets originating from vehicle use.

[0045] A binary classification of the data set obtained into “normal” signals and “aberrant” signals is carried out, step 35.

[0046] A first neural network training is carried out, step 36, in order to identify at the output the “aberrant” signals of the vehicle using a multiclass classifier. The input data of this training are on the one hand the quality configuration obtained in step 33 and the classified data obtained in step 35.

[0047] The information necessary for a second neural network training for the choice of the signal correction configuration is identified, step 37. This includes the list of outlier signals and the list of possible correction configurations such as "keep the last valid value", etc., as described above.

[0048] The correction configurations are applied, step 38, to the aberrant signals of step 35.

[0049] The data necessary for learning the choice of the correction configuration are prepared, step 39, by taking the aberrant signals corrected by different methods and the normal signals.

[0050] The best correction configuration(s) are chosen, step 40, by comparing the normal signals and the aberrant signals corrected by different methods.

[0051] A second neural network training is carried out, step 41, for the choice of the optimal correction via a multiclass classifier and taking as input data the best configurations obtained in step 40 and the list of all the confi- possible correction figures.

[0052] Two trained neural networks are thus obtained, one for the classification of values and the other for the correction to be applied to the outliers. It is understood that these two neural networks can be seen as two neural sub-networks of the neural network of the first embodiment of [Fig.l] and [Fig.2].

[0053] They are then used in the inference phase, [Fig.4].

[0054] The characteristics of the vehicle to be studied, as well as the data to be collected, are defined, step 45.

[0055] Data is collected, step 46.

[0056] The first neural network is used, step 47, to identify aberrant signals.

[0057] The second neural network is used, step 48, to determine the optimal correction configuration to apply.

[0058] The optimal correction configuration is applied, step 49, to the aberrant signals.

[0059] The set of corrected and uncorrected signals is used, step 50, and feedback on the quality obtained is provided, step 51, for subsequent optimizations, as additional training data.

Claims

Claims

1. Computer-implemented method for managing technical data emitted by a motor vehicle comprising the steps of: • acquisition (23) of a data stream originating from equipment of the motor vehicle; • filtering and correction (25) of the data stream by a neural network previously trained (21) by supervised learning.

2. The method of claim 1, wherein the filtering and correcting the data stream comprises a first sub-step of detecting that a data item is aberrant and a second sub-step of choosing and using a correction function for the aberrant data item.

3. Method according to claim 2, in which the detection that a data is aberrant is carried out by a first neural sub-network and the choice of the correction function is carried out by a second neural sub-network.

4. The method of claim 1, 2 or 3, wherein the supervised training of the neural network comprises using a training data set whose data is labeled as "normal" or "outlier" and the data labeled "outlier" is associated with a correction function.

5. The method of claim 4, wherein after the neural network has been trained by learning with the training data set, new data is filtered and corrected by the neural network and the result is validated to reinforce or correct the training of the neural network.

6. The method of claim 5, wherein the strengthening or correction step is performed iteratively with new data at each iteration.

7. A method according to any preceding claim, wherein the pre-trained neural network is used on data from multiple vehicles of the same type.

8. Computer program product characterized in that it comprises program code instructions for implementing the method according to any one of claims 1 to 7 when the product- program is executed on a computer.

9. System (3) for managing technical data emitted by a motor vehicle comprising: • a sensor (5) adapted to acquire a data flow coming from equipment of the motor vehicle; connected to • a computer (7) adapted to filter and correct the data flow by a neural network previously trained by supervised learning.

10. A motor vehicle comprising a system according to claim 9.

Images