Method for determining the operability of a motor vehicle, control device, and motor vehicle

Abstract

The invention relates to a method for determining the operability of a motor vehicle (10), to a control device, and to a motor vehicle (10). In a step a), current measurement data of the motor vehicle (10) can be detected by means of a sensor system (27) external to the vehicle. In a step b), a deviation of the current measurement data from comparison data (4) can be determined by means of a machine learning model, whereby the operability of the motor vehicle (10) is determined. In a step c), if the deviation is above a specified threshold value, a warning message can be output, which advises a user of the motor vehicle (10) to stop operating the motor vehicle (10) and / or to transmit the current measurement data and / or the deviation to a remote maintenance system in order to initiate a control process in the motor vehicle (10).

Description

[0001] AUDI AG P24229WO.O

[0002] DESCRIPTION:

[0003] Method for determining the operational readiness of a motor vehicle, as well as control device and motor vehicle

[0004] The invention relates to a method for determining the operational capability of a motor vehicle, a control device for carrying out the method, and a motor vehicle comprising the control device.

[0005] Generally, determining the operational readiness of a motor vehicle requires a person to perceive vehicle damage, maintenance needs, and / or operational anomalies, for example, visually, audibly, and / or tactilely. The following describes the state of the art that at least partially automates this process.

[0006] DE 10 2017 221 727 A1 discloses a system for controlling a remotely connected vehicle.

[0007] US patent 2024 / 0086860A1 discloses a vehicle system for predicting maintenance work for a vehicle fleet.

[0008] US Patent 2021 / 0049839A1 discloses a system and procedure for predictive maintenance in the automotive sector.

[0009] The invention is based on the objective of reliably and / or automatically determining the operational capability of a motor vehicle.

[0010] The problem is solved by the subject matter of the independent claims. Advantageous embodiments of the invention are described by the dependent claims, the following description, and the figures. The invention relates to a method for determining the operational readiness or condition of a motor vehicle. The method comprises the following steps: a) Acquiring current measurement data or sensor data, in particular comprising at least one measured variable of the motor vehicle by means of an external sensor, especially while the motor vehicle is driving or while the motor vehicle is in operation, b) Determining a deviation or discrepancy (e.g.,by subtracting the comparison data from the measurement data and / or by measuring a percentage difference) of the current measurement data to comparison data using a machine learning model, thereby determining or quantifying the operational capability of the motor vehicle, c) if the deviation is above a predetermined threshold, e.g. above 10% in percentage points compared to the comparison data:.

[0011] - Issuance of an (acoustic and / or visual and / or haptic) warning message indicating to a user of the motor vehicle, for example, to have the motor vehicle checked in a workshop and / or not to continue operating the motor vehicle and / or

[0012] - Transmitting or sending the current measurement data and / or the deviation, in particular provided as a quantified value, to a remote maintenance system or a cloud server to initiate or cause (automatic) control in the motor vehicle.

[0013] In other words, maintenance and / or damage detection is performed on the vehicle. Using maintenance detection, particularly through steps a) to c), the vehicle's operational readiness can be determined. Operational readiness can be represented by the detected deviation. If this deviation exceeds a predefined threshold, the vehicle can be classified as requiring maintenance.

[0014] By collecting current measurement data, real-time monitoring or live monitoring can be implemented. This allows for the detection of deviations or a so-called live assessment of the vehicle's (or motor vehicle's) condition. This can be compared to vital signs screening in humans, for example, performed by a smartwatch.

[0015] The machine learning model can therefore determine, by using current measurement data and comparison data, whether a deviation falls within the scope of a released specification or a predefined standard, or whether a fault or damage exists, e.g., in a software and / or hardware component of the vehicle. For example, the machine learning model can be trained using historical comparison data to classify the state as "operational." If the measurement data is then entered as input, the trained learning model can perform a classification with a class membership value (e.g., as a percentage).

[0016] In other words, the deviation is an actual value (current measurement data) evaluated by the machine learning model in relation to a tolerated target value (reference data).

[0017] Therefore, if a deviation is detected, measures can be taken, whereby the user may be encouraged, for example, to have the vehicle inspected in a workshop (as a precaution) and / or to refrain from continuing the journey.

[0018] Determining and / or quantifying the operational capability of a motor vehicle can therefore be carried out while the vehicle is in motion or in operation. The invention offers the advantage that real-time monitoring and real-time evaluation of the condition of a motor vehicle can be implemented, particularly by means of recorded, current measurement data.

[0019] This can be implemented particularly effectively while driving a motor vehicle. A further advantage is that the current measurement data is acquired (solely) using external sensors. This means that the vehicle's internal sensors, i.e., sensors mounted on the vehicle itself, are not used for this purpose. By determining and / or quantifying the vehicle's operational capability, the user can be informed early about the vehicle's condition and / or whether maintenance or repairs are necessary. This can prevent (unplanned) downtime of the vehicle and / or its components. Maintenance can be carried out based on operating conditions or the determined and / or quantified operational capability of the vehicle (and not just according to predetermined intervals, e.g.,...).(after 30,000 kilometers of vehicle mileage, or user assumptions). Furthermore, the service life of the vehicle and / or its components can be extended by means of maintenance detection and the resulting timely implementation of maintenance. Another advantage of the invention is that no workshop visit is required, since the operational readiness of the vehicle can be determined and / or quantified during driving by the vehicle's external sensors. In other words, a (time-consuming) diagnosis in the workshop or a workshop visit is (completely) eliminated. The invention is therefore not intended for application or use in a workshop.

[0020] The invention also includes further developments that result in additional advantages.

[0021] Further training stipulates that the comparison data must include expected measurement data acquired (and / or acquired) during normal operation of the vehicle. In other words, expected measurement data can describe measurement data acquired during normal and / or intrusion-free operation of the vehicle. The expected measurements can describe the same quantities as the actual measurement data. "Normal operation" refers to the operation of the vehicle under standard, and in particular, technically sound conditions. This enables, in particular, anomaly detection by the machine learning model and / or the reliable detection and / or quantification of operational capability.

[0022] Further training stipulates that the comparative data must include historical data for the vehicle. "Historical data" can refer not only to expected measurements, but also to any measurements taken in the past for the same vehicle. Any previously recorded deviations can be associated with these general measurements. This allows for quick and / or easy identification of deviations.

[0023] Further training stipulates that the comparative data must include fleet data from comparable vehicles of the same batch size as the vehicle in question, and / or exhibiting at least one performance characteristic, such as the same mileage and / or year of manufacture as the vehicle, and / or homologation data. The fleet data can include, for example, current measurements and / or historical data from vehicles of comparable batch sizes to the vehicle in question. This enables the creation of comprehensive comparative data. By including homologation data, the vehicle can be checked for deviations according to predefined standards. This allows the comparative data to gain another perspective or an additional factor, such as data from a testing facility, regarding any deviation to be determined.

[0024] A further development provides that the (current and / or expected) measurement data are available as time series data. Additionally or alternatively, it can be provided that the comparison data are available as time series data. This simplifies the determination of deviations. A further development provides that the (current and / or expected) measurement data include engine operating data, in particular engine speed and / or oil temperature and / or coolant temperature and / or fuel pressure, and / or exhaust gas measurement data, and / or vehicle dynamics data, in particular acceleration force and / or brake pressure and / or vehicle speed and / or steering angle, and / or noise data, in particular volume and / or frequency spectrum of engine and / or driving noise, and / or infotainment system data, in particular start-up behavior, most preferably a reaction time and / or an error message from a vehicle infotainment system, and / or

[0025] Vibration data, in particular the intensity and / or pattern of vibrations of at least one component of the motor vehicle, and / or temperature data, in particular the temperature of an exhaust manifold and / or catalytic converter and / or tire of a motor vehicle, and / or fuel consumption data, in particular instantaneous and / or average fuel consumption, and / or tire pressure data, and / or battery data, in particular a charging cycle and / or energy consumption, may be included and / or described. Therefore, many and / or different measurement data can be obtained.

[0026] A further training program envisions real-time vehicle monitoring using external sensors. These sensors can be positioned to capture various perspectives of the vehicle, for example, using one or more cameras. Furthermore, the external sensor system can include a microphone and / or a mobile emissions measuring device for recording exhaust emissions. External sensors can refer to any sensors and measuring systems that are not installed on or in the vehicle itself. These sensors can be connected to the vehicle via a cloud server. One advantage of external sensors is the ability to capture vehicle data from an independent perspective, without requiring any modifications to the vehicle itself. Another advantage is that no sensors need to be installed in the vehicle, nor do existing systems need to be modified.This eliminates the need to open and / or modify the vehicle to, for example, determine and / or quantify its operational capability. In particular, the vehicle's operational capability can be determined and / or quantified during a test drive.

[0027] Further training stipulates that real-time monitoring is implemented using at least one vehicle that precedes and / or follows the motor vehicle. This vehicle includes external sensors or a portion thereof. In principle, this vehicle can be equipped with (external) sensors to collect current measurement data about other vehicles, such as the motor vehicle itself, within a radius of, for example, 50 centimeters to 500 meters. This vehicle and / or the motor vehicle can then transmit the current measurement data to the remote maintenance system. By integrating at least one vehicle equipped with sensors for real-time monitoring of the motor vehicle, the monitoring area of ​​the motor vehicle can be extended and / or implemented. Furthermore, this allows for the acquisition of comprehensive measurement data using external sensors, which, for example,which could not be determined using the vehicle's internal sensors alone.

[0028] One advanced training program stipulates that real-time monitoring is implemented using an infrastructure system, such as a road traffic camera and / or red-light camera and / or stationary measuring device. This infrastructure system includes the vehicle's external sensors. The infrastructure system can, for example, include a microphone and / or an exhaust gas sensor. The infrastructure system and / or at least one vehicle can be connected to the vehicle and record its current location. Real-time monitoring can be initiated as soon as the vehicle falls within a predetermined distance of the infrastructure system. Another advanced training program stipulates that the vehicle's internal sensors include at least a camera and / or an onboard microphone and / or a temperature sensor and / or vibration sensor and / or accelerometer and / or exhaust gas sensor."In-vehicle" means that the sensors are located within the vehicle or at least partially on the vehicle.

[0029] Further training stipulates that the vehicle's external sensors must include at least an external camera and / or an external microphone and / or an external exhaust gas sensor and / or a chassis dynamometer and / or an X-ray fluorescence analyzer and / or a telescopic endoscope and / or a thermal imaging camera. Using these external sensors, the operational readiness of the vehicle can be comprehensively and / or flexibly determined and / or quantified, particularly without interfering with the vehicle's internal components.

[0030] Further training stipulates that the vehicle's external sensor system must include at least a pyrometer and / or a LiDAR sensor and / or a radar sensor and / or an ultrasonic sensor and / or an acoustic camera and / or an electrochemical sensor and / or a magnetic field sensor and / or a particle counter and / or an infrared spectrometer and / or a spectral camera. The advantage here is that the variety of different sensors allows for the detection of various physical, chemical, and / or optical properties of the vehicle and / or its environment, particularly without requiring any structural modifications to the vehicle itself.

[0031] A training course involves recording current measurement data while the vehicle is in operation. In other words, the data is collected while the vehicle is moving. A particular advantage of this method is that the data is collected under real-world operating conditions. An artificial test situation, such as on a test bench, is therefore unnecessary. Furthermore, no workshop visit is required. The data is collected "in the background" during normal operation or while the vehicle is moving. The vehicle does not need to be taken out of service. Additionally, driving dynamics can be recorded, which can be crucial for assessing, recording, or quantifying operational readiness, such as temperature profiles, exhaust emissions, and / or noise levels.

[0032] Further training stipulates that the current measurement data is generated by a combination of in-vehicle and external sensors. This means that the measurement data can be simultaneously acquired and / or combined by both internal and external sensors. In particular, this allows the respective measurement data to validate each other. For example, external sensors can acquire current measurement data that is inaccessible or not obtainable through measurement by the in-vehicle sensors. Conversely, internal sensors can acquire current measurement data that is not obtainable by external sensors.

[0033] Further training provides for the ability to use the control system to deactivate the vehicle and / or at least one component of the vehicle and / or to initiate or perform a remote update, in particular a software update and / or firmware update, for at least one component of the vehicle. The vehicle and / or a component of the vehicle, e.g., an infotainment system and / or an electronic parking brake (so that it only needs to be operated manually if the electronic parking brake is defective), can thus be taken out of service, thereby preventing potential or further damage. Furthermore, this ensures that at least one component of the vehicle meets the latest standards. In addition, it allows at least one defective component, e.g., exhibiting a configuration error and / or software error, to be repaired without physical access to the vehicle.For use cases or application situations that may arise during the procedure and are not explicitly described here, it may be provided that, according to the procedure, an error message and / or a request for user feedback is issued and / or a default setting and / or a predetermined initial state is set.

[0034] The invention also includes a control device. The control device can comprise a data processing device or a processor circuit configured to perform an embodiment of the method according to the invention. For this purpose, the processor circuit can comprise at least one microprocessor and / or at least one microcontroller and / or at least one FPGA (Field Programmable Gate Array) and / or at least one DSP (Digital Signal Processor). In particular, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or an NPU (Neural Processing Unit) can be used as the microprocessor. Furthermore, the processor circuit can comprise program code configured to perform the embodiment of the method according to the invention when executed by the processor circuit. The program code can be stored in a data memory of the processor circuit.The processor setup can be based on at least one circuit board and / or at least one SoC (System on Chip).

[0035] The control device can be included in the motor vehicle. The motor vehicle according to the invention is preferably designed as a motor vehicle, in particular as a passenger car or truck, or as a passenger bus or motorcycle.

[0036] The vehicle's external sensors can be part of a system or be fully integrated into the system.

[0037] As a further solution, the invention also includes a computer-readable storage medium comprising program code which, when executed by a computer or a computer network, causes it to execute an embodiment of the method according to the invention. The storage medium can be provided at least partially as a non-volatile data storage medium (e.g., as flash memory and / or as an SSD - solid state drive) and / or at least partially as a volatile data storage medium (e.g., as RAM - random access memory). The storage medium can be located within the computer or computer network. However, the storage medium can also be operated, for example, as an app store server and / or cloud server on the internet. The computer or computer network can provide a processor circuit with, for example, at least one microprocessor.The program code can be provided as binary code, assembly code, source code in a programming language (e.g., C), or a program script (e.g., Python). Alternatively, the computer-readable storage medium can be implemented as a signal containing computer-readable data, such as a time-varying voltage signal or a radio signal.

[0038] The invention also includes combinations of the features of the described embodiments. The invention therefore also includes realizations that each exhibit a combination of the features of several of the described embodiments, provided that the embodiments have not been described as mutually exclusive.

[0039] The following are exemplary embodiments of the invention described. This is illustrated by:

[0040] Fig. 1 is a sketch illustrating a motor vehicle, featuring sensors for recording current measurement data; and

[0041] Fig. 2 shows a schematic representation of an embodiment of the method according to the invention. The exemplary embodiments described below are preferred embodiments of the invention. In these exemplary embodiments, the described components of the embodiments each represent individual features of the invention that can be considered independently of one another and which further develop the invention independently of one another. Therefore, the disclosure is intended to include combinations of features of the embodiments other than those shown. Furthermore, the described embodiments can also be supplemented by further features of the invention already described.

[0042] In the figures, identical reference symbols denote functionally equivalent elements.

[0043] Fig. 1 shows a sketch illustrating a motor vehicle 10, comprising (in-vehicle and / or external) sensors 7, 27 for acquiring measurement data. The motor vehicle 10 can include at least one camera 3 and / or an onboard microphone 13 and / or a temperature sensor and / or vibration sensor and / or acceleration sensor and / or exhaust gas sensor 8. The motor vehicle 10 can communicate with the external sensors 27, for example, via a cloud server 6 and / or a mobile data connection. The external sensors 27 can include at least one external camera 3 and / or an external microphone 13 and / or an external exhaust gas sensor 8 and / or a chassis dynamometer 11 and / or an X-ray fluorescence analyzer 2 and / or a telescopic endoscope 17 and / or a thermal imaging camera 3.

[0044] Fig. 2 shows a schematic representation of an embodiment according to the idea for determining the operational capability of the motor vehicle 10.

[0045] In step a), current measurement data from the vehicle 10 can be acquired using an internal vehicle sensor 7 and / or an external vehicle sensor 27. In step b), a deviation of the current measurement data from reference data 4 can be determined using a machine learning model. In step c), if the deviation exceeds a predefined threshold, at least one of the following actions can be initiated: issuing a warning message advising a user of the vehicle 10 to have the vehicle 10 checked at a workshop and / or to stop operating the vehicle 10, and / or transmitting the current measurement data and / or the deviation to a remote maintenance system to initiate a control action in the vehicle 10, thereby determining the operational readiness of the vehicle 10.

[0046] According to the embodiment, the machine learning model (or the AI ​​or so-called AI-supported operational capability assessment) can be compared and / or evaluated based on (current) measurement data, which are compared and / or evaluated in the context of comparative data 4 (e.g., past data or historical data of the vehicle itself or the motor vehicle 10 and / or fleet data of other vehicles (of the same batch size) and / or homologation data). The evaluation may lead to the recommendation to have the motor vehicle 10 inspected in a workshop as a precautionary measure or, for example, to advise against further driving.

[0047] For this purpose, the motor vehicle can be equipped with at least the following (in-vehicle) sensor technology 7 or measuring sensor technology:

[0048] - Camera 3 and / or

[0049] - Microphone 13 and / or

[0050] - On-board sensors (e.g. including control units and / or temperature sensors, vibration sensors and / or acceleration sensors and / or exhaust gas sensors 8).

[0051] Additionally, vehicle-external sensors 27 can be considered, which are made available to the vehicle 10 via a server and e.g. via a mobile data connection, in particular comprehensively:

[0052] - External cameras 3 and / or

[0053] - External microphones 13 and / or - External exhaust gas measurement and / or

[0054] - Roller test stand 11 and / or

[0055] - X-ray analysis or X-ray fluorescence analyzer 2 and / or

[0056] - Endoscope or telescopic endoscope 17 and / or

[0057] - Thermal camera 3

[0058] Example 1: For example, the engine noise has suddenly changed due to a damaged engine gasket. The onboard microphones 13 and / or external microphones 13 can record the engine noise and analyze its characteristics:

[0059] - Past data of motor vehicle 10 or a vehicle of the same lot size

[0060] - Fleet data from other vehicles (of the same or a comparable lot size) and / or

[0061] - Compare homologation data.

[0062] The AI ​​or machine learning model can then compare the deviation of an actual value (current measurement data) to a tolerated target value (reference data 4).

[0063] Example 2: The (in-vehicle) sensor 7 in the vehicle 10 measures the infotainment system's startup behavior after a cold start and registers that the value has deteriorated from, for example, 5 seconds to 15 seconds over the years. The AI ​​(artificial intelligence) can then compare the startup times with a comparable batch size from other users (e.g., with identical vehicle age and / or identical mileage) and uses the AI ​​to assess whether this deterioration is within the approved specifications or whether a fault and / or damage (e.g., in a software or hardware component) is present.

[0064] Example 3: A visit to a certification body or testing company, e.g., for a periodic technical inspection, can be simplified for the user by having them provide their onboard measurement data and measurement data from external measurements (collectively described as current measurement data) (e.g., to a designated test bench). The testing company or test bench can then use fleet data from other users or customers to make numerous statements about vehicle suitability, e.g., regarding operational safety. This allows for a significantly faster inspection, e.g., for certification purposes.

[0065] Example 4:

[0066] External cameras 3 (e.g., mounted on a vehicle driving ahead and / or behind and / or on an infrastructure system) can observe or measure the vehicle 10 live or in real time at any given time. This allows for an assessment of the operational readiness or maintenance needs of the vehicle 10 at any given time.

[0067] Overall, the examples show how automated and AI-supported damage detection and / or maintenance detection can be provided.

[0068] Reference symbol list

[0069] X-ray fluorescence analyzer camera

[0070] comparative data

[0071] Cloud server, vehicle-integrated sensors, exhaust gas sensor

[0072] motor vehicle

[0073] Roller test bench

[0074] microphone

[0075] Interior camera

[0076] Telescope endoscope, vehicle ahead, vehicle following

[0077] 27 external vehicle sensors

Claims

PATENT CLAIMS:

1. Method for determining the operational capability of the motor vehicle (10), comprising the steps of: a) acquiring current measurement data of the motor vehicle (10) using an external sensor (27), b) determining a deviation of the current measurement data to reference data (4) using a machine learning model, thereby quantifying the operational capability of the motor vehicle (10), c) if the deviation is above a predetermined threshold: - Issuance of a warning message advising a user of the motor vehicle (10) not to continue operating the motor vehicle (10), and / or - Transmitting the current measurement data and / or deviation to a remote maintenance system to initiate control in the motor vehicle (10).

2. Method according to claim 1, wherein additional current measurement data are acquired by means of an in-vehicle sensor system (7) of the motor vehicle (10).

3. Method according to claim 2, wherein the vehicle-internal sensor system (7) comprises at least a camera (3) and / or an onboard microphone (13) and / or a temperature sensor and / or vibration sensor and / or acceleration sensor and / or exhaust gas sensor (8) and / or humidity sensor.

4. Method according to one of the preceding claims, wherein the comparison data (4) comprise expected measurement data obtained during normal operation of the motor vehicle (10).

5. Method according to any of the preceding claims, wherein the comparison data (4) comprise historical data of the motor vehicle (10).

6. Method according to any of the preceding claims, wherein the comparison data (4) comprise fleet data of comparable vehicles and / or homologation data.

7. Method according to one of the preceding claims, wherein the measurement data are available as time series data.

8. Method according to any of the preceding claims, wherein the current measurement data includes engine operating data and / or exhaust gas measurement data and / or vehicle dynamics data and / or noise data and / or infotainment system data and / or start-up behavior data and / or vibration data and / or temperature data and / or fuel consumption data and / or tire pressure data and / or battery data.

9. Method according to one of the preceding claims, wherein real-time monitoring of the motor vehicle (10) is implemented by means of the vehicle-external sensor technology (27).

10. Method according to claim 9, wherein the real-time monitoring is carried out by means of at least one vehicle which precedes and / or follows the motor vehicle (10), wherein the at least one vehicle comprises the vehicle-external sensor technology (27) or a part thereof.

11. Method according to one of claims 9 or 10, wherein the real-time monitoring is implemented by means of an infrastructure system, the infrastructure system comprising the vehicle-external sensor technology (27).

12. Method according to one of the preceding claims, wherein the vehicle-external sensor system (27) comprises at least an external camera (3) and / or an external microphone (13) and / or an external exhaust gas sensor (8) and / or a roller test bench (11) and / or an X-ray fluorescence analyzer (2) and / or a telescopic endoscope (17) and / or a thermal camera (3). 19 13. Method according to one of the preceding claims, wherein the vehicle-external sensor system (27) comprises at least a pyrometer and / or a LIDAR sensor and / or a radar sensor and / or an ultrasonic sensor and / or an acoustic camera and / or an electrochemical sensor and / or a magnetic field sensor and / or a particle counter and / or an infrared spectrometer and / or a spectral camera.

14. Method according to one of the preceding claims, wherein the current measurement data are recorded in a ferry operation of the motor vehicle (10).

15. Method according to one of the preceding claims, wherein the current measurement data are generated by a combination of the vehicle-internal sensor technology (7) and the vehicle-external sensor technology (27).

16. Method according to one of the preceding claims, wherein the control unit is used to deactivate the motor vehicle (10) and / or at least one component of the motor vehicle (10) and / or to initiate a remote update for a component of the motor vehicle (10).

17. Control device, wherein the control device comprises a processor unit comprising program instructions which, when executed by the processor unit, cause it to perform a method according to one of the preceding method claims.

18. Motor vehicle (10) comprising a control device according to claim 17.

Images