Method and system for fault detection in a motor vehicle that is at least partially automated

Abstract

According to a first aspect of the invention, a method for fault detection in an at least partially automated motor vehicle is proposed. It comprises the steps of at least partially automated driving along a defined route, acquiring measurement data during the test route using at least one sensor arranged within the motor vehicle, wherein the measurement data particularly represents acoustic signals and / or acceleration and / or rotational speed, and evaluating the measurement data with respect to a faulty component of the motor vehicle. In particular, automated driving along the test route eliminates the need for human drivers and allows fault detection under defined, optionally standardized conditions, such as driving parameters. The acquisition and evaluation of the measurement data enables precise and reliable fault detection.

Description

[0001] The invention relates to a method for fault detection in a motor vehicle that is at least partially automated. The invention further relates to a computer program. In particular, the invention relates to the acquisition and evaluation of measurement data during a test drive that is at least partially automated in order to detect assembly errors, incorrect installations, or wear on vehicle parts. State of the art

[0002] In automotive manufacturing, it is standard practice to drive every newly produced vehicle over a vibration test track to detect noises that could indicate faulty assembly or installation, or incomplete assembly where there is no actual defect but rather incomplete finishing. However, these tests require a significant number of drivers and are physically demanding. Furthermore, the results are not always consistent due to individual differences in noise perception and driving style.

[0003] The patent application DE 102017100380 A1 discloses a diagnostic test execution control system comprising a remote data processing system and multiple vehicles, using data from vehicle system sensors.

[0004] Patent specification KR 102099552 B1 describes a vehicle performance test and a test track combined with photovoltaic power generation. It describes the testing of autonomously driving vehicles within the test track using sensors installed along the track. Disclosure of the invention

[0005] It can therefore be considered an object of the invention to provide a reliable method or system for fault detection in an at least partially automated motor vehicle.

[0006] In particular, it should be possible to conduct a test drive at least partially automatically, possibly even without a driver.

[0007] According to a first aspect of the invention, a method for fault detection in an at least partially automated motor vehicle is proposed. It comprises the steps of at least partially automated driving along a defined route, acquiring measurement data during the test route using at least one sensor arranged within the motor vehicle, wherein the measurement data particularly represents acoustic signals and / or acceleration and / or rotational speed, and evaluating the measurement data with respect to a faulty component of the motor vehicle. In particular, automated driving along the test route eliminates the need for human drivers and allows fault detection under defined, optionally standardized conditions, such as driving parameters. The acquisition and evaluation of the measurement data enables precise and reliable fault detection.

[0008] In a preferred embodiment of the invention, the defined track is designed as a test track within a factory area, in particular as a vibration track. The test track is preferably driven automatically, i.e., without a driver, with driving parameters and test conditions predefined. The vibrations and / or noises caused, for example, by defined unevenness in the surface of the vibration track can be reliably and reproducibly detected by one or more sensors arranged inside the vehicle. This offers the particular advantage that using a vibration track within a factory area ensures that the test conditions are standardized and reproducible, which increases the comparability and reliability of the test results.

[0009] According to an alternative preferred embodiment of the invention, the motor vehicle can also be checked for faults after delivery to an end customer, i.e., during normal driving, for example, upon reaching certain mileages and / or when specific driving behavior occurs. For instance, a corresponding message can be issued to the driver, who can then manually activate the diagnostic mode via a control element in the vehicle. A section of road, for example, a public road, is selected as the test track based on the current position of the motor vehicle and / or a digital map. Existing road surface irregularities, such as cobblestones or speed bumps, are utilized. After activation and, if necessary, confirmation by the driver, the following are performed:Using satellite navigation and / or a digital map, a suitable test route is selected and specified nearby. Suitable routes are well-known roads with specific characteristics such as cobblestones, speed bumps, or similar features. Upon arrival at the destination, warnings can be issued, followed by specific driving instructions such as speed, steering, etc. The driver can then execute these instructions accordingly. Instead of a human driver, a partially or highly automated driving system (e.g., Level 3 Low Speed) can also be used. During the test drive, the vehicle's internal sensors are used to record measurement data, such as noise and vibrations. This data can be processed with known filters and compared to reference profiles.Once the test track has been driven and the measurement data has been evaluated, relevant information can be provided.

[0010] The dynamic determination of the test route is preferably based on the current position and digital maps, thus enabling flexible and context-dependent tests, which expands the applicability of the method. This allows for the reliable detection of defects that, for example, were overlooked during quality control at the factory or arise from subsequent wear and tear, even during regular vehicle operation. For instance, the invention allows for the advantageous identification of component wear even outside of a workshop. The vehicle does not need to be taken to the workshop only on suspicion or as part of a routine maintenance cycle. The wear can be identified as soon as it occurs.

[0011] In an alternative preferred embodiment of the invention, the test track is located within a parking garage, and the fault detection is performed during an automated parking process. For this purpose, an AVP (Automated Valet Parking) system is suitable, in which a vehicle is guided driverless to a parking space within a parking infrastructure. Performing the fault detection according to the invention during such an automated parking process utilizes existing infrastructure and reduces the additional effort required for dedicated test tracks.

[0012] When using Autopilot (AVP) in a parking garage (all types according to ISO 23374-1:2023 are conceivable), the user can decide, for example, whether an additional diagnostic check should be performed during the parking process and / or while the vehicle is in the garage. Since the parking garage is known to the AVP system with all its characteristics, no additional satellite navigation or digital maps are required in this implementation. The fault detection procedure can be carried out during the initial parking process or at specific times within the parking garage. In the latter case, an additional AVP run can be initiated, and the vehicle can then return to the same or a new parking space as its final position. During the AVP run, specific driving profiles are followed, taking the parking garage characteristics into account. The vehicle's internal sensors also record measurement data, such as...Noise and vibrations are recorded, processed with filters and / or compared with reference data. After the test track has been completed and the measurement data has been evaluated, relevant information can be output.

[0013] Preferably, the evaluation of the data can be used to detect incorrect assembly of a vehicle component. The ability to detect incorrect assembly improves quality assurance and reduces the risk of failures or safety problems during the vehicle's subsequent operation.

[0014] Furthermore, the evaluation of the data can preferably be used to detect wear on a vehicle component. Detecting wear enables early maintenance and repair, which extends the service life of the vehicle parts and increases operational safety.

[0015] Preferably, the measurement data is evaluated for errors using filters and / or reference models. The use of filters and reference models enables a precise and reliable evaluation of the measurement data, which further improves the accuracy of error detection.

[0016] Particularly advantageous is the evaluation of measurement data from multiple sensors spatially distributed within the vehicle. This allows for the localization of a faulty part by, for example, relating the measurement data to each other and to the known position of the corresponding sensor within the vehicle, and then evaluating the data accordingly. Evaluating measurement data from multiple sensors enables precise localization of the faulty component, thus increasing the efficiency of troubleshooting.

[0017] A second aspect proposes a fault detection system based on a method described in the first aspect. The system comprises at least one sensor located within the vehicle for acquiring measurement data. Specifically, the sensor is configured as at least one microphone and / or at least one rotational speed sensor and / or at least one acceleration sensor. The system also includes an evaluation unit configured to analyze the measurement data acquired during the test track with regard to a faulty component of the vehicle.

[0018] The system enables comprehensive and precise fault detection through the integration of sensors and an evaluation unit specifically configured for analyzing the measurement data. For example, microphones already present in the vehicle can be used as part of the system, such as the microphone of a hands-free system or an emergency call system. The microphone(s) can be activated for data acquisition even during production and / or transport modes. Measurement data can then be compared using specified filters and comparison models to determine the vehicle's status. For this purpose, previous journeys can be provided as reference cases—either fault cases or fault-free cases—for a specific vehicle model and a particular test track.

[0019] Alternatively or additionally, an existing vehicle dynamics control system (electric braking and vehicle dynamics systems) or its inertial sensors can be used. For example, using the yaw rate sensor / acceleration sensor allows for the detection of vibrations. Evaluation is again performed using specified filters and reference models. Reference models can also be pre-recorded and made available.

[0020] In a preferred embodiment, the sensor(s) can be designed as part of a sensor module that can be temporarily mounted and operated within the vehicle, in particular a sensor module for monitoring the vehicle's interior. The use of temporarily mountable sensor modules enables flexible and cost-effective implementation of the system in various vehicle models.

[0021] In a preferred embodiment, the evaluation unit can be located outside the vehicle. In this case, the vehicle can have a data transmission unit for transferring the measurement data to the evaluation unit. For example, a cloud system or an external computer with higher processing power can be used for data analysis. Outsourcing the evaluation unit reduces the demands on the vehicle's on-board electronics and enables more efficient data processing.

[0022] According to a third aspect, a computer program is proposed, comprising instructions which, when executed by a computer, in particular the evaluation unit of a system according to the second aspect, cause it to execute a procedure according to the first aspect. The computer program enables a simple and efficient implementation of the fault detection procedure on various evaluation units.

[0023] According to a fourth aspect, a machine-readable storage medium is proposed on which the computer program, as described in the third aspect, is stored. The machine-readable storage medium ensures that the computer program can be stored and retrieved securely and reliably.

[0024] The present invention therefore provides a method and a system for automated fault detection in at least partially automated motor vehicles. By driving a defined test track in a partially automated manner and acquiring and evaluating measurement data using in-vehicle sensors, precise and reliable detection of assembly errors, incorrect installations, and wear is enabled. The use of filters and reference models, as well as the integration of the sensors and the evaluation unit into a single system module, contribute to the efficiency and accuracy of quality control. These technical advantages improve quality assurance and reduce the risk of failures and / or safety problems during subsequent vehicle operation.

[0025] The phrase "at least partially automated" includes one or more of the following cases: assisted driving, semi-automated driving, highly automated driving, fully automated driving of a motor vehicle.

[0026] Assisted driving means that the driver of the vehicle is permanently responsible for either the lateral or longitudinal control of the vehicle. The other driving task (i.e., controlling the longitudinal or lateral movement of the vehicle) is performed automatically. This means that with assisted driving, either the lateral or longitudinal control of the vehicle is automatic.

[0027] Partially automated driving means that in a specific situation (for example: driving on a highway, driving within a parking lot, overtaking an object, driving within a lane defined by lane markings) and / or for a certain period of time, the longitudinal and lateral control of the vehicle is automated. The driver does not need to manually control the vehicle's longitudinal and lateral steering. However, the driver must continuously monitor the automated control of the longitudinal and lateral steering in order to be able to intervene manually if necessary. The driver must be ready to take over full control of the vehicle at any time.

[0028] Highly automated driving means that for a certain period of time in a specific situation (for example: driving on a highway, driving within a parking lot, overtaking an object, driving within a lane defined by lane markings), the longitudinal and lateral control of the vehicle is automated. The driver does not need to manually control the vehicle's longitudinal and lateral steering. The driver does not need to constantly monitor the automated control of longitudinal and lateral steering in order to intervene manually if necessary. If required, a takeover request is automatically issued to the driver to assume control of longitudinal and lateral steering, with a sufficient time buffer. Therefore, the driver must be potentially capable of taking over control of longitudinal and lateral steering.The limits of automatic control of lateral and longitudinal guidance are automatically detected. With highly automated guidance, it is not possible to automatically create a risk-minimizing state in every initial situation.

[0029] Fully automated driving means that in a specific situation (for example: driving on a highway, driving within a parking lot, overtaking an object, driving within a lane defined by lane markings), the longitudinal and lateral control of the vehicle is automated. The driver does not need to manually control the vehicle's longitudinal and lateral movements. The driver does not need to monitor the automated control of longitudinal and lateral movements in order to intervene manually if necessary. Before the automated control of longitudinal and lateral movements ends, the driver is automatically prompted to take over the driving task (controlling the vehicle's longitudinal and lateral movements), with sufficient time to do so. If the driver does not take over the driving task, the system automatically returns to a low-risk state.The limits of automatic control of lateral and longitudinal guidance are automatically detected. In all situations, it is possible to automatically return to a system state with minimal risk.

[0030] Driverless control means that, regardless of the specific application (for example, driving on a highway, driving within a parking lot, overtaking an object, driving within a lane defined by lane markings), the longitudinal and lateral control of the vehicle is automated. The driver does not need to manually control the vehicle's longitudinal and lateral movements. The driver does not need to monitor the automated control of longitudinal and lateral movements in order to intervene manually if necessary. Thus, the vehicle's longitudinal and lateral movements are automatically controlled for all road types, speed ranges, and environmental conditions. The driver's entire driving task is therefore automated. The driver is no longer required.The vehicle can therefore travel from any starting position to any destination position without a driver. Potential problems are solved automatically, without driver intervention.

[0031] Remote control of a motor vehicle means that the vehicle's lateral and longitudinal steering is controlled remotely. This means, for example, that remote control signals are sent to the vehicle to control its lateral and longitudinal steering. Remote control is carried out, for example, using a remote control device. Brief description of the characters

[0032] With reference to the attached figures, embodiments of the invention are described in detail. Fig. Figure 1 shows an automated motor vehicle performing a fault detection method according to a first embodiment of the invention. Fig. Figure 2 shows an automated motor vehicle performing a fault detection method according to a second embodiment of the invention. Fig. Figure 3 shows an embodiment of a fault detection system according to the invention as a block diagram. Fig. Figure 4 shows a flowchart of a method for fault detection according to the invention. Fig. Figure 5 shows a machine-readable storage medium on which a computer program according to the invention is stored. Preferred embodiments of the invention

[0033] In the following description of exemplary embodiments of the invention, identical elements are designated by the same reference numerals, and a repeated description of these elements may be omitted. The figures represent the subject matter of the invention only schematically.

[0034] Fig. Figure 1 shows an automated motor vehicle 20 performing a fault detection method according to a first embodiment of the invention. The automated motor vehicle 20 moves driverless within a factory site 110. The factory site 110 is equipped with a so-called AVM-P (Automated Vehicle Maneuvering - Plant) system. This system allows the motor vehicle 20 to be controlled driverless within the factory site 110. For this purpose, the AVM-P system has several stationary environmental sensors 12 arranged within the factory site 110, as well as an external control unit 112 that transmits driving commands to the motor vehicle 20.

[0035] To perform a fault detection according to the invention, the motor vehicle 20 is automatically guided over a vibration track 30. The vibration track 30 has various sections 32, 34 with differently designed surface irregularities. Acoustic signals are recorded by means of at least one microphone 22 arranged inside the motor vehicle while the vehicle is traversing the vibration track 30. Alternatively or additionally, vibrations can be recorded by means of one or more acceleration and / or rotational speed sensors (not shown). The measurement data thus acquired can be evaluated with regard to a faulty component of the motor vehicle 20. The evaluation is carried out, for example, by an evaluation unit inside the motor vehicle 20, or by a separate evaluation unit, which may, for example, be included in the control unit 112.

[0036] Fig. Figure 2 shows an automated vehicle 20 performing an alternative fault detection procedure. The automated vehicle 20 moves driverless within a parking garage 120. The parking garage 120 is equipped with an automated valet parking system 122 (AVP system). For this purpose, environmental sensors 13 are arranged within the parking garage 120 to acquire the environmental information required for the fully automated, driverless operation of the vehicle 20. The AVP system 122 generates driving commands and transmits them, for example wirelessly, to the vehicle 20.

[0037] To detect defective parts or wear, the vehicle 20, after the user has authorized or initiated the corresponding process and before it is guided to its final parking space, or during the time the vehicle 20 is parked in the parking garage 120, is driven along a test track 40 defined within the parking garage 120. During this drive, specific driving profiles are executed, taking into account the characteristics of the parking garage 120 or the test track 40. The vehicle's internal sensors, which include, for example, one or more microphones 22 and / or acceleration or rotational speed sensors, also record noise and vibrations, process them with filters, and compare them with references. The measurement data thus acquired can be evaluated with regard to a defective part or wear on the vehicle 20.The evaluation is carried out, for example, by an evaluation unit within the motor vehicle 20, or a separate evaluation unit, which may be included, for example, by the AVP system 122.

[0038] Fig. Figure 3 shows a block diagram of an embodiment of a system 300 according to the invention for fault detection in an at least partially automated motor vehicle 310.

[0039] In this example, the motor vehicle 310 comprises three sensor groups 312, 314, and 316 arranged within the vehicle. The first sensor group 312 is an interchangeable sensor module for vehicle interior monitoring ("RideCare") comprising, for example, one or more microphones and acceleration sensors. The second sensor group 314 consists of sensors for the vehicle's electronic stability control (ESC), a known driver assistance system for controlling vehicle dynamics. Such systems typically include yaw rate and / or acceleration sensors. The third sensor group 316 consists of one or more microphones in the vehicle's interior. These microphones can, for example, be part of a hands-free system or an emergency call system.

[0040] The vehicle 310 also includes a control module 318, which enables at least partially automated control of the vehicle 310. The control module 318 is designed to receive and execute driving commands from an external (infrastructure) system, such as an AVP or AVM system.

[0041] In this example, system 300 also includes an AVM infrastructure 320, which is configured to generate driving commands and transmit them to the control module 318. Using these control commands, the vehicle 310 can automatically drive along a specific test track, for example, a vibration test track. During the test track traversal, measurement data is acquired and recorded using at least one, preferably all, of the sensor groups 312, 314, and 316. The measurement data is transmitted via a data readout interface 324 to an evaluation unit 326, where the measurement data is filtered and compared with reference data. Depending on the result of the evaluation, an output 328 is generated. This output can include, for example, information about potentially incorrectly assembled or installed vehicle parts and / or wear.

[0042] In an alternative configuration of the system 300, instead of driving commands, driving instructions can also be generated and issued by the infrastructure 320 or within the motor vehicle 310, with a human driver carrying out these driving instructions to drive the test track.

[0043] Fig. Figure 4 shows a flowchart 500 of an embodiment of a method according to the invention for fault detection in an at least partially automated motor vehicle.

[0044] In a first step, 510, driving commands for at least partially automated driving along a defined test track are generated and transmitted to the vehicle.

[0045] In step 520, the test track is driven at least partially automatically based on the driving commands, during which measurement data is recorded by means of at least one sensor located inside the vehicle. This measurement data consists in particular of acoustic signals and / or signals representing acceleration and / or rotational speed.

[0046] In step 530, the recorded measurement data regarding a faulty component of the motor vehicle are evaluated.

[0047] Fig. Figure 5 shows a machine-readable storage medium 301 on which a computer program 303 according to the invention is stored. The computer program includes, for example, instructions that execute a method as described in Figure 5. Fig. 4 described, illustrate. QUOTES INCLUDED IN THE DESCRIPTION

[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited patent literature

[0000] DE 102017100380 A1

[0003] KR 102099552 B1

[0004]

Claims

[1] Method for fault detection in a motor vehicle that is at least partially automated (20, 310), comprising the steps: - At least semi-automated driving along a defined test track (30, 40), - During the driving of the test track (30, 40), measurement data is acquired by means of at least one sensor (22, 312, 314, 316) arranged inside the motor vehicle (20, 310), wherein the measurement data particularly represent acoustic signals and / or an acceleration and / or a rotational speed; - Evaluating the measurement data regarding a faulty component of the motor vehicle (20, 310). [2] Method according to claim 1, wherein the defined section is designed as a test section (30) within a factory area (110), in particular as a vibration section. [3] Method according to claim 1, wherein a road section is determined as a test track based on a current position of the motor vehicle (20, 310) and / or a digital map. [4] Method according to claim 1, wherein the test track (40) is formed within a parking garage (120) and the fault detection is performed during an automated parking process. [5] Method according to one of claims 1 to 4, wherein a faulty assembly of a component of the motor vehicle (20, 310) can be detected by evaluating the data. [6] Method according to any one of claims 1 to 5, wherein wear of a component of the motor vehicle (20, 310) can be detected by evaluating the data. [7] Method according to any one of claims 1 to 6, wherein the evaluation is carried out using filters and / or reference models. [8] Method according to any one of claims 1 to 7, wherein measurement data from several sensors (22, 312, 314, 316) distributed spatially within the motor vehicle are evaluated, and a defective part is located. [9] System (300) for fault detection according to a method according to one of claims 1 to 8 for an at least partially automated motor vehicle (20, 310), wherein the motor vehicle (20, 310) is configured to drive a test track (30, 40) at least partially automatically, the system (300) comprising: - at least one sensor (22, 312, 314, 416) arranged inside the motor vehicle (20, 310) for recording measurement data, in particular at least one microphone and / or at least one rotational speed sensor and / or at least one acceleration sensor; - Evaluation unit (326), designed to evaluate the measurement data recorded during the driving of the test track (30, 40) with regard to a faulty component of the motor vehicle (20, 310). [10] System (300) according to claim 9, wherein the sensor(s) (316) are designed as part of a sensor module that can be temporarily mounted and operated inside the motor vehicle (20, 310), in particular a sensor module for monitoring the interior of the motor vehicle. [11] System according to one of claims 9 or 10, wherein the evaluation unit (326) is located outside the motor vehicle (20, 310) and the motor vehicle (20, 310) has a data transmission unit for transmitting the measurement data to the evaluation unit (326). [12] Computer program (303) comprising instructions which, when the computer program (303) is executed by a computer, in particular the evaluation unit of a system according to one of claims 9 to 11, cause it to execute a method according to one of claims 1 to 8. [13] Machine-readable storage medium (301) on which the computer program (303) according to claim 12 is stored.

Images