Method for Checking at Least One Vehicle, and Electronic Computing Device

Abstract

A method for checking a vehicle includes receiving measured data by an electronic computing device which is external to the vehicle and which is different from the vehicle. The measured data are received from a measurement device which is different from the vehicle and different from the electronic computing device and the measured data characterize an acceleration of the vehicle recorded by the measurement device and/or a noise of the vehicle recorded by the measurement device and/or an image of a subregion of the vehicle recorded by the measurement device. The received measured data are evaluated by the electronic computing device and the vehicle is checked for a malfunction based on the evaluating of the received measured data by the electronic computing device.

Claims

1.-10. (canceled)

11. A method for checking a vehicle, comprising the steps of: receiving first measured data by an electronic computing device which is external to a first vehicle and which is different from the first vehicle; wherein the first measured data are received from a first measurement device which is different from the first vehicle and different from the electronic computing device and wherein the first measured data characterize a first acceleration of the first vehicle recorded by the first measurement device and/or a first noise of the first vehicle recorded by the first measurement device and/or a first image of a first subregion of the first vehicle recorded by the first measurement device; evaluating the received first measured data by the electronic computing device; and checking the first vehicle for a malfunction based on the evaluating of the received first measured data by the electronic computing device.

12. The method according to claim 11, wherein the first measured data characterize a state of the first vehicle and/or a position of the first vehicle.

13. The method according to claim 11 further comprising the step of training an artificial intelligence regarding determining the malfunction based on the first measured data by the electronic computing device.

14. The method according to claim 11 further comprising the steps of: receiving second measured data by the electronic computing device which is external to a second vehicle and which is different from the second vehicle; wherein the second measured data are received from a second measurement device which is different from the second vehicle and different from the electronic computing device and characterize a second acceleration of the second vehicle recorded by the second measurement device and/or a second noise of the second vehicle recorded by the second measurement device and/or a second image of a second subregion of the second vehicle recorded by the second measurement device; evaluating the received second measured data by the electronic computing device; and checking the first vehicle for the malfunction based on the evaluating of the received second measured data by the electronic computing device.

15. The method according to claim 14, wherein the first measured data are assigned to a first component of the first vehicle and the second measured data are assigned to a second component of the second vehicle, wherein the second component is structurally identical to the first component, and wherein at least the first component is checked for the malfunction.

16. The method according to claim 11 further comprising the step of providing the first measurement device with result data resulting from the evaluating by the electronic computing device.

17. The method according to claim 11 further comprising the steps of: receiving simulation data which characterize a simulation of a part of the first vehicle and/or production data which characterize a production of the first vehicle and/or maintenance data which characterize a maintenance of the first vehicle and/or test stand data which characterize a test of the first vehicle carried out by a test stand by the electronic computing device; and checking the first vehicle for the malfunction based on the simulation data and/or the production data and/or the maintenance data and/or the test stand data by the electronic computing device.

18. A method for checking a vehicle, comprising the steps of: recording an acceleration of the vehicle and/or a noise of the vehicle and/or an image of a subregion of the vehicle by a measurement device which is different from the vehicle; receiving an input effected by a person by the measurement device; assigning a description to the recorded acceleration and/or the recorded noise and/or the recorded image by the measurement device based on the input; and providing measured data which characterize the recorded acceleration and/or the recorded noise and/or the recorded image and the description by the measurement device in order to check the vehicle by an electronic computing device which is external to the vehicle and to the measurement device and which is different from the vehicle and from the measurement device.

19. A method for checking a vehicle, comprising the steps of: recording an acceleration of the vehicle and/or a noise of the vehicle and/or an image of a subregion of the vehicle by a measurement device which is different from the vehicle; providing measured data which characterize the recorded acceleration and/or the recorded noise and/or the recorded image by the measurement device; receiving the measured data provided by the measurement device by an electronic computing device which is external to the vehicle and to the measurement device and which is different from the vehicle and the measurement device; evaluating the received measured data by the electronic computing device; and checking the vehicle for a malfunction based on the evaluating of the received measured data by the electronic computing device.

Description

BRIEF DESCRIPTION OF THE DRAWINGS

[0039] FIG. 1 is a diagram to illustrate a method according to the invention;

[0040] FIG. 2 is a further diagram to illustrate the method;

[0041] FIG. 3 is a further diagram to illustrate the method;

[0042] FIG. 4 is a schematic depiction of a graphic user interface which is displayed on an electronic display of a measurement device used in the context of the method;

[0043] FIG. 5 is a further schematic depiction of the graphic user interface;

[0044] FIG. 6 is a further schematic depiction of the graphic user interface; and

[0045] FIG. 7 is a further schematic depiction of the graphic user interface.

DETAILED DESCRIPTION OF THE DRAWINGS

[0046] Identical or functionally identical elements are provided with the same reference signs in the figures.

[0047] FIG. 1 shows a schematic diagram, with a method for checking at least one vehicle being described below using the figure. An electronic measurement device 10 is used in the method, which device, in the exemplary embodiment illustrated in the figure, is designed as a mobile terminal and thus as a mobile transmitter present in the form of a smart phone. The measurement device 10 has a central processing unit which can execute or executes a software application, also referred to as app or application. The measurement device 10 furthermore has an electronic display 12, also referred to as screen or electronic screen, which displays a graphic user interface 14 of the software application. The graphic user interface is also referred to as interface or user interface. The display 12 is designed for example as a touch-sensitive screen, such that a person, i.e., a user, of the measurement device 10 can perform inputs into the measurement device 10 via the user interface 14 and via the touch-sensitive screen.

[0048] The measurement device 10 also has a recording device 16, which comprises for example at least one camera and/or at least one microphone and/or at least one acceleration sensor of the measurement device 10. In the context of the method, at least one measured variable is recorded by means of the recording device 16 by means of the at least one measurement device 10 different from the at least one vehicle, wherein the measured variable is at least one acceleration and/or at least one noise of the at least one vehicle. Alternatively or additionally, the measured variable comprises at least one image of at least one subregion of the at least one vehicle. The acceleration of the at least one vehicle is recorded for example by means of the acceleration sensor. Alternatively or additionally, the noise which is emitted by the vehicle is recorded for example by means of the microphone of the measurement device 10. Alternatively or additionally, the image is recorded by means of the camera of the measurement device 10. Moreover, at least one input effected by a person via the user interface 14 is received by means of the measurement device. A description is assigned to the recorded measured variable by means of the measurement device 10, based on the input. This assigning of the description to the measured variable is also referred to as labelling, and therefore the measured variable is labelled. As illustrated by an arrow 18 in FIG. 1, the measurement device provides the measured data, preferably provided with the description, in particular wirelessly. An electronic computing device 20 external to the at least one vehicle and to the measurement device 10 and different from the at least one vehicle and from the measurement device 10, which electronic computing device is also referred to as server or back-end and has for example a database and/or forms a neural network or is a constituent of the neural network, receives the measured data provided by the measurement device 10. The measured data are stored for example in a database. The received measured data are evaluated by means of the electronic computing device 20.

[0049] The at least one vehicle is checked, in particular for at least one malfunction, based on the evaluation of the measured data by means of the electronic computing device 20.

[0050] As illustrated by an arrow 22 in FIG. 1, the electronic computing device 20 provides for example result data resulting from the evaluation. The result data are transmitted from the computing device 20 to the measurement device 10 and received by the measurement device 10, in particular wirelessly. The transmission of the result data to the measurement device 10 is thus a response, in particular regarding phenomena identified using the evaluation. This means that the evaluation of the measured data makes it possible to determine at least one or more phenomena which are responsible for the measured variable or which cause the measured variable. Further, for example, it is possible to determine whether the phenomenon has been assigned to a malfunction or else to a functional state of the at least one vehicle, and therefore the evaluation of the measured data makes it possible to determine whether the at least one vehicle has a malfunction or else has no malfunctions and is therefore functional.

[0051] The measurement device 10 is connected to the at least one vehicle, for example via a wireless data link illustrated by an arrow 24, in particular via Bluetooth and/or radio waves. The measurement device 10 receives for example driving data, provided by the at least one vehicle, via the, in particular wireless, data link. The driving data characterize for example a state, in particular a driving state, of the at least one vehicle, wherein the driving data are assigned to the measured data or are linked to the measured data. As a result, in particular in the context of the measured data, the driving data are also transmitted to the electronic computing device 20, and therefore for example the electronic computing device 20 can check the at least one vehicle also based on the driving data or based on the state of the vehicle.

[0052] As further illustrated by an arrow 26, the measurement device 10 can receive sensor data from an external sensor system, in particular via a wireless data link, which sensor system is for example an integrated and/or additional sensor system. The sensor data characterize for example at least one further state of the at least one vehicle. As further illustrated by an arrow 28, the measurement device 10 for example receives, in particular via a wireless data link, measurement instrumentation data, which for example characterize acoustic phenomena or noises, in particular of the at least one vehicle. As further illustrated by an arrow 30, the measurement device 10 receives, for example via a wireless data link, metadata, which characterize a state of construction and/or special accessories and/or other variables of the at least one vehicle, wherein the metadata originate from one or more vehicle databases 32. The sensor data and/or the measurement instrumentation data and/or the metadata are for example linked to the measured data and transmitted from the measurement device 10 to the electronic computing device 20 in the context of the measured data and received by the electronic computing device 20, and therefore the electronic computing device 20 can also check the at least one vehicle based on measurement instrumentation data and/or metadata and/or based on the sensor data. By evaluating the measured data, the driving data and/or the sensor data and/or the measurement instrumentation data and/or the metadata are also evaluated, and, using this, the at least one vehicle is checked.

[0053] The measured data which are transmitted from the measurement device 10 to the electronic computing device 20 and received by the electronic computing device 20 are used, for example, in order to populate the database and/or to train an artificial intelligence, for example the neural network, in particular in terms of detecting a malfunction of the at least one vehicle. The artificial intelligence is also denoted AI.

[0054] FIG. 2 shows a diagram for further illustrating the method. The measured data are for example used to carry out feature recognition by means of the artificial intelligence AI. In the context of the feature recognition, at least one phenomenon from which the measured variable results is determined. By determining the phenomenon, it is possible to determine whether the measured variable results from a malfunction or else from a fault-free state of the at least one vehicle. The phenomenon is thus a result of the evaluation of the measured data, wherein the result—as also illustrated in FIG. 2 by the arrow 22—is transmitted back to the measurement device 10.

[0055] The measured variable is for example determined by a test driver in the context of a test drive, wherein the measured data are for example noise vibration harshness (NVH) measured data, and therefore characterize at least one noise or noises of the at least one vehicle. In order to record the measured variable in the context of the test drive and subsequently accordingly transmit the measured data to the electronic computing device 20 via the measurement device 10, a test drive mode of the software application is for example set and selected, in particular via the user interface 14.

[0056] A noise expert for example carries out a further test of the vehicle designated 34 in FIG. 2, and therefore the measured data are for example NVH training data. The NVH training data, also simply referred to as training data, are for example used in a training mode of the software application, also referred to as learning mode, in order to train the electronic computing device 20, in respect of determining a respective phenomenon causing the measured variable, using the training data.

[0057] Alternatively or additionally, for example, databases, designated 36 in FIG. 2, are provided, in which data sets are stored, which data sets characterize respective noises or noise behaviour of the vehicle 34. The data sets are also for example transmitted to the electronic computing device 20 and received by same, and therefore the electronic computing device 20 can check the vehicle 34 based on the data sets from the databases 36. For example, a manual extraction of the data sets from the databases 36 takes place.

[0058] As illustrated by an arrow 38 in FIG. 2, the artificial intelligence AI is trained using the measured data, in particular using the training data, in order to be able to produce a particularly high detection rate. The detection rate characterizes a probability of the artificial intelligence AI or the computing device 20 being able to correctly detect a respective phenomenon which is responsible for the respective measured variable or which causes the respective measured variable. By correctly detecting the phenomenon causing the measured variable, it is possible, using the evaluation of the measured data, to detect whether the measured variable results from a fault or from a malfunction of the vehicle 34 or otherwise from a fault-free state of the vehicle 34.

[0059] FIG. 3 shows a further diagram to illustrate the method. The measured data are for example driving data which are determined during a journey of the vehicle 34. Further, the measured data can comprise the abovementioned measurement instrumentation data, which are determined by means of, in particular stationary, measurement instrumentation. Alternatively or additionally, the measured data can comprise test stand data, which are determined by means of a test stand, by means of which the vehicle 34 is tested. The abovementioned data sets are for example stock data which are provided by the databases 36. Alternatively or additionally, simulation data can be provided, on the basis of which the electronic computing device 20 checks the vehicle 34. The measured data or the driving data, the measurement instrumentation data, the test stand data, the stock data and the simulation data are transmitted for example to a data cloud 40 and thus to the electronic computing device 20 and received by the latter, and therefore there is central data access to the data. The measured data are used to determine, by means of the artificial intelligence AI, whether the acceleration and/or the noise and/or the image results from a fault-free state or from a faulty state of the vehicle 34, as a result of which the vehicle 34 can be effectively and efficiently checked. Moreover, it is conceivable to take into account maintenance data which characterize a maintenance or service of the vehicle 34, and/or production data which characterize a production of the vehicle 34, and/or customer data which characterize a customer operation of the vehicle 34, in order to check the at least one vehicle 34 by means of the electronic computing device 20.

[0060] FIG. 4 shows a schematic depiction of a first menu of the graphic user interface 14. The measurement device is connected for example via a wireless data link, for example Bluetooth, and therefore wirelessly, to the vehicle 34. The abovementioned person then selects an operating element 42 of the user interface 14, wherein in the present case the operating element 42 is a partial surface of the user interface 14. The person touches the touch-sensitive screen in a region in which the partial surface is displayed on the touch-sensitive screen. As a result, the abovementioned learning mode of the software application is started. An operating element 44 of the user interface 14 according to FIG. 5 is accordingly displayed on the touch-sensitive screen. If the person actuates the operating element 44 by the person touching the region of the touch-sensitive screen in which the operating element 44 is displayed, for example the recording of the measured variable by means of the measurement device 10 is started.

[0061] The abovementioned labelling is illustrated using FIG. 6. In order to carry out the labelling, a further menu of the user interface 14 is displayed on the touch-sensitive screen. The further menu according to FIG. 6 comprises further operating elements 46a-e. The respective operating element 46a-e corresponds to a respective description which can be assigned to the previously recorded measured variable. If the measured variable is for example a noise, the respective description can be used to assign a designation to the noise, by means of which designation for example the noise can be verbally named by a person. The person assigned the description to the measured variable by the person touching the region of the touch-sensitive screen in which the operating element 46a-e is displayed, which operating element corresponds to the description which should be assigned to the measured variable. The description is therefore a type which characterizes the measured variable.

[0062] In the learning mode, therefore, measured data can be communicated to the electronic computing device 20, which measured data characterize measured variables and therefore the phenomena causing the measured variables. Consequently, the electronic computing device 20 can distinguish between those measured variables or phenomena which occur during a fault-free state of the vehicle 34, and those measured variables or phenomena which result from malfunctions of the vehicle 34.

[0063] If the person wishes, for example, to execute not the learning mode but rather a measurement run, then the person touches the region of the touch-sensitive screen in which an operating element 48, shown in FIG. 4, of the user interface 14 is displayed. Like the operating element 42, the operating element 48 is also a surface or partial surface of the user interface 14. By activating the normal measurement run, the measured variable is recorded by means of the measurement device 10, the measured data are transmitted to the computing device 20, which can then determine whether the measured variable results from a malfunction or else from a fault-free state of the vehicle 34. To this end, the computing device 20 can compare for example the measured data received in the context of the measurement run with the measured data which the computing device 20 received in the context of the learning mode. Since for example the measured data resulting from the learning mode characterize a malfunction, the computing device 20 can compare the measured data from the measurement run with the measured data from the learning mode. For example, if the measured data from the measurement run correspond to the measured data from the learning mode, the computing device 20 can conclude that there is a malfunction of the vehicle 34. If, however, the measured data from the measurement run deviate from the measured data from the learning mode, the computing device 20 can conclude that there is a fault-free state of the vehicle 34.

[0064] FIG. 7 shows a further menu of the user interface 14. The further menu according to FIG. 7 comprises further operating elements 48a-f, by means of which further descriptions can be assigned to the respective measured variable or measured data.